Technologies

26 pages, 16943 KiB

Open AccessArticle

Nu—A Marine Life Monitoring and Exploration Submarine System

by Ali A. M. R. Behiry, Tarek Dafar, Ahmed E. M. Hassan, Faisal Hassan, Abdullah AlGohary and Mounib Khanafer

Technologies 2025, 13(1), 41; https://doi.org/10.3390/technologies13010041 - 20 Jan 2025

Viewed by 764

Abstract

Marine life exploration is constrained by factors such as limited scuba diving time, depth restrictions for divers, costly expeditions, safety risks to divers’ health, and minimizing harm to marine ecosystems, where traditional diving often risks disturbing marine life. This paper introduces Nu (named [...] Read more.

Marine life exploration is constrained by factors such as limited scuba diving time, depth restrictions for divers, costly expeditions, safety risks to divers’ health, and minimizing harm to marine ecosystems, where traditional diving often risks disturbing marine life. This paper introduces Nu (named after an ancient Egyptian deity), a 3D-printed Remotely Operated Underwater Vehicle (ROUV) designed in an attempt to address these challenges. Nu employs Long Range (LoRa), a low-power and long-range communication technology, enabling wireless operation via a manual controller. The vehicle features an onboard live-feed camera with a separate communication system that transmits video to an external real-time machine learning (ML) pipeline for fish species classification, reducing human error by taxonomists. It uses Brushless Direct Current (BLDC) motors for long-distance movement and water pump motors for precise navigation, minimizing disturbance, and reducing damage to surrounding species. Nu’s functionality was evaluated in a controlled 2.5-m-deep body of water, focusing on connectivity, maneuverability, and fish identification accuracy. The fish detection algorithm achieved an average precision of 60% in identifying fish presence, while the classification model achieved 97% precision in assigning species labels, with unknown species flagged correctly. The testing of Nu in a controlled environment has met the system design expectations. Full article

(This article belongs to the Topic Technological Innovation to Support Reef Research and Conservation)

► Show Figures

Figure 1

21 pages, 9000 KiB

Open AccessArticle

An Investigation of Infrared Small Target Detection by Using the SPT–YOLO Technique

by Yongjun Qi, Shaohua Yang, Zhengzheng Jia, Yuanmeng Song, Jie Zhu, Xin Liu and Hongxing Zheng

Technologies 2025, 13(1), 40; https://doi.org/10.3390/technologies13010040 - 17 Jan 2025

Viewed by 721

Abstract

To detect and recognize small-size and submerged complex background targets in infrared images, we combine a dynamic receptive field fusion strategy and a multi-scale feature fusion mechanism to improve the detection performance of small targets significantly. The space-to-depth convolution module is introduced as [...] Read more.

To detect and recognize small-size and submerged complex background targets in infrared images, we combine a dynamic receptive field fusion strategy and a multi-scale feature fusion mechanism to improve the detection performance of small targets significantly. The space-to-depth convolution module is introduced as a downsampling layer in the backbone first and achieves the same sampling effect. More detailed information is retained at the same time. Thus, the model’s detection capability for small targets has been enhanced. Then, the pyramid level 2 feature map with minimum receptive field and maximum resolution is added to the neck, which reduces the loss of positional information during feature sampling. Furthermore, x-small detection heads are added, the understanding of the overall characteristics and structure of the target is enhanced much more, and the representation and localization of small targets have been improved. Finally, the cross-entropy loss function in the original network model is replaced by an adaptive threshold focal loss function, forcing the model to allocate more attention to target features. The above methods are based on a public tool, the eighth version of You Only Look Once (YOLO) improved, it is named SPT–YOLO (SPDConv + P2 + Adaptive Threshold + YOLOV8s) in this paper. Some experiments on datasets such as infrared small object detection (IR-SOD) and infrared small target detection 1K(IRSTD-1K), etc. have been executed to verify the proposed algorithm; and the mean average precision of 94.0% and 69% under the condition of threshold at 0.5 and over a range from 0.5 to 0.95 is obtained, respectively. The results show that the proposed method achieves the best performance of infrared small target detection compared to existing methods. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

13 pages, 5005 KiB

Open AccessArticle

Pneumatically Actuated Rehabilitation Equipment for the Sagittal and Frontal Plane Movements of the Neck Joint

by Sarah Mareş, Andrea Deaconescu and Tudor Deaconescu

Technologies 2025, 13(1), 39; https://doi.org/10.3390/technologies13010039 - 16 Jan 2025

Viewed by 597

Abstract

The timely reintegration into their daily routine of patients suffering from work-related musculoskeletal disorders is a priority in medical rehabilitation. This can be accomplished by means of certain procedures and adequate medical rehabilitation equipment. Starting from these considerations this paper proposes an original [...] Read more.

The timely reintegration into their daily routine of patients suffering from work-related musculoskeletal disorders is a priority in medical rehabilitation. This can be accomplished by means of certain procedures and adequate medical rehabilitation equipment. Starting from these considerations this paper proposes an original constructive solution of a rehabilitation device designed for the passive mobilization of the neck joint in the sagittal and frontal plane. The constructive solution that is put forward uses a pneumatic muscle as the actuation element, ensuring the adaptability of the equipment to the particular pain tolerance of each patient. The construction and dimensioning calculations of the equipment are presented, followed by the determination of the torsional rigidity and compliance permitted by the system. Based on the results the paper concludes with recommendations for the optimum deployment of the rehabilitation equipment. Full article

(This article belongs to the Special Issue Assistive Technologies in Care and Rehabilitation: Research, Developments, and International Initiatives)

► Show Figures

Figure 1

17 pages, 2046 KiB

Open AccessArticle

Advanced Autonomous System for Monitoring Soil Parameters

by Băjenaru Valentina-Daniela, Istrițeanu Simona-Elena and Paul-Nicolae Ancuța

Technologies 2025, 13(1), 38; https://doi.org/10.3390/technologies13010038 - 16 Jan 2025

Viewed by 560

Abstract

Context: This research investigates the advantages of real-time monitoring of soil quality for various land management practices. It also highlights the significance of spatio-temporal soil modeling and mapping in providing a clear and visual understanding of how aridity changes over time and [...] Read more.

Context: This research investigates the advantages of real-time monitoring of soil quality for various land management practices. It also highlights the significance of spatio-temporal soil modeling and mapping in providing a clear and visual understanding of how aridity changes over time and across different locations. Aims: This paper aims to provide a comprehensive guide to the key processes required for the development of a laboratory-based soil quality monitoring system. Methods: The applied methodologies involved the processes of sensor deployment, data acquisition infrastructure establishment, and sensor calibration. These procedures culminated in the development of a soil quality assessment model that was subsequently subjected to two months of laboratory testing using three distinct soil types. The analysis yielded a strong positive linear correlation between the measured and predicted soil quality values. Key Results: As expected, the assimilation of prior soil quality estimates within the modeling framework demonstrated a significant enhancement in the accuracy of real-time soil quality estimations. Conclusions: This research promotes the importance of iterative improvements of the soil quality monitoring system. The need for a long-term perspective and a plan for maintenance and continuous improvement of such systems in the ecosystem is important to improve the ease of making predictions to avoid soil aridization. The results of this research will be useful for researchers and practitioners involved in the design and implementation of soil monitoring systems. Full article

(This article belongs to the Special Issue Advanced Autonomous Systems and Artificial Intelligence Stage)

► Show Figures

Figure 1

51 pages, 26899 KiB

Open AccessReview

Robotic Systems for Hand Rehabilitation—Past, Present and Future

by Bogdan Gherman, Ionut Zima, Calin Vaida, Paul Tucan, Adrian Pisla, Iosif Birlescu, Jose Machado and Doina Pisla

Technologies 2025, 13(1), 37; https://doi.org/10.3390/technologies13010037 - 16 Jan 2025

Viewed by 1677

Abstract

Background: Cerebrovascular accident, commonly known as stroke, Parkinson’s disease, and multiple sclerosis represent significant neurological conditions affecting millions globally. Stroke remains the third leading cause of death worldwide and significantly impacts patients’ hand functionality, making hand rehabilitation crucial for improving quality of life. [...] Read more.

