Search

Real time vehicle detection is a challenging task for urban traffic surveillance. Increase in urbanization leads to increase in accidents and traffic congestion in junction areas resulting in delayed travel time. In order to solve these problems, an intelligent system utilizing automatic detection and tracking system is significant. But this becomes a challenging task at road intersection areas which require a wide range of field view. For this reason, fish eye cameras are widely used in real time vehicle detection purpose to provide large area coverage and 360 degree view at junctions. However, it introduces challenges such as light glare from vehicles and street lights, shadow, non-linear distortion, scaling issues of vehicles and proper localization of small vehicles. To overcome each of these challenges, a modified YOLOv5 object detection scheme is proposed. YOLOv5 is a deep learning oriented convolutional neural network (CNN) based object detection method. The proposed scheme for detecting vehicles in fish-eye images consists of a light-weight day-night CNN classifier so that two different solutions can be implemented to address the day-night detection issues. Furthurmore, challenging instances are upsampled in the dataset for proper localization of vehicles and later on the detection model is ensembled and trained in different combination of vehicle datasets for better generalization, detection and accuracy. For testing, a real world fisheye dataset provided by the Video and Image Processing (VIP) Cup organizer ISSD has been used which includes images from video clips of different fisheye cameras at junction of different cities during day and night time. Experimental results show that our proposed model has outperformed the YOLOv5 model on the dataset by 13.7% mAP @ 0.5.

Distributed Denial of Service (DDoS) attacks make the challenges to provide the services of the data resources to the web clients. In this paper, we concern to study and apply different Machine Learning (ML) techniques to separate the DDoS attack instances from benign instances. Our experimental results show that forward and backward data bytes of our dataset are observed more similar for DDoS attacks compared to the data bytes for benign attempts. This paper uses different machine learning techniques for the detection of the attacks efficiently in order to make sure the offered services from web servers available. This results from the proposed approach suggest that 97.1% of DDoS attacks are successfully detected by the Support Vector Machine (SVM). These accuracies are better while comparing to the several existing machine learning approaches.

The rapid development of digital stages has greatly compounded the dispersal of untrue data, dissolving certainty and judgment in society, especially among the Bengali-speaking community. Our ponder addresses this critical issue by presenting an interesting strategy that utilizes a profound learning innovation, particularly the Gated Repetitive Unit (GRU), to recognize fake news within the Bangla dialect. The strategy of our proposed work incorporates intensive information preprocessing, which includes lemmatization, tokenization, and tending to course awkward nature by oversampling. This comes about in a dataset containing 58,478 passages. We appreciate the creation of a demonstration based on GRU (Gated Repetitive Unit) that illustrates remarkable execution with a noteworthy precision rate of 94%. This ponder gives an intensive clarification of the methods included in planning the information, selecting the show, preparing it, and assessing its execution. The performance of the model is investigated by reliable metrics like precision, recall, F1 score, and accuracy. The commitment of the work incorporates making a huge fake news dataset in Bangla and a demonstration that has outperformed other Bangla fake news location models., Comment: 6 pages, THE 15th INTERNATIONAL IEEE CONFERENCE ON COMPUTING, COMMUNICATION AND NETWORKING TECHNOLOGIES (ICCCNT)

A mutation in the DNA of a single cell that compromises its function initiates leukemia,leading to the overproduction of immature white blood cells that encroach upon the space required for the generation of healthy blood cells.Leukemia is treatable if identified in its initial stages. However,its diagnosis is both arduous and time consuming. This study proposes a novel approach for diagnosing leukemia across four stages Benign,Early,Pre,and Pro using deep learning techniques.We employed two Convolutional Neural Network (CNN) models as MobileNetV2 with an altered head and a custom model. The custom model consists of multiple convolutional layers,each paired with corresponding max pooling layers.We utilized MobileNetV2 with ImageNet weights,adjusting the head to integrate the final results.The dataset used is the publicly available "Acute Lymphoblastic Leukemia (ALL) Image Dataset", and we applied the Synthetic Minority Oversampling Technique (SMOTE) to augment and balance the training dataset.The custom model achieved an accuracy of 98.6%, while MobileNetV2 attained a superior accuracy of 99.69%. The pretrained model showed promising results,indicating an increased likelihood of real-world application., Comment: 4 pages, 4 figures, Submitted to UCICS

Skin diseases can arise from infections, allergies, genetic factors, autoimmune disorders, hormonal imbalances, or environmental triggers such as sun damage and pollution. Some skin diseases, such as Actinic Keratosis and Psoriasis, can be fatal if not treated in time. Early identification is crucial, but the diagnostic methods for these conditions are often expensive and not widely accessible. In this study, we propose a novel and efficient method for diagnosing skin diseases using deep learning techniques. This approach employs a modified VGG16 Convolutional Neural Network (CNN) model. The model includes several convolutional layers and utilizes ImageNet weights with modified top layers. The top layer is updated with fully connected layers and a final softmax activation layer to classify skin diseases. The dataset used, titled "Skin Disease Dataset," is publicly available. While the VGG16 architecture does not include data augmentation by default, preprocessing techniques such as rotation, shifting, and zooming were applied to augment the data prior to model training. The proposed methodology achieved 90.67% accuracy using the modified VGG16 model, demonstrating its reliability in classifying skin diseases. The promising results highlight the potential of this approach for real-world applications.

Breast cancer is one of the deadliest cancers causing about massive number of patients to die annually all over the world according to the WHO. It is a kind of cancer that develops when the tissues of the breast grow rapidly and unboundly. This fatality rate can be prevented if the cancer is detected before it gets malignant. Using automation for early-age detection of breast cancer, Artificial Intelligence and Machine Learning technologies can be implemented for the best outcome. In this study, we are using the Breast Cancer Image Classification dataset collected from the Kaggle depository, which comprises 9248 Breast Ultrasound Images and is classified into three categories: Benign, Malignant, and Normal which refers to non-cancerous, cancerous, and normal images.This research introduces three pretrained model featuring custom classifiers that includes ResNet50, MobileNet, and VGG16, along with a custom CNN model utilizing the ReLU activation function.The models ResNet50, MobileNet, VGG16, and a custom CNN recorded accuracies of 98.41%, 97.91%, 98.19%, and 92.94% on the dataset, correspondingly, with ResNet50 achieving the highest accuracy of 98.41%.This model, with its deep and powerful architecture, is particularly successful in detecting aberrant cells as well as cancerous or non-cancerous tumors. These accuracies show that the Machine Learning methods are more compatible for the classification and early detection of breast cancer.

Kesterite is a leading candidate among inorganic thin-film photovoltaic technologies, offering sustainable and environmentally friendly solutions without reliance on critical raw materials. This study investigates the performance of CZTSSe-based kesterite solar cells using SCAPS-1D simulations. Four device configurations are analyzed by integrating the CZTSSe absorber layer with buffer materials, including CdS, SnS2, IGZO, and ZnSe, selected based on their energy band alignment. Moreover, key parameters influencing device efficiency, such as absorber defect density, buffer layer thickness, and the donor and defect densities of the buffer materials, are systematically examined. The thickness of the absorber layer and acceptor density are optimized, considering practical manufacturing constraints. Following optimization, the i-ZnO/SnS2/CZTSSe/Au configuration achieves a notable efficiency of 28.38%, with a VOC of 0.83 V, a JSC of 39.93 mA/cm2, and a fill factor of 85.4%. Furthermore, the stability of the optimized structures is evaluated under varying conditions, including resistances, temperature, generation and recombination dynamics, as well as JV and QE characteristics. These findings provide valuable insights for advancing the efficiency and stability of CZTSSe solar cells, contributing to the development of sustainable photovoltaic technologies., Comment: 25 pages, 10 figures, 2 tables

This study investigates transformer model compression by systematically pruning its layers. We evaluated 14 pruning strategies across nine diverse datasets, including 12 strategies based on different signals obtained from layer activations, mutual information, gradients, weights, and attention. To address the limitations of single-signal strategies, we introduced two fusion strategies, linear regression and random forest, which combine individual strategies (i.e., strategic fusion), for more informed pruning decisions. Additionally, we applied knowledge distillation to mitigate any accuracy loss during layer pruning. Our results reveal that random forest strategic fusion outperforms individual strategies in seven out of nine datasets and achieves near-optimal performance in the other two. The distilled random forest surpasses the original accuracy in six datasets and mitigates accuracy drops in the remaining three. Knowledge distillation also improves the accuracy-to-size ratio by an average factor of 18.84 across all datasets. Supported by mathematical foundations and biological analogies, our findings suggest that strategically combining multiple signals can lead to efficient, high-performing transformer models for resource-constrained applications., Comment: 15 pages, 1 table, 8 figures; will be submitted to ICML 2025; codes will be made public after acceptance

The increasing cybersecurity threats to critical manufacturing infrastructure necessitate proactive strategies for vulnerability identification, classification, and assessment. Traditional approaches, which define vulnerabilities as weaknesses in computational logic or information systems, often overlook the physical and cyber-physical dimensions critical to manufacturing systems, comprising intertwined cyber, physical, and human elements. As a result, existing solutions fall short in addressing the complex, domain-specific vulnerabilities of manufacturing environments. To bridge this gap, this work redefines vulnerabilities in the manufacturing context by introducing a novel characterization based on the duality between vulnerabilities and defenses. Vulnerabilities are conceptualized as exploitable gaps within various defense layers, enabling a structured investigation of manufacturing systems. This paper presents a manufacturing-specific cyber-physical defense-in-depth model, highlighting how security-aware personnel, post-production inspection systems, and process monitoring approaches can complement traditional cyber defenses to enhance system resilience. Leveraging this model, we systematically identify and classify vulnerabilities across the manufacturing cyberspace, human element, post-production inspection systems, production process monitoring, and organizational policies and procedures. This comprehensive classification introduces the first taxonomy of cyber-physical vulnerabilities in smart manufacturing systems, providing practitioners with a structured framework for addressing vulnerabilities at both the system and process levels. Finally, the effectiveness of the proposed model and framework is demonstrated through an illustrative smart manufacturing system and its corresponding threat model., Comment: 34 pages (including references), 12 figures

Reinforcement learning (RL) has shown great promise in simulated environments, such as games, where failures have minimal consequences. However, the deployment of RL agents in real-world systems such as autonomous vehicles, robotics, UAVs, and medical devices demands a higher level of safety and transparency, particularly when facing adversarial threats. Safe RL algorithms have been developed to address these concerns by optimizing both task performance and safety constraints. However, errors are inevitable, and when they occur, it is essential that the RL agents can also explain their actions to human operators. This makes trust in the safety mechanisms of RL systems crucial for effective deployment. Explainability plays a key role in building this trust by providing clear, actionable insights into the agent's decision-making process, ensuring that safety-critical decisions are well understood. While machine learning (ML) has seen significant advances in interpretability and visualization, explainability methods for RL remain limited. Current tools fail to address the dynamic, sequential nature of RL and its needs to balance task performance with safety constraints over time. The re-purposing of traditional ML methods, such as saliency maps, is inadequate for safety-critical RL applications where mistakes can result in severe consequences. To bridge this gap, we propose xSRL, a framework that integrates both local and global explanations to provide a comprehensive understanding of RL agents' behavior. xSRL also enables developers to identify policy vulnerabilities through adversarial attacks, offering tools to debug and patch agents without retraining. Our experiments and user studies demonstrate xSRL's effectiveness in increasing safety in RL systems, making them more reliable and trustworthy for real-world deployment. Code is available at https://github.com/risal-shefin/xSRL., Comment: Accepted to 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025)

Vision transformers (ViTs) have dominated computer vision in recent years. However, ViTs are computationally expensive and not well suited for mobile devices; this led to the prevalence of convolutional neural network (CNN) and ViT-based hybrid models for mobile vision applications. Recently, Vision GNN (ViG) and CNN hybrid models have also been proposed for mobile vision tasks. However, all of these methods remain slower compared to pure CNN-based models. In this work, we propose Multi-Level Dilated Convolutions to devise a purely CNN-based mobile backbone. Using Multi-Level Dilated Convolutions allows for a larger theoretical receptive field than standard convolutions. Different levels of dilation also allow for interactions between the short-range and long-range features in an image. Experiments show that our proposed model outperforms state-of-the-art (SOTA) mobile CNN, ViT, ViG, and hybrid architectures in terms of accuracy and/or speed on image classification, object detection, instance segmentation, and semantic segmentation. Our fastest model, RapidNet-Ti, achieves 76.3\% top-1 accuracy on ImageNet-1K with 0.9 ms inference latency on an iPhone 13 mini NPU, which is faster and more accurate than MobileNetV2x1.4 (74.7\% top-1 with 1.0 ms latency). Our work shows that pure CNN architectures can beat SOTA hybrid and ViT models in terms of accuracy and speed when designed properly., Comment: Accepted in 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)

Phase-sensitive integrated photonic devices are highly susceptible to minor manufacturing deviations, resulting in significant performance inconsistencies. This variability has limited the scalability and widespread adoption of these devices. Here, a major advancement is achieved through continuous-wave (CW) visible light (405 nm and 520 nm) trimming of plasma-enhanced chemical vapor deposition (PECVD) silicon-rich nitride (SRN) waveguides. The demonstrated method achieves precise, bidirectional refractive index tuning with a single laser source in CMOS-compatible SRN samples with refractive indices of 2.4 and 2.9 (measured at 1550 nm). By utilizing a cost-effective setup for real-time resonance tracking in micro-ring resonators, the resonant wavelength shifts as fine as 10 pm are attained. Additionally, a record red shift of 49.1 nm and a substantial blue shift of 10.6 nm are demonstrated, corresponding to refractive index changes of approximately 0.11 and -0.02. The blue and red shifts are both conclusively attributed to thermal annealing. These results highlight SRN's exceptional capability for permanent optical tuning, establishing a foundation for stable, precisely controlled performance in phase-sensitive integrated photonic devices., Comment: 21 pages, 11 figures

Gait recognition is a significant biometric technique for person identification, particularly in scenarios where other physiological biometrics are impractical or ineffective. In this paper, we address the challenges associated with gait recognition and present a novel approach to improve its accuracy and reliability. The proposed method leverages advanced techniques, including sequential gait landmarks obtained through the Mediapipe pose estimation model, Procrustes analysis for alignment, and a Siamese biGRU-dualStack Neural Network architecture for capturing temporal dependencies. Extensive experiments were conducted on large-scale cross-view datasets to demonstrate the effectiveness of the approach, achieving high recognition accuracy compared to other models. The model demonstrated accuracies of 95.7%, 94.44%, 87.71%, and 86.6% on CASIA-B, SZU RGB-D, OU-MVLP, and Gait3D datasets respectively. The results highlight the potential applications of the proposed method in various practical domains, indicating its significant contribution to the field of gait recognition.

Understanding video content is pivotal for advancing real-world applications like activity recognition, autonomous systems, and human-computer interaction. While scene graphs are adept at capturing spatial relationships between objects in individual frames, extending these representations to capture dynamic interactions across video sequences remains a significant challenge. To address this, we present TCDSG, Temporally Consistent Dynamic Scene Graphs, an innovative end-to-end framework that detects, tracks, and links subject-object relationships across time, generating action tracklets, temporally consistent sequences of entities and their interactions. Our approach leverages a novel bipartite matching mechanism, enhanced by adaptive decoder queries and feedback loops, ensuring temporal coherence and robust tracking over extended sequences. This method not only establishes a new benchmark by achieving over 60% improvement in temporal recall@k on the Action Genome, OpenPVSG, and MEVA datasets but also pioneers the augmentation of MEVA with persistent object ID annotations for comprehensive tracklet generation. By seamlessly integrating spatial and temporal dynamics, our work sets a new standard in multi-frame video analysis, opening new avenues for high-impact applications in surveillance, autonomous navigation, and beyond.

Traveling through toll plazas is one of the primary causes of congestion, as identified in recent studies. Electronic Toll Collection (ETC) systems can mitigate this problem. This experiment focuses on enhancing the security of ETC using RFID tags and number plate verification. For number plate verification, image processing is employed, and a CNN classifier is implemented to detect vehicle registration numbers. Based on the registered number, a notification email is sent to the respective owner for toll fee payment within a specific timeframe to avoid fines. Additionally, toll fees are automatically deducted in real-time from the owner's balance. This system benefits travelers by eliminating the need to queue for toll payment, thereby reducing delays and improving convenience.

Approximate Nearest Neighbor search is one of the keys to high-scale data retrieval performance in many applications. The work is a bridge between feature extraction and ANN indexing through fine-tuning a ResNet50 model with various ANN methods: FAISS and Annoy. We evaluate the systems with respect to indexing time, memory usage, query time, precision, recall, F1-score, and Recall@5 on a custom image dataset. FAISS's Product Quantization can achieve a precision of 98.40% with low memory usage at 0.24 MB index size, and Annoy is the fastest, with average query times of 0.00015 seconds, at a slight cost to accuracy. These results reveal trade-offs among speed, accuracy, and memory efficiency and offer actionable insights into the optimization of feature-based image retrieval systems. This study will serve as a blueprint for constructing actual retrieval pipelines and be built on fine-tuned deep learning networks and associated ANN methods.

Artificial intelligence (AI) is widely used in various fields including healthcare, autonomous vehicles, robotics, traffic monitoring, and agriculture. Many modern AI applications in these fields are multi-tasking in nature (i.e. perform multiple analysis on same data) and are deployed on resource-constrained edge devices requiring the AI models to be efficient across different metrics such as power, frame rate, and size. For these specific use-cases, in this work, we propose a new paradigm of neural network architecture (ILASH) that leverages a layer sharing concept for minimizing power utilization, increasing frame rate, and reducing model size. Additionally, we propose a novel neural network architecture search framework (ILASH-NAS) for efficient construction of these neural network models for a given set of tasks and device constraints. The proposed NAS framework utilizes a data-driven intelligent approach to make the search efficient in terms of energy, time, and CO2 emission. We perform extensive evaluations of the proposed layer shared architecture paradigm (ILASH) and the ILASH-NAS framework using four open-source datasets (UTKFace, MTFL, CelebA, and Taskonomy). We compare ILASH-NAS with AutoKeras and observe significant improvement in terms of both the generated model performance and neural search efficiency with up to 16x less energy utilization, CO2 emission, and training/search time., Comment: 9 pages, 3 figures, 6 tables

Author profiling, the analysis of texts to uncover attributes such as gender and age of the author, has become essential with the widespread use of social media platforms. This paper focuses on author profiling in the Bangla language, aiming to extract valuable insights about anonymous authors based on their writing style on social media. The primary objective is to introduce and benchmark the performance of machine learning approaches on a newly created Bangla Author Profiling dataset, BN-AuthProf. The dataset comprises 30,131 social media posts from 300 authors, labeled by their age and gender. Authors' identities and sensitive information were anonymized to ensure privacy. Various classical machine learning and deep learning techniques were employed to evaluate the dataset. For gender classification, the best accuracy achieved was 80% using Support Vector Machine (SVM), while a Multinomial Naive Bayes (MNB) classifier achieved the best F1 score of 0.756. For age classification, MNB attained a maximum accuracy score of 91% with an F1 score of 0.905. This research highlights the effectiveness of machine learning in gender and age classification for Bangla author profiling, with practical implications spanning marketing, security, forensic linguistics, education, and criminal investigations, considering privacy and biases., Comment: Accepted to be Published in 2024 27th International Conference on Computer and Information Technology (ICCIT)

Although software developers of mHealth apps are responsible for protecting patient data and adhering to strict privacy and security requirements, many of them lack awareness of HIPAA regulations and struggle to distinguish between HIPAA rules categories. Therefore, providing guidance of HIPAA rules patterns classification is essential for developing secured applications for Google Play Store. In this work, we identified the limitations of traditional Word2Vec embeddings in processing code patterns. To address this, we adopt multilingual BERT (Bidirectional Encoder Representations from Transformers) which offers contextualized embeddings to the attributes of dataset to overcome the issues. Therefore, we applied this BERT to our dataset for embedding code patterns and then uses these embedded code to various machine learning approaches. Our results demonstrate that the models significantly enhances classification performance, with Logistic Regression achieving a remarkable accuracy of 99.95\%. Additionally, we obtained high accuracy from Support Vector Machine (99.79\%), Random Forest (99.73\%), and Naive Bayes (95.93\%), outperforming existing approaches. This work underscores the effectiveness and showcases its potential for secure application development., Comment: I am requesting the withdrawal of my paper due to critical issues identified in the methodology/results that may impact its accuracy and reliability. I also plan to make substantial revisions that go beyond minor corrections

Extractive Text Summarization is the process of selecting the most representative parts of a larger text without losing any key information. Recent attempts at extractive text summarization in Bengali, either relied on statistical techniques like TF-IDF or used naive sentence similarity measures like the word averaging technique. All of these strategies suffer from expressing semantic relationships correctly. Here, we propose a novel Word pair-based Gaussian Sentence Similarity (WGSS) algorithm for calculating the semantic relation between two sentences. WGSS takes the geometric means of individual Gaussian similarity values of word embedding vectors to get the semantic relationship between sentences. It compares two sentences on a word-to-word basis which rectifies the sentence representation problem faced by the word averaging method. The summarization process extracts key sentences by grouping semantically similar sentences into clusters using the Spectral Clustering algorithm. After clustering, we use TF-IDF ranking to pick the best sentence from each cluster. The proposed method is validated using four different datasets, and it outperformed other recent models by 43.2% on average ROUGE scores (ranging from 2.5% to 95.4%). It is also experimented on other low-resource languages i.e. Turkish, Marathi, and Hindi language, where we find that the proposed method performs as similar as Bengali for these languages. In addition, a new high-quality Bengali dataset is curated which contains 250 articles and a pair of summaries for each of them. We believe this research is a crucial addition to Bengali Natural Language Processing (NLP) research and it can easily be extended into other low-resource languages. We made the implementation of the proposed model and data public on https://github.com/FMOpee/WGSS.

In the modern agricultural industry, technology plays a crucial role in the advancement of cultivation. To increase crop productivity, soil require some specific characteristics. For watermelon cultivation, soil needs to be sandy and of high temperature with proper irrigation. This research aims to design and implement an intelligent IoT-based soil characterization system for the watermelon field to measure the soil characteristics. IoT based developed system measures moisture, temperature, and pH of soil using different sensors, and the sensor data is uploaded to the cloud via Arduino and Raspberry Pi, from where users can obtain the data using mobile application and webpage developed for this system. To ensure the precision of the framework, this study includes the comparison between the readings of the soil parameters by the existing field soil meters, the values obtained from the sensors integrated IoT system, and data obtained from soil science laboratory. Excessive salinity in soil affects the watermelon yield. This paper proposes a model for the measurement of soil salinity based on soil resistivity. It establishes a relationship between soil salinity and soil resistivity from the data obtained in the laboratory using artificial neural network (ANN).

There has been little systematic study on how dialectal differences affect toxicity detection by modern LLMs. Furthermore, although using LLMs as evaluators ("LLM-as-a-judge") is a growing research area, their sensitivity to dialectal nuances is still underexplored and requires more focused attention. In this paper, we address these gaps through a comprehensive toxicity evaluation of LLMs across diverse dialects. We create a multi-dialect dataset through synthetic transformations and human-assisted translations, covering 10 language clusters and 60 varieties. We then evaluated three LLMs on their ability to assess toxicity across multilingual, dialectal, and LLM-human consistency. Our findings show that LLMs are sensitive in handling both multilingual and dialectal variations. However, if we have to rank the consistency, the weakest area is LLM-human agreement, followed by dialectal consistency. Code repository: \url{https://github.com/ffaisal93/dialect_toxicity_llm_judge}

Although real surfaces exhibit intricate topologies at the nanoscale, rough surface consideration is often overlooked in nanoscale heat transfer studies. Superimposed sinusoidal functions effectively model the complexity of these surfaces. This study investigates the impact of sinusoidal roughness on liquid argon condensation over a functional gradient wetting (FGW) surface with 84% hydrophilic content using molecular dynamics simulations. Argon atoms are confined between two platinum substrates: a flat lower substrate heated to 130K and a rough upper substrate at 90K. Key metrics of the nanoscale condensation process, such as nucleation, surface heat flux, and total energy per atom, are analyzed. Rough surfaces significantly enhance nucleation, nearly doubling cluster counts compared to smooth surfaces and achieving a more extended atomic density profile with a peak of approximately and improved heat flux. Stronger atom-surface interactions also lead to more efficient energy dissipation. These findings underscore the importance of surface roughness in optimizing condensation and heat transfer, offering a more accurate representation of surface textures and a basis for designing surfaces that achieve superior heat transfer performance., Comment: 9 pages, 7 figures, conference

In recent years, YouTube has become the leading platform for Bangla movies and dramas, where viewers express their opinions in comments that convey their sentiments about the content. However, not all comments are relevant for sentiment analysis, necessitating a filtering mechanism. We propose a system that first assesses the relevance of comments and then analyzes the sentiment of those deemed relevant. We introduce a dataset of 14,000 manually collected and preprocessed comments, annotated for relevance (relevant or irrelevant) and sentiment (positive or negative). Eight transformer models, including BanglaBERT, were used for classification tasks, with BanglaBERT achieving the highest accuracy (83.99% for relevance detection and 93.3% for sentiment analysis). The study also integrates LIME to interpret model decisions, enhancing transparency., Comment: Accepted for publication in Fifth International Conference on Advances in Electrical, Computing, Communications and Sustainable Technologies (ICAECT 2025)

A significant challenge in automating hate speech detection on social media is distinguishing hate speech from regular and offensive language. These identify an essential category of content that web filters seek to remove. Only automated methods can manage this volume of daily data. To solve this problem, the community of Natural Language Processing is currently investigating different ways of hate speech detection. In addition to those, previous approaches (e.g., Convolutional Neural Networks, multi-channel BERT models, and lexical detection) have always achieved low precision without carefully treating other related tasks like sentiment analysis and emotion classification. They still like to group all messages with specific words in them as hate speech simply because those terms often appear alongside hateful rhetoric. In this research, our paper presented the hate speech text classification system model drawn upon deep learning and machine learning. In this paper, we propose a new multitask model integrated with shared emotional representations to detect hate speech across the English language. The Transformer-based model we used from Hugging Face and sentiment analysis helped us prevent false positives. Conclusion. We conclude that utilizing sentiment analysis and a Transformer-based trained model considerably improves hate speech detection across multiple datasets., Comment: 20 Pages

That datasets that are used in todays research are especially vast in the medical field. Different types of medical images such as X-rays, MRI, CT scan etc. take up large amounts of space. This volume of data introduces challenges like accessing and retrieving specific images due to the size of the database. An efficient image retrieval system is essential as the database continues to grow to save time and resources. In this paper, we propose an approach to medical image retrieval using DenseNet for feature extraction and use FAISS for similarity search. DenseNet is well-suited for feature extraction in complex medical images and FAISS enables efficient handling of high-dimensional data in large-scale datasets. Unlike existing methods focused solely on classification accuracy, our method prioritizes both retrieval speed and diagnostic relevance, addressing a critical gap in real-time case comparison for radiologists. We applied the classification of breast cancer images using the BIRADS system. We utilized DenseNet's powerful feature representation and FAISSs efficient indexing capabilities to achieve high precision and recall in retrieving relevant images for diagnosis. We experimented on a dataset of 2006 images from the Categorized Digital Database for Low Energy and Subtracted Contrast Enhanced Spectral Mammography (CDD-CESM) images available on The Cancer Imaging Archive (TCIA). Our method outperforms conventional retrieval techniques, achieving a precision of 80% at k=5 for BIRADS classification. The dataset includes annotated CESM images and medical reports, providing a comprehensive foundation for our research., Comment: 34 pages, 5 figures

Time series forecasting is a key tool in financial markets, helping to predict asset prices and guide investment decisions. In highly volatile markets, such as cryptocurrencies like Bitcoin (BTC) and Ethereum (ETH), forecasting becomes more difficult due to extreme price fluctuations driven by market sentiment, technological changes, and regulatory shifts. Traditionally, forecasting relied on statistical methods, but as markets became more complex, deep learning models like LSTM, Bi-LSTM, and the newer FinBERT-LSTM emerged to capture intricate patterns. Building upon recent advancements and addressing the volatility inherent in cryptocurrency markets, we propose a hybrid model that combines Bidirectional Long Short-Term Memory (Bi-LSTM) networks with FinBERT to enhance forecasting accuracy for these assets. This approach fills a key gap in forecasting volatile financial markets by blending advanced time series models with sentiment analysis, offering valuable insights for investors and analysts navigating unpredictable markets.

In the digital age, the exposure of sensitive information poses a significant threat to security. Leveraging the ubiquitous nature of code-sharing platforms like GitHub and BitBucket, developers often accidentally disclose credentials and API keys, granting unauthorized access to critical systems. Despite the availability of tools for detecting such breaches in source code, detecting secret breaches in software issue reports remains largely unexplored. This paper presents a novel technique for secret breach detection in software issue reports using a combination of language models and state-of-the-art regular expressions. We highlight the challenges posed by noise, such as log files, URLs, commit IDs, stack traces, and dummy passwords, which complicate the detection process. By employing relevant pre-processing techniques and leveraging the capabilities of advanced language models, we aim to mitigate potential breaches effectively. Drawing insights from existing research on secret detection tools and methodologies, we propose an approach combining the strengths of state-of-the-art regexes with the contextual understanding of language models. Our method aims to reduce false positives and improve the accuracy of secret breach detection in software issue reports. We have curated a benchmark dataset of 25000 instances with only 437 true positives. Although the data is highly skewed, our model performs well with a 0.6347 F1-score, whereas state-of-the-art regular expression hardly manages to get a 0.0341 F1-Score with a poor precision score. We have also developed a secret breach mitigator tool for GitHub, which will warn the user if there is any secret in the posted issue report. By addressing this critical gap in contemporary research, our work aims at enhancing the overall security posture of software development practices., Comment: Under review in Empirical Software Engineering (EMSE)

The growing volume of biomedical scholarly document abstracts presents an increasing challenge in efficiently retrieving accurate and relevant information. To address this, we introduce a novel approach that integrates an optimized topic modelling framework, OVB-LDA, with the BI-POP CMA-ES optimization technique for enhanced scholarly document abstract categorization. Complementing this, we employ the distilled MiniLM model, fine-tuned on domain-specific data, for high-precision answer extraction. Our approach is evaluated across three configurations: scholarly document abstract retrieval, gold-standard scholarly documents abstract, and gold-standard snippets, consistently outperforming established methods such as RYGH and bio-answer finder. Notably, we demonstrate that extracting answers from scholarly documents abstracts alone can yield high accuracy, underscoring the sufficiency of abstracts for many biomedical queries. Despite its compact size, MiniLM exhibits competitive performance, challenging the prevailing notion that only large, resource-intensive models can handle such complex tasks. Our results, validated across various question types and evaluation batches, highlight the robustness and adaptability of our method in real-world biomedical applications. While our approach shows promise, we identify challenges in handling complex list-type questions and inconsistencies in evaluation metrics. Future work will focus on refining the topic model with more extensive domain-specific datasets, further optimizing MiniLM and utilizing large language models (LLM) to improve both precision and efficiency in biomedical question answering.

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks, which poses a critical problem. These attacks target LLMs applications through using carefully designed input prompts to divert the model from adhering to original instruction, thereby it could execute unintended actions. These manipulations pose serious security threats which potentially results in data leaks, biased outputs, or harmful responses. This project explores the security vulnerabilities in relation to prompt injection attacks. To detect whether a prompt is vulnerable or not, we follows two approaches: 1) a pre-trained LLM, and 2) a fine-tuned LLM. Then, we conduct a thorough analysis and comparison of the classification performance. Firstly, we use pre-trained XLM-RoBERTa model to detect prompt injections using test dataset without any fine-tuning and evaluate it by zero-shot classification. Then, this proposed work will apply supervised fine-tuning to this pre-trained LLM using a task-specific labeled dataset from deepset in huggingface, and this fine-tuned model achieves impressive results with 99.13\% accuracy, 100\% precision, 98.33\% recall and 99.15\% F1-score thorough rigorous experimentation and evaluation. We observe that our approach is highly efficient in detecting prompt injection attacks., Comment: I am requesting the withdrawal of my paper due to critical issues identified in the methodology/results that may impact its accuracy and reliability. I also plan to make substantial revisions that go beyond minor corrections

Data imputation addresses the challenge of imputing missing values in database instances, ensuring consistency with the overall semantics of the dataset. Although several heuristics which rely on statistical methods, and ad-hoc rules have been proposed. These do not generalise well and often lack data context. Consequently, they also lack explainability. The existing techniques also mostly focus on the relational data context making them unsuitable for wider application contexts such as in graph data. In this paper, we propose a graph data imputation approach called GIG which relies on graph differential dependencies (GDDs). GIG, learns the GDDs from a given knowledge graph, and uses these rules to train a transformer model which then predicts the value of missing data within the graph. By leveraging GDDs, GIG incoporates semantic knowledge into the data imputation process making it more reliable and explainable. Experimental results on seven real-world datasets highlight GIG's effectiveness compared to existing state-of-the-art approaches., Comment: 12 pages, 4 figures, published to ADC

In this study, we propose a novel and robust framework, Self-DenseMobileNet, designed to enhance the classification of nodules and non-nodules in chest radiographs (CXRs). Our approach integrates advanced image standardization and enhancement techniques to optimize the input quality, thereby improving classification accuracy. To enhance predictive accuracy and leverage the strengths of multiple models, the prediction probabilities from Self-DenseMobileNet were transformed into tabular data and used to train eight classical machine learning (ML) models; the top three performers were then combined via a stacking algorithm, creating a robust meta-classifier that integrates their collective insights for superior classification performance. To enhance the interpretability of our results, we employed class activation mapping (CAM) to visualize the decision-making process of the best-performing model. Our proposed framework demonstrated remarkable performance on internal validation data, achieving an accuracy of 99.28\% using a Meta-Random Forest Classifier. When tested on an external dataset, the framework maintained strong generalizability with an accuracy of 89.40\%. These results highlight a significant improvement in the classification of CXRs with lung nodules., Comment: 31 pages

We present a comprehensive survey on the use of annotations in information visualizations, highlighting their crucial role in improving audience understanding and engagement with visual data. Our investigation encompasses empirical studies on annotations, showcasing their impact on user engagement, interaction, comprehension, and memorability across various contexts. We also study the existing tools and techniques for creating annotations and their diverse applications, enhancing the understanding of both practical and theoretical aspects of annotations in data visualization. Additionally, we identify existing research gaps and propose potential future research directions, making our survey a valuable resource for researchers, visualization designers, and practitioners by providing a thorough understanding of the application of annotations in visualization.

Mamba is emerging as a novel approach to overcome the challenges faced by Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) in computer vision. While CNNs excel at extracting local features, they often struggle to capture long-range dependencies without complex architectural modifications. In contrast, ViTs effectively model global relationships but suffer from high computational costs due to the quadratic complexity of their self-attention mechanisms. Mamba addresses these limitations by leveraging Selective Structured State Space Models to effectively capture long-range dependencies with linear computational complexity. This survey analyzes the unique contributions, computational benefits, and applications of Mamba models while also identifying challenges and potential future research directions. We provide a foundational resource for advancing the understanding and growth of Mamba models in computer vision. An overview of this work is available at https://github.com/maklachur/Mamba-in-Computer-Vision., Comment: Under Review

Retrieval-Augmented Generation (RAG) has been shown to enhance the factual accuracy of Large Language Models (LLMs), but existing methods often suffer from limited reasoning capabilities in effectively using the retrieved evidence, particularly when using open-source LLMs. To mitigate this gap, we introduce a novel framework, Open-RAG, designed to enhance reasoning capabilities in RAG with open-source LLMs. Our framework transforms an arbitrary dense LLM into a parameter-efficient sparse mixture of experts (MoE) model capable of handling complex reasoning tasks, including both single- and multi-hop queries. Open-RAG uniquely trains the model to navigate challenging distractors that appear relevant but are misleading. As a result, Open-RAG leverages latent learning, dynamically selecting relevant experts and integrating external knowledge effectively for more accurate and contextually relevant responses. In addition, we propose a hybrid adaptive retrieval method to determine retrieval necessity and balance the trade-off between performance gain and inference speed. Experimental results show that the Llama2-7B-based Open-RAG outperforms state-of-the-art LLMs and RAG models such as ChatGPT, Self-RAG, and Command R+ in various knowledge-intensive tasks. We open-source our code and models at https://openragmoe.github.io/, Comment: Accepted to EMNLP 2024 Findings. Website: https://openragmoe.github.io/. 14 pages, 7 figures, 5 tables

This paper considers the Target Set Selection (TSS) Problem in social networks, a fundamental problem in viral marketing. In the TSS problem, a graph and a threshold value for each vertex of the graph are given. We need to find a minimum size vertex subset to "activate" such that all graph vertices are activated at the end of the propagation process. Specifically, we propose a novel approach called "a census-based genetic algorithm" for the TSS problem. In our algorithm, we use the idea of a census to gather and store information about each individual in a population and collect census data from the individuals constructed during the algorithm's execution so that we can achieve greater diversity and avoid premature convergence at locally optimal solutions. We use two distinct census information: (a) for each individual, the algorithm stores how many times it has been identified during the execution (b) for each network node, the algorithm counts how many times it has been included in a solution. The proposed algorithm can also self-adjust by using a parameter specifying the aggressiveness employed in each reproduction method. Additionally, the algorithm is designed to run in a parallelized environment to minimize the computational cost and check each individual's feasibility. Moreover, our algorithm finds the optimal solution in all cases while experimenting on random graphs. Furthermore, we execute the proposed algorithm on 14 large graphs of real-life social network instances from the literature, improving around 9.57 solution size (on average) and 134 vertices (in total) compared to the best solutions obtained in previous studies.

The geotechnical evaluation of seabed sediments is important for engineering projects and naval applications, offering valuable insights into sediment properties, behavior, and strength. Obtaining high-quality seabed samples can be a challenging task, making in-situ testing an essential part of site characterization. Free Fall Penetrometers (FFP) have emerged as robust tools for rapidly profiling seabed surface sediments, even in energetic nearshore or estuarine conditions and shallow as well as deep depths. While methods for interpretation of traditional offshore Cone Penetration Testing (CPT) data are well-established, their adaptation to FFP data is still an area of research. In this study, we introduce an innovative approach that utilizes machine learning algorithms to create a sediment behavior classification system based on portable free fall penetrometer (PFFP) data. The proposed model leverages PFFP measurements obtained from locations such as Sequim Bay (Washington), the Potomac River, and the York River (Virginia). The result shows 91.1\% accuracy in the class prediction, with the classes representing cohesionless sediment with little to no plasticity, cohesionless sediment with some plasticity, cohesive sediment with low plasticity, and cohesive sediment with high plasticity. The model prediction not only provides the predicted class but also yields an estimate of inherent uncertainty associated with the prediction, which can provide valuable insight about different sediment behaviors. These uncertainties typically range from very low to very high, with lower uncertainties being more common, but they can increase significantly dpending on variations in sediment composition, environmental conditions, and operational techniques. By quantifying uncertainty, the model offers a more comprehensive and informed approach to sediment classification.

Modern high-end systems are increasingly becoming heterogeneous, providing users options to use general purpose Graphics Processing Units (GPU) and other accelerators for additional performance. High Performance Computing (HPC) and Artificial Intelligence (AI) applications are often carefully arranged to overlap communications and computation for increased efficiency on such platforms. This has led to efforts to extend popular communication libraries to support GPU awareness and more recently, GPU-initiated operations. In this paper, we present Intel SHMEM, a library that enables users to write programs that are GPU aware, in that API calls support GPU memory, and also support GPU-initiated communication operations by embedding OpenSHMEM style calls within GPU kernels. We also propose thread-collaborative extensions to the OpenSHMEM standard that can enable users to better exploit the strengths of GPUs. Our implementation adapts to choose between direct load/store from GPU and the GPU copy engine based transfer to optimize performance on different configurations.

With the increasing adoption of AI-driven tools in software development, large language models (LLMs) have become essential for tasks like code generation, bug fixing, and optimization. Tools like ChatGPT, GitHub Copilot, and Codeium provide valuable assistance in solving programming challenges, yet their effectiveness remains underexplored. This paper presents a comparative study of ChatGPT, Codeium, and GitHub Copilot, evaluating their performance on LeetCode problems across varying difficulty levels and categories. Key metrics such as success rates, runtime efficiency, memory usage, and error-handling capabilities are assessed. GitHub Copilot showed superior performance on easier and medium tasks, while ChatGPT excelled in memory efficiency and debugging. Codeium, though promising, struggled with more complex problems. Despite their strengths, all tools faced challenges in handling harder problems. These insights provide a deeper understanding of each tool's capabilities and limitations, offering guidance for developers and researchers seeking to optimize AI integration in coding workflows.

Phishing attacks are a growing cybersecurity threat, leveraging deceptive techniques to steal sensitive information through malicious websites. To combat these attacks, this paper introduces PhishGuard, an optimal custom ensemble model designed to improve phishing site detection. The model combines multiple machine learning classifiers, including Random Forest, Gradient Boosting, CatBoost, and XGBoost, to enhance detection accuracy. Through advanced feature selection methods such as SelectKBest and RFECV, and optimizations like hyperparameter tuning and data balancing, the model was trained and evaluated on four publicly available datasets. PhishGuard outperformed state-of-the-art models, achieving a detection accuracy of 99.05% on one of the datasets, with similarly high results across other datasets. This research demonstrates that optimization methods in conjunction with ensemble learning greatly improve phishing detection performance.

Automatic Traffic Sign Recognition is paramount in modern transportation systems, motivating several research endeavors to focus on performance improvement by utilizing large-scale datasets. As the appearance of traffic signs varies across countries, curating large-scale datasets is often impractical; and requires efficient models that can produce satisfactory performance using limited data. In this connection, we present 'FUSED-Net', built-upon Faster RCNN for traffic sign detection, enhanced by Unfrozen Parameters, Pseudo-Support Sets, Embedding Normalization, and Domain Adaptation while reducing data requirement. Unlike traditional approaches, we keep all parameters unfrozen during training, enabling FUSED-Net to learn from limited samples. The generation of a Pseudo-Support Set through data augmentation further enhances performance by compensating for the scarcity of target domain data. Additionally, Embedding Normalization is incorporated to reduce intra-class variance, standardizing feature representation. Domain Adaptation, achieved by pre-training on a diverse traffic sign dataset distinct from the target domain, improves model generalization. Evaluating FUSED-Net on the BDTSD dataset, we achieved 2.4x, 2.2x, 1.5x, and 1.3x improvements of mAP in 1-shot, 3-shot, 5-shot, and 10-shot scenarios, respectively compared to the state-of-the-art Few-Shot Object Detection (FSOD) models. Additionally, we outperform state-of-the-art works on the cross-domain FSOD benchmark under several scenarios., Comment: 19 pages, 8 figures, 5 tables, submitted to IEEE Access for review

The accuracy of recommender systems influences their trust and decision-making when using them. Providing additional information, such as visualizations, offers context that would otherwise be lacking. However, the role of visualizations in influencing trust and decisions with recommender systems is under-explored. To bridge this gap, we conducted a two-part human-subject experiment to investigate the impact of scatterplots on recommender system decisions. Our first study focuses on high-level decisions, such as selecting which recommender system to use. The second study focuses on low-level decisions, such as agreeing or disagreeing with a specific recommendation. Our results show scatterplots accompanied by higher levels of accuracy influence decisions and that participants tended to trust the recommendations more when scatterplots were accompanied by descriptive accuracy (e.g., \textit{high}, \textit{medium}, or \textit{low}) instead of numeric accuracy (e.g., \textit{90\%}). Furthermore, we observed scatterplots often assisted participants in validating their decisions. Based on the results, we believe that scatterplots and visualizations, in general, can aid in making informed decisions, validating decisions, and building trust in recommendation systems.