Detection Task Research Articles

Phishing URL and Website Detection using MI

Phishing attacks remain a significant threat in the digital landscape, with cybercriminals constantly developing sophisticated techniques to deceive users into revealing sensitive information. This study presents a robust framework for phishing URLs and website detection utilizing the XG-Boost (Extreme Gradient Boosting) algorithm, known for its superior performance and efficiency in classification tasks. The proposed system focuses on analyzing various features extracted from URLs and webpage content, including lexical, structural, and host-based attributes, to distinguish between legitimate and malicious sites. By leveraging the strengths of the XG-Boost algorithm, the framework aims to improve detection accuracy and reduce false positive rates, thereby enhancing user safety in online environments. The research involves a comprehensive evaluation of the XG-Boost model's performance against several benchmark datasets representative of real-world phishing scenarios. The model is trained on a diverse set of features, with hyperparameter tuning conducted to optimize its predictive capabilities. Results indicate that the XG-Boost based approach achieves a high classification accuracy while demonstrating robustness against imbalanced datasets common in phishing detection tasks. The findings underscore the effectiveness of machine learning techniques in cybersecurity applications and highlight the potential for implementing the XG-Boost algorithm in real-time phishing detection systems to safeguard users from online threats. The proposed system leverages a diverse set of URL-based and website features such as the presence of special characters, domain age, HTTPS usage, and the similarity of the website's content to known phishing sites. These features are collected from URLs and website characteristics to form a feature vector for each website. The XG-Boost algorithm is trained on a labeled dataset consisting of both phishing and legitimate websites, learning to identify patterns indicative of phishing activities. XG-Boost's gradient boosting framework allows for a more accurate classification by combining multiple weak decision trees into a strong predictive model, making it highly suitable for this task. To evaluate the effectiveness of the proposed system, extensive experiments are conducted using publicly available datasets containing thousands of phishing and legitimate URLs. The model's performance is measured in terms of accuracy, precision, recall, and F1 score. The results demonstrate that the XG-Boost-based model outperforms traditional machine learning algorithms, such as decision trees and support vector machines (SVM), in detecting phishing websites with high accuracy and minimal false positives. This highlights the superiority of XG-Boost in handling the imbalanced nature of phishing datasets, where phishing samples are often underrepresented compared to legitimate ones. Key Words: XG-Boost (Extreme Gradient Boosting), Classifier, Features, Phishing, Train, Accuracy.

An automatic pipeline for temporal monitoring of radiotherapy-induced toxicities in head and neck cancer patients

Radiotherapy for head and neck cancer often causes a spectrum of toxicities. Such toxicities are usually unavailable as structured data and are reported within textual clinical reports. To reduce the burden of manual assessment of toxicities, we propose a language processing model for the automatic extraction of toxicities. The cohort consists of 384 patients with head and neck cancer who underwent radiotherapy, either as monotherapy or in combination with chemotherapy or surgery. A total of 3510 notes were extracted. The toxicities were then manually annotated. Two tasks of toxicity mention detection and toxicity extraction were defined. Pre-trained language models such as BERT, Clinical BioBERT, and Clinical Longformer were fine-tuned. Our best model achieves an F1 score of 90% for automatic extraction of toxicity mentions. An automatic system enables real-time extraction of toxicities and insights into their temporal patterns, offering actionable data to support dose optimization and minimize toxicities in personalized treatments.

AUMEs: AU Detection-Based Dual-Stream Multi-task 3DCNN for Micro-expression Recognition

Micro-expressions are brief, involuntary facial movements that can reveal real emotions. However, their short duration and low intensity pose a challenge for feature extraction and learning of neural networks. To overcome this challenge, we propose AUMEs, a 3DCNN-based multi-task learning framework that utilizes deep learning-based Lagrangian motion magnification and optical flow computation methods to enhance spatio-temporal features of micro-expressions, thus solving the problem of weak micro-expression motion intensity. AUMEs also use AU detection as a parallel task to improve the accuracy of micro-expression recognition by transferring knowledge from the AU detection task, and focal loss is utilized in model training to handle category imbalance in the micro-expression dataset. AUMEs achieve competitive results compared with existing SOTA methods on the CASMEII and SAMM datasets, achieving accuracy (Acc.) of 81.05% and 79.85%, UF1 score reaches 0.8880 and 0.7450 on the five-category task, and on the three-category UAR reached 89.02% and 75.86% and 0.8880 and 0.7450 for UF1. Furthermore, in both dataset analyses, the multi-task approach surpassed the single-task method across both the five-category and three-category classifications.

