Deep Learning-based System Research Articles

UC-stack: a deep learning computer automatic detection system for diabetic retinopathy classification.

Object. The existing diagnostic paradigm for diabetic retinopathy (DR) greatly relies on subjective assessments by medical practitioners utilizing optical imaging, introducing susceptibility to individual interpretation. This work presents a novel system for the early detection and grading of DR, providing an automated alternative to the manual examination.Approach. First, we use advanced image preprocessing techniques, specifically contrast-limited adaptive histogram equalization and Gaussian filtering, with the goal of enhancing image quality and module learning capabilities. Second, a deep learning-based automatic detection system is developed. The system consists of a feature segmentation module, a deep learning feature extraction module, and an ensemble classification module. The feature segmentation module accomplishes vascular segmentation, the deep learning feature extraction module realizes the global feature and local feature extraction of retinopathy images, and the ensemble module performs the diagnosis and classification of DR for the extracted features. Lastly, nine performance evaluation metrics are applied to assess the quality of the model's performance.Main results. Extensive experiments are conducted on four retinal image databases (APTOS 2019, Messidor, DDR, and EyePACS). The proposed method demonstrates promising performance in the binary and multi-classification tasks for DR, evaluated through nine indicators, including AUC and quadratic weighted Kappa score. The system shows the best performance in the comparison of three segmentation methods, two convolutional neural network architecture models, four Swin Transformer structures, and the latest literature methods.Significance. In contrast to existing methods, our system demonstrates superior performance across multiple indicators, enabling accurate screening of DR and providing valuable support to clinicians in the diagnostic process. Our automated approach minimizes the reliance on subjective assessments, contributing to more consistent and reliable DR evaluations.

DL-HIDS: deep learning-based host intrusion detection system using system calls-to-image for containerized cloud environment

DL-HIDS: deep learning-based host intrusion detection system using system calls-to-image for containerized cloud environment

Skin Disease Detection Using Deep Learning

Skin diseases are a major public health problem worldwide, requiring effective and timely diagnosis for effective treatment. In this paper, we present a new approach to automatically detect skin diseases using deep learning technology. The model we propose uses a Convolutional Neural Network (CNN) to analyze dermatological images with high accuracy, providing reliable and fast diagnosis. The system was trained on a variety of datasets to provide reliable performance across a variety of skin conditions. Experimental results show that the proposed model outperforms existing methods, demonstrating its potential for integration into clinical settings. Implementation of this deep learning-based skin disease detection system has the potential to revolutionize dermatological diagnostics and provide a cost-effective and scalable solution to improve patient care.

Modified fuzzy rough set technique with stacked autoencoder model for magnetic resonance imaging based breast cancer detection

Breast cancer is the common cancer in women, where early detection reduces the mortality rate. The magnetic resonance imaging (MRI) images are efficient in analyzing breast cancer, but it is hard to identify the abnormalities. The manual breast cancer detection in MRI images is inefficient; therefore, a deep learning-based system is implemented in this manuscript. Initially, the visual quality improvement is done using region growing and adaptive histogram equalization (AHE), and then, the breast lesion is segmented by Otsu thresholding with morphological transform. Next, the features are extracted from the segmented lesion, and a modified fuzzy rough set technique is proposed to reduce the dimensions of the extracted features that decreases the system complexity and computational time. The active features are fed to the stacked autoencoder for classifying the benign and malignant classes. The results demonstrated that the proposed model attained 99% and 99.22% of classification accuracy on the benchmark datasets, which are higher related to the comparative classifiers: decision tree, naïve Bayes, random forest and k-nearest neighbor (KNN). The obtained results state that the proposed model superiorly screens and detects the breast lesions that assists clinicians in effective therapeutic intervention and timely treatment.

