Detection Framework Research Articles

Identification of surface defects on solar PV panels and wind turbine blades using attention based deep learning model

The global generation of renewable energy has rapidly increased, primarily due to the installation of large-scale renewable energy power plants. However, monitoring renewable energy assets in these large plants remains challenging due to environmental factors that could result in reduced power generation, malfunctioning, and degradation of asset life. Therefore, the detection of surface defects on renewable energy assets is crucial for maintaining the performance and efficiency of these plants. This paper proposes an innovative detection framework to achieve an economical surface monitoring system for renewable energy assets. High-resolution images of the assets are captured regularly and inspected to identify surface or structural damages on solar panels and wind turbine blades. Vision transformer (ViT), one of the latest attention-based deep learning (DL) models in computer vision, is proposed in this work to classify surface defects. The ViT model outperforms other DL models, including MobileNet, VGG16, Xception, EfficientNetB7, and ResNet50, achieving high accuracy scores above 97% for both wind and solar plant assets. From the results, our proposed model demonstrates its potential for monitoring and detecting damages in renewable energy assets for efficient and reliable operation of renewable power plants.

A Framework for Detection of Malicious Code by Exploiting Machine Learning Techniques on Portable Executables

Executable files coming from the internet bring along with them many potential hazards and vul- nerabilities in the form of malware to computer systems. The executables can be of form raw binaries, mnemonics, libraries, and function calls/APIs. They can misguide many of the conventional malware detection techniques. This paper explores the potential of Machine Learning- based methods for malware detection problems. The scope of the work here is currently limited to Static Anal- ysis of Executable files. Various feature selection tech- niques are implemented to reduce the size of the training data. Machine learning algorithms like K-Nearest Neigh- bors and Random Forest Classifier were trained on the curated feature sets. The outperforming experiment re- sult was shown by the Random Forest Classifier having an accuracy of 99.5%. We have developed a framework as a two-step module; in the first step, a list of features are extracted from a given executable file, and then for the next step, trained algorithm is integrated into the framework which will classify whether the given executa- ble file is malicious or not. This framework is demon- strated in the form of a Webapp developed in Python. Furthermore, this framework is evaluated based on its performance on a small dataset containing 35 portable executables (.exe) files and it is observed to be retaining the accuracy of the trained algorithm.

Probabilistic Analysis of Random Check Intrusion Detection System

The ubiquitous adoption of network-based technologies has left organizations vulnerable to malicious attacks. It has become vital to have effective intrusion detection systems (IDS) that protect the network from attacks. In this paper, we study the intrusion detection problem through the lens of probability theory. We consider a situation where a network receives random malicious signals at discrete time instances, and an IDS attempts to capture these signals via a random check process. We aim to develop a probabilistic framework for intrusion detection under the given scenario. Concretely, we calculate the detection rate of a network attack by an IDS and determine the expected number of detections. We perform extensive theoretical and experimental analyses of the problem. The results presented in this paper would be helpful tools for designing and analyzing intrusion detection systems. We propose a probabilistic framework that could be useful for IDS experts; for a network-based IDS that monitors in real-time, analyzing the entire traffic flow can be computationally expensive. By probabilistically sampling only a fraction of the network traffic, the IDS can still perform its task effectively while reducing the computational cost. However, checking only a fraction of the traffic increases the possibility of missing an attack. This research can help IDS designers achieve appropriate detection rates while maintaining a low false alarm rate. The groundwork laid out in this paper could be used for future research on understanding the probabilities related to intrusion detection.

Trustworthy semi‐supervised anomaly detection for online‐to‐offline logistics business in merchant identification

