Journal of Sensor and Actuator Networks

19 pages, 748 KiB

Open AccessArticle

Eye-Net: A Low-Complexity Distributed Denial of Service Attack-Detection System Based on Multilayer Perceptron

by Ramzi Khantouchi, Ibtissem Gasmi and Mohamed Amine Ferrag

J. Sens. Actuator Netw. 2024, 13(4), 45; https://doi.org/10.3390/jsan13040045 - 12 Aug 2024

Viewed by 856

Distributed Denial of Service (DDoS) attacks disrupt service availability, leading to significant financial setbacks for individuals and businesses. This paper introduces Eye-Net, a deep learning-based system optimized for DDoS attack detection that combines feature selection, balancing methods, Multilayer Perceptron (MLP), and quantization-aware training [...] Read more.

Distributed Denial of Service (DDoS) attacks disrupt service availability, leading to significant financial setbacks for individuals and businesses. This paper introduces Eye-Net, a deep learning-based system optimized for DDoS attack detection that combines feature selection, balancing methods, Multilayer Perceptron (MLP), and quantization-aware training (QAT) techniques. An Analysis of Variance (ANOVA) algorithm is initially applied to the dataset to identify the most distinctive features. Subsequently, the Synthetic Minority Oversampling Technique (SMOTE) balances the dataset by augmenting samples for under-represented classes. Two distinct MLP models are developed: one for the binary classification of flow packets as regular or DDoS traffic and another for identifying six specific DDoS attack types. We store MLP model weights at 8-bit precision by incorporating the quantization-aware training technique. This adjustment slashes memory use by a factor of four and reduces computational cost similarly, making Eye-Net suitable for Internet of Things (IoT) devices. Both models are rigorously trained and assessed using the CICDDoS2019 dataset. Test results reveal that Eye-Net excels, surpassing contemporary DDoS detection techniques in accuracy, recall, precision, and F1 Score. The multiclass model achieves an impressive accuracy of 96.47% with an error rate of 8.78%, while the binary model showcases an outstanding 99.99% accuracy, maintaining a negligible error rate of 0.02%. Full article

(This article belongs to the Section Network Security and Privacy)

► Show Figures

Figure 1

23 pages, 496 KiB

Open AccessArticle

AI and Computing Horizons: Cloud and Edge in the Modern Era

by Nasif Fahmid Prangon and Jie Wu

J. Sens. Actuator Netw. 2024, 13(4), 44; https://doi.org/10.3390/jsan13040044 - 9 Aug 2024

Viewed by 924

Abstract

Harnessing remote computation power over the Internet without the need for expensive hardware and making costly services available to mass users at a marginal cost gave birth to the concept of cloud computing. This survey provides a concise overview of the growing confluence [...] Read more.

Harnessing remote computation power over the Internet without the need for expensive hardware and making costly services available to mass users at a marginal cost gave birth to the concept of cloud computing. This survey provides a concise overview of the growing confluence of cloud computing, edge intelligence, and AI, with a focus on their revolutionary impact on the Internet of Things (IoT). The survey starts with a fundamental introduction to cloud computing, overviewing its key parts and the services offered by different service providers. We then discuss how AI is improving cloud capabilities through its indigenous apps and services and is creating a smarter cloud. We then focus on the impact of AI in one of the popular cloud paradigms called edge cloud and discuss AI on Edge and AI for Edge. We discuss how AI implementation on edge devices is transforming edge and IoT networks by pulling cognitive processing closer to where the data originates, improving efficiency and response. We also discuss major cloud providers and their service offerings within the ecosystem and their respective use cases. Finally, this research looks ahead at new trends and future scopes that are now becoming possible at the confluence of the cloud, edge computing, and AI in IoT. The purpose of this study is to demystify edge intelligence, including cloud computing, edge computing, and AI, and to focus on their synergistic role in taking IoT technologies to new heights. Full article

► Show Figures

Figure 1

27 pages, 5449 KiB

Open AccessArticle

Smart Stick Navigation System for Visually Impaired Based on Machine Learning Algorithms Using Sensors Data

by Sadik Kamel Gharghan, Hussein S. Kamel, Asaower Ahmad Marir and Lina Akram Saleh

J. Sens. Actuator Netw. 2024, 13(4), 43; https://doi.org/10.3390/jsan13040043 - 3 Aug 2024

Viewed by 863

Abstract

Visually Impaired People (VIP) face significant challenges in their daily lives, relying on others or trained dogs for assistance when navigating outdoors. Researchers have developed the Smart Stick (SS) system as a more effective aid than traditional ones to address these challenges. Developing [...] Read more.