An Explainable and Resilient Intrusion Detection System for Industry 5.0

Industry 5.0 is a futuristic transformative model that aims to develop a hyperconnected, automated, and data-driven industrial ecosystem. This digital transformation will boost productivity and efficiency throughout the production process but will be more prone to new sophisticated cyber-attacks. Deep learning-based Intrusion Detection Systems (IDS) have the potential to recognize intrusions with high accuracy. However, these models are complex and are treated as a black box by developers and security analysts due to the inability to interpret the decisions made by these models. Motivated by the challenges, this paper presents an explainable and resilient IDS for Industry 5.0. The proposed IDS is designed by combining bidirectional long short-term memory networks (BiLSTM), a bidirectional-gated recurrent unit (Bi-GRU), fully connected layers and a softmax classifier to enhance the intrusion detection process in Industry 5.0. Then, we employ the SHapley Additive exPlanations (SHAP) mechanism to interpret and understand the features that contributed the most in the decision of the proposed cyber-resilient IDS. The evaluation of the proposed model using the explainability can ensure that the model is working as expected. The experimental results based on the CICIDDoS2019 dataset confirms the superiority of the proposed IDS over some recent approaches.

Fast region based convolutional neural network ResNet-50 model for on tree Mango fruit yield estimation

<p><span>The foundation of the Indian economy is agriculture, the amount of land available for agricultural activities has decreased due to numerous factors. To fulfill the demands of the expanding population, the maximum yield must be produced on the least amount of land that is accessible. To overcome the challenges of agriculture, many researches have been carried out to adopt technology into agriculture. As India is one of the world's top producers of Mangoes and has a vast market, and has encouraged extensive Mango farm development. Automatic yield estimation of Mangoes in the early stage is important to improve the quality and quantity of production which improves both domestic and export markets. The work proposes a fast region (FR) based convolutional neural network (CNN) residual network (ResNet)-50 model for efficient deep learning-based Mango crop yield estimation system to count the Mango fruit from the images of individual trees. A temporal Mango fruit database is used to estimate the yield of on tree Mango fruits, and a framework is provided to estimate Mango fruit yield in red, green, and blue (RGB) image. This experiment shows that the suggested FRCNN ResNet-50 model attained a better accuracy of 98.20% on the proposed dataset.</span></p>

Intelligent deep learning-based disease monitoring system in 5G network using multi-disease big data

Recently, real-world disease monitoring techniques designed based on wearable medical equipment efficiently minimize the mortality rate. Initially, the data are manually collected from the patients to predict five diseases using 5 G frameworks. Then, the collected data are pre-processed to obtain high-quality data using the techniques like contrast enhancement, median filtering, fill empty space, remove repeated value and stemming. The pre-processed data are taken for extracting the features using a One-Dimensional Convolutional Neural Network (1D-CNN) to obtain the deep features. The parameters like hidden neuron count and epoch are tuned by the proposed Modified Predator Presence Probability-based Squirrel Search-Glowworm Swarm Optimization (MPPP-SSGSO) algorithm to enhance the variance. Then, the extracted features acquired using the 1D-CNN are given to the ensemble boosting-based models for predicting the score, which is combined by comprising approaches like Adaptive Boosting (AdaBoost), eXtreme Gradient Boosting (XGBoost) and Category Boosting (CatBoost). Further, the predicted scores obtained from such models are concatenated and passed to the Ensemble Boosting Scores-based Fuzzy Classifier (EBS-FC) for classifying the five different diseases. Here, the membership function of the fuzzy is optimized by the same developed MPPP-SSGSO algorithm for enhancing accuracy. Experiments are conducted, and validation is performed, which showcased that the recommended framework achieved a better outcome rate than the conventional techniques. Finally, the suggested strategy outperforms the current state-of-the-art methods with an accuracy rate of 91.34%. Communicated by Ramaswamy H. Sarma

Sustainable education on improving the quality of peer assessment: design and implementation of an online deep learning-based peer assessment system