AbstractThe rise of online‐to‐offline (O2O) e‐commerce business has brought tremendous opportunities to the logistics industry. In the online‐to‐offline logistics business, it is essential to detect anomaly merchants with fraudulent shipping behaviours, such as sending other merchants' packages for profit with their low discounts. This can help reduce the financial losses of platforms and ensure a healthy environment. Existing anomaly detection studies have mainly focused on online fraud behaviour detection, such as fraudulent purchase and comment behaviours in e‐commerce. However, these methods are not suitable for anomaly merchant detection in logistics due to the more complex online and offline operation of package‐sending behaviours and the interpretable requirements of offline deployment in logistics. MultiDet, a semi‐supervised multi‐view fusion‐based Anomaly Detection framework in online‐to‐offline logistics is proposed, which consists of a basic version SemiDet and an attention‐enhanced multi‐view fusion model. In SemiDet, pair‐wise data augmentation is first conducted to promote model robustness and address the challenge of limited labelled anomaly instances. Then, SemiDet calculates the anomaly scoring of each merchant with an auto‐encoder framework. Considering the multi‐relationships among logistics merchants, a multi‐view attention fusion‐based anomaly detection network is further designed to capture merchants' mutual influences and improve the anomaly merchant detection performance. A post‐hoc perturbation‐based interpretation model is designed to output the importance of different views and ensure the trustworthiness of end‐to‐end anomaly detection. The framework based on an eight‐month real‐world dataset collected from one of the largest logistics platforms in China is evaluated, involving 6128 merchants and 16 million historical order consignor records in Beijing. Experimental results show that the proposed model outperforms other baselines in both AUC‐ROC and AUC‐PR metrics.

Improving Windows Malware Detection Using the Random Forest Algorithm and Multi-View Analysis

Cybercriminals motivated by malign purpose and financial gain are rapidly developing new variants of sophisticated malware using automated tools, and most of these malware target Windows operating systems. This serious threat demands efficient techniques to analyze and detect zero-day, polymorphic and metamorphic malware. This paper introduces two frameworks for Windows malware detection using random forest algorithms. The first scheme uses features obtained from static and dynamic analysis for training, and the second scheme uses features obtained from static, dynamic, malware image analysis, location-sensitive hashing and file format inspections. We carried out an extensive experiment on two feature sets, and the proposed schemes are evaluated using seven standard evaluation metrics. The experiment results demonstrate that the second scheme recognizes unseen malware better than the first scheme and three state-of-the-art works. The findings show that the second scheme’s multi-view feature set contributes to its 99.58% accuracy and lowers false positive rate of 0.54%.

A 2D Acridine‐Based Covalent Organic Framework for Selective Detection and Efficient Extraction of Gold from Complex Aqueous‐Based Matrices

Developing candidate materials which possess the ability of both selective detection and efficient capture of precious metal gold is highly desirable for environment and economy. However, most of reported materials only focus on single function, which seriously restricts their practical application as probes or adsorbents. Herein, a two dimensional (2D) acridine‐based covalent organic framework (TpDa‐COF) is prepared via the linkage of imine bonds for gold detection and adsorption. The synthesized COF can achieve both fluorescence and colorimetric dual sensing for Au3+ in a low concentration range (0.1 – 1.5 ppm) with the limit of detection (LOD) of 0.036 ppm. Impressively, the selectivity of TpDa‐COF for the detection of Au3+ is admirable (Fe3+, Fe2+ and Cu2+ for negligible influence on its fluorescence). In addition, TpDa‐COF exhibits ultrahigh adsorption capacity of 982.5 mg·g‐1 for gold at pH = 4, which is attributed the synergistic effect of both selective coordination and reductive process of Au(III) to Au(0). Meanwhile, both positive entropy change (ΔS = 76.07 J·mol‐1·K‐1) and high distribution coefficient (Kd = 12484.8 mL·g‐1) confirm the good affinity between TpDa‐COF framework and gold. This work gives us a new insight to prepare COF with pyridine nitrogen sites for gold detection and adsorption.

A2D Acridine-Based Covalent Organic Framework for Selective Detection and Efficient Extraction of Gold from Complex Aqueous-Based Matrices.

