Learning Accuracy Research Articles

Accuracy of deep learning in the differential diagnosis of coronary artery stenosis: a systematic review and meta-analysis

BackgroundIn recent years, as deep learning has received widespread attention in the field of heart disease, some studies have explored the potential of deep learning based on coronary angiography (CAG) or coronary CT angiography (CCTA) images in detecting the extent of coronary artery stenosis. However, there is still a lack of a systematic understanding of its diagnostic accuracy, impeding the advancement of intelligent diagnosis of coronary artery stenosis. Therefore, we conducted this study to review the accuracy of image-based deep learning in detecting coronary artery stenosis.MethodsWe retrieved PubMed, Cochrane, Embase, and Web of Science until April 11, 2023. The risk of bias in the included studies was appraised using the QUADAS-2 tool. We extracted the accuracy of deep learning in the test set and performed subgroup analyses by binary and multiclass classification scenarios. We performed a subgroup analysis based on different degrees of stenosis and applied a double arcsine transformation to process the data. The analysis was done by using R.ResultsOur systematic review finally included 18 studies, involving 3568 patients and 13,362 images. In the included studies, deep learning models were constructed based on CAG and CCTA. In binary classification tasks, the accuracy for detecting > 25%, > 50% and > 70% degrees of stenosis at the vessel level were 0.81 (95% CI: 0.71–0.85), 0.73 (95% CI: 0.58–0.88) and 0.61 (95% CI: 0.56–0.65), respectively. In multiclass classification tasks, the accuracy for detecting 0–25%, 25–50%, 50–70%, and 70–100% degrees of stenosis at the vessel level were 0.78 (95% CI: 0.73–0.84), 0.86 (95% CI: 0.78–0.93), 0.83 (95% CI: 0.70–0.97), and 0.70 (95% CI: 0.42–0.98), respectively.ConclusionsOur study shows that deep learning models based on CAG and CCTA appear to be relatively accurate in diagnosing different degrees of coronary artery stenosis. However, for various degrees of stenosis, their accuracy still needs to be further improved.

Classification of cervical vertebral maturation stages with machine learning models: leveraging datasets with high inter- and intra-observer agreement

ObjectivesThis study aimed to assess the accuracy of machine learning (ML) models with feature selection technique in classifying cervical vertebral maturation stages (CVMS). Consensus-based datasets were used for models training and evaluation for their model generalization capabilities on unseen datasets.MethodsThree clinicians independently rated CVMS on 1380 lateral cephalograms, resulting in the creation of five datasets: two consensus-based datasets (Complete Agreement and Majority Voting), and three datasets based on a single rater’s evaluations. Additionally, landmarks annotation of the second to fourth cervical vertebrae and patients’ information underwent a feature selection process. These datasets were used to train various ML models and identify the top-performing model for each dataset. These models were subsequently tested on their generalization capabilities.ResultsFeatures that considered significant in the consensus-based datasets were consistent with a CVMS guideline. The Support Vector Machine model on the Complete Agreement dataset achieved the highest accuracy (77.4%), followed by the Multi-Layer Perceptron model on the Majority Voting dataset (69.6%). Models from individual ratings showed lower accuracies (60.4–67.9%). The consensus-based training models also exhibited lower coefficient of variation (CV), indicating superior generalization capability compared to models from single raters.ConclusionML models trained on consensus-based datasets for CVMS classification exhibited the highest accuracy, with significant features consistent with the original CVMS guidelines. These models also showed robust generalization capabilities, underscoring the importance of dataset quality.

Enhanced multidimensional neo-fuzzy classification system and its learning for the video classification task

This research introduces an innovative hybrid neo-fuzzy system for video classification, integrating multidimensional neo-fuzzy components with adjustable synaptic weights and Gaussian membership functions. By combining extended neo-fuzzy neurons (ENFN) and neo-fuzzy units (NFU) with nonlinear activation functions and incorporating extended nonlinear synapses (ENS), the system leverages the neuro-fuzzy Takagi-Sugeno-Kang inference system to enhance traditional models' approximating capabilities. Video classification is complex due to high data volume and variability, especially with moving objects and varying video quality. Traditional models struggle with real-time processing and maintaining accuracy, necessitating advanced techniques for robust performance. The goal is to develop and optimize a hybrid neo-fuzzy system for real-time video stream classification, maintaining high accuracy. Computational experiments demonstrated its robustness, achieving high precision and recall. The proposed optimization algorithm, using cross-entropy learning with one-hot encoding and adaptive δ-rule adjustments, improved learning speed and accuracy. The novelty lies in developing a hybrid neo-fuzzy system with advanced components and a unique optimization algorithm, ensuring robustness and efficiency in complex video classification tasks.

