Advances In Deep Learning Research Articles

Polarimetric image denoising via non-local based cube matching convolutional neural network

Due to rapid advances in deep learning, many polarimetric image denoising networks have been developed and achieved promising results. However, these methods are based on general network architectures that do not fully exploit problem-specific knowledge, leading to over-smoothing results and poor generalization. Inspired by the non-local, which is an effective prior for image restoration, we propose a cube matching convolutional neural network to incorporate non-local operations into denoising models for polarimetric images. Specifically, the cube matching technique allows the denoising network to simultaneously exploit the non-local correlation and polarization relationship between the corresponding voxels of similar cubes. Rather than applying self-similarity directly in an isolated manner, the proposed cube matching module can be flexibly integrated into existing deep networks by combining with 3D convolution, achieving an effect equivalent to non-local means. This design enhances the generalization ability against various types and levels of noise. Experimental results show that using cube matching operations significantly improves denoising performance.

Leaf disease detection and classification with a CNN-LSTM hybrid model

Abstract. Smart agriculture refers to the use of modern information technology, Internet of Things technology, and artificial intelligence to achieve accurate management, efficient operation and sustainable development of the entire process of agricultural production. Smart agriculture mainly includes the application of data collection and analysis, intelligent agricultural machinery, precise fertilization, disease and pest detection and agricultural products traceability. Leaf disease detection and classification are considered as challenging yet important tasks in smart agriculture. Deep leaning methods have been proven effective for these image-based recognition tasks. In this study, two advanced deep learning methods, namely, Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) are combined together to achieve a further improvement. Numerical results demonstrate that the proposed method outperforms both CNN and LSTM variants.

A Comprehensive Analysis of Face Recognition Based on Advanced Deep Learning Technology

Abstract. Facial recognition technology is becoming increasingly important in many fields due to its non-invasiveness and rapid improvements in accuracy. This study provides a comprehensive review of face recognition methods, covering both traditional and modern approaches. The key models such as feature face, Fischer face, Visual Geometry Group face (VGG-Face), FaceNet and ArcFace are analyzed, and the complete process from data preprocessing to feature extraction and model training is described in detail. By using the Wild Labeled Face Dataset (LFW) and the Network Face Dataset of the Institute of Automation of the Chinese Academy of Sciences (CASIA-WebFace) for experiments, the research found that although the deep learning model has high accuracy, it also faces challenges such as data dependence and large computing requirements. At the same time, the research highlights the issues of fairness and bias in these models, providing directions for future research and contributing to the sustainable and ethical development of face recognition technology.

Deep Learning-Based Freight Recommendation System for Freight Brokerage Platform

Platform-based businesses in the logistics market are evolving under the influence of digital transformation. Transforming the freight market into an environment where various types of freight can be traded across multiple markets and locations. Freight brokerage platforms have revolutionized the trading relationship between freight owners and vehicle owners. However, this type of system has also introduced inefficiencies, such as unestablished contracts, leading to unnecessary costs and delays. To address this issue, a freight recommendation system can assist users in finding what they are looking for while aiming to reduce failed contracts. With current advances in deep learning, complex patterns based on users’ past behaviors and preferences can be learned, enabling more accurate and personalized recommendations. This study proposes a deep learning-based freight recommendation system to provide personalized services and reduce failed contracts on freight brokerage platforms. The system is built by creating a freight transaction dataset, classifying freight categories through natural language processing and text mining techniques, and incorporating externally derived data on transportation distances. The deep learning model is trained using Autoencoder, Word2Vec, and Graph Neural Networks (GNN), with recommendation logic implemented to suggest suitable freight matches for vehicle owners. This system is expected to increase the market efficiency of the freight logistics industry and is a key step toward improving the long-term profit structure.

