Deep Learning Convolutional Neural Network Research Articles

CNN-Based Neurodegenerative Disease Classification Using QR-Represented Gait Data.

The primary aim of this study is to develop an effective and reliable diagnostic system for neurodegenerative diseases by utilizing gait data transformed into QR codes and classified using convolutional neural networks (CNNs). The objective of this method is to enhance the precision of diagnosing neurodegenerative diseases, including amyotrophic lateral sclerosis (ALS), Parkinson's disease (PD), and Huntington's disease (HD), through the introduction of a novel approach to analyze gait patterns. The research evaluates the CNN-based classification approach using QR-represented gait data to address the diagnostic challenges associated with neurodegenerative diseases. The gait data of subjects were converted into QR codes, which were then classified using a CNN deep learning model. The dataset includes recordings from patients with Parkinson's disease (n = 15), Huntington's disease (n = 20), and amyotrophic lateral sclerosis (n = 13), and from 16 healthy controls. The accuracy rates obtained through 10-fold cross-validation were as follows: 94.86% for NDD versus control, 95.81% for PD versus control, 93.56% for HD versus control, 97.65% for ALS versus control, and 84.65% for PD versus HD versus ALS versus control. These results demonstrate the potential of the proposed system in distinguishing between different neurodegenerative diseases and control groups. The results indicate that the designed system may serve as a complementary tool for the diagnosis of neurodegenerative diseases, particularly in individuals who already present with varying degrees of motor impairment. Further validation and research are needed to establish its wider applicability.

Using the GoogLeNet deep-learning model to distinguish between benign and malignant breast masses based on conventional ultrasound: a systematic review and meta-analysis.

Breast cancer is one of the most common malignancies in women worldwide, and early and accurate diagnosis is crucial for improving treatment outcomes. Conventional ultrasound (CUS) is a widely used screening method for breast cancer; however, the subjective nature of interpreting the results can lead to diagnostic errors. The current study sought to estimate the effectiveness of using a GoogLeNet deep-learning convolutional neural network (CNN) model to identify benign and malignant breast masses based on CUS. A literature search was conducted of the Embase, PubMed, Web of Science, Wanfang, China National Knowledge Infrastructure (CNKI), and other databases to retrieve studies related to GoogLeNet deep-learning CUS-based models published before July 15, 2023. The diagnostic performance of the GoogLeNet models was evaluated using several metrics, including pooled sensitivity (PSEN), pooled specificity (PSPE), the positive likelihood ratio (PLR), the negative likelihood ratio (NLR), the diagnostic odds ratio (DOR), and the area under the curve (AUC). The quality of the included studies was evaluated using the Quality Assessment of Diagnostic Accuracy Studies Scale (QUADAS). The eligibility of the included literature were independently searched and assessed by two authors. All of the 12 studies that used pathological findings as the gold standard were included in the meta-analysis. The overall average estimation of sensitivity and specificity was 0.85 [95% confidence interval (CI): 0.80-0.89] and 0.86 (95% CI: 0.78-0.92), respectively. The PLR and NLR were 6.2 (95% CI: 3.9-9.9) and 0.17 (95% CI: 0.12-0.23), respectively. The DOR was 37.06 (95% CI: 20.78-66.10). The AUC was 0.92 (95% CI: 0.89-0.94). No obvious publication bias was detected. The GoogLeNet deep-learning model, which uses a CNN, achieved good diagnostic results in distinguishing between benign and malignant breast masses in CUS-based images.

Forensic analysis of microtraces using image recognition through machine learning

Traces found at a crime scene can be interpreted as vectors of information that help describe the possible dynamics of the crime. However, some analyses show that pattern recognition, especially in materials, is subjective, as it depends on the analyst’s references. Based on this problem, the work aimed to use different statistical methods to establish pattern recognition in silver tapes. For this, two approaches were used, one based on deep learning (convolutional neural networks) and the other using a different method (Pearson’s correlation, distance metrics, and Principal Component Analysis). The dataset comprised four brands of silver-tape available in the retail market in the crime scene region, and fragments of tape originating after the detonation of a handmade explosive device. These materials were analyzed using a Leica DVM6 microscope. In both approaches, it was possible to recognize patterns. In deep learning, it was possible to establish that the fragments came from a common origin. The best model demonstrated that 92.1 % of the real materials questioned were the same silver-tape, with a confidence level of 0.94. By combining the methods, it was possible to observe a trend among the results. These responses demonstrated that using images in a computer vision context could remove the subjectivity of forensic analysis and correlate the microtraces found at a crime scene. In this way, these techniques can open new perspectives for the forensic area, making the interpretation more objective and transparent in its responses to society.