Background: Cerebrovascular accident, commonly known as stroke, Parkinson’s disease, and multiple sclerosis represent significant neurological conditions affecting millions globally. Stroke remains the third leading cause of death worldwide and significantly impacts patients’ hand functionality, making hand rehabilitation crucial for improving quality of life. Methods: A comprehensive literature review was conducted analyzing over 300 papers, and categorizing them based on mechanical design, mobility, and actuation systems. To evaluate each device, a database with 45 distinct criteria was developed to systematically assess their characteristics. Results: The analysis revealed three main categories of devices: rigid exoskeletons, soft exoskeletons, and hybrid devices. Electric actuation represents the most common source of power. The dorsal placement of the mechanism is predominant, followed by glove-based, lateral, and palmar configurations. A correlation between mass and functionality was observed during the analysis; an increase in the number of actuated fingers or in functionality automatically increases the mass of the device. The research shows significant technological evolution with considerable variation in design complexity, with 29.4% of devices using five or more actuators while 24.8% employ one or two actuators. Conclusions: While substantial progress has been made in recent years, several challenges persist, including missing information or incomplete data from source papers and a limited number of clinical studies to evaluate device effectiveness. Significant opportunities remain to improve device functionality, usability, and therapeutic effectiveness, as well as to implement advanced power systems for portable devices. Full article

(This article belongs to the Special Issue Assistive Technologies in Care and Rehabilitation: Research, Developments, and International Initiatives)

► Show Figures

Figure 1

17 pages, 5166 KiB

Open AccessArticle

Implementing a Wide-Area Network and Low Power Solution Using Long-Range Wide-Area Network Technology

by Floarea Pitu and Nicoleta Cristina Gaitan

Technologies 2025, 13(1), 36; https://doi.org/10.3390/technologies13010036 - 16 Jan 2025

Viewed by 717

Abstract

In recent decades, technology has undergone significant transformations, aimed at optimizing and enhancing the quality of human life. A prime example of this progress is the Internet of Things (IoT) technology. Today, the IoT is widely applied across diverse sectors, including logistics, communications, [...] Read more.

In recent decades, technology has undergone significant transformations, aimed at optimizing and enhancing the quality of human life. A prime example of this progress is the Internet of Things (IoT) technology. Today, the IoT is widely applied across diverse sectors, including logistics, communications, agriculture, education, and infrastructure, demonstrating its versatility and profound relevance in various domains. Agriculture has historically been a fundamental sector for meeting humanity’s basic needs, and it is indispensable for survival and development. A critical factor in this regard is climatic and meteorological conditions directly influencing agricultural productivity. Therefore, real-time monitoring and analysis of these variables becomes imperative for optimizing production and reducing vulnerability to climate change. This paper presents the development and implementation of a low-power wide-area network (LPWAN) solution using LoRaWAN (long-range wide-area network) technology, designed for real-time environmental monitoring in agricultural applications. The system consists of energy-efficient end nodes and a custom-configured gateway, designed to optimize data transmission and power consumption. The end nodes integrate advanced sensors for temperature, humidity, and pressure, ensuring accurate data collection. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

20 pages, 2004 KiB

Open AccessArticle

A Dual-Stage Processing Architecture for Unmanned Aerial Vehicle Object Detection and Tracking Using Lightweight Onboard and Ground Server Computations

by Odysseas Ntousis, Evangelos Makris, Panayiotis Tsanakas and Christos Pavlatos

Technologies 2025, 13(1), 35; https://doi.org/10.3390/technologies13010035 - 16 Jan 2025

Viewed by 595

Abstract

UAVs are widely used for multiple tasks, which in many cases require autonomous processing and decision making. This autonomous function often requires significant computational capabilities that cannot be integrated into the UAV due to weight or cost limitations, making the distribution of the [...] Read more.

UAVs are widely used for multiple tasks, which in many cases require autonomous processing and decision making. This autonomous function often requires significant computational capabilities that cannot be integrated into the UAV due to weight or cost limitations, making the distribution of the workload and the combination of the results produced necessary. In this paper, a dual-stage processing architecture for object detection and tracking in Unmanned Aerial Vehicles (UAVs) is presented, focusing on efficient resource utilization and real-time performance. The proposed system delegates lightweight detection tasks to onboard hardware while offloading computationally intensive processes to a ground server. The UAV is equipped with a Raspberry Pi for onboard data processing, utilizing an Intel Neural Compute Stick 2 (NCS2) for accelerated object detection. Specifically, YOLOv5n is selected as the onboard model. The UAV transmits selected frames to the ground server, which handles advanced tracking, trajectory prediction, and target repositioning using state-of-the-art deep learning models. Communication between the UAV and the server is maintained through a high-speed Wi-Fi link, with a fallback to a 4G connection when needed. The ground server, equipped with an NVIDIA A40 GPU, employs YOLOv8x for object detection and DeepSORT for multi-object tracking. The proposed architecture ensures real-time tracking with minimal latency, making it suitable for mission-critical UAV applications such as surveillance and search and rescue. The results demonstrate the system’s robustness in various environments, highlighting its potential for effective object tracking under limited onboard computational resources. The system achieves recall and accuracy scores as high as 0.53 and 0.74, respectively, using the remote server, and is capable of re-identifying a significant portion of objects of interest lost by the onboard system, measured at approximately 70%. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

33 pages, 15628 KiB

Open AccessArticle

Towards Transparent AI in Medicine: ECG-Based Arrhythmia Detection with Explainable Deep Learning

by Oleksii Kovalchuk, Oleksandr Barmak, Pavlo Radiuk, Liliana Klymenko and Iurii Krak

Technologies 2025, 13(1), 34; https://doi.org/10.3390/technologies13010034 - 14 Jan 2025

Viewed by 845

Abstract

Cardiovascular diseases are the leading cause of death globally, highlighting the need for accurate diagnostic tools. To address this issue, we introduce a novel approach for arrhythmia detection based on electrocardiogram (ECG) that incorporates explainable artificial intelligence through three key methods. First, we [...] Read more.