Developing candidate materials which possess the ability of both selective detection and efficient capture of precious metal gold is highly desirable for environment and economy. However, most of reported materials only focus on single function, which seriously restricts their practical application as probes or adsorbents. Herein, a two dimensional (2D) acridine-based covalent organic framework (TpDa-COF) is prepared via the linkage of imine bonds for gold detection and adsorption. The synthesized COF can achieve both fluorescence and colorimetric dual sensing for Au3+ in a low concentration range (0.1 - 1.5 ppm) with the limit of detection (LOD) of 0.036 ppm. Impressively, the selectivity of TpDa-COF for the detection of Au3+ is admirable (Fe3+, Fe2+ and Cu2+ for negligible influence on its fluorescence). In addition, TpDa-COF exhibits ultrahigh adsorption capacity of 982.5 mg·g-1 for gold at pH = 4, which is attributed the synergistic effect of both selective coordination and reductive process of Au(III) to Au(0). Meanwhile, both positive entropy change (ΔS = 76.07 J·mol-1·K-1) and high distribution coefficient (Kd = 12484.8 mL·g-1) confirm the good affinity between TpDa-COF framework and gold. This work gives us a new insight to prepare COF with pyridine nitrogen sites for gold detection and adsorption.

Adversarial attack detection framework based on optimized weighted conditional stepwise adversarial network

AbstractArtificial Intelligence (AI)-based IDS systems are susceptible to adversarial attacks and face challenges such as complex evaluation methods, elevated false positive rates, absence of effective validation, and time-intensive processes. This study proposes a WCSAN-PSO framework to detect adversarial attacks in IDS based on a weighted conditional stepwise adversarial network (WCSAN) with a particle swarm optimization (PSO) algorithm and SVC (support vector classifier) for classification. The Principal component analysis (PCA) and the least absolute shrinkage and selection operator (LASSO) are used for feature selection and extraction. The PSO algorithm optimizes the parameters of the generator and discriminator in WCSAN to improve the adversarial training of IDS. The study presented three distinct scenarios with quantitative evaluation, and the proposed framework is evaluated with adversarial training in balanced and imbalanced data. Compared with existing studies, the proposed framework accomplished an accuracy of 99.36% in normal and 98.55% in malicious traffic in adversarial attacks. This study presents a comprehensive overview for researchers interested in adversarial attacks and their significance in computer security.

A GNN-based fraud detector with dual resistance to graph disassortativity and imbalance

With the prosperity of Internet services, various fraudulent activities have emerged, and some graph neural network-based methods have been proposed for fraud detection. These methods have achieved significant performances based on the assortativity assumption where the connected nodes tend to have the same labels. However, the fraud graphs are not always assortative but more likely disassortative as fraudsters usually disguise themselves by deliberately making extensive connections to benign users. Furthermore, some studies have noticed node imbalance issues as the fraudsters are far fewer than normal users. But for another one, the edge imbalance issue is unexplored, and they also failed to make full use of these rare but valuable edges. Therefore, we propose an imbalanced disassortative graph learning framework for fraud detection. Specifically, a learnable dual-channel graph convolution filter is introduced to adaptively aggregate low- and high-frequency signals from its neighbors to assimilate/discriminate nodes with assortative/disassortative edges. Then, the label-aware node and edge samplers are designed to remedy graph imbalance problems. Furthermore, the sampled edges are treated as the auxiliary supervision signal to explicitly facilitate the training of graph filters. Extensive experiments on real-world datasets verify the superiority of our method.

Multi-branch myocardial infarction detection and localization framework based on multi-instance learning and domain knowledge.


Myocardial infarction (MI) is a serious cardiovascular disease that can cause irreversible damage to the heart, making early identification and treatment crucial. However, automatic MI detection and localization from an electrocardiogram (ECG) remain challenging. In this study, we propose two models, MFB-SENET and MFB-DMIL, for MI detection and localization, respectively. The MFB-SENET model is designed to detect MI, while the MFB-DMIL model is designed to localize MI. The MI localization model employs a specialized attention mechanism to integrate multi-instance learning with domain knowledge. This approach incorporates handcrafted features and introduces a new loss function called lead-loss, to improve MI localization. Grad-CAM is employed to visualize the decision-making process.
Main Results:
The proposed method was evaluated on the PTB and PTB-XL databases. Under the inter-patient scheme, the accuracy of MI detection and localization on the PTB database reached 93.88% and 67.17%, respectively. The accuracy of MI detection and localization on the PTB-XL database were 94.89% and 85.83%, respectively. Our method achieved comparable or better performance than other state-of-the-art algorithms. The proposed method combined deep learning and medical domain knowledge, demonstrates effectiveness and reliability, holding promise as an efficient MI diagnostic tool to assist physicians in formulating accurate diagnoses.&#xD.