Automated Diabetic Retinopathy Detection Using Convolutional Neural Networks For Feature Extraction And Classification (ADRFEC)

Diabetic Retinopathy (DR) is a significant complication of Diabetes Mellitus, leading to various retinal abnormalities that can impair vision and, in severe cases, result in blindness. Approximately 80% of patients with long-standing diabetes for 10–15 years develop DR. The manual process of diagnosing and detecting DR for timely treatment is both time-consuming and unreliable, mainly due to resource constraints and the need for expert opinion. To address this challenge, computerized diagnostic systems utilizing Deep Learning (DL) Convolutional Neural Network (CNN) architectures have been proposed to learn DR patterns from fundus images and assess disease severity. The proposed model performs an exhaustive analysis of these architectures upon fundus images, and derives the best performing DL architecture for DR feature extraction and fundus image classification. Amongst all the models, ResNet50 has achieved the highest training accu- racy whereas VGG-16 has achieved the lowest training accuracy. Again, VGG-16 has achieved lowest validation accuracy whereas ResNet101 has achieved highest validation accuracy.

An improved man-in-the-middle (MITM) attack detections using convolutional neural networks

The increasing reliance on digital communication networks has made information security a critical concern for individuals, organizations, and governments worldwide. Man-in-the-middle (MITM) attacks are significant, prevalent, and damaging concerning cyber-attacks. Detecting MitM attacks is complex due to their stealthy nature and the sophisticated methods employed by attackers. There is the need for researchers to address this issue using current and novel methods like artificial intelligence. In this paper, an improved MitM attack detection approach using the Convolutional Neural Network (CNN) deep learning algorithm is developed, resulting in an overall detection accuracy of 0.986%. The results confirms that the proposed model is very efficient in comparision to other proposed solutions by other authors.

Using a Convolutional Neural Network for Early Infectious Disease Detection During Public Health Emergencies

Proactively detecting infectious illnesses aids in delivering superior therapy and improves preventing and managing such diseases. This work proposed a Convolutional Neural Network for early Infectious Disease Detection during Public Health Emergencies (CNN-IDD-PHE). The objective is to mitigate the significant damages that Public Health Emergencies (PHE) inflicted on individuals' well-being, everyday routines, and the whole national economy. Statistics on Tuberculosis (TB) cases in a city were gathered from July 2020 to 2022. The Structural Equation Model (SEM) is designed to ascertain the correlation between latent and observed variables by identifying the appropriate indicators and estimating the parameters. A prediction model using Convolutional Neural Network (CNN) has been developed. The strategy's efficacy is validated by assessing the loss value and accuracy of the detection model during both the training and testing phases. Hence, using CNN in Deep Learning (DL) for early warning systems performs better in predicting and alerting Public Health (PH) situations. This advancement is of great importance in enhancing the capabilities of early warning systems.

Herbal plant leaves classification for traditional medicine using convolutional neural network

<p>The classification of herbal plant leaves can be implemented in agriculture and traditional medicine. Primarily, sorting leaves was done before it was processed into medicinal ingredients. Currently, the sorting was still done manually by writing it on notes. Sometimes there were errors in the selection of leaves for medicinal ingredients. Herbal plants had various forms and are very greatly. Artificial intelligence technology was needed to have fast-paced time efficiency in sorting leaves. In the field of artificial intelligence, there was a specific or detailed learning process known as deep learning. The objective of this research was to classify herbal plant leaves images by applying and combining the convolutional neural network (CNN) deep learning method with data augmentation methods without the pre-trained architecture such as MobileNet and LeNet. This technique consisted of 4 main stages such as collecting data, preprocessing or normalizing data, building a model, and evaluating. The dataset used in this research were 4 types of herbal plants that do not flower and do not bear fruit including gulma siam, piduh, sirih, and tobacco. Each class had 250 images with total dataset used in this research was 1,000 images of herbal plant leaves and divided into 2 data, namely 80% data training 20% data testing, and validation. The data was trained with the epoch of 100 for the best training. It had an accuracy score of 98.74%. Without the data augmentation process it had an accuracy score of 91.43%.</p>

ATC-CNN-Based IoT Framework for Real-Time Cardiovascular Monitoring: A Comparative Analysis with Deep Learning Models