Cardiovascular diseases are the leading cause of death globally, highlighting the need for accurate diagnostic tools. To address this issue, we introduce a novel approach for arrhythmia detection based on electrocardiogram (ECG) that incorporates explainable artificial intelligence through three key methods. First, we developed an enhanced R peak detection method that integrates domain-specific knowledge into the ECG, improving peak identification accuracy by accounting for the characteristic features of R peaks. Second, we proposed an arrhythmia classification method utilizing a modified convolutional neural network (CNN) architecture with additional convolutional and batch normalization layers. This model processes a triad of cardio cycles—the preceding, current, and following cycles—to capture temporal dependencies and hidden features related to arrhythmias. Third, we implemented an interpretation method that explains CNN’s decisions using clinically relevant features, making the results understandable to clinicians. Using the MIT-BIH database, our approach achieved an accuracy of 99.43%, with F1-scores approaching 100% for major arrhythmia classes. The integration of these methods enhances both the performance and transparency of arrhythmia detection systems. Full article

(This article belongs to the Special Issue The Future of Healthcare: Biomedical Technology and Integrated Artificial Intelligence 2nd Edition)

► Show Figures

Figure 1

16 pages, 11605 KiB

Open AccessArticle

Application of Graph Theory and Variants of Greedy Graph Coloring Algorithms for Optimization of Distributed Peer-to-Peer Blockchain Networks

by Miljenko Švarcmajer, Denis Ivanović, Tomislav Rudec and Ivica Lukić

Technologies 2025, 13(1), 33; https://doi.org/10.3390/technologies13010033 - 13 Jan 2025

Viewed by 675

Abstract

This paper investigates the application of graph theory and variants of greedy graph coloring algorithms for the optimization of distributed peer-to-peer networks, with a special focus on private blockchain networks. The graph coloring problem, as an NP-hard problem, presents a challenge in determining [...] Read more.

This paper investigates the application of graph theory and variants of greedy graph coloring algorithms for the optimization of distributed peer-to-peer networks, with a special focus on private blockchain networks. The graph coloring problem, as an NP-hard problem, presents a challenge in determining the minimum number of colors needed to efficiently allocate resources within the network. The paper deals with the influence of different graph density, i.e., the number of links, on the efficiency of greedy algorithms such as DSATUR, Descending, and Ascending. Experimental results show that increasing the number of links in the network contributes to a more uniform distribution of colors and increases the resistance of the network, whereby the DSATUR algorithm achieves the most uniform color saturation. The optimal configuration for a 100-node network has been identified at around 2000 to 2500 links, which achieves stability without excessive redundancy. These results are applied in the context of a private blockchain network that uses optimal connectivity to achieve high resilience and efficient resource allocation. The research findings suggest that adapting network configuration using greedy algorithms can contribute to the optimization of distributed systems, making them more stable and resilient to loads. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

32 pages, 1348 KiB

Open AccessReview

Vision Transformers for Image Classification: A Comparative Survey

by Yaoli Wang, Yaojun Deng, Yuanjin Zheng, Pratik Chattopadhyay and Lipo Wang

Technologies 2025, 13(1), 32; https://doi.org/10.3390/technologies13010032 - 12 Jan 2025

Viewed by 1091

Abstract

Transformers were initially introduced for natural language processing, leveraging the self-attention mechanism. They require minimal inductive biases in their design and can function effectively as set-based architectures. Additionally, transformers excel at capturing long-range dependencies and enabling parallel processing, which allows them to outperform [...] Read more.

Transformers were initially introduced for natural language processing, leveraging the self-attention mechanism. They require minimal inductive biases in their design and can function effectively as set-based architectures. Additionally, transformers excel at capturing long-range dependencies and enabling parallel processing, which allows them to outperform traditional models, such as long short-term memory (LSTM) networks, on sequence-based tasks. In recent years, transformers have been widely adopted in computer vision, driving remarkable advancements in the field. Previous surveys have provided overviews of transformer applications across various computer vision tasks, such as object detection, activity recognition, and image enhancement. In this survey, we focus specifically on image classification. We begin with an introduction to the fundamental concepts of transformers and highlight the first successful Vision Transformer (ViT). Building on the ViT, we review subsequent improvements and optimizations introduced for image classification tasks. We then compare the strengths and limitations of these transformer-based models against classic convolutional neural networks (CNNs) through experiments. Finally, we explore key challenges and potential future directions for image classification transformers. Full article

(This article belongs to the Collection Review Papers Collection for Advanced Technologies)

► Show Figures

Figure 1

24 pages, 2817 KiB

Open AccessArticle

Study on the Dynamic Response of the Carbody–Anti-Bending Bars System

by Ioana-Izabela Apostol, Traian Mazilu and Mădălina Dumitriu

Technologies 2025, 13(1), 31; https://doi.org/10.3390/technologies13010031 - 12 Jan 2025

Viewed by 617

Abstract

Ride comfort is an important requirement that passenger rail vehicles must meet. Carbody–anti-bending system is a relatively new passive method to enhance the ride comfort in passenger rail vehicles with long and light carbody. The resonance frequency of the first bending mode (FBM) [...] Read more.

Ride comfort is an important requirement that passenger rail vehicles must meet. Carbody–anti-bending system is a relatively new passive method to enhance the ride comfort in passenger rail vehicles with long and light carbody. The resonance frequency of the first bending mode (FBM) of such vehicle is within the most sensitive frequency range that affects ride comfort. Anti-bending bars consist of two bars that are mounted under the longitudinal beams of the carbody chassis using vertical supports. When the carbody bends, the anti-bending bars develop moments in the neutral axis of the carbody opposing the bending of the carbody. In this way, the carbody structure becomes stiffer and the resonance frequency of the FBM can be increased beyond the upper limit of the discomfort range of frequency, improving the ride comfort. The theoretical principle of this method has been demonstrated employing a passenger rail vehicle model that includes the carbody as a free–free Euler–Bernoulli beam and the anti-bending bars as longitudinal springs jointed to the vertical supports. Also, the method feasibility has been verified in the past using an experimental scale demonstrator system. In this paper, a new model of the carbody–anti-bending bar system is proposed by including three-directional elastic elements (vertical and longitudinal direction and rotation in the vertical–longitudinal plane) to model the fastening of the anti-bending bars to the supports and the vertical motion of the anti-bending bars modelled as free–free Euler–Bernoulli beams connected to the elastic elements of the fastening. In the longitudinal direction, the anti-bending bars work as springs connected to the longitudinal elastic elements of the fastening. The modal analysis method is applied to point out the basic properties of the frequency response functions (FRFs) of the carbody–anti-bending bars system, considering the bounce and FBMs of both the carbody and the anti-bending bars. A parametric study of the FRF of the carbody shows that the vertical stiffness of the fastening should be sufficiently high enough to eliminate the influence of the modes of the anti-bending bars upon the carbody response and to reduce the anti-bending bars vibration in the frequency range of interest. Longitudinal stiffness of the elastic elements of the fastening is critical to increase the bending resonance frequency of the carbody out of the sensitive range. Longer anti-bending bars can improve the capability of the anti-bending bars to increase the bending resonance without the risk of interference effects caused by the bounce and bending modes of the anti-bending bars. Full article

► Show Figures

Figure 1

21 pages, 6806 KiB

Open AccessArticle

Increasing the Wear Resistance of Stamping Tools for Coordinate Punching of Sheet Steel Using CrAlSiN and DLC:Si Coatings

by Sergey N. Grigoriev, Marina A. Volosova, Ilya A. Korotkov, Vladimir D. Gurin, Artem P. Mitrofanov, Sergey V. Fedorov and Anna A. Okunkova

Technologies 2025, 13(1), 30; https://doi.org/10.3390/technologies13010030 - 12 Jan 2025

Viewed by 717

Abstract

The punching of holes or recesses on computer numerical control coordinate presses occurs in sheets at high speeds (up to 1200 strokes/min) with an accuracy of ~0.05 mm. One of the most effective approaches to the wear rate reduction of stamping tools is [...] Read more.