Defect-engineered monolayer MoS2 with enhanced memristive and synaptic functionality for neuromorphic computing

Two-dimensional transition metal dichalcogenides (TMDs)-based memristors are promising candidates for realizing artificial synapses in next-generation computing. However, practical implementation faces several challenges, such as high non-linearity and asymmetry in synaptic weight updates, limited dynamic range, and cycle-to-cycle variability. Here, utilizing optimal-power argon plasma treatment, we significantly enhance the performance matrix of memristors fabricated from monolayer MoS2. Our approach not only improves linearity and symmetry in synaptic weight updates but also increases the number of available synaptic weight updates and enhances Spike-Time Dependent Plasticity. Notably, it broadens the switching ratio by two orders, minimizes cycle-to-cycle variability, reduces non-linear factors, and achieves an energy consumption of ~30 fJ per synaptic event. Implementation of these enhancements is demonstrated through Artificial Neural Network simulations, yielding a learning accuracy of ~97% on the MNIST hand-written digits dataset. Our findings underscore the significance of defect engineering as a powerful tool in advancing the synaptic functionality of memristors.

Modular stochastic configuration network with attention mechanism for soft measurement of water quality parameters in wastewater treatment processes

Due to the complex and multi-distributed nature of wastewater treatment process data, stochastic configuration networks (SCNs) face difficulties such as large network structure and complex construction process when dealing with data modeling tasks. To address these challenges, this paper proposes a modular stochastic configuration network with attention mechanism, which integrates the advantages of modular partitioning, attention mechanism, and SCN. The model employs a fuzzy mean clustering strategy to simplify and decompose the complex multi-case and multi-distribution nonlinear modeling task, thereby reducing the modeling complexity of a single model. Furthermore, the model utilizes a stochastic configuration algorithm to learn the subtasks and construct corresponding sub-networks. The output weights are then assigned to each sub-network based on the attention mechanism to obtain the model’s final output. The validity of the proposed method is validated through two benchmark experiments. Then the model is applied to measure effluent ammonia nitrogen. The results indicate that compared with the classical randomized and modularized network models, the proposed model exhibits certain advantages in terms of learning accuracy and generalization performance.

Knee Osteoporosis Diagnosis Based on Deep Learning

Osteoporosis, a silent yet debilitating disease, presents a significant challenge due to its asymptomatic nature until fractures occur. Rapid bone loss outpaces regeneration, leading to pain, disability, and loss of independence. Early detection is pivotal for effective management and fracture risk reduction, yet current diagnostic methods are time-consuming. Despite its importance, research addressing early diagnosis remains limited. Deep learning, particularly convolutional neural networks (CNNs), has emerged as a potent tool in image analysis. This paper presents a novel approach utilizing transfer learning with CNNs for osteoporosis detection from X-ray images. The proposed approach not only achieves a high accuracy of osteoporosis diagnosis but also offers a revealed feature map that can guide medical professionals for osteoporosis diagnosis. The innovation lies in a dual strategy: (i) a model integrating transfer learning from CNN architectures such as AlexNet, VGG-16, ResNet-50, VGG-19, InceptionNet, XceptionNet, and a custom CNN, and (ii) a dataset collection augmentation mechanism to enhance learning accuracy. The study includes binary and multiclass classification of knee joint X-ray images into normal, osteopenia, and osteoporosis groups, utilizing a dataset of 1947 knee X-rays for training and testing. Performance comparisons against state-of-the-art models reveal the proposed VGG-19 model achieves the highest accuracy at 92.0% for multiclass and 97.5% for binary. These findings underscore the potential of deep learning with transfer learning in aiding early osteoporosis detection, thereby mitigating fracture risks.