Injury prevention and rehabilitation strategies in physical education: A machine learning-based approach using biomechanical characteristics

The field of sports biomechanics employs concepts from physics, biology, and engineering to investigate the mechanical characteristics of human motion and how they affect the body’s anatomy and functions. With the development of technology, sports biomechanics has emerged as a crucial component of sports medicine, training, and rehabilitation. To reduce the risk of injury and enhance athletic performance, sports biomechanics examines motions in sports in great length. The purpose of the study is to establish injury prevention and rehabilitation strategies for physical education (PE) teaching based on biomechanical characteristics. The early warning mode of sports injuries is recognized using advanced deep learning (DL) techniques, specifically resilient convolutional neural networks (RCNN). Biomechanical data from wearable sensors is used in this study to find trends related to sports-related injuries. A questionnaire survey of 228 students from various colleges was conducted. Individualized rehabilitation strategies will be provided to injured participants, taking into account their unique biomechanical deficiencies. These programs will be created in conjunction with physical therapists, and they will be updated in response to the patient’s progress toward recovery. The study found that their sports injuries were acute and chronic. This research demonstrated the treatment, prevention, and rehabilitation strategies of injuries in sports. The study emphasizes that biomechanical analysis is crucial for improving PE programs, which will eventually enhance students’ performance and overall health.

Edge Computing for Smart-City Human Habitat: A Pandemic-Resilient, AI-Powered Framework

The COVID-19 pandemic has highlighted the need for a robust medical infrastructure and crisis management strategy as part of smart-city applications, with technology playing a crucial role. The Internet of Things (IoT) has emerged as a promising solution, leveraging sensor arrays, wireless communication networks, and artificial intelligence (AI)-driven decision-making. Advancements in edge computing (EC), deep learning (DL), and deep transfer learning (DTL) have made IoT more effective in healthcare and pandemic-resilient infrastructures. DL architectures are particularly suitable for integration into a pandemic-compliant medical infrastructures when combined with medically oriented IoT setups. The development of an intelligent pandemic-compliant infrastructure requires combining IoT, edge and cloud computing, image processing, and AI tools to monitor adherence to social distancing norms, mask-wearing protocols, and contact tracing. The proliferation of 4G and beyond systems including 5G wireless communication has enabled ultra-wide broadband data-transfer and efficient information processing, with high reliability and low latency, thereby enabling seamless medical support as part of smart-city applications. Such setups are designed to be ever-ready to deal with virus-triggered pandemic-like medical emergencies. This study presents a pandemic-compliant mechanism leveraging IoT optimized for healthcare applications, edge and cloud computing frameworks, and a suite of DL tools. The framework uses a composite attention-driven framework incorporating various DL pre-trained models (DPTMs) for protocol adherence and contact tracing, and can detect certain cyber-attacks when interfaced with public networks. The results confirm the effectiveness of the proposed methodologies.

Constructing a 22-year internal wave dataset for the northern South China Sea: spatiotemporal analysis using MODIS imagery and deep learning

Abstract. Internal waves (IWs) are an important ocean phenomenon facilitating energy transfer between multiscale ocean processes. Understanding such processes necessitates the collection and analysis of extensive observational data. IWs predominantly occur in marginal seas, with the South China Sea (SCS) being one of the most active regions, characterized by frequent and large-amplitude IW activities. In this study, we present a comprehensive IW dataset for the northern SCS (https://doi.org/10.12157/IOCAS.20240409.001, Zhang and Li, 2024), covering the area from 112.40 to 121.32° E and from 18.32 to 23.19° N, spanning the period from 2000 to 2022 with a 250 m spatial resolution. During the 22 years, a total of 15 830 MODIS images were downloaded for further processing. Out of these, 3085 high-resolution MODIS true-color images were identified to contain IW information and were included in the dataset with precise IW positions extracted using advanced deep learning techniques. IWs in the northern SCS are categorized into four regions based on extracted IW spatial distributions. This classification enables detailed analyses of IW characteristics, including their spatial and temporal distributions across the entire northern SCS and its specific sub-regions. Interestingly, our temporal analysis reveals characteristic “double-peak” patterns aligned with the lunar day, highlighting the strong connection between IWs and tidal cycles. Furthermore, our spatial analysis identifies two IW quiescent zones within the IW clusters influenced by underwater topography, highlighting regional variations in IW characteristics and suggesting underlying mechanisms which merit further investigation. There are also three gap regions between distinct IW clusters, which may indicate different IW sources. The constructed dataset holds significant potential for studying IW–environment interactions, developing monitoring and prediction models, validating numerical simulations, and serving as an educational resource to promote awareness and interest in IW research.