Visually Impaired People (VIP) face significant challenges in their daily lives, relying on others or trained dogs for assistance when navigating outdoors. Researchers have developed the Smart Stick (SS) system as a more effective aid than traditional ones to address these challenges. Developing and utilizing the SS systems for VIP improves mobility, reliability, safety, and accessibility. These systems help users by identifying obstacles and hazards, keeping VIP safe and efficient. This paper presents the design and real-world implementation of an SS using an Arduino Nano microcontroller, GPS, GSM module, heart rate sensor, ultrasonic sensor, moisture sensor, vibration motor, and Buzzer. Based on sensor data, the SS can provide warning signals to VIP about the presence of obstacles and hazards around them. Several Machine Learning (ML) algorithms were used to improve the SS alert decision accuracy. Therefore, this paper used sensor data to train and test ten ML algorithms to find the most effective alert decision accuracy. Based on the ML algorithms, the alert decision, including the presence of obstacles, environmental conditions, and user health conditions, was examined using several performance metrics. Results showed that the AdaBoost, Gradient boosting, and Random Forest ML algorithms outperformed others and achieved an AUC and specificity of 100%, with 99.9% accuracy, F1-score, precision, recall, and MCC in the cross-validation phase. Integrating sensor data with ML algorithms revealed that the SS enables VIP to live independently and move safely without assistance. Full article

(This article belongs to the Section Actuators, Sensors and Devices)

► Show Figures

Figure 1

19 pages, 6382 KiB

Open AccessArticle

Tool Condition Monitoring in the Milling Process Using Deep Learning and Reinforcement Learning

by Devarajan Kaliyannan, Mohanraj Thangamuthu, Pavan Pradeep, Sakthivel Gnansekaran, Jegadeeshwaran Rakkiyannan and Alokesh Pramanik

J. Sens. Actuator Netw. 2024, 13(4), 42; https://doi.org/10.3390/jsan13040042 - 30 Jul 2024

Viewed by 688

Abstract

Tool condition monitoring (TCM) is crucial in the machining process to confirm product quality as well as process efficiency and minimize downtime. Traditional methods for TCM, while effective to a degree, often fall short in real-time adaptability and predictive accuracy. This research work [...] Read more.

Tool condition monitoring (TCM) is crucial in the machining process to confirm product quality as well as process efficiency and minimize downtime. Traditional methods for TCM, while effective to a degree, often fall short in real-time adaptability and predictive accuracy. This research work aims to advance the state-of-the-art methods in predictive maintenance for TCM and improve tool performance and reliability during the milling process. The present work investigates the application of Deep Learning (DL) and Reinforcement Learning (RL) techniques to monitor tool conditions in milling operations. DL models, including Long Short-Term Memory (LSTM) networks, Feed Forward Neural Networks (FFNN), and RL models, including Q-learning and SARSA, are employed to classify tool conditions from the vibration sensor. The performance of the selected DL and RL algorithms is evaluated through performance metrics like confusion matrix, recall, precision, F1 score, and Receiver Operating Characteristics (ROC) curves. The results revealed that RL based on SARSA outperformed other algorithms. The overall classification accuracies for LSTM, FFNN, Q-learning, and SARSA were 94.85%, 98.16%, 98.50%, and 98.66%, respectively. In regard to predicting tool conditions accurately and thereby enhancing overall process efficiency, SARSA showed the best performance, followed by Q-learning, FFNN, and LSTM. This work contributes to the advancement of TCM systems, highlighting the potential of DL and RL techniques to revolutionize manufacturing processes in the era of Industry 5.0. Full article

(This article belongs to the Special Issue Fault Diagnosis in the Internet of Things Applications)

► Show Figures

Figure 1

18 pages, 1703 KiB

Open AccessArticle

Hybrid Encryption Model for Secured Three-Phase Authentication Protocol in IoT

by Amr Munshi and Bandar Alshawi

J. Sens. Actuator Netw. 2024, 13(4), 41; https://doi.org/10.3390/jsan13040041 - 17 Jul 2024

Viewed by 689

Abstract

The Internet of things (IoT) has recently received a great deal of attention, and there has been a large increase in the number of IoT devices owing to its significance in current communication networks. In addition, the validation of devices is an important [...] Read more.