Detecting schizophrenia, bipolar disorder, psychosis vulnerability and major depressive disorder from 5 minutes of online-collected speech.

Psychosis poses substantial social and healthcare burdens. The analysis of speech is a promising approach for the diagnosis and monitoring of psychosis, capturing symptoms like thought disorder and flattened affect. Recent advancements in Natural Language Processing (NLP) methodologies enable the automated extraction of informative speech features, which has been leveraged for early psychosis detection and assessment of symptomology. However, critical gaps persist, including the absence of standardized sample collection protocols, small sample sizes, and a lack of multi-illness classification, limiting clinical applicability. Our study aimed to (1) identify an optimal assessment approach for the online and remote collection of speech, in the context of assessing the psychosis spectrum and evaluate whether a fully automated, speech-based machine learning (ML) pipeline can discriminate among different conditions on the schizophrenia-bipolar spectrum (SSD-BD-SPE), help-seeking comparison subjects (MDD), and healthy controls (HC) at varying layers of analysis and diagnostic complexity. We adopted online data collection methods to collect 20 minutes of speech and demographic information from individuals. Participants were categorized as "healthy" help-seekers (HC), having a schizophrenia-spectrum disorder (SSD), bipolar disorder (BD), major depressive disorder (MDD), or being on the psychosis spectrum with sub-clinical psychotic experiences (SPE). SPE status was determined based on self-reported clinical diagnosis and responses to the PHQ-8 and PQ-16 screening questionnaires, while other diagnoses were determined based on self-report from participants. Linguistic and paralinguistic features were extracted and ensemble learning algorithms (e.g., XGBoost) were used to train models. A 70%-30% train-test split and 30-fold cross-validation was used to validate the model performance. The final analysis sample included 1140 individuals and 22,650 minutes of speech. Using 5-minutes of speech, our model could discriminate between HC and those with a serious mental illness (SSD or BD) with 86% accuracy (AUC = 0.91, Recall = 0.7, Precision = 0.98). Furthermore, our model could discern among HC, SPE, BD and SSD groups with 86% accuracy (F1 macro = 0.855, Recall Macro = 0.86, Precision Macro = 0.86). Finally, in a 5-class discrimination task including individuals with MDD, our model had 76% accuracy (F1 macro = 0.757, Recall Macro = 0.758, Precision Macro = 0.766). Our ML pipeline demonstrated disorder-specific learning, achieving excellent or good accuracy across several classification tasks. We demonstrated that the screening of mental disorders is possible via a fully automated, remote speech assessment pipeline. We tested our model on relatively high number conditions (5 classes) in the literature and in a stratified sample of psychosis spectrum, including HC, SPE, SSD and BD (4 classes). We tested our model on a large sample (N = 1150) and demonstrated best-in-class accuracy with remotely collected speech data in the psychosis spectrum, however, further clinical validation is needed to test the reliability of model performance.

Using MRI Texture Analysis Machine Learning Models to Assess Graft Interstitial Fibrosis and Tubular Atrophy in Patients with Transplanted Kidneys

Objective: Interstitial fibrosis/tubular atrophy (IFTA) is a common, irreversible, and progressive form of chronic kidney allograft injury, and it is considered a critical predictor of kidney allograft outcomes. The extent of IFTA is estimated through a graft biopsy, while a non-invasive test is lacking. The aim of this study was to evaluate the feasibility and accuracy of an MRI radiomic-based machine learning (ML) algorithm to estimate the degree of IFTA in a cohort of transplanted patients. Approach: Patients who underwent MRI and renal biopsy within a 6-month interval from 1 January 2012 to 1 March 2021 were included. Stable MRI sequences were selected, and renal parenchyma, renal cortex and medulla were segmented. After image filtering and pre-processing, we computed radiomic features that were subsequently selected through a LASSO algorithm for their highest correlation with the outcome and lowest intercorrelation. Selected features and relevant patients’ clinical data were used to produce ML algorithms using 70% of the study cases for feature selection, model training and validation with a 10-fold cross-validation, and 30% for model testing. Performances were evaluated using AUC with 95% confidence interval. Main results: A total of 70 coupled tests (63 patients, 35.4% females, mean age 52.2 years) were included and subdivided into a wider cohort of 50 for training and a smaller cohort of 20 for testing. For IFTA ≥ 25%, the AUCs in test cohort were 0.60, 0.59, and 0.54 for radiomic features only, clinical variables only, and a combined radiomic–clinical model, respectively. For IFTA ≥ 50%, the AUCs in training cohort were 0.89, 0.84, and 0.96, and in the test cohort, they were 0.82, 0.83, and 0.86, for radiomic features only, clinical variables only, and the combined radiomic–clinical model, respectively. Significance: An ML-based MRI radiomic algorithm showed promising discrimination capacity for IFTA > 50%, especially when combined with clinical variables. These results need to be confirmed in larger cohorts.

Accuracy of machine learning in predicting outcomes post-percutaneous coronary intervention: a systematic review.

Recent studies have shown potential in introducing machine learning (ML) algorithms to predict outcomes post-percutaneous coronary intervention (PCI). We aimed to critically appraise current ML models' effectiveness as clinical tools to predict outcomes post-PCI. Searches of four databases were conducted for articles published from the database inception date to 29 May 2021. Studies using ML to predict outcomes post-PCI were included. For individual post-PCI outcomes, measures of diagnostic accuracy were extracted. An adapted checklist comprising existing frameworks for new risk markers, diagnostic accuracy, prognostic tools and ML was used to critically appraise the included studies along the stages of the translational pathway: development, validation, and impact. Quality of training data and methods of dealing with missing data were evaluated. Twelve cohorts from 11 studies were included with a total of 4,943,425 patients. ML models performed with high diagnostic accuracy. However, there are concerns over the development of the ML models. Methods of dealing with missing data were problematic. Four studies did not discuss how missing data were handled. One study removed patients if any of the predictor variable data points were missing. Moreover, at the validation stage, only three studies externally validated the models presented. There could be concerns over the applicability of these models. None of the studies discussed the cost-effectiveness of implementing the models. ML models show promise as a useful clinical adjunct to traditional risk stratification scores in predicting outcomes post-PCI. However, significant challenges need to be addressed before ML can be integrated into clinical practice.

Machine learning value in the diagnosis of vertebral fractures: A systematic review and meta-analysis

PurposeTo evaluate the diagnostic accuracy of machine learning (ML) in detecting vertebral fractures, considering varying fracture classifications, patient populations, and imaging approaches. MethodA systematic review and meta-analysis were conducted by searching PubMed, Embase, Cochrane Library, and Web of Science up to December 31, 2023, for studies using ML for vertebral fracture diagnosis. Bias risk was assessed using QUADAS-2. A bivariate mixed-effects model was used for the meta-analysis. Meta-analyses were performed according to five task types (vertebral fractures, osteoporotic vertebral fractures, differentiation of benign and malignant vertebral fractures, differentiation of acute and chronic vertebral fractures, and prediction of vertebral fractures). Subgroup analyses were conducted by different ML models (including ML and DL) and modeling methods (including CT, X-ray, MRI, and clinical features). ResultsEighty-one studies were included. ML demonstrated a diagnostic sensitivity of 0.91 and specificity of 0.95 for vertebral fractures. Subgroup analysis showed that DL (SROC 0.98) and CT (SROC 0.98) performed best overall. For osteoporotic fractures, ML showed a sensitivity of 0.93 and specificity of 0.96, with DL (SROC 0.99) and X-ray (SROC 0.99) performing better. For differentiating benign from malignant fractures, ML achieved a sensitivity of 0.92 and specificity of 0.93, with DL (SROC 0.96) and MRI (SROC 0.97) performing best. For differentiating acute from chronic vertebral fractures, ML showed a sensitivity of 0.92 and specificity of 0.93, with ML (SROC 0.96) and CT (SROC 0.97) performing best. For predicting vertebral fractures, ML had a sensitivity of 0.76 and specificity of 0.87, with ML (SROC 0.80) and clinical features (SROC 0.86) performing better. ConclusionsML, especially DL models applied to CT, MRI, and X-ray, shows high diagnostic accuracy for vertebral fractures. ML also effectively predicts osteoporotic vertebral fractures, aiding in tailored prevention strategies. Further research and validation are required to confirm ML’s clinical efficacy.

Emulating Low-Power Synaptic Plasticity in a Solution-Processed Oxide-Based Long Retention Memory Transistor with High Learning Accuracy.

The exploration of synaptic plasticity in metal-oxide-based ferroelectric thin-film transistors has been limited. As a perovskite ferroelectric material, LiNbO3 is widely studied; but its potential use as a neuromorphic device, like synaptic transistors, has not been realized. In this study, a solution-processed ferroelectric thin-film transistor (FeTFT) with an alternating layer of LiNbO3 and Li5AlO4 as a gate dielectric has been fabricated. This configuration reduces the depolarization field by leveraging the large ionic polarization of Li+ ions in the Li5AlO4 layer, while the wide bandgap helps mitigate the leakage current. FeTFT exhibits impressive transistor performance, including a saturation mobility of 0.478 cm2V-1 s-1, an on/off ratio of 3.08 × 103, and a low trap-state density of 1.3 × 1013 cm-2. Moreover, the device demonstrates good memory retention, retaining information for nearly 1 day. It successfully emulates synaptic plasticity, specifically short-term plasticity and long-term plasticity. Besides, a 94% training accuracy has been achieved through artificial neural network simulation. Notably, the FeTFT consumes minimal power, with energy consumption of approximately 3.09 nJ per synaptic event, which is remarkably low compared to other reported solution-processed FeTFT devices.

Automatic detection of adenoid hypertrophy on lateral nasopharyngeal radiographs of children based on deep learning.

Adenoid hypertrophy is a prevalent cause of upper airway obstruction in children, potentially leading to various otolaryngological complications and even systemic sequelae. The lateral nasopharyngeal radiograph is routinely employed for the diagnosis of adenoid hypertrophy. This study aimed to evaluate the accuracy and reliability of deep learning, using lateral nasopharyngeal radiographs, for the diagnosis of adenoid hypertrophy in pediatric patients. In the retrospective study, the lateral nasopharyngeal X-ray images were collected from children receiving therapy in the Children's Hospital of Soochow University, the 983th Hospital of Joint Logistics Support Forces of Chinese PLA and the Suzhou Wujiang District Children's Hospital from January 2023 to November 2023. Five deep learning models, i.e., AlexNet, VGG16, Inception v3, ResNet50 and DenseNet121, were used for model training and validation. Receiver operating characteristic (ROC) curve analyses were used to evaluate the performance of each model. The best algorithm was compared with interpretations from three radiologists on 208 images in the internal validation group. The lateral nasopharyngeal X-ray images were collected from 1,188 children, including 705 males (59.3%) and 483 females (40.7%), aged 8 months to 13 years, with a mean age of 5.57±2.66 years. Among the five deep learning models, DenseNet-121 performed the best, with area under the curve (AUC) values of 0.892 and 0.872, with accuracy of 0.895 and 0.878, sensitivity of 0.870 and 0.838, and specificity of 0.913 and 0.906 in the internal and external validation groups, respectively. The diagnostic performance of DenseNet-121 was higher than that of the junior and mid-level radiologists (0.892 vs. 0.836, 0.892 vs. 0.869), close to the senior radiologist (0.892 vs. 0.901). However, Delong's test revealed no significant difference between DenseNet121 and each radiologist in the validation group (P=0.24, P=0.52, P=0.79). All the five deep learning models in the study showed good performance for the diagnosis of adenoid hypertrophy, with DenseNet121 being the best, which was clinically relevant for the automatic identification of adenoid hypertrophy.

Exploring the Accuracy of Machine Learning and Deep Learning in Engine Knock Detection

This study explores the use of machine learning for real-time detection of engine knocking, aiming to enhance early vehicle fault recognition. We extracted frequency modulation amplitude demodulation (FMAD) features from engine sound data and evaluated various machine-learning algorithms using MATLAB. The coarse decision tree algorithm emerged as the most effective, achieving a classification accuracy of 66.01%. Subsequently, by using deep learning models, we significantly improved the accuracy: a convolutional neural network (CNN) achieved 45.16%. accuracy, a deep learning recurrent neural network (RNN) model in LSTM achieved 90% accuracy, and further refinements pushed the accuracy to 93.55%. Additionally, we introduced a knock index to quantify noise levels during each engine cycle. This index, calculated from the integral of the absolute value of the first derivative of a band-pass-filtered vibration signal, provides a visual representation of knock strength. This approach shows promise for early detection of engine knocking, although further refinement of feature extraction methods and algorithm optimization is necessary for practical application. The study highlights the potential of integrating machine learning into real-time vehicle fault detection systems to improve their reliability and effectiveness.