The punching of holes or recesses on computer numerical control coordinate presses occurs in sheets at high speeds (up to 1200 strokes/min) with an accuracy of ~0.05 mm. One of the most effective approaches to the wear rate reduction of stamping tools is the use of solid lubricants, such as wear-resistant coatings, where the bulk properties of the tool are combined with high microhardness and lubricating ability to eliminate waste disposal and remove oil contaminants from liquid lubricants. This work describes the efficiency of complex CrAlSiN/DLC:Si coatings deposited using a hybrid unit combining physical vapor deposition and plasma-assisted chemical vapor deposition technologies to increase the wear resistance of a punch tool made of X165CrMoV12 die steel during coordinate punching of 4.0 mm thick 41Cr4 carbon structural steel sheets. The antifriction layer of DLC:Si allows for minimizing the wear under thermal exposure of 200 °C. The wear criterion of the lateral surface was 250 μm. The tribological tests allow us to consider the CrAlSiN/DLC:Si coatings as effective in increasing the wear resistance of stamping tools (21,000 strokes for the uncoated tool and 48,000 strokes for the coated one) when solving a wide range of technological problems in sheet stamping of structural steels. Full article

(This article belongs to the Topic Advances in Design, Manufacturing, and Dynamics of Complex Systems)

► Show Figures

Figure 1

22 pages, 6268 KiB

Open AccessArticle

Real-Time Deployment of Ultrasound Image Interpretation AI Models for Emergency Medicine Triage Using a Swine Model

by Sofia I. Hernandez Torres, Lawrence Holland, Theodore Winter, Ryan Ortiz, Krysta-Lynn Amezcua, Austin Ruiz, Catherine R. Thorpe and Eric J. Snider

Technologies 2025, 13(1), 29; https://doi.org/10.3390/technologies13010029 - 11 Jan 2025

Viewed by 661

Abstract

Ultrasound imaging is commonly used for medical triage in both civilian and military emergency medicine sectors. One specific application is the eFAST, or the extended focused assessment with sonography in trauma exam, where pneumothorax, hemothorax, or abdominal hemorrhage injuries are identified. However, the [...] Read more.

Ultrasound imaging is commonly used for medical triage in both civilian and military emergency medicine sectors. One specific application is the eFAST, or the extended focused assessment with sonography in trauma exam, where pneumothorax, hemothorax, or abdominal hemorrhage injuries are identified. However, the diagnostic accuracy of an eFAST exam depends on obtaining proper scans and making quick interpretation decisions to evacuate casualties or administer necessary interventions. To improve ultrasound interpretation, we developed AI models to identify key anatomical structures at eFAST scan sites, simplifying image acquisition by assisting with proper probe placement. These models plus image interpretation diagnostic models were paired with two real-time eFAST implementations. The first implementation was a manual AI-driven ultrasound eFAST tool that used guidance models to select correct frames prior to making any diagnostic predictions. The second implementation was a robotic imaging platform capable of providing semi-autonomous image acquisition combined with diagnostic image interpretation. We highlight the use of both real-time approaches in a swine injury model and compare their performance of this emergency medicine application. In conclusion, AI can be deployed in real time to provide rapid triage decisions, lowering the skill threshold for ultrasound imaging at or near the point of injury. Full article

(This article belongs to the Special Issue The Future of Healthcare: Biomedical Technology and Integrated Artificial Intelligence 2nd Edition)

► Show Figures

Figure 1

22 pages, 18812 KiB

Open AccessArticle

Enhancing Thyroid Nodule Detection in Ultrasound Images: A Novel YOLOv8 Architecture with a C2fA Module and Optimized Loss Functions

by Shidan Wang, Zi-An Zhao, Yuze Chen, Ye-Jiao Mao and James Chung-Wai Cheung

Technologies 2025, 13(1), 28; https://doi.org/10.3390/technologies13010028 - 9 Jan 2025

Viewed by 771

Abstract

Thyroid-related diseases, particularly thyroid cancer, are rising globally, emphasizing the critical need for the early detection and accurate screening of thyroid nodules. Ultrasound imaging has inherent limitations—high noise, low contrast, and blurred boundaries—that make manual interpretation subjective and error-prone. To address these challenges, [...] Read more.

Thyroid-related diseases, particularly thyroid cancer, are rising globally, emphasizing the critical need for the early detection and accurate screening of thyroid nodules. Ultrasound imaging has inherent limitations—high noise, low contrast, and blurred boundaries—that make manual interpretation subjective and error-prone. To address these challenges, YOLO-Thyroid, an improved model for the automatic detection of thyroid nodules in ultrasound images, is presented herein. Building upon the YOLOv8 architecture, YOLO-Thyroid introduces the C2fA module—an extension of C2f that incorporates Coordinate Attention (CA)—to enhance feature extraction. Additionally, loss functions were incorporated, including class-weighted binary cross-entropy to alleviate class imbalance and SCYLLA-IoU (SIoU) to improve localization accuracy during boundary regression. A publicly available thyroid ultrasound image dataset was optimized using format conversion and data augmentation. The experimental results demonstrate that YOLO-Thyroid outperforms mainstream object detection models across multiple metrics, achieving a higher detection precision of 54%. The recall, calculated based on the detection of nodules containing at least one feature suspected of being malignant, reaches 58.2%, while the model maintains a lightweight structure. The proposed method significantly advances ultrasound nodule detection, providing an effective and practical solution for enhancing diagnostic accuracy in medical imaging. Full article

(This article belongs to the Special Issue The Future of Healthcare: Biomedical Technology and Integrated Artificial Intelligence 2nd Edition)

► Show Figures

Figure 1

30 pages, 10771 KiB

Open AccessArticle

Implementing Computer Vision in Android Apps and Presenting the Background Technology with Mathematical Demonstrations

by Roland Szabo

Technologies 2025, 13(1), 27; https://doi.org/10.3390/technologies13010027 - 9 Jan 2025

Viewed by 874

Abstract

The aim of this paper is to create image-processing Android apps to launch on the Google Play Store. Three apps with different usages will be presented for different situations. The first app is a night-vision app on an Android phone that uses OpenCV. [...] Read more.

