Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
 
 
Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (8,718)

Search Parameters:
Keywords = deep convolution convolutional neural network

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
20 pages, 5693 KiB  
Article
H-QNN: A Hybrid Quantum–Classical Neural Network for Improved Binary Image Classification
by Muhammad Asfand Hafeez, Arslan Munir and Hayat Ullah
AI 2024, 5(3), 1462-1481; https://doi.org/10.3390/ai5030070 (registering DOI) - 19 Aug 2024
Abstract
Image classification is an important application for deep learning. With the advent of quantum technology, quantum neural networks (QNNs) have become the focus of research. Traditional deep learning-based image classification involves using a convolutional neural network (CNN) to extract features from the image [...] Read more.
Image classification is an important application for deep learning. With the advent of quantum technology, quantum neural networks (QNNs) have become the focus of research. Traditional deep learning-based image classification involves using a convolutional neural network (CNN) to extract features from the image and a multi-layer perceptron (MLP) network to create the decision boundaries. However, quantum circuits with parameters can extract rich features from images and also create complex decision boundaries. This paper proposes a hybrid QNN (H-QNN) model designed for binary image classification that capitalizes on the strengths of quantum computing and classical neural networks. Our H-QNN model uses a compact, two-qubit quantum circuit integrated with a classical convolutional architecture, making it highly efficient for computation on noisy intermediate-scale quantum (NISQ) devices that are currently leading the way in practical quantum computing applications. Our H-QNN model significantly enhances classification accuracy, achieving a 90.1% accuracy rate on binary image datasets. In addition, we have extensively evaluated baseline CNN and our proposed H-QNN models for image retrieval tasks. The obtained quantitative results exhibit the generalization of our H-QNN for downstream image retrieval tasks. Furthermore, our model addresses the issue of overfitting for small datasets, making it a valuable tool for practical applications. Full article
(This article belongs to the Special Issue Advances in Quantum Computing and Quantum Machine Learning)
Show Figures

Figure 1

23 pages, 4484 KiB  
Article
Classification of Diabetic Foot Ulcers from Images Using Machine Learning Approach
by Nouf Almufadi and Haifa F. Alhasson
Diagnostics 2024, 14(16), 1807; https://doi.org/10.3390/diagnostics14161807 (registering DOI) - 19 Aug 2024
Abstract
Diabetic foot ulcers (DFUs) represent a significant and serious challenge associated with diabetes. It is estimated that approximately one third of individuals with diabetes will develop DFUs at some point in their lives. This common complication can lead to serious health issues if [...] Read more.
Diabetic foot ulcers (DFUs) represent a significant and serious challenge associated with diabetes. It is estimated that approximately one third of individuals with diabetes will develop DFUs at some point in their lives. This common complication can lead to serious health issues if not properly managed. The early diagnosis and treatment of DFUs are crucial to prevent severe complications, including lower limb amputation. DFUs can be categorized into two states: ischemia and infection. Accurate classification is required to avoid misdiagnosis due to the similarities between these two states. Several convolutional neural network (CNN) models have been used and pre-trained through transfer learning. These models underwent evaluation with hyperparameter tuning for the binary classification of different states of DFUs, such as ischemia and infection. This study aimed to develop an effective classification system for DFUs using CNN models and machine learning classifiers utilizing various CNN models, such as EfficientNetB0, DenseNet121, ResNet101, VGG16, InceptionV3, MobileNetV2, and InceptionResNetV2, due to their excellent performance in diverse computer vision tasks. Additionally, the head model functions as the ultimate component for making decisions in the model, utilizing data collected from preceding layers to make precise predictions or classifications. The results of the CNN models with the suggested head model have been used in different machine learning classifiers to determine which ones are most effective for enhancing the performance of each CNN model. The most optimal outcome in categorizing ischemia is a 97% accuracy rate. This was accomplished by integrating the suggested head model with the EfficientNetB0 model and inputting the outcomes into the logistic regression classifier. The EfficientNetB0 model, with the proposed modifications and by feeding the outcomes to the AdaBoost classifier, attains an accuracy of 93% in classifying infections. Full article
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
Show Figures