The Internet of things (IoT) has recently received a great deal of attention, and there has been a large increase in the number of IoT devices owing to its significance in current communication networks. In addition, the validation of devices is an important concern and a major safety demand in IoT systems, as any faults in the authentication or identification procedure will lead to threatening attacks that cause the system to close. In this study, a new, three-phase authentication protocol in IoT is implemented. The initial phase concerns the user registration phase, in which encryption takes place with a hybrid Elliptic Curve Cryptography (ECC)–Advanced Encryption Standard (AES) model with an optimization strategy, whereby key generation is optimally accomplished via a Self-Improved Aquila Optimizer (SI-AO). The second and third phases include the login process and the authentication phase, in which information flow control-based authentication is conducted. Finally, decryption is achieved based on the hybrid ECC–AES model. The employed scheme’s improvement is established using various metrics. Full article

(This article belongs to the Special Issue Security and Smart Applications in IoT and Wireless Sensor and Actuator Networks)

► Show Figures

Figure 1

46 pages, 5284 KiB

Open AccessReview

Recent Studies on Smart Textile-Based Wearable Sweat Sensors for Medical Monitoring: A Systematic Review

by Asma Akter, Md Mehedi Hasan Apu, Yedukondala Rao Veeranki, Turki Nabieh Baroud and Hugo F. Posada-Quintero

J. Sens. Actuator Netw. 2024, 13(4), 40; https://doi.org/10.3390/jsan13040040 - 11 Jul 2024

Viewed by 909

Abstract

Smart textile-based wearable sweat sensors have recently received a lot of attention due to their potential for use in personal medical monitoring. They have a variety of desirable qualities, including low cost, easy implementation, stretchability, flexibility, and light weight. Wearable sweat sensors are [...] Read more.

Smart textile-based wearable sweat sensors have recently received a lot of attention due to their potential for use in personal medical monitoring. They have a variety of desirable qualities, including low cost, easy implementation, stretchability, flexibility, and light weight. Wearable sweat sensors are a potential approach for personalized medical devices because of these features. Moreover, real-time textile-based sweat sensors can easily monitor health by analyzing the sweat produced by the human body. We reviewed the most recent advancements in wearable sweat sensors from the fabrication, materials, and disease detection and monitoring perspectives. To integrate real-time biosensors with electronics and introduce advancements to the field of wearable technology, key chemical constituents of sweat, sweat collection technologies, and concerns of textile substrates are elaborated. Perspectives for building wearable biosensing systems based on sweat are reviewed, as well as the methods and difficulties involved in enhancing wearable sweat-sensing performance. Full article

► Show Figures

Figure 1

26 pages, 2233 KiB

Open AccessReview

Transformative Technologies in Digital Agriculture: Leveraging Internet of Things, Remote Sensing, and Artificial Intelligence for Smart Crop Management

by Fernando Fuentes-Peñailillo, Karen Gutter, Ricardo Vega and Gilda Carrasco Silva

J. Sens. Actuator Netw. 2024, 13(4), 39; https://doi.org/10.3390/jsan13040039 - 8 Jul 2024

Cited by 1 | Viewed by 2105

Abstract

This paper explores the potential of smart crop management based on the incorporation of tools like digital agriculture, which considers current technological tools applied in agriculture, such as the Internet of Things (IoT), remote sensing, and artificial intelligence (AI), to improve crop production [...] Read more.

This paper explores the potential of smart crop management based on the incorporation of tools like digital agriculture, which considers current technological tools applied in agriculture, such as the Internet of Things (IoT), remote sensing, and artificial intelligence (AI), to improve crop production efficiency and sustainability. This is essential in the context of varying climatic conditions that affect the availability of resources for agriculture. The integration of tools such as IoT and sensor networks can allow farmers to obtain real-time data on their crops, assessing key health factors, such as soil conditions, plant water status, presence of pests, and environmental factors, among others, which can finally result in data-based decision-making to optimize irrigation, fertilization, and pest control. Also, this can be enhanced by incorporating tools such as drones and unmanned aerial vehicles (UAVs), which can increase monitoring capabilities through comprehensive field surveys and high-precision crop growth tracking. On the other hand, big data analytics and AI are crucial in analyzing extensive datasets to uncover patterns and trends and provide valuable insights for improving agricultural practices. This paper highlights the key technological advancements and applications in smart crop management, addressing challenges and barriers to the global adoption of these current and new types of technologies and emphasizing the need for ongoing research and collaboration to achieve sustainable and efficient crop production. Full article