A Hardware Accelerator for Real-Time Processing Platforms Used in Synthetic Aperture Radar Target Detection Tasks

A Hardware Accelerator for Real-Time Processing Platforms Used in Synthetic Aperture Radar Target Detection Tasks

Task-dependent Modulation Masking of a 4-Hz Envelope Following Responses.

The perception and recognition of natural sounds, like speech, rely on the processing of slow amplitude modulations. Perception can be hindered by interfering modulations at similar rates, a phenomenon known as modulation masking. Cortical envelope following responses (EFRs) are highly sensitive to these slow modulations, but it is unclear how modulation masking impacts these cortical envelope responses. To dissociate stimulus-driven and attention-driven effects, we recorded EEG responses to a 4-Hz modulated noise in a two-way factorial design, varying the level of modulation masking and intermodal attention. Auditory stimuli contained one of three random masking bands in the stimulus envelope, at various proximities in modulation frequency to the 4-Hz target, or an unmasked reference condition. During EEG recordings, the same stimuli were presented while participants performed either an auditory or a visual change detection task. Attention to the auditory modality resulted in a general enhancement of sustained EFR responses to the 4-Hz target. In the visual task condition only, EFR 4-Hz power systematically decreased with increasing modulation masking, consistent with psychophysical masking patterns. However, during the auditory task, the 4-Hz EFRs were unaffected by masking and remained strong even with the highest degrees of masking. Rather than indicating a general bottom-up modulation selective process, these results indicate that the masking of cortical envelope responses interacts with attention. We propose that auditory attention allows robust tracking of masked envelopes, possibly through a form of glimpsing of the target, whereas envelope responses to task-irrelevant auditory stimuli reflect stimulus salience.

Leveraging paired mammogram views with deep learning for comprehensive breast cancer detection

Employing two standard mammography views is crucial for radiologists, providing comprehensive insights for reliable clinical evaluations. This study introduces paired mammogram view based-network(PMVnet), a novel algorithm designed to enhance breast lesion detection by integrating relational information from paired whole mammograms, addressing the limitations of current methods. Utilizing 1,636 private mammograms, PMVnet combines cosine similarity and the squeeze-and-excitation method within a U-shaped architecture to leverage correlated information. Performance comparisons with single view-based models with VGGnet16, Resnet50, and EfficientnetB5 as encoders revealed PMVnet’s superior capability. Using VGGnet16, PMVnet achieved a Dice Similarity Coefficient (DSC) of 0.709 in segmentation and a recall of 0.950 at 0.156 false positives per image (FPPI) in detection tasks, outperforming the single-view model, which had a DSC of 0.579 and a recall of 0.813 at 0.188 FPPI. These findings demonstrate PMVnet’s effectiveness in reducing false positives and avoiding missed true positives, suggesting its potential as a practical tool in computer-aided diagnosis systems. PMVnet can significantly enhance breast lesion detection, aiding radiologists in making more precise evaluations and improving patient outcomes. Future applications of PMVnet may offer substantial benefits in clinical settings, improving patient care through enhanced diagnostic accuracy.

VM-YOLO: YOLO with VMamba for Strawberry Flowers Detection

Computer vision technology is widely used in smart agriculture, primarily because of its non-invasive nature, which avoids causing damage to delicate crops. Nevertheless, the deployment of computer vision algorithms on agricultural machinery with limited computing resources represents a significant challenge. Algorithm optimization with the aim of achieving an equilibrium between accuracy and computational power represents a pivotal research topic and is the core focus of our work. In this paper, we put forward a lightweight hybrid network, named VM-YOLO, for the purpose of detecting strawberry flowers. Firstly, a multi-branch architecture-based fast convolutional sampling module, designated as Light C2f, is proposed to replace the C2f module in the backbone of YOLOv8, in order to enhance the network’s capacity to perceive multi-scale features. Secondly, a state space model-based lightweight neck with a global sensitivity field, designated as VMambaNeck, is proposed to replace the original neck of YOLOv8. After the training and testing of the improved algorithm on a self-constructed strawberry flower dataset, a series of experiments is conducted to evaluate the performance of the model, including ablation experiments, multi-dataset comparative experiments, and comparative experiments against state-of-the-art algorithms. The results show that the VM-YOLO network exhibits superior performance in object detection tasks across diverse datasets compared to the baseline. Furthermore, the results also demonstrate that VM-YOLO has better performances in the mAP, inference speed, and the number of parameters compared to the YOLOv6, Faster R-CNN, FCOS, and RetinaNet.