TRANSFORMING BANKING SECURITY: THE ROLE OF DEEP LEARNING IN FRAUD DETECTION SYSTEMS

In the digital banking landscape, the increasing volume of online transactions has heightened the risk of fraudulent activities, necessitating the development of more effective detection systems. This study investigates the efficacy of various machine learning and deep learning algorithms in identifying fraudulent transactions, emphasizing Long Short-Term Memory (LSTM) networks. We implemented and evaluated multiple algorithms, including Logistic Regression, Random Forest, Gradient Boosting Machines (GBM), and XGBoost, on a large-scale credit card transaction dataset. Our results demonstrate that the LSTM model outperforms traditional machine learning algorithms, achieving an accuracy of 98.5%, precision of 87.2%, recall of 85.0%, and an Area Under the Curve (AUC) score of 0.94. These findings highlight the superior capability of LSTM networks to capture complex patterns in sequential transaction data, making them an asset for real-time fraud detection in banking. This research underscores the need for financial institutions to adopt advanced deep learning techniques to enhance their fraud detection systems, thereby minimizing financial losses and improving customer trust.

Intelligent rehabilitation assistant: Application of deep learning methods in sports injury recovery

In recent years, sports injury rehabilitation has developed into a specialized field that has forced the combination of an orthopedic surgeon, sports physiotherapist, and sports physician. Determining the appropriate time for an injured athlete to resume practice or competition is regarded as sports rehabilitation. Discovering the best solutions to avoid injuries, maximize recovery, and enhance performance is crucial for sports activities. The study introduced an intelligent rehabilitation assistant (IRA) that leverages advanced deep learning (DL) methods to enhance sports injury recovery. In this study, the IRA incorporates redefined prairie dog optimized bidirectional long-short-term memory (RPDO-Bi-LSTM) to enhance accuracy, predicting sports injury recovery. The study collected data on the state of rehabilitation, physiological parameters, and general health using wearable sensors and movement patterns. The data was preprocessed using a median filter to remove noise from sensor data. Region-based segmentation using segmented images from preprocessed data. Convolutional neural networks (CNN) using extracted features from obtained data. The IRA provides personalized recovery plans and real-time feedback. The framework consists of the components, suggested models to create quality scores for motions, measurements to quantify motion performance, and scoring of performance measurement elements into numerical quality scores. The proposed method is implemented using Python software. RPDO-Bi-LSTM presentation is evaluated by various metrics, such as accuracy 94.2% recall 98.2%, precision 96.5%, and specificity 95.2%, f1 score 95.6%, he planned technique attained good performance and improved the accuracy of sports injury recovery.

ACORN+: Adaptive Compression-Reconstruction for Device-Cloud Collaboration Video Services

With the improvement of edge-based autonomous systems such as mobile Industrial IoT(IIoT) networks, edge devices can capture and upload videos with increasing bitrates. Massive edge-computing end nodes are eager for adequate multimedia data to satisfy the requirements of real-time video services. However, existing encoding standards for video services in Web 2.0 are specifically designed for something other than IoT video streaming. We have improved our Adaptive Compression-Reconstruction framework ACORN to obtain ACORN+, based on compressed sensing and recent advances in deep learning. At end nodes, we compress multiple sequential video frames into a single frame to reduce video volume. Given that multiple kinds of intelligent tasks are expected to be finished on the device side, we also designed a device-cloud collaboration scheme where deep learning-based algorithms can be executed on both the device and server sides. Experiments reveal that video analytics can be conducted on compressed frames. Taking action recognition as a device-cloud collaboration use case, we find ACORN+ obtains more than 3x speedup on compressed frames. The reconstruction algorithm in ACORN+ is with 1- 4 dB improvements. Moreover, the encoding time cost and the encoded video volume are reduced by more than 4x under the ACORN+ framework. 1