PurposeAs global issues such as climate change, economic growth, social equality and the wealth gap are widely discussed, education for sustainable development (ESD) allows every human being to acquire the knowledge, skills, attitudes and values necessary to shape a sustainable future. It also requires participatory teaching and learning methods that motivate and empower learners to change their behavior and take action for sustainable development. Teachers have begun rating pupils based on peer assessment for open evaluation. Peer assessment enables students to transition from passive to active feedback recipients. The assessors improve critical thinking and encourage introspection, resulting in more significant recommendations. However, the quality of peer assessment is variable, resulting in reviewers not recognizing the remarks of other reviewers, therefore the benefits of peer assessment cannot be fulfilled. In the past, researchers frequently employed post-event questionnaires to examine the effects of peer assessment on learning effectiveness, which did not accurately reflect the quality of peer assessment in real time.Design/methodology/approachThis study employs a multi-label model and develops a self-feedback system in order to use the AIOLPA system in the classroom to enhance students' learning efficacy and the validity of peer assessment.FindingsThe research findings indicate that the better peer assessment through the rapid feedback system, for the evaluator, encourages more self-reflection and attempts to provide more ideas, so bringing the peer rating closer to the instructor rating and assisting the evaluator. Improve self-evaluation and critical thinking for the evaluator, peers make suggestions and comments to help improve the work and support the growth of students' learning effectiveness, which can lead to more suggestions and an increase in the work’s quality.Originality/value ESD consequently promotes competencies like critical thinking, imagining future scenarios and making decisions in a collaborative way. This study builds an online peer assessment system with a self-feedback mechanism capable of classifying peer comments, comparing them with scores in a consistent manner and providing prompt feedback to critics.

A Deep Learning-Based System for the Assessment of Dental Caries Using Colour Dental Photographs.

D1ental caries remains the most common chronic disease in childhood, affecting almost half of all children globally. Dental care and examination of children living in remote and rural areas is an ongoing challenge that has been compounded by COVID. The development of a validated system with the capacity to screen large numbers of children with some degree of automation has the potential to facilitate remote dental screening at low costs. In this study, we aim to develop and validate a deep learning system for the assessment of dental caries using color dental photos. Three state-of-the-art deep learning networks namely VGG16, ResNet-50 and Inception-v3 were adopted in the context. A total of 1020 child dental photos were used to train and validate the system. We achieved an accuracy of 79% with precision and recall respectively 95% and 75% in classifying 'caries' versus 'sound' with inception-v3.

A deep learning-based biomonitoring system for detecting water pollution using Caenorhabditis elegans swimming behaviors

Caenorhabditis elegans is a representative organism whose DNA structure has been fully elucidated. It has been used as a model organism for various analyses, including genetic functional analysis, individual behavioral analysis, and group behavioral analysis. Recently, it has also been studied as an important bioindicator of water pollution. In previous studies, traditional machine learning methods, such as the Hidden Markov Model (HMM), were used to determine water pollution and identify pollutants based on the differences in the swimming behavior of C. elegans before and after exposure to chemicals. However, these traditional machine learning models have low accuracy and a relatively high false-negative rate. This study proposes a method for detecting water pollution and identifying the types of pollutants using the Long Short-Term Memory (LSTM) model, a deep learning model suitable for time-series data analysis. The swimming activities of C. elegans in each of the image frames are characterized by the Branch Length Similarity (BLS) entropy profile. These BLS entropy profiles are converted into input vectors through additional preprocessing using two clustering methods. We conduct experiments using formaldehyde and benzene at 0.1 mg/L each, with observation time intervals varying from 30 to 180 s. The performance of the proposed method is compared with that of the previously proposed HMM approach and variants of LSTM models, such as Gated Recurrent Unit (GRU) and Bidirectional LSTM (BiLSTM).

Development of Architectural Object Automatic Classification Technology for Point Cloud-Based Remodeling of Aging Buildings

In this study, we address the challenge of efficiently handling the maintenance and remodeling of buildings constructed post-1960s, lacking architectural drawings. The conventional approach involves manual measurements and data recording, followed by digital drawing creation. However, we leverage Fourth Industrial Revolution technologies to develop a deep learning-based automatic object classification system using point cloud data. We employ the FCAF3D network with multiscale cells, optimizing its configuration for classifying building components such as walls, floors, roofs, and other objects. While classifying walls, floors, and roofs using bounding boxes led to some boundary-related errors, the model performed well for objects with distinct shapes. Our approach emphasizes efficiency in the remodeling process rather than precise numerical calculations, reducing labor and improving architectural planning quality. While our dataset labeling strategy involved bounding boxes with limitations in numerical precision, future research could explore polygon-based labeling, minimizing loss of space and potentially yielding more meaningful results in classification. In summary, our technology aligns with the initial research objectives, and further investigations could enhance the methodology for even more accurate building object classification.