The aim of this paper is to create image-processing Android apps to launch on the Google Play Store. Three apps with different usages will be presented for different situations. The first app is a night-vision app on an Android phone that uses OpenCV. The second app is a tooth-brushing assistant application. The app is made for mobile phones and uses advanced image-processing techniques to detect when the tooth is brushed correctly or incorrectly. The main focus is on the direction of the toothbrush movement because this is one of the key aspects of correctly brushing teeth. The direction of movement of the brush is detected using movement vectors. The third app is a lane-detection app on the smartphone. Lane detection is carried out using OpenCV and TensorFlow libraries. The mobile app was implemented on the Android operating system. The app has a live video feed of the surroundings. When in the area of view, there will be a road with a lane. The system detects the lane and draws a green line over it. Full article

(This article belongs to the Special Issue Advanced Autonomous Systems and Artificial Intelligence Stage)

► Show Figures

Figure 1

22 pages, 36914 KiB

Open AccessArticle

Cross-Attention Fusion of Visual and Geometric Features for Large-Vocabulary Arabic Lipreading

by Samar Daou, Achraf Ben-Hamadou, Ahmed Rekik and Abdelaziz Kallel

Technologies 2025, 13(1), 26; https://doi.org/10.3390/technologies13010026 - 9 Jan 2025

Viewed by 660

Abstract

Lipreading involves recognizing spoken words by analyzing the movements of the lips and surrounding area using visual data. It is an emerging research topic with many potential applications, such as human–machine interaction and enhancing audio-based speech recognition. Recent deep learning approaches integrate visual [...] Read more.

Lipreading involves recognizing spoken words by analyzing the movements of the lips and surrounding area using visual data. It is an emerging research topic with many potential applications, such as human–machine interaction and enhancing audio-based speech recognition. Recent deep learning approaches integrate visual features from the mouth region and lip contours. However, simple methods such as concatenation may not effectively optimize the feature vector. In this article, we propose extracting optimal visual features using 3D convolution blocks followed by a ResNet-18, while employing a graph neural network to extract geometric features from tracked lip landmarks. To fuse these complementary features, we introduce a cross-attention mechanism that combines visual and geometric information to obtain an optimal representation of lip movements for lipreading tasks. To validate our approach for Arabic, we introduce the first large-scale Lipreading in the Wild for Arabic (LRW-AR) dataset, consisting of 20,000 videos across 100 word classes, spoken by 36 speakers. Experimental results on both the LRW-AR and LRW datasets demonstrate the effectiveness of our approach, achieving accuracies of 85.85% and 89.41%, respectively. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

25 pages, 7319 KiB

Open AccessArticle

A Reinforcement Learning-Based Dynamic Clustering of Sleep Scheduling Algorithm (RLDCSSA-CDG) for Compressive Data Gathering in Wireless Sensor Networks

by Alaa N. El-Shenhabi, Ehab H. Abdelhay, Mohamed A. Mohamed and Ibrahim F. Moawad

Technologies 2025, 13(1), 25; https://doi.org/10.3390/technologies13010025 - 8 Jan 2025

Viewed by 638

Abstract

Energy plays a major role in wireless sensor networks (WSNs), and measurements demonstrate that transmission consumes more energy than processing. Hence, organizing the transmission process and managing energy usage throughout the network are the main goals for maximizing the network’s lifetime. This paper [...] Read more.

Energy plays a major role in wireless sensor networks (WSNs), and measurements demonstrate that transmission consumes more energy than processing. Hence, organizing the transmission process and managing energy usage throughout the network are the main goals for maximizing the network’s lifetime. This paper proposes an algorithm called RLDCSSA-CDG, which is processed through the 3F phases: foundation, formation, and forwarding phases. Firstly, the network architecture is founded, and the cluster heads (CHs) are determined in the foundation phase. Secondly, sensor nodes are dynamically gathered into clusters for better communication in the formation phase. Finally, the transmitting process will be adequately organized based on an adaptive wake-up/sleep scheduling algorithm to transmit the data at the “right time” in the forwarding phase. The MATLAB platform was utilized to conduct simulation studies to validate the proposed RLDCSSA-CDG’s effectiveness. Compared to a very recent work called RLSSA and RLDCA for CDG, the proposed RLDCSSA-CDG reduces total data transmissions by 22.7% and 63.3% and energy consumption by 8.93% and 38.8%, respectively. It also achieves the lowest latency compared to the two contrastive algorithms. Furthermore, the proposed algorithm increases the whole network lifetime by 77.3% and promotes data recovery accuracy by 91.1% relative to the compared algorithms. Full article

► Show Figures

Figure 1

16 pages, 1894 KiB

Open AccessArticle

Smart Sport Watch Usage: The Dominant Role of Technology Readiness over Exercise Motivation and Sensation Seeking

by Gershon Tenenbaum, Tomer Ben-Zion, Yair Amichai-Hamburger, Yair Galily and Assaf Lev

Technologies 2025, 13(1), 24; https://doi.org/10.3390/technologies13010024 - 7 Jan 2025

Viewed by 669

Abstract

The study examines the link between technology readiness/acceptance, motivation for exercising, and sensation seeking and using or avoiding Smart Sport Watches (SSW). A sample of 315 adolescents, Mage = 29.6 (SD = 11.01) and healthy male (n = 95, 30.2%) and female [...] Read more.

The study examines the link between technology readiness/acceptance, motivation for exercising, and sensation seeking and using or avoiding Smart Sport Watches (SSW). A sample of 315 adolescents, Mage = 29.6 (SD = 11.01) and healthy male (n = 95, 30.2%) and female (n = 179, 56.85%), completed all the measures of these variables’ dimensions via the internet. Multiple followed by univariate analyses of variance (MANOVA, ANOVA) were performed for each of the study’s psychological dimensions and single variables. The two categorical factors (e.g., BS factors) were the use of SSW (yes/no) and walk/run (yes/no). Results revealed that adolescents using SSW rated themselves significantly (p < 0.05) and substantially higher than their non-SSW users on positive readiness for technology (d = 0.47), and specifically on optimism (d = 0.34) and innovation (d = 0.51). Moreover, users of SSW reported significantly (p < 0.05) and substantially lower negative readiness for technology than their non-SSW users’ counterparts (d = −0.49), and specifically on discomfort (d = −0.38) and distrust (d = −50), but neither on the overall motivation for exercise dimensions nor on sensation-seeking. Moreover, adolescents who walk/run reported being more internally motivated (d = 0.38), integrated (d = 0.61), and identified (d = 0.34) than their sedentary counterparts. Discussion centers on the important role of readiness/acceptance in using technological devices and the need to use technology-specific motivation and personality measures to further explore this phenomenon. Full article

(This article belongs to the Special Issue Assistive Technologies in Care and Rehabilitation: Research, Developments, and International Initiatives)

► Show Figures

Figure 1

43 pages, 2436 KiB

Open AccessReview

Blockchain Applications in the Military Domain: A Systematic Review

by Nikos Kostopoulos, Yannis C. Stamatiou, Constantinos Halkiopoulos and Hera Antonopoulou

Technologies 2025, 13(1), 23; https://doi.org/10.3390/technologies13010023 - 6 Jan 2025

Viewed by 1221

Abstract

Background: Blockchain technology can transform military operations, increasing security and transparency and gaining efficiency. It addresses many problems related to data security, privacy, communication, and supply chain management. The most researched aspects are its integration with emerging technologies, such as artificial intelligence, the [...] Read more.