Synergistic use of handcrafted and deep learning features for tomato leaf disease classification.

This research introduces a Computer-Aided Diagnosis-system designed aimed at automated detections & classification of tomato leaf diseases, combining traditional handcrafted features with advanced deep learning techniques. The system's process encompasses preprocessing, feature extraction, feature fusion, and classification. It utilizes enhancement filters and segmentation algorithms to isolate with Regions-of-Interests (ROI) in images tomato leaves. These features based arranged in ABCD rule (Asymmetry, Borders, Colors, and Diameter) are integrated with outputs from a Convolutional Neural Network (CNN) pretrained on ImageNet. To address data imbalance, we introduced a novel evaluation method that has shown to improve classification accuracy by 15% compared to traditional methods, achieving an overall accuracy rate of 92% in field tests. By merging classical feature engineering with modern machine learning techniques under mutual information-based feature fusion, our system sets a new standard for precision in agricultural diagnostics. Specific performance metrics showcasing the effectiveness of our approach in automated detection and classifying of tomato leaf disease.

Advanced Deep Learning Models for Accurate Citrus Disease Classification: Performance Analysis and Insights

Advanced Deep Learning Models for Accurate Citrus Disease Classification: Performance Analysis and Insights

Adversarial Attacks on Pre-trained Deep Learning Models for Encrypted Traffic Analysis

For web security, it’s essential to accurately classify traffic across various web applications to detect malicious activities lurking within network traffic. However, the encryption protocols for privacy protection, such as TLS 1.3 and IPSec, make it difficult to apply traditional traffic classification methods like deep packet inspection (DPI). Recently, the advent of deep learning has significantly advanced the field of encrypted traffic analysis (ETA), outperforming traditional traffic analysis approaches. Notably, pre-trained deep learning based ETA models have demonstrated superior analytical capabilities. However, the security aspects of these deep learning models are often overlooked during the design and development process. In this paper, we conducted adversarial attacks to evaluate the security of pre-trained ETA models. We targeted ET-BERT, a state-of-the-art model demonstrating superior performance, to generate adversarial traffic examples. To carry out the adversarial example generation, we drew inspiration from adversarial attacks on discrete data, such as natural language, defining fluency from a network traffic perspective and proposing a new attack algorithm that can preserve this fluency. Finally, in our experiments, we showed our target model is vulnerable to the proposed adversarial attacks.

Advanced deep learning approaches for early detection and localization of ocular diseases

Rece with t advancements in modern technology have significantly enhanced the transmission of information, particularly in image processing, utilizing deep learning algorithms. This study aims to propose a a robust deep-learning strategy for detecting and recognizing eye defects and diseases from medical images. We present a detailed practical simulation of hybrid deep learning techniques designed for medical image classification based on multi-descriptor algorithms. The focus is on the classification of eye diseases by applying an advanced deep-learning algorithm to a dataset comprising various pathological eye conditions. Training operations for the proposed algorithm were conducted following the initialization phase, which included the extraction of multi-specification features. This enables the deep learning model to effectively analyze input eye images and accurately diagnose conditions. Our results demonstrate a diagnostic efficiency of 99%, with an error rate not exceeding 0.015%. The findings underscore the high efficiency and accuracy of deep learning algorithms in classifying and analyzing image data, thereby significantly reducing the workload for healthcare professionals.