Deep Learning-Based Fish Detection Using Above-Water Infrared Camera for Deep-Sea Aquaculture: A Comparison Study

Long-term, automated fish detection provides invaluable data for deep-sea aquaculture, which is crucial for safe and efficient seawater aquafarming. In this paper, we used an infrared camera installed on a deep-sea truss-structure net cage to collect fish images, which were subsequently labeled to establish a fish dataset. Comparison experiments with our dataset based on Faster R-CNN as the basic objection detection framework were conducted to explore how different backbone networks and network improvement modules influenced fish detection performances. Furthermore, we also experimented with the effects of different learning rates, feature extraction layers, and data augmentation strategies. Our results showed that Faster R-CNN with the EfficientNetB0 backbone and FPN module was the most competitive fish detection network for our dataset, since it took a significantly shorter detection time while maintaining a high AP50 value of 0.85, compared to the best AP50 value of 0.86 being achieved by the combination of VGG16 with all improvement modules plus data augmentation. Overall, this work has verified the effectiveness of deep learning-based object detection methods and provided insights into subsequent network improvements.

LAGSwin: Local attention guided Swin-transformer for thermal infrared sports object detection.

Compared with visible light images, thermal infrared images have poor resolution, low contrast, signal-to-noise ratio, blurred visual effects, and less information. Thermal infrared sports target detection methods relying on traditional convolutional networks capture the rich semantics in high-level features but blur the spatial details. The differences in physical information content and spatial distribution of high and low features are ignored, resulting in a mismatch between the region of interest and the target. To address these issues, we propose a local attention-guided Swin-transformer thermal infrared sports object detection method (LAGSwin) to encode sports objects' spatial transformation and orientation information. On the one hand, Swin-transformer guided by local attention is adopted to enrich the semantic knowledge of low-level features by embedding local focus from high-level features and generating high-quality anchors while increasing the embedding of contextual information. On the other hand, an active rotation filter is employed to encode orientation information, resulting in orientation-sensitive and invariant features to reduce the inconsistency between classification and localization regression. A bidirectional criss-cross fusion strategy is adopted in the feature fusion stage to enable better interaction and embedding features of different resolutions. At last, the evaluation and verification of multiple open-source sports target datasets prove that the proposed LAGSwin detection framework has good robustness and generalization ability.

An efficient Parkinson's disease detection framework: Leveraging time-frequency representation and AlexNet convolutional neural network

Parkinson's disease (PD) is a progressive neurodegenerative disorder affecting the quality of life of over 10 million individuals worldwide. Early diagnosis is crucial for timely intervention and better patient outcomes. Electroencephalogram (EEG) signals are commonly used for early PD diagnosis due to their potential in monitoring disease progression. But traditional EEG-based methods lack exploration of brain regions that provide essential information about PD, and their performance falls short for real-time applications. To address these limitations, this study proposes a novel approach using a Time-Frequency Representation (TFR) based AlexNet Convolutional Neural Network (CNN) model to explore EEG channel-based analysis and identify critical brain regions efficiently diagnosing PD from EEG data. The Wavelet Scattering Transform (WST) is employed to capture distinct temporal and spectral characteristics, while AlexNet CNN is utilized to detect complex spatial patterns at different scales, accurately identifying intricate EEG patterns associated with PD. The experiment results on two real-time EEG PD datasets: San Diego dataset and the Iowa dataset demonstrate that frontal and central brain regions, including AF4 and AFz electrodes, contribute significantly to providing more representative features compared to other regions for PD detection. The proposed architecture achieves an impressive accuracy of 99.84% for the San Diego dataset and 95.79% for the Iowa dataset, outperforming existing EEG-based PD detection methods. The findings of this research will assist to create an essential technology for efficient PD diagnosis, enhancing patient care and quality of life.