Background: Cardiovascular diseases (CVDs), including hypertension, coronary heart disease, and ventricular fibrillation, remain the leading cause of death worldwide. The COVID-19 pandemic accelerated the adoption of telecardiology to minimize in-person interactions, enhancing access to cardiovascular care, especially in remote areas. However, traditional real-time monitoring (RTM) systems often require patient visits, creating a need for cost-effective, user-friendly alternatives that leverage IoT and AI for improved patient management. Methods: This study developed an IoT-enabled RTM system integrated with an Adaptive Thresholding Classifier-Convolutional Neural Network (ATC-CNN) framework for managing cardiovascular patients (CP). Data from a heart failure dataset in the UCI Machine Learning Archive was used to train and evaluate the model. Multiple deep learning (DL) algorithms, including MLP, CNN, LSTM, RNN, and the proposed ATC-CNN, were assessed based on accuracy, precision, recall, and F1 scores. Results: The ATC-CNN model achieved an accuracy of 0.9831, outperforming other DL models, including MLP, CNN, LSTM, and RNN. It demonstrated superior capabilities in handling complex cardiovascular data, offering reliable and timely diagnosis with high precision and recall. The integration of IoT and AI facilitated continuous monitoring and real-time data analysis, addressing key limitations of traditional RTM systems. Conclusion: The ATC-CNN framework shows great potential for revolutionizing cardiovascular care by enhancing remote monitoring capabilities and clinical decision-making. It provides an effective, real-time solution for early diagnosis and intervention, particularly in remote and underserved areas. Future research should focus on expanding datasets and refining the model for broader adaptability in diverse healthcare settings.

Analyzing urban footprints over four coastal cities of India and the association with rainfall and temperature using deep learning models

Capabilities of deep-learning models CNN and ConvLSTM are explored for analyzing and projecting future urban growth in four Indian coastal cities, viz., Mumbai, Chennai, Kochi, and Vishakhapatnam. ConvLSTM performed better with higher overall accuracy, Cohen's kappa, macro F1-score (> 95 %), and R2 and NSE values (> 0.87). The urbanization trends indicate a higher growth in Kochi (∼90.5 %), and greater projected rate for Mumbai (∼42.5 %). The monthly accumulated rainfall and mean temperature are analyzed and forecasted through the ConvLSTM model. The Mann-Kendall test-based analysis (with p-value <0.05), suggest no significant rainfall pattern for the cities except Mumbai, which exhibits an increasing trend. The projected rainfall trend is unaltered except for Vishakhapatnam, which is expected to increase in the coming years. The mean temperature over all the cities, shows an increasing trend (slope ∼ 0.02). However, in the coming years, the ‘increasing trend’ is expected to change into a ‘no significant trend’ for Mumbai and Vishakhapatnam. The forecasted results indicate a continuous urban expansion, which is expected to have a significant impact on rainfall and temperature trends. The outcome could assist urban planners in defining the timeline for improving drainage and include green spaces in the city development plans.

Metformin dampens the progression of cholangiofibrosis induced by thioacetamide using deep learning

PurposeThe consistent use of metformin has been linked to a reduced incidence of neoplastic diseases among diabetic populations. As a preventive intervention, metformin may offer a more favorable risk-benefit profile. Here, we explored the efficacy of metformin in the primary prevention of cholangiofibrosis, which can precede the carcinogen-induced development of cholangiocarcinoma (CCA). Our objective was to assess the potential of metformin to act as an intervention prior to the onset of these conditions. MethodsA rat model of thioacetamide (TAA)-induced cholangiofibrosis was utilized to assess the impact of metformin on the induction process of cholangiocarcinoma (CCA). Liver tissues were harvested and analyzed histologically using light microscopy, complemented by a deep-learning convolutional neural network for enhanced evaluation. Additionally, RNA sequencing (RNA-seq) was performed to investigate the genetic alterations associated with metformin treatment in this TAA-induced cholangiofibrosis model. ResultsIn the rat model, the TAA control group exhibited an increased incidence and average count of cholangiofibrosis cases in the liver, with rates of 100 % and an average of 12.0, compared to the metformin-treated group, which showed an incidence of 70 % and an average of 3.3. Notably, the progression from normal cholangioles to cholangiofibrosis was associated with the upregulation of several proteins critical for metabolic processes and the tumor microenvironment. These alterations were significantly mitigated by metformin treatment. ConclusionsLong-term metformin use may offer protective benefits against cholangiofibrosis, partially by regulating metabolic processes and improving the tumor microenvironment.