Empowering robust biometric authentication: The fusion of deep learning and security image analysis

Many societal entities now have more excellent standards for the efficacy and dependability of identification systems due to the ongoing advancement of computer technology. Traditional identification methods, such as keys and smart cards, have been supplanted by biometric systems in highly secure environments. This research presents a smart computational method for automatically authenticating fingerprints for identity (ID) verification and personal identification. Compared to more traditional machine learning algorithms, the results from applying Deep learning (DL) in areas like computer vision, image identification, robotics, and voice processing have generally been positive. Due to their capacity to analyse big data size and deal with fluctuations in biometric data (such as ageing or expression problems), DL has been heavily used by the artificial intelligence research community. Several biometric systems have succeeded with automatic feature extraction employing deep learning approaches like Convolutional Neural Networks (CNNs). In this research, we provide a biometric process that uses convolutional neural networks. This work introduces a deep learning-based biometric identification system that uses Monte Carlo Dropout (MC Dropout). Combining these two systems makes the authentication process more secure and dependable. Fingerprint image enhancement techniques involve the application of Gabor filters and structure-adaptive anisotropic filters, which have proven to be effective in enhancing the clarity and distinctiveness of fingerprint patterns. To improve the efficiency of deep learning models, this work proposes the Inception-Augmentation GAN (IAGAN) model for data augmentation. The study adds to security development by integrating novel biometric identification and authentication approaches with cutting-edge neural network technology. In this research, we provide a new activation function to speed up the convergence of deep neural networks. The results of 99.6% on Gabor filters and 99.8% on the structure-adaptive anisotropic filter with GACNN with MCD show that deep neural networks can excel over competing approaches with enough training data.

Navigating Unstructured Space: Deep Action Learning-Based Obstacle Avoidance System for Indoor Automated Guided Vehicles

Automated guided vehicles (AGVs) have become prevalent over the last decade. However, numerous challenges remain, including path planning, security, and the capacity to operate safely in unstructured environments. This study proposes an obstacle avoidance system that leverages deep action learning (DAL) to address these challenges and meet the requirements of Industry 4.0 for AGVs, such as speed, accuracy, and robustness. In the proposed approach, the DAL is integrated into an AGV platform to enhance its visual navigation, object recognition, localization, and decision-making capabilities. Then DAL itself was introduced to combine the work of You Only Look Once (YOLOv4), speeded-up robust features (SURF), and k-nearest neighbor (kNN) and AGV control in indoor visual navigation. The DAL system triggers SURF to differentiate two navigation images, and kNN is used to verify visual distance in real time to avoid obstacles on the floor while searching for the home position. The testing findings show that the suggested system is reliable and fits the needs of advanced AGV operations.

Uncertainty-aware deep learning-based CAD system for breast cancer classification using ultrasound and mammography images

ABSTRACT Breast cancer is one of the most common types of cancer in women. Early and accurate diagnosis of breast cancer can increase the treatment chances and decrease the mortality rate. Thus, the development of accurate and reliable Computer-Aided Diagnosis (CAD) systems using breast cancer images is an immediate priority for early diagnosis. Deep learning methods have had a widespread role in CAD systems. In spite of the advantages, most deep learning-based CADs cannot quantify the uncertainty of their predictions. Uncertainty in the predicted results from a CAD system might endanger people’s life in these crucial steps for breast cancer classification. Therefore, in this study, the Monte Carlo Dropout method is utilised as an uncertainty quantification method. Furthermore, differently from most existing studies, we present an uncertainty-aware deep learning model which can classify accurately from different types of images, namely, mammograms and ultrasound. The results show the proposed model achieved the accuracy of 99.95% in mammogram dataset, namely, DDSM and 98.40% and 91.34% in ultrasound datasets, namely, BUSM and BUSI, respectively. Finally, since we found the proposed model shows high uncertainty in misclassifications, we suggested to use the uncertainty values to find appropriate subsets for further inspection to increase the performance.