A neural network framework based on ConvNeXt for side‐channel hardware Trojan detection

AbstractResearchers in the field of hardware security have been dedicated to the study of hardware Trojan detection. Among the various approaches, side‐channel detection methods are widely used because of their high detection accuracy and fewer constraints. However, most side‐channel detection methods cannot make full use of side‐channel information. In this paper, we propose a framework that utilizes the continuous wavelet transform to convert time‐series information and employs an improved ConvNeXt network to detect hardware Trojans. This detection framework first converts one‐dimensional time‐series information into a two‐dimensional time–frequency map using the continuous wavelet transform to leverage frequency information in electromagnetic side‐channel signals. Then, the two‐dimensional time–frequency map is fed into the improved ConvNeXt network, which increases the weight of the informative parts in the two‐dimensional time–frequency map and enhances detection efficiency. The results indicate that the method proposed in this paper significantly improves the accuracy of hardware Trojan detection.

Distantly Supervised Explainable Stance Detection via Chain-of-Thought Supervision

Investigating public attitudes on social media is crucial for opinion mining systems. Stance detection aims to predict the attitude towards a specific target expressed in a text. However, effective neural stance detectors require substantial training data, which are challenging to curate due to the dynamic nature of social media. Moreover, deep neural networks (DNNs) lack explainability, rendering them unsuitable for scenarios requiring explanations. We propose a distantly supervised explainable stance detection framework (DS-ESD), comprising an instruction-based chain-of-thought (CoT) method, a generative network, and a transformer-based stance predictor. The CoT method employs prompt templates to extract stance detection explanations from a very large language model (VLLM). The generative network learns the input-explanation mapping, and a transformer-based stance classifier is trained with VLLM-annotated stance labels, implementing distant supervision. We propose a label rectification strategy to mitigate the impact of erroneous labels. Experiments on three benchmark datasets showed that our model outperformed the compared methods, validating its efficacy in stance detection tasks. This research contributes to the advancement of explainable stance detection frameworks, leveraging distant supervision and label rectification strategies to enhance performance and interpretability.

Enhancing object detection and classification using deep learning: A novel approach with annotated dataset and YOLO-C3GTR architecture

In the rapidly evolving field of computer vision, the need for advancements in object detection is paramount. For a variety of reasons, including security, maritime surveillance, and environmental monitoring, the identification and categorization of ships in aerial pictures is an essential component. In this study, two distinctive approaches are proposed to improve the accuracy of ship detection and categorization in satellite imagery. In the beginning, the dataset for ship detection that was provided by Airbus was separated into five distinct categories: oil tanker, bulk carrier, container ship, sand carrier, and general ship class. Setting up this division was done with the idea of increasing the precision of the ship classification in the imagery. Moreover, we deployed the YOLO-C3GTR model, which is part of our Object Detection framework and helped us to distinguish ships using the technique of Object Detection. The application of the methodology that we have proposed has the potential to significantly improve the precision of these systems when they are used in real-world scenarios and to make a novel addition to the field of ship identification and classification. We have used multiple algorithms of YOLOv5 tested on this dataset like TPHYOLOv5, YOLOv5x, YOLOv5l and our proposed architecture YOLO-C3GTR and it surpassed all the existing approaches by the mAP of 0.83. Furthermore, we intend to perform additional research in this field while simultaneously working to improve our technique. A comparison was made between the performance of the model and that of other deep learning approaches. The model was evaluated and trained with the categorized dataset.

Adversarially robust and real-time DDoS detection and classification framework using AutoML

ABSTRACT Denial of Service (DoS) attacks target the availability part of the CIA triad (Confidentiality, Availability, and Integrity). A special category of these attacks is the Distributed DoS (DDoS) attack, where the attacker uses a network of compromised systems called a botnet to flood a target server with requests and refuses to serve legitimate users. DDoS attacks can cost an organization millions of dollars in terms of lost revenue, remediation costs, and damage to brand reputation. Hence, all organizations need speedy real-time detection of DDoS attacks. This work presents a DDoS detection and classification framework using the flow-based approach for feature engineering and the AutoML technique. Our detection system is trained on the latest DDoS datasets – CIC-DDoS 2019 and CIC-IDS 2017, which contain various categories of DDoS attacks. We use various tools to perform adversarial attacks on our trained model. We retrain our models using adversarially crafted network packet captures and then test our models for robustness against practical adversarial attacks that an attacker might use to evade detection. Finally, we deploy our model in real-time using a GUI-based tool. Our model achieves a validation accuracy of 99.9% and a low false positive rate of 0.05%.