(This article belongs to the Special Issue Security and Smart Applications in IoT and Wireless Sensor and Actuator Networks)

► Show Figures

Figure 1

20 pages, 1146 KiB

Open AccessArticle

Distributed Consensus Multi-Distribution Filter for Heavy-Tailed Noise

by Guan-Nan Chang, Wen-Xing Fu, Tao Cui, Ling-Yun Song and Peng Dong

J. Sens. Actuator Netw. 2024, 13(4), 38; https://doi.org/10.3390/jsan13040038 - 28 Jun 2024

Viewed by 524

Abstract

Distributed state estimation is one of the critical technologies in the field of target tracking, where the process noise and measurement noise may have a heavy-tailed distribution. Traditionally, heavy-tailed distributions like the student-t distribution are employed, but our observation reveals that Gaussian noise [...] Read more.

Distributed state estimation is one of the critical technologies in the field of target tracking, where the process noise and measurement noise may have a heavy-tailed distribution. Traditionally, heavy-tailed distributions like the student-t distribution are employed, but our observation reveals that Gaussian noise predominates in many instances, with occasional outliers. This sporadic reliance on heavy-tailed distributions can degrade performances or necessitate frequent parameter adjustments. To overcome this, we introduce a novel distributed consensus multi-distribution state estimation method that combines Gaussian and student-t filters. Our approach establishes a system model using both Gaussian and student-t distributions. We derive a multi-distribution filter for a single sensor, assigning probabilities to Gaussian and student-t noise models. Parallel estimation under both distributions, utilizing Gaussian and student-t filters, allows us to calculate the likelihood of each distribution. The fusion of these results yields a mixed-state estimation and corresponding error matrix. Recognizing the increasing degrees of freedom in the student-t distribution over time, we provide an effective approximation. An information consensus strategy for multi-distribution filters is introduced, achieving global estimation through consensus on fused local filter results via interaction with neighboring nodes. This methodology is extended to the distributed case, and the recursive process of the distributed multi-distribution consensus state estimation method is presented. Simulation results demonstrate that the estimation accuracy of the proposed algorithm improved by at least 20% compared to that of the traditional algorithm in scenarios involving both Gaussian and heavy-tailed distributions. Full article

► Show Figures

Figure 1

19 pages, 7416 KiB

Open AccessArticle

Beta Maximum Power Extraction Operation-Based Model Predictive Current Control for Linear Induction Motors

by Mohamed. A. Ghalib, Samir A. Hamad, Mahmoud F. Elmorshedy, Dhafer Almakhles and Hazem Hassan Ali

J. Sens. Actuator Netw. 2024, 13(4), 37; https://doi.org/10.3390/jsan13040037 - 28 Jun 2024

Cited by 1 | Viewed by 623

Abstract

There is an increasing interest in achieving global climate change mitigation targets that target environmental protection. Therefore, electric vehicles (as linear metros) were developed to avoid greenhouse gas emissions, which negatively impact the climate. Hence, this paper proposes a finite set-model predictive-based current [...] Read more.

There is an increasing interest in achieving global climate change mitigation targets that target environmental protection. Therefore, electric vehicles (as linear metros) were developed to avoid greenhouse gas emissions, which negatively impact the climate. Hence, this paper proposes a finite set-model predictive-based current control (FS-MPCC) strategy of linear induction motor (LIM) for linear metro drives fed by solar cells with a beta maximum power extraction (B-MPE) control approach to achieve lower thrust ripples and eliminate a selection of weighting factors, the main limitation of conventional model predictive-based thrust control (which can be time consuming and challenging). The B-MPE control approach ensures that the solar cells operate at their maximum power output, maximizing the energy harvested from the sun. Considering a single cost function of primary current errors between the predicted values and their references in αβ-axes, the proposed method eliminates the need for weighting factor selection, thus simplifying the control process. A comparison between the conventional and the presented control method is conducted using MATLAB/Simulink under different scenarios. Comprehensive simulation results of the presented system on a 3 kW LIM prototype revealed that the introduced system based on FS-MPCC surpasses the conventional technique, resulting in a maximum power extraction from solar cells and a suppression of the thrust ripples as well as an avoidance of weighting factor tuning, leading to fewer computational steps. Full article