Train Once, Locate Anytime for Anyone: Adversarial Learning-based Wireless Localization

Among numerous indoor localization systems, WiFi fingerprint-based localization has been one of the most attractive solutions, which is known to be free of extra infrastructure and specialized hardware. To push forward this approach for wide deployment, three crucial goals on high deployment ubiquity, high localization accuracy, and low maintenance cost are desirable. However, due to severe challenges about signal variation, device heterogeneity, and database degradation root in environmental dynamics, pioneer works usually make a trade-off among them. In this article, we propose iToLoc, a deep learning-based localization system that achieves all three goals simultaneously. Once trained, iToLoc will provide accurate localization service for everyone using different devices and under diverse network conditions, and automatically update itself to maintain reliable performance anytime. iToLoc is purely based on WiFi fingerprints without relying on specific infrastructures. The core components of iToLoc are a domain adversarial neural network and a co-training-based semi-supervised learning framework. Extensive experiments across 7 months with eight different devices demonstrate that iToLoc achieves remarkable performance with an accuracy of 1.92 m and >95% localization success rate. Even 7 months after the original fingerprint database was established, the rate still maintains >90%, which significantly outperforms previous works.

A deep learning approach based on multi-view consensus for SQL injection detection

SQL injection (SQLi) attacks are one of the oldest and most serious security threats, consistently ranking among the top ten critical web security risks. Traditional defense mechanisms against SQL injection predominantly use blacklists to disallow common injection characters or terms. However, the major challenge for these systems is to create a comprehensive list of potential SQLi characters, terms, and multi-terms that encompass various types of SQLi attacks (time-based, error-based, etc.), taking into account various SQL datasets (such as MySQL, Oracle, and NoSQL). Recently, some research studies have concentrated on feature learning from SQL queries by applying some well-known deep architectures to detect SQLi attacks. Motivated by a similar objective, this research introduces a novel deep learning-based SQLi detection system named “Bidirectional LSTM-CNN based on Multi-View Consensus” (MVC-BiCNN). The proposed method implements a pre-processing step that generates multiple views from SQL data by semantically encoding SQL statements into their corresponding SQL tags. By utilizing two different main layers, which are bidirectional long short-term memory (LSTM) and convolutional neural network (CNN), the proposed method learns a joint latent space from multi-view representations. In the detection phase, the proposed method yields separate predictions for each representation and assesses whether the query constitutes an SQLi attack based on a consensus function’s output. Moreover, Interpretable Model-Agnostic Annotations (LIME), one of the methods of Explainable Artificial Intelligence (XAI), is employed for the purpose of interpreting the model’s results and analyzing the SQL injection (SQLi) inputs. The experimental results demonstrate that MVC-BiCNN outperforms the baseline methods, yielding 99.96% detection rate.

A newly developed deep learning-based system for automatic detection and classification of small bowel lesions during double-balloon enteroscopy examination

BackgroundDouble-balloon enteroscopy (DBE) is a standard method for diagnosing and treating small bowel disease. However, DBE may yield false-negative results due to oversight or inexperience. We aim to develop a computer-aided diagnostic (CAD) system for the automatic detection and classification of small bowel abnormalities in DBE.Design and methodsA total of 5201 images were collected from Renmin Hospital of Wuhan University to construct a detection model for localizing lesions during DBE, and 3021 images were collected to construct a classification model for classifying lesions into four classes, protruding lesion, diverticulum, erosion & ulcer and angioectasia. The performance of the two models was evaluated using 1318 normal images and 915 abnormal images and 65 videos from independent patients and then compared with that of 8 endoscopists. The standard answer was the expert consensus.ResultsFor the image test set, the detection model achieved a sensitivity of 92% (843/915) and an area under the curve (AUC) of 0.947, and the classification model achieved an accuracy of 86%. For the video test set, the accuracy of the system was significantly better than that of the endoscopists (85% vs. 77 ± 6%, p < 0.01). For the video test set, the proposed system was superior to novices and comparable to experts.ConclusionsWe established a real-time CAD system for detecting and classifying small bowel lesions in DBE with favourable performance. ENDOANGEL-DBE has the potential to help endoscopists, especially novices, in clinical practice and may reduce the miss rate of small bowel lesions.