Detection of myocardial infarction using Shannon energy envelope, FA-MVEMD and deterministic learning

AbstractMyocardial infarction (MI) poses a significant clinical challenge, necessitating expeditious and precise detection to mitigate potentially fatal outcomes. Current MI diagnosis predominantly relies on electrocardiography (ECG); however, it is fraught with limitations, including inter-observer variability and a reliance on expert interpretation. This study introduces an automated MI detection framework that capitalizes on hybrid signal processing methodologies and deterministic learning theory. The initial step involves the extraction of the Shannon energy envelope (SEE) and its derivative from a single-lead ECG. Integration of the SEE into the ECG’s phase portrait provides a means to capture the underlying nonlinear system dynamics. Subsequently, the application of fast and adaptive multivariate empirical mode decomposition (FA-MVEMD) yields discriminative features originating from the most energetically dominant intrinsic mode components (IMFs) within the SEE. Profound dissimilarities are discernible between ECG signals recorded from healthy subjects and those afflicted with MI. In the subsequent phase, deterministic learning theory, implemented through neural networks, is employed to facilitate the classification of ECG signals into two distinct groups. The method’s efficacy is meticulously evaluated using the PTB diagnostic ECG database, resulting in a noteworthy average classification accuracy of 99.21$$\%$$ % within a tenfold cross-validation framework. In summation, the findings affirm that the proposed features not only complement conventional ECG attributes but also align closely with the underlying dynamics of the ECG system, ultimately fortifying the automatic detection of MI. The imperative requirement for early and accurate MI diagnosis is addressed through our approach, offering a robust and dependable means to fulfill this pivotal clinical need.

Improving the Machine Learning Performance for Image Recognition Using a New Set of Mountain Fourier Moments

The orthogonal moments are giving relevant results of these last years within the framework of object detection, pattern recognition and image reconstruction. This article is based on orthogonal functions called "Orthogonal Mountain functions (OMFs)" and we introduce a new set of moments called the multichannel Mountain Fourier moments (MMFMs), their performance is in reconstruction, noise invariants, rotation, scale and translation for image color. To validate these proposed techniques, we made several experimental tests to analyse images. We compare the results obtained from invariant moments and other current orthogonal invariant moments; the experiments show the power of the proposed moments.

Development of a fluorescent scaffold by utilizing quercetin template for selective detection of Hg2+: Experimental and theoretical studies along with live cell imaging

Quercetin is an important antioxidant with high bioactivity and it has been used as SARS-CoV-2 inhibitor significantly. Quercetin, one of the most abundant flavonoids in nature, has been in the spot of numerous experimental and theoretical studies in the past decade due to its great biological and medicinal importance. But there have been limited instances of employing quercetin and its derivatives as a fluorescent framework for specific detection of various cations and anions in the chemosensing field. Therefore, we have developed a novel chemosensor based on quercetin coupled benzyl ethers (QBE) for selective detection of Hg2+ with “naked-eye” colorimetric and “turn-on” fluorometric response. Initially QBE itself exhibited very weak fluorescence with low quantum yield (Φ = 0.009) due to operating photoinduced electron transfer (PET) and inhibition of excited state intramolecular proton transfer (ESIPT) as well as intramolecular charge transfer (ICT) within the molecule. But in presence of Hg2+, QBE showed a sharp increase in fluorescence intensity by 18-fold at wavelength 444 nm with high quantum yield (Φ = 0.159) for the chelation-enhanced fluorescence (CHEF) with coordination of Hg2+, which hampers PET within the molecule. The strong binding affinity of QBE towards Hg2+ has been proved by lower detection limit at 8.47 µM and high binding constant value as 2 × 104 M−1. The binding mechanism has been verified by DFT study, Cyclic voltammograms and Jobs plot analysis. For the practical application, the binding selectivity of QBE with Hg2+ has been capitalized in physiological medium to detect intracellular Hg2+ levels in living plant tissue by using green gram seeds. Thus, employing QBE as a fluorescent chemosensor for the specific identification of Hg2+ will pave the way for a novel approach to simplifying the creation of various chemosensors based on quercetin backbone for the precise detection of various biologically significant analytes.