► Show Figures

Figure 1

18 pages, 1222 KiB

Open AccessArticle

A Nature-Inspired Partial Distance-Based Clustering Algorithm

by Mohammed El Habib Kahla, Mounir Beggas, Abdelkader Laouid and Mohammad Hammoudeh

J. Sens. Actuator Netw. 2024, 13(4), 36; https://doi.org/10.3390/jsan13040036 - 21 Jun 2024

Viewed by 727

Abstract

In the rapidly advancing landscape of digital technologies, clustering plays a critical role in the domains of artificial intelligence and big data. Clustering is essential for extracting meaningful insights and patterns from large, intricate datasets. Despite the efficacy of traditional clustering techniques in [...] Read more.

In the rapidly advancing landscape of digital technologies, clustering plays a critical role in the domains of artificial intelligence and big data. Clustering is essential for extracting meaningful insights and patterns from large, intricate datasets. Despite the efficacy of traditional clustering techniques in handling diverse data types and sizes, they encounter challenges posed by the increasing volume and dimensionality of data, as well as the complex structures inherent in high-dimensional spaces. This research recognizes the constraints of conventional clustering methods, including sensitivity to initial centroids, dependence on prior knowledge of cluster counts, and scalability issues, particularly in large datasets and Internet of Things implementations. In response to these challenges, we propose a K-level clustering algorithm inspired by the collective behavior of fish locomotion. K-level introduces a novel clustering approach based on greedy merging driven by distances in stages. This iterative process efficiently establishes hierarchical structures without the need for exhaustive computations. K-level gives users enhanced control over computational complexity, enabling them to specify the number of clusters merged simultaneously. This flexibility ensures accurate and efficient hierarchical clustering across diverse data types, offering a scalable solution for processing extensive datasets within a reasonable timeframe. The internal validation metrics, including the Silhouette Score, Davies–Bouldin Index, and Calinski–Harabasz Index, are utilized to evaluate the K-level algorithm across various types of datasets. Additionally, comparisons are made with rivals in the literature, including UPGMA, CLINK, UPGMC, SLINK, and K-means. The experiments and analyses show that the proposed algorithm overcomes many of the limitations of existing clustering methods, presenting scalable and adaptable clustering in the dynamic landscape of evolving data challenges. Full article

► Show Figures

Figure 1

26 pages, 10517 KiB

Open AccessArticle

Estimation of Vehicle Traffic Parameters Using an Optical Distance Sensor for Use in Smart City Road Infrastructure

by Rafał Burdzik, Ireneusz Celiński, Minvydas Ragulskis, Vinayak Ranjan and Jonas Matijošius

J. Sens. Actuator Netw. 2024, 13(4), 35; https://doi.org/10.3390/jsan13040035 - 21 Jun 2024

Viewed by 612

Abstract

In recent decades, the dynamics of road vehicle traffic have significantly evolved, compelling traffic engineers to develop innovative traffic monitoring solutions, especially for dense road networks. Traditional methods for measuring traffic volume along road sections may no longer suffice for modern traffic control [...] Read more.

In recent decades, the dynamics of road vehicle traffic have significantly evolved, compelling traffic engineers to develop innovative traffic monitoring solutions, especially for dense road networks. Traditional methods for measuring traffic volume along road sections may no longer suffice for modern traffic control systems. This is particularly true for induction loops, a widely used method since the last century. In contrast, measuring techniques using microwaves or visible light offer better accuracy but are often hindered by the high cost of sensors. This paper presents new techniques for measuring traffic flow and other parameters that adapt to changing traffic dynamics using low-cost optical distance sensors. Our study demonstrates that the integration of multiple monitoring approaches enhances measurement accuracy, contingent on the dynamics and specific characteristics of the traffic. The results indicate that cheap optical distance sensors are particularly well suited for use in smart city road networks. Full article

(This article belongs to the Section Network Services and Applications)

► Show Figures

Figure 1

Journal Menu

Journal Browser

J. Sens. Actuator Netw., Volume 13, Issue 4 (August 2024) – 11 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI