Deep Learning Architecture Research Articles

Detection of Android Malware Using Word2Vec and Deep Learning

To fortify Android devices against evolving threats, the project unfolds with a commitment to contribute to security endeavors significantly. The core purpose is to leverage machine-learning techniques, particularly deep-learning architectures, to construct robust mechanisms for identifying and classifying Android malware. A hybrid deep learning model combining Long Short-Term Memory (LSTM) networks with Convolutional Neural Networks (CNN) is employed to classify the applications as benign or malicious. The LSTM-CNN model is designed to effectively capture both temporal dependencies and spatial patterns within the feature vectors. Additionally, a Random Forest classifier is used to identify the most important features for classification, improving the performance and efficiency of the deep learning model. The proposed approach is evaluated on the CICMalDroid2020 dataset, demonstrating its ability to detect and classify Android malware accurately. This highlights the effectiveness of static feature analysis combined with advanced deep learning architectures for enhancing Android malware detection systems.

A Comprehensive Survey on Brain Tumor Detection and Classification Techniques Using Machine Learning and Deep Learning Models

Abstract: Brain tumor detection and classification have become critical areas of research due to the complexities and challenges involved in accurate diagnosis. With the advancement of machine learning and deep learning techniques, numerous intelligent systems have been proposed to automate and enhance the process of detecting and classifying brain tumors. This survey paper reviews recent approaches and techniques used for brain tumor detection, focusing primarily on deep learning architectures like Convolutional Neural Networks (CNNs) and pre-trained models such as VGG, ResNet, and EfficientNet. In particular, methods using MRI images to classify tumors into categories such as glioma, meningioma, pituitary tumors, and healthy tissue are explored. A detailed analysis of various models, their architectures, training strategies, and evaluation metrics is provided. Moreover, the paper identifies the key challenges faced in the field, including imbalanced datasets, generalization issues, and computational efficiency. By comparing different approaches, we aim to highlight the strengths and limitations of each method and provide insights into how future research can address these challenges. The paper concludes with a discussion on promising future directions in the application of intelligent techniques for brain tumor detection, including the integration of multimodal data and the development of more interpretable models. This survey serves as a comprehensive resource for researchers interested in understanding the current landscape of brain tumor detection using advanced deep learning techniques.

A Multi-model Deep Learning Architecture for Diagnosing Multi-class Skin Diseases.

Skin diseases are a significant global public health concern, affecting 21-85% of the world's population, particularly those in low- and middle-income countries. Accurate and timely diagnosis is crucial for effective treatment and improved patient outcomes. This study introduces a novel deep-learning multi-model architecture designed for high-precision skin disease diagnosis. The system employs a five-category Xception model to classify skin lesions into five classes: Atopic Dermatitis, Acne and Rosacea, Skin Cancer, Bullous, and Others. Trained on 25,010 images, the model achieved 95% accuracy and an AUROC of 99.4%. To further enhance accuracy, transfer learning was applied, resulting in specialized models for each class, with strong performance across 40 skin conditions. Specifically, the Acne and Rosacea model achieved an accuracy of 90.0%, with a precision of 90.7%, recall of 90.1%, f1-score of 90.2%, and an AUROC of 99.0%. The Skin Cancer model demonstrated 94.0% accuracy, 94.8% precision, 94.2% recall, 94.1% f1-score, and a 99.5% AUROC. The Atopic Dermatitis model reported 91.8% accuracy, 92.2% precision, 91.8% recall, 91.9% f1-score, and a 98.8% AUROC. Finally, the Bullous model showed 90.0% accuracy, 90.6% precision, 90.0% recall, 90.0% f1-score, and a 98.9% AUROC. This approach surpasses previous studies, offering a more comprehensive diagnostic tool for skin diseases. To facilitate result reproducibility, the training and testing codes for the models utilized in this study are accessible via the GitHub repository ( https://github.com/SaraEl-Metwally/A-Multi-Model-Deep-Learning-for-Diagnosing-Skin-Diseases ).

XAI-FruitNet: An explainable deep model for accurate fruit classification

In agricultural technology, precise fruit classification is essential yet challenging due to inherent interclass similarities and intra-class variabilities among fruit species. Despite their impressive performance, traditional deep learning models suffer from a lack of interpretability, which hampers their transparency and trustworthiness in practical applications. To address these issues, we present XAI-FruitNet, a novel hybrid deep learning architecture designed to enhance feature discrimination by integrating average and max pooling techniques. XAI-FruitNet, an optimized architecture for efficiency evaluated across the Fruits-360, Fruit Recognition, Fruit and Vegetables Image Recognition, and Dry Fruit datasets, consistently achieves over 97 % accuracy, surpassing existing state-of-the-art models and underscoring its remarkable generalization capability. A significant advancement of XAI-FruitNet is its built-in interpretability, which enhances the model's transparency and fosters trust among endusers. Through rigorous experimentation, we demonstrate that XAI-FruitNet advances state-of-the-art fruit classification accuracy and sets a new standard for explainable artificial intelligence (XAI) in agricultural applications. This hybrid approach ensures that stakeholders can rely on the classification outcomes' high performance and comprehensible nature, thereby offering a robust and trustworthy solution for modern agricultural needs.

Analysis of the power during machining of Inconel 718 for different geometrical profiles and the development of power prediction models using multisensor data

This article presents analyses and prediction of machining power during end milling of Inconel 718 for different geometric features namely angular slot, half slot, square pocket, rectangular pocket, and blind hole. The experimental study revealed that among the machining features examined, angular slot required the highest specific cutting energy, while blind holes consumed the least, across different machining conditions. A 40% increase in cutting speed raised specific cutting energy by 4–9%, while a similar increase in feed rate lowered specific cutting energy by 40–44% across all profiles. Doubling depth of cut reduced specific cutting energy by 50% for angular slots, half slots, square pockets, and rectangular pockets, but increased it for blind holes. Power prediction models were developed using multisensor data, employing two machine learning and two deep learning architectures. The performance of the four power prediction models was compared for all geometric profiles using both raw data and statistical feature data extracted from machining signals from force dynamometer, accelerometer, and acoustic emission (AE) sensors. Long–Short-Term Memory model outperformed other models in case of raw data for all geometric profiles. The Random Forest Regression method consistently fared better for power predictions models developed based on feature-extracted data. Predictive models trained without AE sensor data performed better than those trained with AE.

Wheat Flour Discrimination Using Two-Dimensional Correlation Spectroscopy and Deep Learning.

The continuous evolution of deep learning has garnered significant attention in spectroscopy. This study focuses on identifying wheat flour, presenting a more efficient and accurate method by combining two-dimensional correlation spectroscopy (2D-COS) and deep learning techniques. A data set of 316 near-infrared (NIR) spectral samples of four types of wheat flour was collected. By applying three disparate 2D-COS techniques, i.e., synchronous, asynchronous, and integrated, we crafted 948 2D-COS images. These images, obtained by transforming the original one-dimensional spectra into 2D representations, offer richer information for deep learning analysis. The study introduced an 18-layer residual network incorporating a convolutional attention mechanism, specifically tailored for the 2D-COS analysis of wheat flour, aimed at enhancing the model's discriminative capabilities by refining the residual neural network's structure. Achieving an unprecedented recognition accuracy of 100% through methodical optimization and rigorous training on the synchronous 2D-COS data set of wheat flour, the proposed model is a testament to the efficacy of deep learning in spectroscopic analysis. To further exhibit the confluence of 2D-COS with deep learning, t-distributed stochastic neighbor embedding was employed to visualize the distinctive 2D-COS features within the deep learning architecture. Additionally, the model's performance was juxtaposed with prevailing NIR spectral recognition methods, including random forest, gradient boosting decision tree, and artificial neural network. This comparison cemented the proposed approach's superiority in wheat flour categorization. The findings of this study not only introduce a novel and efficient solution for wheat flour quality analysis but also underscore the significant potential of deep learning techniques in spectroscopy applications.

Automatic Gesture-Based Arabic Sign Language Recognition: A Federated Learning Approach

Featuring machine learning algorithms for recognizing hand gesture patterns adjusted for individuals with disabilities is an expanding trend in assisted living. This paper addresses the challenge of interpreting the semantics of image-based hand gestures by introducing a federated deep learning architecture for Arabic sign language recognition. The proposed model manages distributed learning through a client-server paradigm, wherein several edge nodes collaborate to jointly learn the discriminative features of confidential data without breaching its privacy. This model will enable more accessibility for people with deafness or impairment using image gestures. The federated learning procedure is primarily based on the ResNet32 deep backbone and federated averaging mechanism. The experimental results show the effectiveness of the proposed FL model, achieving an accuracy of 98.30% with 33 seconds on average for each client in a single training round. This demonstrates its high capabilities in recognizing Arabic sign language and improving the communication experience for people with disabilities.

DAB-LSTMNN: A novel respiratory disease diagnosis deep CNN framework based on attention scheme and BLSTM neural networks

Respiratory diseases have a significant impact on modern society, posing considerable public health risks. With the emergence of the COVID-19 pandemic, addressing respiratory issues has become increasingly urgent and important. Recently, artificial intelligence-based methods utilizing the acoustic recordings of suspected patients have shown promise in the diagnosis of various respiratory diseases, enabling localized treatment and containment of their spread. As the existing methods cannot efficiently extract subtle differences between the sound samples, thereby limiting their generalization ability. To improve the diagnosis accuracy, this paper proposes a novel multi-channel, multi-modal deep learning architecture based on the attention mechanism. The proposed framework combines a deep convolutional neural network (DCNN) with a bidirectional long short-term memory (BLSTM) network, and also utilizes the attention scheme to extract temporal and spectral features from different modalities of speech data (e.g. coughs, counting sounds and sustained vowel articulation). The proposed method effectively classifies COVID-19 patients, asthma patients and healthy individuals, with a test accuracy of 89.27 ± 0.1%, and an F1 score of 85.42 ± 0.2%. The experimental results validate the feasibility of our method, and also indicate that it is competitive with the existing deep networks.

A SYSTEMATIC LITERATURE REVIEW OF PREDICTIVE MODELS AND ANALYTICS IN AI-DRIVEN CREDIT SCORING

This systematic review examines the transformative role of AI-driven models in credit scoring, highlighting their advances over traditional statistical methods in terms of predictive accuracy, adaptability, and inclusivity. By synthesizing findings from 70 studies, this review demonstrates that machine learning techniques, particularly ensemble models such as random forests and gradient boosting, effectively capture complex, non-linear relationships in borrower data, providing more accurate risk assessments across diverse demographics. Deep learning models, especially convolutional and recurrent neural networks, extend credit scoring capabilities to unstructured and alternative data sources, supporting financial inclusion by enabling assessments of individuals without traditional credit histories. Hybrid models that integrate logistic regression with neural networks offer an optimal balance between interpretability and predictive power, addressing regulatory demands for transparency while maintaining robust accuracy. Ensemble techniques like stacking and blending enhance model adaptability, allowing credit scoring systems to integrate multiple perspectives and improve prediction accuracy in varied borrower contexts. Despite these advancements, challenges remain in the form of ethical concerns and the need for model interpretability, particularly with complex deep-learning architectures. The review underscores the importance of developing fairness-aware and explainable AI frameworks to ensure that as AI-driven credit scoring evolves, it remains both transparent and equitable. These insights suggest that with careful attention to ethics and transparency, AI has the potential to create a more inclusive and resilient credit scoring landscape, accommodating the needs of an increasingly diverse global population.

Artificial intelligence assisted common maternal fetal planes prediction from ultrasound images based on information fusion of customized convolutional neural networks.

Ultrasound imaging is frequently employed to aid with fetal development. It benefits from being real-time, inexpensive, non-intrusive, and simple. Artificial intelligence is becoming increasingly significant in medical imaging and can assist in resolving many problems related to the classification of fetal organs. Processing fetal ultrasound (US) images increasingly uses deep learning (DL) techniques. This paper aims to assess the development of existing DL classification systems for use in a real maternal-fetal healthcare setting. This experimental process has employed two publicly available datasets, such as FPSU23 Dataset and Fetal Imaging. Two novel deep learning architectures have been designed in the proposed architecture based on 3-residual and 4-residual blocks with different convolutional filter sizes. The hyperparameters of the proposed architectures were initialized through Bayesian Optimization. Following the training process, deep features were extracted from the average pooling layers of both models. In a subsequent step, the features from both models were optimized using an improved version of the Generalized Normal Distribution Optimizer (GNDO). Finally, neural networks are used to classify the fused optimized features of both models, which were first combined using a new fusion technique. The best classification scores, 98.5 and 88.6% accuracy, were obtained after multiple steps of analysis. Additionally, a comparison with existing state-of-the-art methods revealed a notable improvement in the suggested architecture's accuracy.

GTransCYPs: an improved graph transformer neural network with attention pooling for reliably predicting CYP450 inhibitors

State‑of‑the‑art medical studies proved that predicting CYP450 enzyme inhibitors is beneficial in the early stage of drug discovery. However, accurate machine learning-based (ML) in silico methods for predicting CYP450 inhibitors remains challenging. Here, we introduce GTransCYPs, an improved graph neural network (GNN) with a transformer mechanism for predicting CYP450 inhibitors. This model significantly enhances the discrimination between inhibitors and non-inhibitors for five major CYP450 isozymes: 1A2, 2C9, 2C19, 2D6, and 3A4. GTransCYPs learns information patterns from molecular graphs by aggregating node and edge representations using a transformer. The GTransCYPs model utilizes transformer convolution layers to process features, followed by a global attention-pooling technique to synthesize the graph-level information. This information is then fed through successive linear layers for final output generation. Experimental results demonstrate that the GTransCYPs model achieved high performance, outperforming other state-of-the-art methods in CYP450 prediction.Scientific contributionThe prediction of CYP450 inhibition via computational techniques utilizing biological information has emerged as a cost-effective and highly efficient approach. Here, we presented a deep learning (DL) architecture based on GNN with transformer mechanism and attention pooling (GTransCYPs) to predict CYP450 inhibitors. Four GTransCYPs of different pooling technique were tested on an experimental tasks on the CYP450 prediction problem for the first time. Graph transformer with attention pooling algorithm achieved the best performances. Comparative and ablation experiments provide evidence of the efficacy of our proposed method in predicting CYP450 inhibitors. The source code is publicly available at https://github.com/zonwoo/GTransCYPs.

Towards high-performance deep learning architecture and hardware accelerator design for robust analysis in diffuse correlation spectroscopy

This study proposes a compact deep learning (DL) architecture and a highly parallelized computing hardware platform to reconstruct the blood flow index (BFi) in diffuse correlation spectroscopy (DCS). We leveraged a rigorous analytical model to generate autocorrelation functions (ACFs) to train the DL network. We assessed the accuracy of the proposed DL using simulated and milk phantom data. Compared to convolutional neural networks (CNN), our lightweight DL architecture achieves 66.7% and 18.5% improvement in MSE for BFi and the coherence factor β, using synthetic data evaluation. The accuracy of rBFi over different algorithms was also investigated. We further simplified the DL computing primitives using subtraction for feature extraction, considering further hardware implementation. We extensively explored computing parallelism and fixed-point quantization within the DL architecture. With the DL model's compact size, we employed unrolling and pipelining optimizations for computation-intensive for-loops in the DL model while storing all learned parameters in on-chip BRAMs. We also achieved pixel-wise parallelism, enabling simultaneous, real-time processing of 10 and 15 autocorrelation functions on Zynq-7000 and Zynq-UltraScale+ field programmable gate array (FPGA), respectively. Unlike existing FPGA accelerators that produce BFi and the β from autocorrelation functions on standalone hardware, our approach is an encapsulated, end-to-end on-chip conversion process from intensity photon data to the temporal intensity ACF and subsequently reconstructing BFi and β. This hardware platform achieves an on-chip solution to replace post-processing and miniaturize modern DCS systems that use single-photon cameras. We also comprehensively compared the computational efficiency of our FPGA accelerator to CPU and GPU solutions.

A comprehensive comparison of deep learning-based compound-target interaction prediction models to unveil guiding design principles

The evaluation of compound-target interactions (CTIs) is at the heart of drug discovery efforts. Given the substantial time and monetary costs of classical experimental screening, significant efforts have been dedicated to develop deep learning-based models that can accurately predict CTIs. A comprehensive comparison of these models on a large, curated CTI dataset is, however, still lacking. Here, we perform an in-depth comparison of 12 state-of-the-art deep learning architectures that use different protein and compound representations. The models were selected for their reported performance and architectures. To reliably compare model performance, we curated over 300 thousand binding and non-binding CTIs and established several gold-standard datasets of varying size and information. Based on our findings, DeepConv-DTI consistently outperforms other models in CTI prediction performance across the majority of datasets. It achieves an MCC of 0.6 or higher for most of the datasets and is one of the fastest models in training and inference. These results indicate that utilizing convolutional-based windows as in DeepConv-DTI to traverse trainable embeddings is a highly effective approach for capturing informative protein features. We also observed that physicochemical embeddings of targets increased model performance. We therefore modified DeepConv-DTI to include normalized physicochemical properties, which resulted in the overall best performing model Phys-DeepConv-DTI. This work highlights how the systematic evaluation of input features of compounds and targets, as well as their corresponding neural network architectures, can serve as a roadmap for the future development of improved CTI models.Scientific contributionThis work features comprehensive CTI datasets to allow for the objective comparison and benchmarking of CTI prediction algorithms. Based on this dataset, we gained insights into which embeddings of compounds and targets and which deep learning-based algorithms perform best, providing a blueprint for the future development of CTI algorithms. Using the insights gained from this screen, we provide a novel CTI algorithm with state-of-the-art performance.

Federated Deep Learning Model for False Data Injection Attack Detection in Cyber Physical Power Systems

Cyber-physical power systems (CPPS) integrate information and communication technology into conventional electric power systems to facilitate bidirectional communication of information and electric power between users and power grids. Despite its benefits, the open communication environment of CPPS is vulnerable to various security attacks. This paper proposes a federated deep learning-based architecture to detect false data injection attacks (FDIAs) in CPPS. The proposed work offers a strong, decentralized alternative with the ability to boost detection accuracy while maintaining data privacy, presenting a significant opportunity for real-world applications in the smart grid. This framework combines state-of-the-art machine learning and deep learning models, which are used in both centralized and federated learning configurations, to boost the detection of false data injection attacks in cyber-physical power systems. In particular, the research uses a multi-stage detection framework that combines several models, including classic machine learning classifiers like Random Forest and ExtraTrees Classifiers, and deep learning architectures such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The results demonstrate that Bidirectional GRU and LSTM models with attention layers in a federated learning setup achieve superior performance, with accuracy approaching 99.8%. This approach enhances both detection accuracy and data privacy, offering a robust solution for FDIA detection in real-world smart grid applications.

Deep learning analysis of histopathological images predicts immunotherapy prognosis and reveals tumour microenvironment features in non-small cell lung cancer.

Non-small cell lung cancer (NSCLC) is one of the leading causes of cancer mortality worldwide. Immune checkpoint inhibitors (ICIs) have emerged as a crucial treatment option for patients with advanced NSCLC. However, only a subset of patients experience clinical benefit from ICIs. Therefore, identifying biomarkers that can predict response to ICIs is imperative for optimising patient selection. Hematoxylin and eosin (H&E) images of NSCLC patients were obtained from the local cohort (n = 106) and The Cancer Genome Atlas (TCGA) (n = 899). We developed an ICI-related pathological prognostic signature (ir-PPS) based on H&E stained histopathology images to predict prognosis in NSCLC patients treated with ICIs using deep learning. To accomplish this, we employed a modified ResNet model (ResNet18-PG), a widely-used deep learning architecture well-known for its effectiveness in handling complex image recognition tasks. Our modifications include a progressive growing strategy to improve the stability of model training and the use of the AdamW optimiser, which enhances the optimisation process by adjusting the learning rate based on training dynamics. The deep learning model, ResNet18-PG, achieved an area under the receiver operating characteristic curve (AUC) of 0.918 and a recall of 0.995 on the local cohort. The ir-PPS effectively risk-stratified NSCLC patients. Patients in the low-risk group (n = 40) had significantly improved progression-free survival (PFS) after ICI treatment compared to those in the high-risk group (n = 66, log-rank P = 0.004, hazard ratio (HR) = 3.65, 95%CI: 1.75-7.60). The ir-PPS demonstrated good discriminatory power for predicting 6-month PFS (AUC = 0.750), 12-month PFS (AUC = 0.677), and 18-month PFS (AUC = 0.662). The low-risk group exhibited increased expression of immune checkpoint molecules, cytotoxicity-related genes, an elevated abundance of tumour-infiltrating lymphocytes, and enhanced activity in immune stimulatory pathways. The ir-PPS signature derived from H&E images using deep learning could predict ICIs prognosis in NSCLC patients. The ir-PPS provides a novel imaging biomarker that may help select optimal candidates for ICIs therapy in NSCLC.

Machine learning for base transceiver stations power failure prediction: A multivariate approach

The widespread deployment of cellular networks has improved communication access, driving economic growth and enhancing social connections across diverse regions. Base Transceiver Stations (BTSs), are foundational to mobile networks but are vulnerable to power failures, disrupting service delivery and causing user inconvenience. This paper proposes a machine-learning-based framework for preemptive BTS power failure prediction using multivariate time-series data from power and environmental monitoring systems. We employ a combination of deep learning architectures, including Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and hybrid CNN-LSTM models, to achieve accurate and timely predictions of BTS power failures. CNNs were selected for extracting dependencies among features of a multivariate time-series data, while LSTMs effectively capture temporal dependencies, making them suitable for predicting power failures.The proposed models exhibit noteworthy predictive performance, with the LSTM network emerging as the most accurate model (MSE: 0.001, MAPE: 2.528), followed by the hybrid CNN-LSTM (MSE: 0.001, MAPE: 2.843) and the CNN (MSE: 0.223, MAPE: 2.843). This work demonstrates deep learning’s effectiveness in preemptive BTS failure prediction, enabling proactive maintenance and improved network resilience.

Deep Learning Approaches for Wildfire Severity Prediction: A Comparative Study of Image Segmentation Networks and Visual Transformers on the EO4WildFires Dataset

This paper investigates the applicability of deep learning models for predicting the severity of forest wildfires, utilizing an innovative benchmark dataset called EO4WildFires. EO4WildFires integrates multispectral imagery from Sentinel-2, SAR data from Sentinel-1, and meteorological data from NASA Power annotated with EFFIS data for forest fire detection and size estimation. These data cover 45 countries with a total of 31,730 wildfire events from 2018 to 2022. All of these various sources of data are archived into data cubes, with the intention of assessing wildfire severity by considering both current and historical forest conditions, utilizing a broad range of data including temperature, precipitation, and soil moisture. The experimental setup has been arranged to test the effectiveness of different deep learning architectures in predicting the size and shape of wildfire-burned areas. This study incorporates both image segmentation networks and visual transformers, employing a consistent experimental design across various models to ensure the comparability of the results. Adjustments were made to the training data, such as the exclusion of empty labels and very small events, to refine the focus on more significant wildfire events and potentially improve prediction accuracy. The models’ performance was evaluated using metrics like F1 score, IoU score, and Average Percentage Difference (aPD). These metrics offer a multi-faceted view of model performance, assessing aspects such as precision, sensitivity, and the accuracy of the burned area estimation. Through extensive testing the final model utilizing LinkNet and ResNet-34 as backbones, we obtained the following metric results on the test set: 0.86 F1 score, 0.75 IoU, and 70% aPD. These results were obtained when all of the available samples were used. When the empty labels were absent during the training and testing, the model increased its performance significantly: 0.87 F1 score, 0.77 IoU, and 44.8% aPD. This indicates that the number of samples, as well as their respectively size (area), tend to have an impact on the model’s robustness. This restriction is well known in the remote sensing domain, as accessible, accurately labeled data may be limited. Visual transformers like TeleViT showed potential but underperformed compared to segmentation networks in terms of F1 and IoU scores.

U-Net and Its Variants Based Automatic Tracking of Radial Artery in Ultrasonic Short-Axis Views: A Pilot Study.

Background/Objectives: Radial artery tracking (RAT) in the short-axis view is a pivotal step for ultrasound-guided radial artery catheterization (RAC), which is widely employed in various clinical settings. To eliminate disparities and lay the foundations for automated procedures, a pilot study was conducted to explore the feasibility of U-Net and its variants in automatic RAT. Methods: Approved by the institutional ethics committee, patients as potential RAC candidates were enrolled, and the radial arteries were continuously scanned by B-mode ultrasonography. All acquired videos were processed into standardized images, and randomly divided into training, validation, and test sets in an 8:1:1 ratio. Deep learning models, including U-Net and its variants, such as Attention U-Net, UNet++, Res-UNet, TransUNet, and UNeXt, were utilized for automatic RAT. The performance of the deep learning architectures was assessed using loss functions, dice similarity coefficient (DSC), and Jaccard similarity coefficient (JSC). Performance differences were analyzed using the Kruskal-Wallis test. Results: The independent datasets comprised 7233 images extracted from 178 videos of 135 patients (53.3% women; mean age: 41.6 years). Consistent convergence of loss functions between the training and validation sets was achieved for all models except Attention U-Net. Res-UNet emerged as the optimal architecture in terms of DSC and JSC (93.14% and 87.93%), indicating a significant improvement compared to U-Net (91.79% vs. 86.19%, p < 0.05) and Attention U-Net (91.20% vs. 85.02%, p < 0.05). Conclusions: This pilot study validates the feasibility of U-Net and its variants in automatic RAT, highlighting the predominant performance of Res-UNet among the evaluated architectures.

In-Bed Monitoring: A Systematic Review of the Evaluation of In-Bed Movements Through Bed Sensors

The growing popularity of smart beds and devices for remote healthcare monitoring is based on advances in artificial intelligence (AI) applications. This systematic review aims to evaluate and synthesize the growing literature on the use of machine learning (ML) techniques to characterize patient in-bed movements and bedsore development. This review is conducted according to the principles of PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) and is registered in the International Prospective Register of Systematic Reviews (PROSPERO CRD42022314329). The search was performed through nine scientific databases. The review included 78 articles, including 142 ML models. The applied ML models revealed significant heterogeneity in the various methodologies used to identify and classify patient behaviors and postures. The assortment of ML models encompassed artificial neural networks, deep learning architectures, and multimodal sensor integration approaches. This review shows that the models for analyzing and interpreting in-bed movements perform well in experimental settings. Large-scale real-life studies are lacking in diverse patient populations.

Neutrosophic set and optimized deep learning for classification of chicken Eimeria species: a practical solution for poultry industry

AbstractTo optimize infection control and bolster productivity within the poultry industry, it is imperative to accurately classify Chicken Eimeria species. There are several methods for determining Eimeria disease in chickens. Traditional methods involve watching for clinical symptoms, and macroscopic lesions, and studying the parasite’s biology and oocyst morphology. These methods are frequently time-consuming and labor-intensive, necessitating the manual collection and analysis of samples, which can be especially difficult in large chicken farms. Deep learning algorithms, on the other hand, provide automated, accurate, and non-invasive methods for the detection of Eimeria. This paper proposed a classification model for the automatic classification of chicken Eimeria species. The proposed model is mainly based on integrating neutrosophic set theory and InceptionV3 deep-learning architecture. Three primary phases make up the proposed chicken Eimeria species classification model: the data preprocessing phase, the neutrosophic image conversion phase, and the image classification phase. To address the issue of class imbalance in the adopted dataset and enhance the model’s generalizability, the random oversampling method, and data augmentation techniques are employed during the data preprocessing phase. The preprocessed data is considered to feed the neutrosophic set-based segmentation algorithm, where true, false, and intermediate subsets are extracted. Finally, the true subset is utilized to feed the optimized InceptionV3. To determine the optimal hyperparameter values for InceptionV3, a modified version of the Brown Bear optimization algorithm is proposed in this paper. To evaluate the effectiveness of the proposed model, a real benchmark dataset comprising images of different Eimeria species is adopted. The experimental results revealed that the proposed model offers a more efficient and accurate alternative to traditional methods and state-of-the-art models, enabling faster and more effective diagnosis and treatment of Eimeria infections. It achieved an overall accuracy, specificity, sensitivity, and F1-score of nearly 100%. Additionally, the results showed that the high performance of the proposed model can reduce labor costs and boost throughput, thereby enhancing economic viability even more.