A listening advantage for native speech is reflected by attention-related activity in auditory cortex

The listening advantage for native speech is well known, but the neural basis of the effect remains unknown. Here we test the hypothesis that attentional enhancement in auditory cortex is stronger for native speech, using magnetoencephalography. Chinese and German speech stimuli were recorded by a bilingual speaker and combined into a two-stream, cocktail-party scene, with consistent and inconsistent language combinations. A group of native speakers of Chinese and a group of native speakers of German performed a detection task in the cued target stream. Results show that attention enhances negative-going activity in the temporal response function deconvoluted from the speech envelope. This activity is stronger when the target stream is in the native compared to the non-native language, and for inconsistent compared to consistent language stimuli. We interpret the findings to show that the stronger activity for native speech could be related to better top-down prediction of the native speech streams.

Differences in EEG complexity of cognitive activities among subtypes of schizophrenia

IntroductionThe neural mechanisms that underpin cognitive impairments in patients with schizophrenia remain unclear. Previous studies have typically treated patients as a homogeneous group, despite the existence of distinct symptom presentations between deficit and non-deficit subtypes. This approach has been found to be inadequate, necessitating separate investigation.MethodsThis study was conducted at Daizhuang Hospital in Jining City, China, from January 2022 to October 2023. The study sample comprised 30 healthy controls, 19 patients with deficit schizophrenia, and 19 patients with non-deficit schizophrenia, all aged between 18 and 45 years. Cognitive abilities were evaluated using a change detection task. The NeuroScan EEG/ERP System, comprising 64 channels and utilising standard 10-20 electrode placements, was employed to record EEG signals. The multiscale entropy and sample entropy of the EEG signals were calculated.ResultsThe healthy controls demonstrated superior task performance compared to both the non-deficit (p < 0.001) and deficit groups(p < 0.001). Significant differences in multiscale entropy between the three groups were observed at multiple electrode sites. In the task state, there are significant differences in the sample entropy of the β frequency band among the three groups of subjects. Under simple conditions of difficulty, the performance of the healthy controls exhibited a positive correlation with alpha band sample entropy(r = 0.372) and a negative correlation with beta band sample entropy (r = -0.411). Deficit patients demonstrated positive correlations with alpha band sample entropy (r = 0.370), whereas non-deficit patients exhibited negative correlations with both alpha and beta band sample entropy (r = -0.451, r = -0.362). Under difficult conditions of difficulty, the performance of healthy controls demonstrated a positive correlation with beta band sample entropy (r = 0.486). Deficit patients exhibited a positive correlation with alpha band sample entropy (r = 0.351), while non-deficit patients demonstrated a negative correlation with beta band sample entropy (r = -0.331).ConclusionThe results of this study indicate that cognitive impairment in specific subtypes of schizophrenia may have distinct physiological underpinnings, underscoring the need for further investigation.

IoT and Machine Learning Techniques for Precision Beekeeping: A Review

Integrating Internet of Things (IoT) devices and machine learning (ML) techniques holds immense potential for transforming beekeeping practices. This review paper offers a critical analysis of state-of-the-art IoT-enabled precision beekeeping systems. It examines the diverse sensor technologies deployed for honeybee data acquisition, delving into their strengths and limitations, particularly regarding accuracy, reliability, energy sustainability, transmission range, feasibility, and scalability. Furthermore, this paper dissects prevalent ML models used for bee behaviour analysis, disease detection, and colony monitoring tasks. This paper evaluates their methodologies, performance metrics, and the challenges involved in selecting appropriate machine learning algorithms. It also examines the influence of sensing devices, computational complexity, dataset limitations, validation procedures, evaluation metrics, and the effects of pre-processing techniques on these models’ outcomes. Building upon this analysis, this paper identifies key research gaps and proposes promising avenues for future investigation. The focus is on the synergistic use of IoT and ML to address colony health management challenges and the overall sustainability of the beekeeping industry.