Predicting and Forecasting of Vehicle Charging Station Using ECNN with DHFO Algorithm

The forecast of the optimal placement of a charging station (CS) according to the real-time consumption of electric vehicles is a subject of urgency in this new era. The demand of a charging station in an area based on the trend of consumption can be predicted by means of interpolation and the extrapolation of historical data using a linear function of prediction model. The prediction of the charging station system was performed with distance relevancy methods. An adaptive optimal learning model was proposed to enhance the prediction performance for charging station management and to represent the pattern of vehicles’ travelling directions. The proposed model uses Distributional Homogeneity Feature Optimization (DHFO) using artificial intelligence (AI) to categorize and forecast the charging station from the database. The prediction performance of this model is improved more than the conventional classification model by filtering the apt features from all the electric vehicular and charging station attributes in the database. The Enhanced Cladistic Neural Network (ECNN) is used to improve the pattern learning model and increase learning accuracy. By comparing statistical parameters with other state-of-the-art methodologies, the suggested model’s overall findings were verified.

Intrusion Event Classification of a Drainage Tunnel Based on Principal Component Analysis and Neural Networking

Drainage tunnel stability is crucial for engineering project safety (e.g., mine engineering and dams), and rockfall events and water release are key indicators of drainage tunnel stability. To address this, we developed a monitoring system to simulate drainage tunnel intrusions based on distributed acoustic sensing (DAS), and we obtained typical characteristics of events like rockfall events and water release. Given the multitude of DAS signal feature parameters and challenges, such as high-dimensional features impacting the classification accuracy of machine learning, we proposed an identification method for drainage tunnel intrusion events using principal component analysis (PCA) and neural networks. PCA reveals that amplitude-related parameters—amplitude, mean amplitude, and energy—significantly contribute to DAS signal classification, reducing the feature parameter dimensions by 54.8%. The accuracy of intrusion event classification improves with PCA-processed data compared to unprocessed data, with overall accuracy rates of 79.1% for rockfall events and 72.7% for water release events. Additionally, the artificial neural network model outperforms the Bayesian and logistic regression models, demonstrating that ANN has advantages in handling complex models for intrusion event classification.

Low-energy and tunable LIF neuron using SiGe bandgap-engineered resistive switching transistor

We have proposed leaky integrate-and-fire (LIF) neuron having low-energy consumption and tunable functionality without external circuit components. Our LIF neuron has a simple configuration consisting of only three components: one bandgap-engineered resistive switching transistor (BE-RST), one capacitor, and one resistor. Here, the crucial point is that BE-RST with a silicon–germanium heterojunction possesses an amplified hysteric current switching with a low latch-up voltage due to improved hole storage capability and impact ionization coefficient. Therefore, the proposed neuron utilizing BE-RST requires an energy consumption of 0.36 pJ/spike, which is approximately six times lower than 2.08 pJ/spike of pure silicon-RST based neuron. In addition, the spiking properties can be tuned by modulating the leakage rate and threshold through gate bias, which contributes to energy-efficient sparse-activity and high learning accuracy. As a result, our proposed neuron can be a promising candidate for executing various spiking neural network applications.

Comparative Analysis of Machine Learning and Deep Learning Algorithms for Assessing Agricultural Product Quality Using NIRS.

The success of near-infrared spectroscopy (NIRS) analysis hinges on the precision and robustness of the calibration model. Shallow learning (SL) algorithms like partial least squares discriminant analysis (PLS-DA) often fall short in capturing the interrelationships between adjacent spectral variables, and the analysis results are easily affected by spectral noise, which dramatically limits the breadth and depth of applications of NIRS. Deep learning (DL) methods, with their capacity to discern intricate features from limited samples, have been progressively integrated into NIRS. In this paper, two discriminant analysis problems, including wheat kernels and Yali pears as examples, and several representative calibration models were used to research the robustness and effectiveness of the model. Additionally, this article proposed a near-infrared calibration model, which was based on the Gramian angular difference field method and coordinate attention convolutional neural networks (G-CACNNs). The research results show that, compared with SL, spectral preprocessing has a smaller impact on the analysis accuracy of consensus learning (CL) and DL, and the latter has the highest analysis accuracy in the modeling results using the original spectrum. The accuracy of G-CACNNs in two discrimination tasks was 98.48% and 99.39%. Finally, this research compared the performance of various models under noise to evaluate the robustness and noise resistance of the proposed method.

Enhanced multi‐key privacy‐preserving distributed deep learning protocol with application to diabetic retinopathy diagnosis

SummaryIn this work, privacy‐preserving distributed deep learning (PPDDL) is re‐visited with a specific application to diagnosing long‐term illness like diabetic retinopathy. In order to protect the privacy of participants datasets, a multi‐key PPDDL solution is proposed which is robust against collusion attacks and is also post‐quantum robust. Additionally, the PPDDL solution provides robust network security in terms of integrity of transmitted ciphertexts and keys, forward secrecy, and prevention of man‐in‐the‐middle attacks and is extensively verified using Verifpal. Proposed solution is evaluated on retina image datasets to detect diabetic retinopathy, with deep learning accuracy results of 96.30%, 96.21% and 96.20% for DDL, DDL + SINGLE and DDL + MULTI scenarios respectively. Results from our simulation indicate that accuracy of the PPDDL is maintained while protecting the privacy of the datasets of participants. Our proposed solution is also efficient in terms of the communication and run‐time costs.

Lightweight intrusion detection model based on CNN and knowledge distillation

The problem of network attacks is a primary focus in the domain of intrusion detection. Models face significant challenges in recognizing intrusion behaviors, particularly when dealing with high-dimensional and sparse datasets. Traditional machine learning methods often struggle with these dimensionality issues. In contrast, deep learning, a crucial technology in intrusion detection, excels at managing high-dimensional data. However, traditional image coding methods do not adequately address data sparsification and often overlook the spatial continuity among features. The Fourier transform is a promising solution for data sparsity issues, as it effectively mitigates the impact by converting data into a different domain. Inspired by the Fourier transform, this paper proposes a lightweight intrusion detection model called TFTKD, based on Convolutional Neural Networks (CNN) and knowledge distillation. The model applies a two-dimensional Fourier transform to convert grayscale images from the time domain to the frequency domain. This transformation enhances the similarity between neighboring pixels, effectively addressing data sparsification. During the training phase, a teacher network, comprising an 8-layer CNN, is pre-trained. In the distillation phase, a one-layer CNN serves as the student network, employing Self-adaptive Temperature Knowledge Distillation to enhance the student's generalization capabilities. This approach results in a compact student network model with a constrained parameter count, demonstrating superior learning efficiency and accuracy compared to state-of-the-art methods. Experimental validation was conducted using four publicly accessible intrusion detection datasets, demonstrating the effectiveness of the proposed method.

Q residual non-parametric Distribution on Fault Detection Approach Using Unsupervised LSTM-KDE

It is well known among practitioner, majority collected data from industrial process plant are unlabeled. The collected historical data if utilize, able to provide vital information of process plant condition. Learning from unlabeled dataset, this study proposed Unsupervised LSTM-KDE approach as a measure to predict fault in industrial process plant. The residual based fault detection approach framework is utilized with long short-term memory (LSTM) as the main pattern learner for nonlinear and multimode condition that usually appear in process plant. Furthermore, kernel density approach (KDE) is used to determine the threshold value in non-parametric condition of unlabeled data. The LSTM-KDE approach later is evaluated with numerical data as well as Tennessee Eastman process plant dataset. The performance also was compared to Principal Component Analysis (PCA), Local outlier factor (LOF) and Auto-associative Kernel Regression (AAKR) to further examine the LSTM-KDE performance. The experimental results indicate that the LSTM-KDE fault detection approach has better learning performance and accuracy compared to other approaches