Classification of Healthy and Diseased Broccoli Leaves Using a Custom Deep Learning CNN Model

Classification of Healthy and Diseased Broccoli Leaves Using a Custom Deep Learning CNN Model

Artificial Intelligence Recognition Model Using Liquid-Based Cytology Images to Discriminate Malignancy and Histological Types of Non-Small-Cell Lung Cancer

Introduction: Artificial intelligence image recognition has applications in clinical practice. The purpose of this study was to develop an automated image classification model for lung cancer cytology using a deep learning convolutional neural network (DCNN). Methods: Liquid-based cytology samples from 8 normal parenchymal (N), 22 adenocarcinoma (ADC), and 15 squamous cell carcinoma (SQCC) surgical specimens were prepared, and 45 Papanicolaou-stained slides were scanned using whole-slide imaging. The final dataset of 9,141 patches consisted of 2,737 N, 4,756 ADC, and 1,648 SQCC samples. Densenet-121 was used as the DCNN to classify N versus malignant (ADC+SQCC) and ADC versus SQCC images. AdamW optimizer and 5-fold cross-validation were used in the training. Results: For malignancy prediction, the sensitivity, specificity, and accuracy were 0.97, 0.85, and 0.94, respectively, in the patch-level classification, and 0.92, 0.88, and 0.91, respectively, in the case-level classification. For SQCC prediction, the sensitivity, specificity, and accuracy were 0.86, 0.91, and 0.90, respectively, in the patch-level classification and 0.73, 0.82, and 0.78, respectively, in the case-level classification. Conclusion: The DCNN model performed excellently in predicting malignancy and histological types of lung cancer. This model may be useful for predicting cytopathological diagnosis in clinical situations by reinforcing training.

Enhancing Breast Cancer Detection Through a Tailored Convolutional Neural Network Deep Learning Approach

Enhancing Breast Cancer Detection Through a Tailored Convolutional Neural Network Deep Learning Approach

CNN-Based Damage Identification of Submerged Structure-Foundation System Using Vibration Data

This study presents a convolutional neural network (CNN) deep learning approach for identifying damage in submerged structure-foundation systems using vibration data. Firstly, foundation damage in a lab-scale caisson-foundation system is simulated to measure time-history responses. Singular value decomposition (SVD) responses are derived from the time-history responses. Secondly, the 1-D CNN deep learning model is trained using both the time-history responses and SVD responses. Finally, the trained CNN models are implemented to evaluate the foundation damage under conditions of noise contamination and partially untrained data. The experimental results demonstrate the effectiveness of CNN models for damage identification and highlight the comparative strengths of time-history and SVD data. The CNN model trained using SVD data outperforms the other model when under noise contamination conditions, while the CNN model trained using time-history data maintains better accuracy in partially untrained data conditions. Integrating both types of data enhances the accuracy of damage classification.

Deep learning-based computer vision in project management: Automating indoor construction progress monitoring

Progress monitoring is crucial for effective project management, particularly in construction projects. The adoption of computer vision with deep learning expedites automation, accuracy, and efficiency in construction progress monitoring by overcoming the challenges of laborious, and error prone manual methods. While there is growing attention on developing computer vision based deep learning models for construction progress monitoring, deployment platforms for project managers are lacking. Using computer vision, this study develops a Mask Recurrent Convolutional Neural Network deep learning model. It utilizes progress images of drywall construction from two indoor construction sites and tests the model on a third indoor site in Sydney, Australia. The model is capable of automated as-built visual detection and work-in-progress measurement. The study also provides an understanding on the deployment process of the deep learning model on a cloud-based platform called Streamlit. By developing a model tailored for automatically quantifying work-in-progress of indoor construction elements and detailing the process of deploying that model on a cloud-based platform, this study significantly advances digitalization of construction project management. Project managers, stand to benefit from these advancements by gaining access to more accurate and automated construction progress monitoring for better decision-making.

Beehive Smart Detector Device for the Detection of Critical Conditions That Utilize Edge Device Computations and Deep Learning Inferences.