Background: Blockchain technology can transform military operations, increasing security and transparency and gaining efficiency. It addresses many problems related to data security, privacy, communication, and supply chain management. The most researched aspects are its integration with emerging technologies, such as artificial intelligence, the IoT, application in uncrewed aerial vehicles, and secure communications. Methods: A systematic review of 43 peer-reviewed articles was performed to discover the applications of blockchain in defense. Key areas analyzed include the role of blockchain in securing communications, fostering transparency, promoting real-time data sharing, and using smart contracts for maintenance management. Challenges were assessed, including scalability, interoperability, and integration with the legacy system, alongside possible solutions, such as sharding and optimized consensus mechanisms. Results: In the case of blockchain, great potential benefits were shown in enhancing military operations, including secure communication, immutable record keeping, and real-time integration of data with the IoT and AI. Smart contracts optimized resource allocation and reduced maintenance procedures. However, challenges remain, such as scalability, interoperability, and high energy requirements. Proposed solutions, like sharding and hybrid architecture, show promise to address these issues. Conclusions: Blockchain is set to revolutionize the efficiency and security of the military. Its potential is enormous, but it must overcome scalability, interoperability, and integration issues. Further research and strategic adoption will thus allow blockchain to become one of the cornerstones of future military operations. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

29 pages, 5761 KiB

Open AccessReview

Bridging the Maturity Gaps in Industrial Data Science: Navigating Challenges in IoT-Driven Manufacturing

by Amruta Awasthi, Lenka Krpalkova and Joseph Walsh

Technologies 2025, 13(1), 22; https://doi.org/10.3390/technologies13010022 - 6 Jan 2025

Viewed by 911

Abstract

This narrative review evaluates the curtail components of data maturity in manufacturing industries, the associated challenges, and the application of industrial data science (IDS) to improve organisational decision-making. As data availability grows larger, manufacturing organisations face difficulties comprehending heterogeneous datasets of varying quality, [...] Read more.

This narrative review evaluates the curtail components of data maturity in manufacturing industries, the associated challenges, and the application of industrial data science (IDS) to improve organisational decision-making. As data availability grows larger, manufacturing organisations face difficulties comprehending heterogeneous datasets of varying quality, which may lead to inefficient decision-making and other operational inefficiencies. It underlines that data appropriate for its intended application is considered quality data. The importance of including stakeholders in the data review process to enhance the data quality is accentuated in this paper, specifically when big data analysis is to be integrated into corporate strategies. Manufacturing industries leveraging their data thoughtfully can optimise efficiency and facilitate informed and productive decision-making by establishing a robust technical infrastructure and developing intuitive platforms and solutions. This study highlights the significance of IDS in revolutionising manufacturing sectors within the framework of Industry 4.0 and the Industrial Internet of Things (IIoT), demonstrating that big data can substantially improve efficiency, reduce costs, and guide strategic decision-making. The gaps or maturity levels among industries show a substantial discrepancy in this analysis, which is classified into three types: Industry 4.0 maturity levels, data maturity or readiness condition index, and industrial data science and analytics maturity. The emphasis is given to the pressing need for resilient data science frameworks enabling organisations to evaluate their digital readiness and execute their data-driven plans efficiently and effortlessly. Simultaneously, future work will focus on pragmatic applications to enhance industrial competitiveness within the heavy machinery sector. Full article

(This article belongs to the Section Manufacturing Technology)

► Show Figures

Graphical abstract

20 pages, 8701 KiB

Open AccessArticle

Prosthetic Hand Based on Human Hand Anatomy Controlled by Surface Electromyography and Artificial Neural Network

by Larisa Dunai, Isabel Seguí Verdú, Dinu Turcanu and Viorel Bostan

Technologies 2025, 13(1), 21; https://doi.org/10.3390/technologies13010021 - 2 Jan 2025

Viewed by 891

Abstract

Humans have a complex way of expressing their intuitive intentions in real gestures. That is why many gesture detection and recognition techniques have been studied and developed. There are many methods of human hand signal reading, such as those using electroencephalography, electrocorticography, and [...] Read more.

Humans have a complex way of expressing their intuitive intentions in real gestures. That is why many gesture detection and recognition techniques have been studied and developed. There are many methods of human hand signal reading, such as those using electroencephalography, electrocorticography, and electromyography, as well as methods for gesture recognition. In this paper, we present a method based on real-time surface electroencephalography hand-based gesture recognition using a multilayer neural network. For this purpose, the sEMG signals have been amplified, filtered and sampled; then, the data have been segmented, feature extracted and classified for each gesture. To validate the method, 100 signals for three gestures with 64 samples each signal have been recorded from 2 users with OYMotion sensors and 100 signals for three gestures from 4 users with the MyWare sensors. These signals were used for feature extraction and classification using an artificial neuronal network. The model converges after 10 sessions, achieving 98% accuracy. As a result, an algorithm was developed that aimed to recognize two specific gestures (handling a bottle and pointing with the index finger) in real time with 95% accuracy. Full article

(This article belongs to the Section Assistive Technologies)

► Show Figures

Figure 1

36 pages, 6996 KiB

Open AccessReview

Organic–Inorganic Hybrid Dielectric Layers for Low-Temperature Thin-Film Transistors Applications: Recent Developments and Perspectives

by Javier Meza-Arroyo and Rafael Ramírez-Bon

Technologies 2025, 13(1), 20; https://doi.org/10.3390/technologies13010020 - 2 Jan 2025

Viewed by 918

Abstract

This paper reviews the recent development of organic–inorganic hybrid dielectric materials for application as gate dielectrics in thin-film transistors (TFTs). These hybrid materials consist of the blending of high-k inorganic dielectrics with polymers, and their resulting properties depend on the amount and type [...] Read more.

This paper reviews the recent development of organic–inorganic hybrid dielectric materials for application as gate dielectrics in thin-film transistors (TFTs). These hybrid materials consist of the blending of high-k inorganic dielectrics with polymers, and their resulting properties depend on the amount and type of interactions between the organic and inorganic phases. The resulting amorphous networks, characterized by crosslinked organic and inorganic phases, can be tailored for specific applications, including gate dielectrics in TFTs. As dielectric materials, they offer a synergistic combination of high dielectric constants, low leakage currents, and mechanical flexibility, crucial for next-generation flexible electronics. Furthermore, organic–inorganic hybrid materials are easily processed in solution, allowing for low-temperature deposition compatible with flexible substrates. Various configurations of these hybrid gate dielectrics, such as bilayer structures and polymer nanocomposites, are discussed, with an emphasis on their potential to enhance device performance. Despite the significant advancements, challenges remain in optimizing the performance and stability of these hybrid materials. This review summarizes recent progress and highlights the advantages and emerging applications of low-temperature, solution-processed hybrid dielectrics, with a focus on their integration into flexible, stretchable, and wearable electronic devices. Full article

(This article belongs to the Topic Advances in Microelectronics and Semiconductor Engineering)

► Show Figures

Figure 1

21 pages, 2475 KiB

Open AccessArticle

Optimization of Energy Consumption in Voice Assistants Through AI-Enabled Cache Implementation: Development and Evaluation of a Metric

by Alber Oswaldo Montoya Benitez, Álvaro Suárez Sarmiento, Elsa María Macías López and Jorge Herrera-Ramirez

Technologies 2025, 13(1), 19; https://doi.org/10.3390/technologies13010019 - 2 Jan 2025

Viewed by 806

Abstract

Intelligent systems developed under the Internet of Things (IoT) paradigm offer solutions for various social and productive scenarios. Voice assistants (VAs), as part of IoT-based systems, facilitate task execution in a simple and automated manner, from entertainment to critical activities. Lithium batteries often [...] Read more.