Deep learning-based automatic pipeline system for predicting lateral cervical lymph node metastasis in patients with papillary thyroid carcinoma using computed tomography: A multi-center study.

The assessment of lateral lymph node metastasis (LLNM) in patients with papillary thyroid carcinoma (PTC) holds great significance. This study aims to develop and evaluate a deep learning-based automatic pipeline system (DLAPS) for diagnosing LLNM in PTC using computed tomography (CT). A total of 1,266 lateral lymph nodes (LLNs) from 519 PTC patients who underwent CT examinations from January 2019 to November 2022 were included and divided into training and validation set, internal test set, pooled external test set, and prospective test set. The DLAPS consists of an auto-segmentation network based on RefineNet model and a classification network based on ensemble model (ResNet, Xception, and DenseNet). The performance of the DLAPS was compared with that of manually segmented DL models, the clinical model, and Node Reporting and Data System (Node-RADS). The improvement of radiologists' diagnostic performance under the DLAPS-assisted strategy was explored. In addition, bulk RNA-sequencing was conducted based on 12 LLNs to reveal the underlying biological basis of the DLAPS. The DLAPS yielded good performance with area under the receiver operating characteristic curve (AUC) of 0.872, 0.910, and 0.822 in the internal, pooled external, and prospective test sets, respectively. The DLAPS significantly outperformed clinical models (AUC 0.731, P<0.001) and Node-RADS (AUC 0.602, P<0.001) in the internal test set. Moreover, the performance of the DLAPS was comparable to that of the manually segmented deep learning (DL) model with AUCs ranging 0.814-0.901 in three test sets. Furthermore, the DLAPS-assisted strategy improved the performance of radiologists and enhanced inter-observer consistency. In clinical situations, the rate of unnecessary LLN dissection decreased from 33.33% to 7.32%. Furthermore, the DLAPS was associated with the cell-cell conjunction in the microenvironment. Using CT images from PTC patients, the DLAPS could effectively segment and classify LLNs non-invasively, and this system had a good generalization ability and clinical applicability.

Detection of fibrosing interstitial lung disease-suspected chest radiographs using a deep learning-based computer-aided detection system: a retrospective, observational study

ObjectivesTo investigate the effectiveness of BMAX, a deep learning-based computer-aided detection system for detecting fibrosing interstitial lung disease (ILD) on chest radiographs among non-expert and expert physicians in the real-world...

ANALYZING THE CAN PROTOCOL: VULNERABILITIES, PROTECTIVE MEASURES AND IMPROVEMENTS

The Controller Area Network (CAN) bus, originally designed for internal communication among a limited number of Electronic Control Units (ECUs) within vehicles, faces significant security challenges due to the rapid expansion of ECUs in modern automobiles. This expansion necessitates accessibility for diagnostic purposes, yet the CAN protocol lacks fundamental security features such as encryption, authentication, and integrity checks, rendering it vulnerable to various attacks including message injection, Denial of Service (DoS), and masquerading ECUs. This paper surveys existing literature and investigates potential intrusions on the CAN bus, highlighting attacks ranging from GPS spoofing to remote sensor tampering. Various solutions are discussed, including network subdivision, encryption, authentication techniques, and intrusion detection systems (IDS). Recent research proposes IDS solutions utilizing machine learning algorithms such as Random Forest, Support Vector Machine, and Deep Neural Networks (DNN), demonstrating effectiveness in detecting known attacks. However, challenges persist in identifying unknown attacks and enhancing overall system performance. Innovative approaches, such as event-triggered detection and bloom filtering techniques, show promise in mitigating specific attack vectors but may introduce overhead or limitations in real-time response. Deep learning-based IDS systems exhibit high performance but struggle with the detection of novel attacks. Furthermore, while some solutions address specific vulnerabilities, others propose more comprehensive security measures, such as preventing remote manipulation of critical vehicle functions like steering and braking. Overall, the research emphasizes the critical need for robust security measures in automotive systems to safeguard against evolving threats to vehicle safety and integrity.