Figure 1

19 pages, 5289 KiB  
Article
A Novel Deep Learning Approach for Real-Time Critical Assessment in Smart Urban Infrastructure Systems
by Abdulaziz Almaleh
Electronics 2024, 13(16), 3286; https://doi.org/10.3390/electronics13163286 - 19 Aug 2024
Abstract
The swift advancement of communication and information technologies has transformed urban infrastructures into smart cities. Traditional assessment methods face challenges in capturing the complex interdependencies and temporal dynamics inherent in these systems, risking urban resilience. This study aims to enhance the criticality assessment [...] Read more.
The swift advancement of communication and information technologies has transformed urban infrastructures into smart cities. Traditional assessment methods face challenges in capturing the complex interdependencies and temporal dynamics inherent in these systems, risking urban resilience. This study aims to enhance the criticality assessment of geographic zones within smart cities by introducing a novel deep learning architecture. Utilizing Convolutional Neural Networks (CNNs) for spatial feature extraction and Long Short-Term Memory (LSTM) networks for temporal dependency modeling, the proposed framework processes inputs such as total electricity use, flooding levels, population, poverty rates, and energy consumption. The CNN component constructs hierarchical feature maps through successive convolution and pooling operations, while the LSTM captures sequence-based patterns. Fully connected layers integrate these features to generate final predictions. Implemented in Python using TensorFlow and Keras on an Intel Core i7 system with 32 GB RAM and an NVIDIA GTX 1080 Ti GPU, the model demonstrated a superior performance. It achieved a mean absolute error of 0.042, root mean square error of 0.067, and an R-squared value of 0.935, outperforming existing methodologies in real-time adaptability and resource efficiency. Full article
(This article belongs to the Special Issue AI Technologies and Smart City)
Show Figures

Figure 1

13 pages, 4426 KiB  
Article
A Predictive Model Using Long Short-Time Memory (LSTM) Technique for Power System Voltage Stability
by Muhammad Jamshed Abbass, Robert Lis and Waldemar Rebizant
Appl. Sci. 2024, 14(16), 7279; https://doi.org/10.3390/app14167279 - 19 Aug 2024
Abstract
The stability of the operation of the power system is essential to ensure a continuous supply of electricity to meet the load of the system. In the operational process, voltage stability (VS) should be recognized and predicted as a basic requirement. In electrical [...] Read more.
The stability of the operation of the power system is essential to ensure a continuous supply of electricity to meet the load of the system. In the operational process, voltage stability (VS) should be recognized and predicted as a basic requirement. In electrical systems, deep learning and machine learning algorithms have found widespread applications. These algorithms can learn from previous data to detect and predict future scenarios of potential instability. This study introduces long short-term memory (LSTM) technology to predict the stability of the nominal voltage of the power system. Based on the results, the recommended LSTM technology achieved the highest accuracy target of 99.5%. In addition, the LSTM model outperforms other machine learning (ML) and deep learning techniques, i.e., support vector machines (SVMs), Naive Bayes (NB), and convolutional neural networks (CNNs), when comparing the accuracy of the VS forecast. The results show that the LSTM method is useful to predict the voltage of an electrical system. The IEEE 33-bus system indicates that the recommended approach can rapidly and precisely verify the system stability category. Furthermore, the proposed method outperforms conventional assessment methods that rely on shallow learning. Full article
(This article belongs to the Section Electrical, Electronics and Communications Engineering)
Show Figures

Figure 1

15 pages, 20642 KiB  
Article
Deep Edge-Based Fault Detection for Solar Panels
by Haoyu Ling, Manlu Liu and Yi Fang
Sensors 2024, 24(16), 5348; https://doi.org/10.3390/s24165348 - 19 Aug 2024
Abstract
Solar panels may suffer from faults, which could yield high temperature and significantly degrade their power generation. To detect faults of solar panels in large photovoltaic plants, drones with infrared cameras have been implemented. Drones may capture a huge number of infrared images. [...] Read more.
Solar panels may suffer from faults, which could yield high temperature and significantly degrade their power generation. To detect faults of solar panels in large photovoltaic plants, drones with infrared cameras have been implemented. Drones may capture a huge number of infrared images. It is not realistic to manually analyze such a huge number of infrared images. To solve this problem, we develop a Deep Edge-Based Fault Detection (DEBFD) method, which applies convolutional neural networks (CNNs) for edge detection and object detection according to the captured infrared images. Particularly, a machine learning-based contour filter is designed to eliminate incorrect background contours. Then faults of solar panels are detected. Based on these fault detection results, solar panels can be classified into two classes, i.e., normal and faulty ones (i.e., macro ones). We collected 2060 images in multiple scenes and achieved a high macro F1 score. Our method achieved a frame rate of 28 fps over infrared images of solar panels on an NVIDIA GeForce RTX 2080 Ti GPU. Full article
(This article belongs to the Section Fault Diagnosis & Sensors)
Show Figures

Figure 1

18 pages, 4476 KiB  
Article
Beat-by-Beat Estimation of Hemodynamic Parameters in Left Ventricle Based on Phonocardiogram and Photoplethysmography Signals Using a Deep Learning Model: Preliminary Study
by Jiachen Mi, Tengfei Feng, Hongkai Wang, Zuowei Pei and Hong Tang
Bioengineering 2024, 11(8), 842; https://doi.org/10.3390/bioengineering11080842 - 19 Aug 2024
Abstract
Beat-by-beat monitoring of hemodynamic parameters in the left ventricle contributes to the early diagnosis and treatment of heart failure, valvular heart disease, and other cardiovascular diseases. Current accurate measurement methods for ventricular hemodynamic parameters are inconvenient for monitoring hemodynamic indexes in daily life. [...] Read more.
Beat-by-beat monitoring of hemodynamic parameters in the left ventricle contributes to the early diagnosis and treatment of heart failure, valvular heart disease, and other cardiovascular diseases. Current accurate measurement methods for ventricular hemodynamic parameters are inconvenient for monitoring hemodynamic indexes in daily life. The objective of this study is to propose a method for estimating intraventricular hemodynamic parameters in a beat-to-beat style based on non-invasive PCG (phonocardiogram) and PPG (photoplethysmography) signals. Three beagle dogs were used as subjects. PCG, PPG, electrocardiogram (ECG), and invasive blood pressure signals in the left ventricle were synchronously collected while epinephrine medicine was injected into the veins to produce hemodynamic variations. Various doses of epinephrine were used to produce hemodynamic variations. A total of 40 records (over 12,000 cardiac cycles) were obtained. A deep neural network was built to simultaneously estimate four hemodynamic parameters of one cardiac cycle by inputting the PCGs and PPGs of the cardiac cycle. The outputs of the network were four hemodynamic parameters: left ventricular systolic blood pressure (SBP), left ventricular diastolic blood pressure (DBP), maximum rate of left ventricular pressure rise (MRR), and maximum rate of left ventricular pressure decline (MRD). The model built in this study consisted of a residual convolutional module and a bidirectional recurrent neural network module which learnt the local features and context relations, respectively. The training mode of the network followed a regression model, and the loss function was set as mean square error. When the network was trained and tested on one subject using a five-fold validation scheme, the performances were very good. The average correlation coefficients (CCs) between the estimated values and measured values were generally greater than 0.90 for SBP, DBP, MRR, and MRD. However, when the network was trained with one subject’s data and tested with another subject’s data, the performance degraded somewhat. The average CCs reduced from over 0.9 to 0.7 for SBP, DBP, and MRD; however, MRR had higher consistency, with the average CC reducing from over 0.9 to about 0.85 only. The generalizability across subjects could be improved if individual differences were considered. The performance indicates the possibility that hemodynamic parameters could be estimated by PCG and PPG signals collected on the body surface. With the rapid development of wearable devices, it has up-and-coming applications for self-monitoring in home healthcare environments. Full article
(This article belongs to the Special Issue Cardiovascular Hemodynamic Characterization: Prospects and Challenges)
Show Figures