Intelligent systems developed under the Internet of Things (IoT) paradigm offer solutions for various social and productive scenarios. Voice assistants (VAs), as part of IoT-based systems, facilitate task execution in a simple and automated manner, from entertainment to critical activities. Lithium batteries often power these devices. However, their energy consumption can be high due to the need to remain in continuous listening mode and the time it takes to search for and deliver responses from the Internet. This work proposes the implementation of a VA through Artificial Intelligence (AI) training and using cache memory to minimize response time and reduce energy consumption. First, the difference in energy consumption between VAs in active and passive states is experimentally verified. Subsequently, a communication architecture and a model representing the behavior of VAs are presented, from which a metric is developed to evaluate the energy consumption of these devices. The cache-enabled prototype shows a reduction in response time and energy expenditure (comparing the results of cloud-based VA and cache-based VA), several times lower according to the developed metric, demonstrating the effectiveness of the proposed system. This development could be a viable solution for areas with limited power sources, low coverage, and mobility situations that affect internet connectivity. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

14 pages, 9705 KiB

Open AccessArticle

ZnO Nanoparticles by Hydrothermal Method: Synthesis and Characterization

by Juan Carlos Anaya-Zavaleta, Antonio Serguei Ledezma-Pérez, Carlos Gallardo-Vega, Joelis Rodríguez-Hernández, Carmen Natividad Alvarado-Canché, Perla Elvia García-Casillas, Arxel de León and Agustín Leobardo Herrera-May

Technologies 2025, 13(1), 18; https://doi.org/10.3390/technologies13010018 - 1 Jan 2025

Viewed by 1103

Abstract

The synthesis of reliable, cost-effective, and eco-friendly ZnO piezoelectric nanoparticles (NPs) can contribute to nanotechnology applications in electronics, sensors, and energy harvesting. Herein, ZnO NPs were synthesized using a hydrothermal method under varied reaction times and adding ammonium hydroxide, which provided an advantage [...] Read more.

The synthesis of reliable, cost-effective, and eco-friendly ZnO piezoelectric nanoparticles (NPs) can contribute to nanotechnology applications in electronics, sensors, and energy harvesting. Herein, ZnO NPs were synthesized using a hydrothermal method under varied reaction times and adding ammonium hydroxide, which provided an advantage of a low-cost, scalable, low-temperature, and environmentally friendly process. Characterization through UV–Vis spectroscopy revealed absorption peaks between 374 and 397 nm, showing a blue shift compared to bulk ZnO (400 nm) attributable to nanoscale dimensions. Transmission Electron Microscopy (TEM) analysis indicated particle dimensions with length and width ranges from 150 to 341 nm and from 83 to 120 nm, respectively. X-ray diffraction (XRD) confirmed high-crystalline quality, with crystallite sizes calculated using the Scherrer equation. In addition, the effective mass model provided an estimated band gap that matched with the reported data. Also, the lattice parameters, interplanar distances, and Zn-O bond lengths were consistent with Joint Committee on Powder Diffraction Standards (JCPDS). Finally, a ZnO NP film was deposited on a steel substrate, which generated a displacement of 150 nm under a square wave voltage of 10 V. The piezoelectric behavior of the synthesized ZnO NPs can be useful for fabrication of piezoelectric nanogenerators. The proposed synthesis can allow ZnO NPs with potential application in electronic devices, energy harvesters, and transducers. Full article

(This article belongs to the Special Issue Technological Advances in Science, Medicine, and Engineering 2024)

► Show Figures

Graphical abstract

18 pages, 3764 KiB

Open AccessArticle

Edge or Cloud Architecture: The Applicability of New Data Processing Methods in Large-Scale Poultry Farming

by Gergo Toth, Sandor Szabo, Tamas Haidegger and Marta Alexy

Technologies 2025, 13(1), 17; https://doi.org/10.3390/technologies13010017 - 1 Jan 2025

Viewed by 1334

Abstract

As large-scale poultry farming becomes more intensive and concentrated, a deeper understanding of poultry meat production processes is crucial for achieving maximum economic and ecological efficiency. The transmission and analysis of data collected on birds and the farming environment in large-scale production environments [...] Read more.

As large-scale poultry farming becomes more intensive and concentrated, a deeper understanding of poultry meat production processes is crucial for achieving maximum economic and ecological efficiency. The transmission and analysis of data collected on birds and the farming environment in large-scale production environments using digital tools on a secure platform are not straightforward. In our on-site research, we have investigated two architectures, a cloud-based processing architecture and an edge computing-based one, in large-scale poultry farming circumstances. These results underscore the effectiveness of combining edge and cloud-based solutions to overcome the distinct challenges of precision poultry farming settings. Our system’s dynamic capability, supported by AWS’s robust cloud infrastructure and on-site edge computing solutions, ensured comprehensive monitoring and management of agricultural data, leading to more informed decision-making and improved operational efficiencies. A hybrid approach often represents the most viable strategy when examining contrasting strengths and weaknesses. Combining edge and cloud solutions allows for the robustness and immediate response of edge computing while still leveraging cloud systems’ advanced analytical capabilities and scalability. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

19 pages, 6211 KiB

Open AccessArticle

Predictive Modeling of Total Real and Reactive Power Losses in Contingency Systems Using Function-Fitting Neural Networks with Graphical User Interface

by Alfredo Bonini Neto, Alexandre de Queiroz, Giovana Gonçalves da Silva, André Gifalli, André Nunes de Souza and Enio Garbelini

Technologies 2025, 13(1), 15; https://doi.org/10.3390/technologies13010015 - 1 Jan 2025

Viewed by 823

Abstract

Technical power losses in power systems are unavoidable, caused by factors such as transformer impedance, conductor resistance, equipment inefficiencies, line reactance, and phase imbalances. Reducing these losses is essential for improving system efficiency. This study introduces an innovative approach using Artificial Neural Networks [...] Read more.

Technical power losses in power systems are unavoidable, caused by factors such as transformer impedance, conductor resistance, equipment inefficiencies, line reactance, and phase imbalances. Reducing these losses is essential for improving system efficiency. This study introduces an innovative approach using Artificial Neural Networks (ANN) combined with the graphical interface to predict complete curves of real and reactive power losses in power systems under various contingencies. The key advantage of this methodology is its speed, allowing quick estimation of power loss curves both in normal and contingency conditions, whether mild or severe. ANN models excel at capturing the nonlinear behavior of power systems, eliminating the need for iterative methods commonly used in traditional approaches. The results showed that the ANN performed effectively, with a mean squared error during training below the specified threshold. For samples not included in the training set, the network accurately estimated 99% of the real and reactive power losses within the specified range, with residuals around 10⁻³ and an overall accuracy rate of 99% between the desired and obtained outputs. Additionally, a Graphical User Interface (GUI) was implemented to facilitate user interaction, allowing for easy visualization of power-loss predictions and real-time adjustments. Full article

► Show Figures

Figure 1

18 pages, 2912 KiB

Open AccessArticle

Analog Replicator of Long Chaotic Radio Pulses for Coherent Processing

by Lev Kuzmin, Elena Efremova, Pavel Vladyka and Vadim Itskov

Technologies 2025, 13(1), 16; https://doi.org/10.3390/technologies13010016 - 31 Dec 2024

Viewed by 766

Abstract

The relative structural simplicity of chaotic oscillators and the possibility of obtaining signals with a large dimension is of great interest for wireless data transmission and processing. The diversity of signal waveforms from the same source of chaos is provided by a fundamental [...] Read more.