Detection of tuberculosis using cough audio analysis: a deep learning approach with capsule networks

PurposeTuberculosis (TB) is a widespread infectious disease that requires early detection for effective treatment and control. This study aims to improve TB detection using cough audio analysis, comparing the performance of capsule networks to other deep learning models.MethodsWe used cough audio recordings from 1105 individuals with a new or worsening cough for at least two weeks, totaling 9772 recordings. These recordings were processed into spectral images, and HOG features were extracted. Various models, including Capsule Networks + FCNN, CNN, VGG16, and ResNet50 were trained and evaluated.ResultsCapsule Networks + FCNN achieved the best performance with an accuracy of 0.97, sensitivity of 0.98, specificity of 0.96, F1 score of 0.97, and precision of 0.97, outperforming other models. This attribute is due to the model’s ability to learn complex features from spectral images.ConclusionsThis study concludes that Capsule Networks are more effective than typical CNN-based models in diagnosing TB from cough audio. This suggests that advanced deep learning frameworks could significantly enhance TB screening accuracy, especially in resource-limited areas.

IDENTIFICATION AND LOCALIZATION OF VULNERABILITIES IN SMART CONTRACTS USING ATTENTION VECTORS ANALYSIS IN A BERT-BASED MODEL

Context. With the development of blockchain technology and the increasing use of smart contracts, which are automatically executed in blockchain networks, the significance of securing these contracts has become extremely relevant. Traditional code auditing methods often prove ineffective in identifying complex vulnerabilities, which can lead to significant financial losses. For example, the reentrancy vulnerability that led to the DAO attack in 2016 resulted in the loss of 3.6 million ethers and the split of the Ethereum blockchain network. This underscores the necessity for early detection of vulnerabilities. Objective. The objective of this work is to develop and test an innovative approach for identifying and localizing vulnerabilities in smart contracts based on the analysis of attention vectors in a model using BERT architecture. Method. The methodology described includes data preparation and training a transformer-based model for analyzing smart contract code. The proposed attention vector analysis method allows for the precise identification of vulnerable code segments. The use of the CodeBERT model significantly improves the accuracy of vulnerability identification compared to traditional methods. Specifically, three types of vulnerabilities are considered: reentrancy, timestamp dependence, and tx.origin vulnerability. The data is preprocessed, which includes the standardization of variables and the simplification of functions. Results. The developed model demonstrated a high F-score of 95.51%, which significantly exceeds the results of contemporary approaches, such as the BGRU-ATT model with an F-score of 91.41%. The accuracy of the method in the task of localizing reentrancy vulnerabilities was 82%. Conclusions. The experiments conducted confirmed the effectiveness of the proposed solution. Prospects for further research include the integration of more advanced deep learning models, such as GPT-4 or T5, to improve the accuracy and reliability of vulnerability detection, as well as expanding the dataset to cover other smart contract languages, such as Vyper or LLL, to enhance the applicability and efficiency of the model across various blockchain platforms. Thus, the developed CodeBERT-based model demonstrates high results in detecting and localizing vulnerabilities in smart contracts, which opens new opportunities for research in the field of blockchain platform security.

Differential Analysis of Modern Text Spotting Methods : A Systematic Review

Text spotting, the task of detecting and recognizing text within images, is vital in applications like document analysis, autonomous navigation, and surveillance. The motivation for this review arises from the growing need for accurate automated text extraction methods, driven by the surge of visual data and the complexity of real-world environments. Despite advances in deep learning and computer vision, current text spotting techniques face significant challenges, including handling complex backgrounds, curved or distorted text, varied font styles, and low-resolution images. These limitations restrict their effectiveness in diverse, real-world settings. This systematic review aims to conduct a differential analysis of modern text spotting methods, highlighting their strengths, weaknesses, and performance in addressing such challenges. The objectives are to evaluate state-of-the-art techniques, identify gaps in the field, and propose future research directions. By critically synthesizing recent literature, this review provides insights that can help enhance the robustness and accuracy of text spotting systems, making them more adaptable to real-world conditions.