This paper presents a new edge detection process implemented in an embedded IoT device called Bee Smart Detection node to detect catastrophic apiary events. Such events include swarming, queen loss, and the detection of Colony Collapse Disorder (CCD) conditions. Two deep learning sub-processes are used for this purpose. The first uses a fuzzy multi-layered neural network of variable depths called fuzzy-stranded-NN to detect CCD conditions based on temperature and humidity measurements inside the beehive. The second utilizes a deep learning CNN model to detect swarming and queen loss cases based on sound recordings. The proposed processes have been implemented into autonomous Bee Smart Detection IoT devices that transmit their measurements and the detection results to the cloud over Wi-Fi. The BeeSD devices have been tested for easy-to-use functionality, autonomous operation, deep learning model inference accuracy, and inference execution speeds. The author presents the experimental results of the fuzzy-stranded-NN model for detecting critical conditions and deep learning CNN models for detecting swarming and queen loss. From the presented experimental results, the stranded-NN achieved accuracy results up to 95%, while the ResNet-50 model presented accuracy results up to 99% for detecting swarming or queen loss events. The ResNet-18 model is also the fastest inference speed replacement of the ResNet-50 model, achieving up to 93% accuracy results. Finally, cross-comparison of the deep learning models with machine learning ones shows that deep learning models can provide at least 3-5% better accuracy results.

Learning-assisted specklegram analysis for recognition of simultaneous weights on multimode optical fiber

A deep learning-based recognition of multimode fiber (MMF) specklegrams for various simultaneous weights is presented in this work. Five different random locations have been considered along the length of MMF and the specklegram images are recorded corresponding to seven different combinations of random simultaneous weights applied at these locations. A popular deep learning convolutional neural network (CNN) model, VGG-16 is employed on these images for the recognition of these seven weight combinations. The impact of acoustic vibrations, laser power, external temperature, and image sizes on the recognition accuracy is examined. A 100% recognition accuracy is attained and a negligible accuracy variation of ∼1.9% for acoustic vibrations as well as for changing laser power is observed, whereas a drastic fall in accuracy is observed in case of change in image sizes less than 80 × 80 pixels. Also, a negligible variation of ∼2% is observed for the applied external temperature. The heart of our work lies in the accumulation of a diverse, large volume of specklegram dataset by virtue of conducting brute force experiments that take care of eradication of model overfitting. The proposed proof-of-concept scheme might be useful for low-cost, efficacious, self-assisted multi-weight analysis in structural health monitoring.

Supervised classification and fault detection in grid-connected PV systems using 1D-CNN: Simulation and real-time validation

Photovoltaic (PV) systems are prone to various faults, including short-circuit, open-circuit, partial shading, and inverter bypass diode issues, which reduce power output and can damage components. This study presents an innovative fault detection and online monitoring technique for grid-connected PV (GCPV) systems, combining Internet of Things (IoT) technology with a one-dimensional convolutional neural network (1D-CNN) deep learning approach. The method involves developing a temperature-dependent PV system model using series resistance and ideality factor, capturing real-time data from a 15kWp GCPV system with optimally placed sensors to minimize sensor count while maintaining data accuracy, and validating the model through MATLAB/Simulink simulations and real-time experiments under various fault scenarios. The collected data is used to train the 1D-CNN model to classify different fault types. The model is then implemented on an IoT platform for real-time monitoring and fault detection, displaying system status and alerts via a dashboard. The proposed system achieves a high fault detection accuracy of 98.15 % and 93.12 % during cyberattacks, with an uncertainty of ±4 %, significantly enhancing fault detection reliability and efficiency compared to existing methods. The IoT dashboard provides an effective tool for monitoring system performance and issuing alerts under abnormal conditions.

Retraction Note: An efficient method for human hand gesture detection and recognition using deep learning convolutional neural networks

Retraction Note: An efficient method for human hand gesture detection and recognition using deep learning convolutional neural networks

Enhanced Lithium-Ion Battery SOH Estimation Using Bayesian-Optimized CNN Deep Learning Approach

The accurate health status evaluation of lithium-ion batteries is crucial for preemptive identification of potential battery failures and averting hazardous incidents, given its essential role in indicating the extent of battery degradation. The challenge in determining the State of Health (SOH) arises from the absence of a precise and standardized definition, as well as the difficulty in measuring essential input variables. Therefore, this paper utilizes current and voltage data during the charge and discharge process as direct inputs for SOH estimation and proposes a deep learning-based lithium-ion battery SOH estimation approach. Specifically, it leverages Bayesian optimized Convolutional Neural Network (CNN) within a data-driven framework. Experimental results demonstrate that the proposed deep learning method achieves a Mean Absolute Error (MAE) of 1% and a Maximum Error (MAX) below 4% in estimation accuracy, highlighting its enhanced precision and robustness.