Figure 1

23 pages, 2501 KiB  
Article
MsFNet: Multi-Scale Fusion Network Based on Dynamic Spectral Features for Multi-Temporal Hyperspectral Image Change Detection
by Yining Feng, Weihan Ni, Liyang Song and Xianghai Wang
Remote Sens. 2024, 16(16), 3037; https://doi.org/10.3390/rs16163037 - 18 Aug 2024
Viewed by 332
Abstract
With the development of satellite technology, the importance of multi-temporal remote sensing (RS) image change detection (CD) in urban planning, environmental monitoring, and other fields is increasingly prominent. Deep learning techniques enable a profound exploration of the intrinsic features within hyperspectral (HS) data, [...] Read more.
With the development of satellite technology, the importance of multi-temporal remote sensing (RS) image change detection (CD) in urban planning, environmental monitoring, and other fields is increasingly prominent. Deep learning techniques enable a profound exploration of the intrinsic features within hyperspectral (HS) data, leading to substantial enhancements in CD accuracy while addressing several challenges posed by traditional methodologies. However, existing convolutional neural network (CNN)-based CD approaches frequently encounter issues during the feature extraction process, such as the loss of detailed information due to downsampling, which hampers a model’s ability to accurately capture complex spectral features. Additionally, these methods often neglect the integration of multi-scale information, resulting in suboptimal local feature extraction and, consequently, diminished model performance. To address these limitations, we propose a multi-scale fusion network (MsFNet) which leverages dynamic spectral features for effective multi-temporal HS-CD. Our approach incorporates a dynamic convolution module with spectral attention, which adaptively modulates the receptive field size according to the spectral characteristics of different bands. This flexibility enhances the model’s capacity to focus on critical bands, thereby improving its ability to identify and differentiate changes across spectral dimensions. Furthermore, we develop a multi-scale feature fusion module which extracts and integrates features from deep feature maps, enriching local information and augmenting the model’s sensitivity to local variations. Experimental evaluations conducted on three real-world HS-CD datasets demonstrate that the proposed MsFNet significantly outperforms contemporary advanced CD methods in terms of both efficacy and performance. Full article
(This article belongs to the Special Issue Recent Advances in the Processing of Hyperspectral Images)
Show Figures

Figure 1

18 pages, 55731 KiB  
Article
A Study on the Evolution of Forest Landscape Patterns in the Fuxin Region of China Combining SC-UNet and Spatial Pattern Perspectives
by Feiyue Wang, Fan Yang and Zixue Wang
Sustainability 2024, 16(16), 7067; https://doi.org/10.3390/su16167067 - 17 Aug 2024
Viewed by 441
Abstract
During the vegetation growing season, the forest in the remote sensing image is more distinguishable from other background features, and the forest features are obvious and can show prominent forest area characteristics. However, deep convolutional neural network-based methods tend to overlearn the forest [...] Read more.
During the vegetation growing season, the forest in the remote sensing image is more distinguishable from other background features, and the forest features are obvious and can show prominent forest area characteristics. However, deep convolutional neural network-based methods tend to overlearn the forest features in the forest extraction task, which leads to the extraction speed still having a large amount of room for improvement. In this paper, a convolutional neural network-based model is proposed based on the incorporation of spatial and channel reconstruction convolution in the U-Net model for forest extraction from remote sensing images. The network obtained an extraction accuracy of 81.781% in intersection over union (IoU), 91.317% in precision, 92.177% in recall, and 91.745% in F1-score, with a maximum improvement of 0.442% in precision when compared with the classical U-Net network. In addition, the speed of the model’s forest extraction has been improved by about 6.14 times. On this basis, we constructed a forest land dataset with high-intraclass diversity and fine-grained scale by selecting some Sentinel-2 images in Northeast China. The spatial and temporal evolutionary changes of the forest cover in the Fuxin region of Liaoning province, China, from 2019 to 2023, were obtained using this region as the study area. In addition, we obtained the change of the forest landscape pattern evolution in the Fuxin region from 2019 to 2023 based on the morphological spatial pattern analysis (MSPA) method. The results show that the core area of the forest landscape in the Fuxin region has shown an increasing change, and the non-core area has been decreasing. The SC-UNet method proposed in this paper can realize the high-precision and rapid extraction of forest in a wide area, and at the same time, it can provide a basis for evaluating the effectiveness of ecosystem restoration projects. Full article
Show Figures

Figure 1

26 pages, 5257 KiB  
Article
Towards Equitable Representations of Ageing: Evaluation of Gender, Territories, Aids and Artificial Intelligence
by Vanessa Zorrilla-Muñoz, Daniela Luz Moyano, Carolina Marcos Carvajal and María Silveria Agulló-Tomás
Land 2024, 13(8), 1304; https://doi.org/10.3390/land13081304 - 17 Aug 2024
Viewed by 241
Abstract
There are few studies on the representation of older people regarding aids and assistive devices and even fewer that incorporate more inclusive views (gender, emotions, anti-ageist, territorial or land approach) as well as virtual or land ethnography or artificial intelligence. The general objective [...] Read more.
There are few studies on the representation of older people regarding aids and assistive devices and even fewer that incorporate more inclusive views (gender, emotions, anti-ageist, territorial or land approach) as well as virtual or land ethnography or artificial intelligence. The general objective was to evaluate digital images of aids and assistive aids in the older population, from the perspectives mentioned above. Method. A descriptive and cross-sectional study that searched, observed and analyzed images. An evaluation of intentionally selected images from Freepik, Pixabay, Storyblocks, Splitshire, Gratisography and ArtGPT, included in an original database constructured by several authors of this article, was carried out in the context of the ENCAGEn-CM project (2020–2023, financed by the CAM and FSE). This base was updated and expanded in October and November 2023. In addition, an image generation process was carried out using artificial intelligence, and this was also part of the analysis (ArtGPT). Finally, algorithms were used to solve and retrain with the images. Results. Of the total final images included in the expanded database until November 2023 (n = 427), only a third (28.3%, 121/427) included the aids and assistive aids label. Representations of mixed groups predominated (38.8%) and, to a lesser extent, those of women. A large proportion of the devices were ‘glasses’ (74.6%) and the ‘use of a cane’ (14.9%). To a lesser extent, ‘wheelchairs’ (4.4%) or ‘hearing aids’ (0.9%) and the presence of more than one device (simultaneously) (5.3%) were noted. The main emotions represented were ‘joy’ (45.6%) and ‘emotion not recognized’ (45.6%), with, to a lesser extent, ‘sadness’ (3.5%), ‘surprise’ (4.4%) and ‘anger’ (0.9%). Differences by sex were found in the represented emotions linked to aids and assistive aids. The representation of images of the built environment predominated significantly (70.2%), and it was observed that older women were less represented in natural environments than men. Based on the previous findings, a method is proposed to address stereotypes in images of older individuals. It involves identifying common stereotypical features, like glasses and hospital settings, using deep learning and quantum computing techniques. A convolutional neural network identifies and suppresses these elements, followed by the use of quantum algorithms to manipulate features. This systematic approach aims to mitigate biases and enhance the accuracy in representing older people in digital imagery. Conclusion. A limited proportion of images of assistive devices and older people were observed. Furthermore, among them, the lower representation of images of women in a built environment was confirmed, and the expressions of emotions were limited to only three basic ones (joy, sadness and surprise). In these evaluated digital images, the collective imagination of older people continues to be limited to a few spaces/contexts and emotions and is stereotyped regarding the same variables (sex, age, environment). Technology often overlooks innovative support tools for older adults, and AI struggles in accurately depicting emotions and environments in digital images. There is a pressing need for thorough pretraining analysis and ethical considerations to address these challenges and ensure more accurate and inclusive representations of older persons in digital media. Full article
Show Figures

Figure 1

20 pages, 69470 KiB  
Article
Refined Land Use Classification for Urban Core Area from Remote Sensing Imagery by the EfficientNetV2 Model
by Zhenbao Wang, Yuqi Liang, Yanfang He, Yidan Cui and Xiaoxian Zhang
Appl. Sci. 2024, 14(16), 7235; https://doi.org/10.3390/app14167235 - 16 Aug 2024
Viewed by 624
Abstract
In the context of accelerated urbanization, assessing the quality of the existing built environment plays a crucial role in urban renewal. In the existing research and use of deep learning models, most categories are urban construction areas, forest land, farmland, and other categories. [...] Read more.
In the context of accelerated urbanization, assessing the quality of the existing built environment plays a crucial role in urban renewal. In the existing research and use of deep learning models, most categories are urban construction areas, forest land, farmland, and other categories. These categories are not conducive to a more accurate analysis of the spatial distribution characteristics of urban green space, parking space, blue space, and square. A small sample of refined land use classification data for urban built-up areas was produced using remote sensing images. The large-scale remote sensing images were classified using deep learning models, with the objective of inferring the fine land category of each tile image. In this study, satellite remote sensing images of four cities, Handan, Shijiazhuang, Xingtai, and Tangshan, were acquired by Google Class 19 RGB three-channel satellite remote sensing images to establish a data set containing fourteen urban land use classifications. The convolutional neural network model EfficientNetV2 is used to train and validate the network framework that performs well on computer vision tasks and enables intelligent image classification of urban remote sensing images. The model classification effect is compared and analyzed through accuracy, precision, recall, and F1-score. The results show that the EfficientNetV2 model has a classification recognition accuracy of 84.56% on the constructed data set. The testing set accuracy increases sequentially after transfer learning. This paper verifies that the proposed research framework has good practicality and that the results of the land use classification are conducive to the fine-grained quantitative analysis of built-up environmental quality. Full article
Show Figures

Figure 1

20 pages, 4950 KiB  
Article
Comparison of the Accuracy of Ground Reaction Force Component Estimation between Supervised Machine Learning and Deep Learning Methods Using Pressure Insoles
by Amal Kammoun, Philippe Ravier and Olivier Buttelli
Sensors 2024, 24(16), 5318; https://doi.org/10.3390/s24165318 - 16 Aug 2024
Viewed by 375
Abstract
The three Ground Reaction Force (GRF) components can be estimated using pressure insole sensors. In this paper, we compare the accuracy of estimating GRF components for both feet using six methods: three Deep Learning (DL) methods (Artificial Neural Network, Long Short-Term Memory, and [...] Read more.
The three Ground Reaction Force (GRF) components can be estimated using pressure insole sensors. In this paper, we compare the accuracy of estimating GRF components for both feet using six methods: three Deep Learning (DL) methods (Artificial Neural Network, Long Short-Term Memory, and Convolutional Neural Network) and three Supervised Machine Learning (SML) methods (Least Squares, Support Vector Regression, and Random Forest (RF)). Data were collected from nine subjects across six activities: normal and slow walking, static with and without carrying a load, and two Manual Material Handling activities. This study has two main contributions: first, the estimation of GRF components (Fx, Fy, and Fz) during the six activities, two of which have never been studied; second, the comparison of the accuracy of GRF component estimation between the six methods for each activity. RF provided the most accurate estimation for static situations, with mean RMSE values of RMSE_Fx = 1.65 N, RMSE_Fy = 1.35 N, and RMSE_Fz = 7.97 N for the mean absolute values measured by the force plate (reference) RMSE_Fx = 14.10 N, RMSE_Fy = 3.83 N, and RMSE_Fz = 397.45 N. In our study, we found that RF, an SML method, surpassed the experimented DL methods. Full article
(This article belongs to the Special Issue Biometrics Recognition Systems)
Show Figures

Figure 1

27 pages, 14394 KiB  
Article
Celiac Disease Deep Learning Image Classification Using Convolutional Neural Networks
by Joaquim Carreras
J. Imaging 2024, 10(8), 200; https://doi.org/10.3390/jimaging10080200 - 16 Aug 2024
Viewed by 462
Abstract
Celiac disease (CD) is a gluten-sensitive immune-mediated enteropathy. This proof-of-concept study used a convolutional neural network (CNN) to classify hematoxylin and eosin (H&E) CD histological images, normal small intestine control, and non-specified duodenal inflammation (7294, 11,642, and 5966 images, respectively). The trained network [...] Read more.
Celiac disease (CD) is a gluten-sensitive immune-mediated enteropathy. This proof-of-concept study used a convolutional neural network (CNN) to classify hematoxylin and eosin (H&E) CD histological images, normal small intestine control, and non-specified duodenal inflammation (7294, 11,642, and 5966 images, respectively). The trained network classified CD with high performance (accuracy 99.7%, precision 99.6%, recall 99.3%, F1-score 99.5%, and specificity 99.8%). Interestingly, when the same network (already trained for the 3 class images), analyzed duodenal adenocarcinoma (3723 images), the new images were classified as duodenal inflammation in 63.65%, small intestine control in 34.73%, and CD in 1.61% of the cases; and when the network was retrained using the 4 histological subtypes, the performance was above 99% for CD and 97% for adenocarcinoma. Finally, the model added 13,043 images of Crohn’s disease to include other inflammatory bowel diseases; a comparison between different CNN architectures was performed, and the gradient-weighted class activation mapping (Grad-CAM) technique was used to understand why the deep learning network made its classification decisions. In conclusion, the CNN-based deep neural system classified 5 diagnoses with high performance. Narrow artificial intelligence (AI) is designed to perform tasks that typically require human intelligence, but it operates within limited constraints and is task-specific. Full article
Show Figures

Graphical abstract

18 pages, 7952 KiB  
Article
Deep Learning Prediction of Moisture and Color Kinetics of Apple Slices by Long Short-Term Memory as Affected by Blanching and Hot-Air Drying Conditions
by Zehui Jia, Yanhong Liu and Hongwei Xiao
Processes 2024, 12(8), 1724; https://doi.org/10.3390/pr12081724 - 16 Aug 2024
Viewed by 248
Abstract
This study aimed to improve apple slices’ color and drying kinetics by optimizing the hot-air drying process, utilizing machine and deep learning models. Different steam blanching times (30, 60, 90, and 120 s), drying temperatures (50, 55, 60, 65, and 70 °C), and [...] Read more.
This study aimed to improve apple slices’ color and drying kinetics by optimizing the hot-air drying process, utilizing machine and deep learning models. Different steam blanching times (30, 60, 90, and 120 s), drying temperatures (50, 55, 60, 65, and 70 °C), and humidity control methods (full humidity removal or temperature–humidity control) were examined. These factors significantly affected the quality of apple slices. 60 s blanching, 60 °C temperature, and full dehumidification represented the optimal drying conditions for apple slices’ dehydration, achieving better drying kinetics and the best color quality. However, the fastest drying process (40 min) was obtained at a 60 °C drying temperature combined with complete dehumidification after 90 s blanching. Furthermore, machine and deep learning models, including backpropagation (BP), convolutional neural network–long short-term memory (CNN-LSTM), temporal convolutional network (TCN), and long short-term memory (LSTM) networks, effectively predicted the moisture content and color variation in apple slices. Among these, LSTM networks demonstrated exceptional predictive performance with an R2 value exceeding 0.98, indicating superior accuracy. This study provides a scientific foundation for optimizing the drying process of apple slices and illustrates the potential application of deep learning in the agricultural processing and engineering fields. Full article
(This article belongs to the Special Issue Drying Kinetics and Quality Control in Food Processing, 2nd Edition)
Show Figures

Figure 1

33 pages, 10515 KiB  
Article
Exploring the Processing Paradigm of Input Data for End-to-End Deep Learning in Tool Condition Monitoring
by Chengguan Wang, Guangping Wang, Tao Wang, Xiyao Xiong, Zhongchuan Ouyang and Tao Gong
Sensors 2024, 24(16), 5300; https://doi.org/10.3390/s24165300 - 15 Aug 2024
Viewed by 407
Abstract
Tool condition monitoring technology is an indispensable part of intelligent manufacturing. Most current research focuses on complex signal processing techniques or advanced deep learning algorithms to improve prediction performance without fully leveraging the end-to-end advantages of deep learning. The challenge lies in transforming [...] Read more.
Tool condition monitoring technology is an indispensable part of intelligent manufacturing. Most current research focuses on complex signal processing techniques or advanced deep learning algorithms to improve prediction performance without fully leveraging the end-to-end advantages of deep learning. The challenge lies in transforming multi-sensor raw data into input data suitable for direct model feeding, all while minimizing data scale and preserving sufficient temporal interpretation of tool wear. However, there is no clear reference standard for this so far. In light of this, this paper innovatively explores the processing methods that transform raw data into input data for deep learning models, a process known as an input paradigm. This paper introduces three new input paradigms: the downsampling paradigm, the periodic paradigm, and the subsequence paradigm. Then an improved hybrid model that combines a convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) was employed to validate the model’s performance. The subsequence paradigm demonstrated considerable superiority in prediction results based on the PHM2010 dataset, as the newly generated time series maintained the integrity of the raw data. Further investigation revealed that, with 120 subsequences and the temporal indicator being the maximum value, the model’s mean absolute error (MAE) and root mean square error (RMSE) were the lowest after threefold cross-validation, outperforming several classical and contemporary methods. The methods explored in this paper provide references for designing input data for deep learning models, helping to enhance the end-to-end potential of deep learning models, and promoting the industrial deployment and practical application of tool condition monitoring systems. Full article
Show Figures

Figure 1

12 pages, 1968 KiB  
Article
A Deep Learning Approach for Early Detection of Facial Palsy in Video Using Convolutional Neural Networks: A Computational Study
by Anuja Arora, Jasir Mohammad Zaeem, Vibhor Garg, Ambikesh Jayal and Zahid Akhtar
Computers 2024, 13(8), 200; https://doi.org/10.3390/computers13080200 - 15 Aug 2024
Viewed by 295
Abstract
Facial palsy causes the face to droop due to sudden weakness in the muscles on one side of the face. Computer-added assistance systems for the automatic recognition of palsy faces present a promising solution to recognizing the paralysis of faces at an early [...] Read more.
Facial palsy causes the face to droop due to sudden weakness in the muscles on one side of the face. Computer-added assistance systems for the automatic recognition of palsy faces present a promising solution to recognizing the paralysis of faces at an early stage. A few research studies have already been performed to handle this research issue using an automatic deep feature extraction by deep learning approach and handcrafted machine learning approach. This empirical research work designed a multi-model facial palsy framework which is a combination of two convolutional models—a multi-task cascaded convolutional network (MTCNN) for face and landmark detection and a hyperparameter tuned and parametric setting convolution neural network model for facial palsy classification. Using the proposed multi-model facial palsy framework, we presented results on a dataset of YouTube videos featuring patients with palsy. The results indicate that the proposed framework can detect facial palsy efficiently. Furthermore, the achieved accuracy, precision, recall, and F1-score values of the proposed framework for facial palsy detection are 97%, 94%, 90%, and 97%, respectively, for the training dataset. For the validation dataset, the accuracy achieved is 95%, precision is 90%, recall is 75.6%, and F-score is 76%. As a result, this framework can easily be used for facial palsy detection. Full article
Show Figures

Figure 1

Back to TopTop