FlexSleepTransformer: a transformer-based sleep staging model with flexible input channel configurations

Clinical sleep diagnosis traditionally relies on polysomnography (PSG) and expert manual classification of sleep stages. Recent advancements in deep learning have shown promise in automating sleep stage classification using a single PSG channel. However, variations in PSG acquisition devices and environments mean that the number of PSG channels can differ across sleep centers. To integrate a sleep staging method into clinical practice effectively, it must accommodate a flexible number of PSG channels. In this paper, we proposed FlexSleepTransformer, a transformer-based model designed to handle varying number of input channels, making it adaptable to diverse sleep staging datasets. We evaluated FlexSleepTransformer using two distinct datasets: the public SleepEDF-78 dataset and the local SleepUHS dataset. Notably, FlexSleepTransformer is the first model capable of simultaneously training on datasets with differing number of PSG channels. Our experiments showed that FlexSleepTransformer trained on both datasets together achieved 98% of the accuracy compared to models trained on each dataset individually. Furthermore, it outperformed models trained exclusively on one dataset when tested on the other dataset. Additionally, FlexSleepTransformer surpassed state-of-the-art CNN and RNN-based models on both datasets. Due to its adaptability with varying channels numbers, FlexSleepTransformer holds significant potential for clinical adoption, especially when trained with data from a wide range of sleep centers.

An eXplainable Deep Learning Model for Multi-Modal MRI Grading of IDH-Mutant Astrocytomas

IDH-Mutant-astrocytomas are malignant brain glioma tumors. They are graded as lower (grades II and III) or higher (grade IV) according to their rate of growth and molecular features. Conventional IDH grading requires pathology examination, which is invasive, costly, and time-consuming. Non-invasive MRI methods are widely used but require a high level of interpretation for tumor grading. Recent advances in deep learning have shown potential to aid and improve the accuracy and efficiency of tumor classification. This study proposes a novel non-invasive approach for IDH-Mutant-astrocytomas grading using Light-weight Attention Network (LAN) that integrates multi-modal MRI data, including both conventional and advanced MR modalities. The study addresses inter-modality heterogeneity using Principal Component Analysis (PCA) while minimizing computational complexity. LAN uses a 3D Convolutional Neural Network (CNN) and a volumetric attention mechanism to extract and classify local and global tumor patterns. This is followed by an eXplainable AI approach that use SHapley Additive exPlanations (SHAP) values to understand the model decisions. LAN model outperforms other pre-trained state-of-the-art models, with an overall accuracy of 0.84. The advanced modalities Arterial Spin Labeling (ASL) and the Diffusion-weighted imaging(DWI) SHAP score contributes significantly in improving tumor heterogeneity visualization for aggressive grade II along with conventional MRIs. This work demonstrates the feasibility of integrating explainable deep learning with multi-modal MRI data for precise and comprehensible early glioma grading, potentially leading to better clinical decision-making.

Deep neural networks for knowledge-enhanced molecular modeling

Designing neural networks for molecular modeling is a crucial task in the field of artificial intelligence. The goal is to utilize neural networks to understand and design molecules, which has significant implications for drug development and other real-world applications. Recently, with the advancement of deep learning, molecular modeling has made considerable progress. However, current methods are primarily data-driven, overlooking the role of domain knowledge, such as molecular shapes, in the modeling process. In this paper, we systematically investigate how incorporating molecular shape knowledge can enhance molecular modeling. Specifically, we design two deep neural networks, ShapePred and ShapeGen, to utilize molecular shapes in molecule prediction and generation. Experimental results demonstrate that integrating shape knowledge can significantly improve model performance. Notably, ShapePred exhibits strong performance across 11 molecule prediction datasets, while ShapeGen can more efficiently generate high-quality drug molecules based on given target proteins.