High‐Bit‐Efficiency TOPS Optical Tensor Convolutional Accelerator Using Microcombs

AbstractTensor convolution is a fundamental operation in convolutional neural networks, especially for processing tensors, which are prevalent in real‐world applications. Current methods often convert tensor convolutions into matrix multiplications, leading to data replication, additional memory usage and increased hardware complexity. Here, a high‐bit‐efficiency optical tensor convolution accelerator with reduced data redundancy and lower memory consumption is presented. The bit‐efficiency of the optical tensor convolution accelerator is first explored, significantly improving its effective computing power by utilizing the spatial dimension. Consequently, the optical tensor convolutional accelerator operates at speeds exceeding 3 Tera Operations Per Second (TOPS)—the fastest single‐kernel optical convolutional accelerator to date, to the best of authors' knowledge. Its performance is validated on handwritten digit recognition and histopathologic cancer detection tasks, achieving 93.8% and 77% accuracy, respectively, closely matching in‐silico results. This approach simultaneously multiplexes the physical dimensions—wavelength, time, and space—and leverages the parallelism and high throughput of light, enabling efficient optical processing of tensor data with significant computational power.

A Novel Ensemble Belief Rule-Based Model for Online Payment Fraud Detection

In recent years, with the rapid development of technology and the economy, online transaction fraud has become more and more frequent. In the face of massive records of online transaction data, manual detection methods are long outdated, and machine learning methods have become mainstream. However, although traditional machine learning methods perform well in fraud detection tasks, the lack of interpretability and class imbalance issues have always been pain points that are difficult to resolve for such methods. Unlike traditional methods, the belief rule base, as a rule-based expert system model, can integrate expert knowledge and has excellent interpretability. In this paper, we propose an innovative ensemble BRB (belief rule base) model to solve the credit card fraud detection problem by combining an ensemble learning framework with the BRB model. Compared with traditional machine learning methods, the proposed model has the advantage of high interpretability. And compared with traditional BRB models, the ensemble framework enables better performance in dealing with highly imbalanced classification tasks. In an experimental study, two datasets of credit card fraud detection from Kaggle are used to validate the effectiveness of this work. The results show that this new method can achieve excellent performance in the application of fraud detection and is capable of effectively mitigating the impact of an imbalanced dataset.

Medical image segmentation with hybrid neural networks

Abstract Recent advancements in CNN and Transformer-based models have significantly advanced medical image segmentation. CNN-based models are less effective at capturing global contexts than Transformer-based models and Transformers have structural disadvantages that limit their ability to capture detailed spatial information. In this paper, we introduce an Dual-Encoder Fusion Model that incorporates a novel Correlation Fusion Module (CFM) for medical image segmentation tasks. This model leverages the strengths of Convolutional Neural Networks (CNN) for local context modeling and Transformers for comprehending long-range dependencies in pixel interactions. Experimental results demonstrate a substantial improvement over existing models on the Synapse dataset, achieving enhancements of 2.28% and 3.47% on the dice metric for Aorta and Pancreas organs respectively. Additionally, our model attains the highest mean HD95 score of 9.05 on the Synapse dataset while utilizing fewer parameters. When evaluated on the MSD datasets, our model outperforms a fine-tuned nnUNet in three out of five tumor detection tasks and maintains competitive performance in three out of four organ boundary delineation tasks. Notably, on the MSD-Lung dataset, our model surpasses a fine-tuned nnUNet on the dice metric by 6.4%. These results underscore the effectiveness of the CFM module within the dual-encoder architecture.

Ketamine does not rescue plaque load or gap detection in the 5XFAD mouse model of Alzheimer's disease

Ketamine has received growing attention for its effects on neuroplasticity and neuroinflammation, and as a treatment for depression and other mental health disorders. Recent evidence suggests that early sensory and behavioral deficits in Alzheimer's disease could be caused by synaptic disruption that occurs before irreversible neuropathology. This raises the possibility that ketamine could slow down or prevent network disruption and the ensuing sensory and behavioral deficits in Alzheimer's. Here we tested this idea in the 5XFAD mouse model of Alzheimer's, using either an acute single injection of ketamine, or chronic daily injections over 15 weeks. We tested the effects of ketamine on both amyloid plaque load and on a behavioral auditory gap detection task that is an early Alzheimer's biomarker in both mice and humans. We found that ketamine had no effect on plaque load, nor any effect on gap detection, for either acute or chronic dosing. Chronic ketamine facilitated startle responses specifically in 5XFAD mice, but this could simply be related to experience-dependent effects on stress or habituation rather than any rescue effect of ketamine on Alzheimer's-related deficits. We did find robust correlations between gap detection deficits and plaque load in auditory cortex and in the caudal pontine reticular nucleus, demonstrating that the behavioral deficits seen in 5XFAD mice are directly related to amyloid accumulation in these brain regions, and confirming the validity of gap detection as an early biomarker of Alzheimer's. Ketamine, however, had no effect on the strength of these correlations. We conclude that ketamine has no beneficial effect on the development of behavioral gap detection deficits or plaque load in the 5XFAD Alzheimer's mouse model, following either an acute single dose or a chronic daily dose regimen.

Dual-Branch Seasonal Error Elimination Change Detection Framework Using Target Image Feature Fusion Generator

In change detection tasks, seasonal variations in spectral characteristics and surface cover can negatively impact performance when comparing image pairs from different seasons. Many existing change detection methods do not specifically address the performance degradation caused by seasonal errors. To tackle this issue, the Dual-Branch Seasonal Error Elimination Change Detection Framework using Target Image Feature Fusion Generator (DBSEE-CDF) is introduced. Specifically, the approach utilizes the Target Image Feature Fusion Generator (TIFFG), which incorporates spatial and channel attention mechanisms to extract features from target images and integrates them with deep features from input images using cross-attention. To avoid a severe loss of visual fidelity caused by the significant differences in texture and color features between snow-covered and snow-free images, as well as the different requirements for style transformation, different generators for snow-covered winter images and snow-free winter images are employed to produce intermediate images that eliminate seasonal errors before conducting change detection tasks. The experimental results demonstrate significant improvements in both quantitative and qualitative assessments of change detection tasks compared to directly performing change detection with various models, highlighting the effectiveness of the proposed DBSEE-CDF.

DualAD: Exploring Coupled Dual-Branch Networks for Multi-Class Unsupervised Anomaly Detection

Anomaly detection (AD) is crucial in various domains such as industrial inspection, medical diagnosis, and video surveillance. Previous advancements in unsupervised AD often necessitated training separate models for different objects, which can be inefficient when dealing with diverse categories in real-world scenarios. This paper addresses the recently proposed task of multi-class unsupervised anomaly detection (MUAD), which is more practical and challenging. We begin by reviewing the first MUAD framework, UniAD, and analyzing the characteristics of end-to-end feature reconstruction networks that can adapt to various backbone architectures. Building on these insights, we introduce a novel MUAD framework called DualAD. Our approach is based on the innovative design of a Coupled Dual-Branch Network (CDBN), which integrates a Wide–Shallow Network (WSN) with a Narrow–Deep Network (NDN), leveraging the strengths of both to achieve superior performance. We explore a fully transformer-based homogeneous design for the CDBN and introduce a more lightweight heterogeneous CDBN design that integrates a transformer with a Memory-Augmented Multi-Layer Perceptron (MMLP). Experimental results on the MVTec AD and VisA datasets demonstrate that DualAD outperforms the recent state-of-the-art methods and exhibits robust performance across various pre-trained backbone architectures.

Detection of Aging Maize Seed Vigor and Calculation of Germ Growth Speed Using an Improved YOLOv8-Seg Network

Crop yields are influenced by various factors, including seed quality and environmental conditions. Detecting seed vigor is a critical task for seed researchers, as it plays a vital role in seed quality assessment. Traditionally, this evaluation was performed manually, which is time-consuming and labor-intensive. To address this limitation, this study integrates the ConvUpDownModule (a customized convolutional module), C2f-DSConv(C2f module with Integrated Dynamic Snake Convolution), and T-SPPF (the SPPF module integrated with the transformer multi-head attention mechanism) into the VT-YOLOv8-Seg network (the improved YOLOv8-Seg Network), an enhancement of the YOLOv8-Seg architecture. The ConvUpDownModule reduces the computational complexity and model parameters. The C2f-DSConv leverages flexible convolutional kernels to enhance the accuracy of maize germ edge segmentation. The T-SPPF integrates global information to improve multi-scale segmentation performance. The proposed model is designed for detecting and segmenting maize seeds and germs, facilitating seed germination detection and germination speed computation. In detection tasks, the VT-YOLOv8-Seg model achieved 97.3% accuracy, 97.9% recall, and 98.5% mAP50, while in segmentation tasks, it demonstrated 97.2% accuracy, 97.7% recall, and 98.2% mAP50. Comparative experiments with Mask R-CNN, YOLOv5-Seg, and YOLOv7-Seg further validated the superior performance of our model in both detection and segmentation. Additionally, the impact of seed aging on maize seed growth and development was investigated through artificial aging studies. Key metrics such as germination rate and germ growth speed, both closely associated with germination vigor, were analyzed, demonstrating the effectiveness of the proposed approach for seed vigor assessment.

The Epistemic Uncertainty Gradient in Spaces of Random Projections

This work presents a novel approach to handling epistemic uncertainty estimates with motivation from Bayesian linear regression. We propose treating the model-dependent variance in the predictive distribution—commonly associated with epistemic uncertainty—as a model for the underlying data distribution. Using high-dimensional random feature transformations, this approach allows for a computationally efficient, parameter-free representation of arbitrary data distributions. This allows assessing whether a query point lies within the distribution, which can also provide insights into outlier detection and generalization tasks. Furthermore, given an initial input, minimizing the uncertainty using gradient descent offers a new method of querying data points that are close to the initial input and belong to the distribution resembling the training data, much like auto-completion in associative networks. We extend the proposed method to applications such as local Gaussian approximations, input–output regression, and even a mechanism for unlearning of data. This reinterpretation of uncertainty, alongside the geometric insights it provides, offers an innovative and novel framework for addressing classical machine learning challenges.

Feature Fusion Network with Local Information Exchange for Underwater Object Detection

When using enhanced images for underwater object detection, issues such as detail loss and increased noise often arise, leading to decreased detection efficiency. To address this issue, we propose the Feature Fusion Network with Local Information Exchange (FFNLIE) for underwater object detection. We input raw and enhanced images into the Swin Transformer in parallel for feature extraction. Then, we propose a local information exchange module to enhance the feature extraction capability of the Swin Transformer. In order to fully utilize the complementary information of the two images, our feature fusion module consists of two core components: the Discrepancy Information Addition Block (DIAB) and the Common Information Addition Block (CIAB). The DIAB and CIAB are designed by utilizing and modifying cross-attention mechanisms, which can easily extract image discrepancy information and common information. Finally, the fused features are fed into the object detector to perform object detection tasks. The experimental findings demonstrate that the FFNLIE exhibited exceptional performance across four underwater datasets.

DHQ-DETR: Distributed and High-Quality Object Query for Enhanced Dense Detection in Remote Sensing

With the widespread application of remote sensing technologies and UAV imagery in various fields, dense object detection has become a significant and challenging task in computer vision research. Existing end-to-end detection models, particularly those based on DETR, often face criticism due to their high computational demands, slow convergence rates, and inadequacy in managing dense, multi-scale objects. These challenges are especially acute in remote sensing applications, where accurate analysis of large-scale aerial and satellite imagery relies heavily on effective dense object detection. In this paper, we propose the DHQ-DETR framework, which addresses these issues by modeling bounding box offsets as distributions. DHQ-DETR incorporates the Distribution Focus Loss (DFL) to enhance residual learning, and introduces a High-Quality Query Selection (HQQS) module to effectively balance classification and regression tasks. Additionally, we propose an auxiliary detection head and a sample assignment strategy that complements the Hungarian algorithm to accelerate convergence. Our experimental results demonstrate the superior performance of DHQ-DETR, achieving an average precision (AP) of 53.7% on the COCO val2017 dataset, 54.3% on the DOTAv1.0, and 32.4% on Visdrone, underscoring its effectiveness for real-world dense object detection tasks.