The relative structural simplicity of chaotic oscillators and the possibility of obtaining signals with a large dimension is of great interest for wireless data transmission and processing. The diversity of signal waveforms from the same source of chaos is provided by a fundamental property of chaotic oscillations: sensitivity to the choice of initial conditions. In this paper, this sensitivity is employed in the proposed method for forming analog chaotic radio pulses of arbitrary (specified) duration using an analog oscillator in such a way that the pulse shape can be changed and repeated from pulse to pulse. To repeat the shape of oscillations for an arbitrarily long period of time is not a problem for digital chaotic oscillators, but for analog systems, this is a challenge due to the impossibility of controlling the initial conditions and the evolution of the analog trajectory. In this paper, a new method for generating chaos is proposed, which can both change and repeat the shape of a chaotic signal of arbitrary duration, i.e., long chaotic radio pulses. The generator acts as a reservoir and as a replicator from which, under external influence, a signal of a certain shape can be extracted, and this shape can be reproduced. The term “long” in this case means that the duration of chaotic radio pulses is many times greater than the characteristic time of divergence of chaotic trajectories. To prove the correctness of the proposed generation method, the results of its experimental implementation in the frequency range of 100 to 500 MHz are given. Examples of forming equal pulses with a duration of about 20 to 200 quasi-periods of oscillations (up to 500 ns) are given. The proposed method provides the technical possibility of forming pulses whose dimensions can vary in a wide range, which is important for implementing large processing gains in various wireless applications. The method can be implemented in various frequency ranges in the class of analog generators of chaotic oscillations, since the employed generation method, i.e., modulation of a transistor generator by supply voltage, is natural for radio engineering. Full article

(This article belongs to the Topic Advances in Design, Manufacturing, and Dynamics of Complex Systems)

► Show Figures

Figure 1

27 pages, 11281 KiB

Open AccessArticle

Pre-Occupancy Evaluation of Affective Experiences in Building Information Modeling Through SLR and an e-Delphi Survey

by Balamaheshwaran Renganathan, Radhakrishnan Shanthi Priya and Ramalingam Senthil

Technologies 2025, 13(1), 14; https://doi.org/10.3390/technologies13010014 - 30 Dec 2024

Viewed by 844

Abstract

Building information modeling (BIM) is increasingly used during the conceptual design phase, which focuses on simulations such as energy usage analysis and comfort levels, like temperature and lighting conditions, to enhance user experience and well-being, which are key factors for meeting Sustainable Development [...] Read more.

Building information modeling (BIM) is increasingly used during the conceptual design phase, which focuses on simulations such as energy usage analysis and comfort levels, like temperature and lighting conditions, to enhance user experience and well-being, which are key factors for meeting Sustainable Development Goal 3. This study employs a systematic literature review and an e-Delphi survey to explore how a pre-occupancy evaluation integrated within BIM frameworks addresses affective responses and suggests ways to improve design decisions that align with the UN’s sustainable development goals. The study identified a research gap in how BIM evaluations are conducted during the conceptual design stage, including crucial sensory aspects for human well-being. The research suggests incorporating evidence-based design instruments like body sensor networks (BSN) and immersive virtual reality and methods like neurophenomenology to enhance the assessment of user interactions in the design process. Prioritizing the human-centered design approach right from the start can facilitate the integration of innovative workflows into architecture, engineering, and construction practices. Overcoming resistance to these workflows and methodologies is essential for advancing BIM’s role in fostering spatial environments that support health, well-being, and positive affective experiences. Full article

(This article belongs to the Section Construction Technologies)

► Show Figures

Figure 1

14 pages, 2385 KiB

Open AccessArticle

Analysis of Multidimensional Clinical and Physiological Data with Synolitical Graph Neural Networks

by Mikhail Krivonosov, Tatiana Nazarenko, Vadim Ushakov, Daniil Vlasenko, Denis Zakharov, Shangbin Chen, Oleg Blyus and Alexey Zaikin

Technologies 2025, 13(1), 13; https://doi.org/10.3390/technologies13010013 - 28 Dec 2024

Viewed by 880

Abstract

This paper introduces a novel approach for classifying multidimensional physiological and clinical data using Synolitic Graph Neural Networks (SGNNs). SGNNs are particularly good for addressing the challenges posed by high-dimensional datasets, particularly in healthcare, where traditional machine learning and Artificial Intelligence methods often [...] Read more.

This paper introduces a novel approach for classifying multidimensional physiological and clinical data using Synolitic Graph Neural Networks (SGNNs). SGNNs are particularly good for addressing the challenges posed by high-dimensional datasets, particularly in healthcare, where traditional machine learning and Artificial Intelligence methods often struggle to find global optima due to the “curse of dimensionality”. To apply Geometric Deep Learning we propose a synolitic or ensemble graph representation of the data, a universal method that transforms any multidimensional dataset into a network, utilising only class labels from training data. The paper demonstrates the effectiveness of this approach through two classification tasks: synthetic and fMRI data from cognitive tasks. Convolutional Graph Neural Network architecture is then applied, and the results are compared with established machine learning algorithms. The findings highlight the robustness and interpretability of SGNNs in solving complex, high-dimensional classification problems. Full article

(This article belongs to the Special Issue Data Science and Big Data in Biology, Physical Science and Engineering II)

► Show Figures

Figure 1

15 pages, 8336 KiB

Open AccessArticle

A Novel Vibration Suppression Method for Welding Robots Based on Welding Pool Instability Evaluation and Trajectory Optimization

by Mingtian Ma, Hong Lu, Yongquan Zhang, Zidong Wu, He Huang, Xujie Yuan, Xu Feng, Zhi Liu and Zhangjie Li

Technologies 2025, 13(1), 12; https://doi.org/10.3390/technologies13010012 - 28 Dec 2024

Viewed by 784

Abstract

Industrial robots are widely used in welding operations because of their high production efficiency. The structure of the robot and the complex stress conditions during welding operations lead to the vibration of the end of robot, which leads to welding defects. However, current [...] Read more.

Industrial robots are widely used in welding operations because of their high production efficiency. The structure of the robot and the complex stress conditions during welding operations lead to the vibration of the end of robot, which leads to welding defects. However, current vibration suppression techniques for welding robots usually only consider the robotic performance while overlooking their impact on the welding metal forming process. Therefore, based on the influence of robot vibration on welding pool stability during the welding process, a new welding robot vibration suppression method is proposed in this paper, along with the establishment of a welding pool stability assessment model. The proposed vibration suppression algorithm is based on the optimization of the welding trajectory. To enhance the performance of the method, the Particle Swarm Optimization (PSO) algorithm is applied to optimize the joint angular velocity and angular acceleration. Finally, robot welding experiments are designed and conducted. By comparing vibration measurement data and welding quality before and after the vibration suppression, the effectiveness and stability of the proposed method are validated. Full article

(This article belongs to the Special Issue Wire Arc Additive Manufacturing: Pioneering Techniques, Materials, and Applications)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Technologies, Volume 13, Issue 1 (January 2025) – 41 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI