Md Amiruzzaman

Kadin Matotek, Heather Cassel, Md Amiruzzaman et al.

This study examines the performance of today's open-source, locally hosted large-language models (LLMs) in handling complex competitive programming tasks with extended problem descriptions and contexts. Building on the original Framework for AI-driven Code Generation Evaluation (FACE), the authors retrofit the pipeline to work entirely offline through the Ollama runtime, collapsing FACE's sprawling per-problem directory tree into a handful of consolidated JSON files, and adding robust checkpointing so multi-day runs can resume after failures. The enhanced framework generates, submits, and records solutions for the full Kattis corpus of 3,589 problems across eight code-oriented models ranging from 6.7-9 billion parameters. The submission results show that the overall pass@1 accuracy is modest for the local models, with the best models performing at approximately half the acceptance rate of the proprietary models, Gemini 1.5 and ChatGPT-4. These findings expose a persistent gap between private, cost-controlled LLM deployments and state-of-the-art proprietary services, yet also highlight the rapid progress of open models and the practical benefits of an evaluation workflow that organizations can replicate on in-house hardware.

Fnu Neha, Deepshikha Bhati, Deepak Kumar Shukla et al.

Object detection is a fundamental task in computer vision and image understanding, with the goal of identifying and localizing objects of interest within an image while assigning them corresponding class labels. Traditional methods, which relied on handcrafted features and shallow models, struggled with complex visual data and showed limited performance. These methods combined low-level features with contextual information and lacked the ability to capture high-level semantics. Deep learning, especially Convolutional Neural Networks (CNNs), addressed these limitations by automatically learning rich, hierarchical features directly from data. These features include both semantic and high-level representations essential for accurate object detection. This paper reviews object detection frameworks, starting with classical computer vision methods. We categorize object detection approaches into two groups: (1) classical computer vision techniques and (2) CNN-based detectors. We compare major CNN models, discussing their strengths and limitations. In conclusion, this review highlights the significant advancements in object detection through deep learning and identifies key areas for further research to improve performance.

Tsung Heng Wu, Md Amiruzzaman, Ye Zhao et al.

Street-level visual appearances play an important role in studying social systems, such as understanding the built environment, driving routes, and associated social and economic factors. It has not been integrated into a typical geographical visualization interface (e.g., map services) for planning driving routes. In this paper, we study this new visualization task with several new contributions. First, we experiment with a set of AI techniques and propose a solution of using semantic latent vectors for quantifying visual appearance features. Second, we calculate image similarities among a large set of street-view images and then discover spatial imagery patterns. Third, we integrate these discovered patterns into driving route planners with new visualization techniques. Finally, we present VivaRoutes, an interactive visualization prototype, to show how visualizations leveraged with these discovered patterns can help users effectively and interactively explore multiple routes. Furthermore, we conducted a user study to assess the usefulness and utility of VivaRoutes.

FNU Neha, Deepshikha Bhati, Deepak Kumar Shukla et al.

Generative Adversarial Networks (GANs) have proven to be a powerful tool in generating artistic images, capable of mimicking the styles of renowned painters, such as Claude Monet. This paper introduces a tiered GAN model to progressively refine image quality through a multi-stage process, enhancing the generated images at each step. The model transforms random noise into detailed artistic representations, addressing common challenges such as instability in training, mode collapse, and output quality. This approach combines downsampling and convolutional techniques, enabling the generation of high-quality Monet-style artwork while optimizing computational efficiency. Experimental results demonstrate the architecture's ability to produce foundational artistic structures, though further refinements are necessary for achieving higher levels of realism and fidelity to Monet's style. Future work focuses on improving training methodologies and model complexity to bridge the gap between generated and true artistic images. Additionally, the limitations of traditional GANs in artistic generation are analyzed, and strategies to overcome these shortcomings are proposed.

Deepshikha Bhati, Fnu Neha, Md Amiruzzaman et al.

Interpreting complex neural networks is crucial for understanding their decision-making processes, particularly in applications where transparency and accountability are essential. This proposed method addresses this need by focusing on layer-wise Relevance Propagation (LRP), a technique used in explainable artificial intelligence (XAI) to attribute neural network outputs to input features through backpropagated relevance scores. Existing LRP methods often struggle with precision in evaluating individual neuron contributions. To overcome this limitation, we present a novel approach that improves the parsing of selected neurons during LRP backward propagation, using the Visual Geometry Group 16 (VGG16) architecture as a case study. Our method creates neural network graphs to highlight critical paths and visualizes these paths with heatmaps, optimizing neuron selection through accuracy metrics like Mean Squared Error (MSE) and Symmetric Mean Absolute Percentage Error (SMAPE). Additionally, we utilize a deconvolutional visualization technique to reconstruct feature maps, offering a comprehensive view of the network's inner workings. Extensive experiments demonstrate that our approach enhances interpretability and supports the development of more transparent artificial intelligence (AI) systems for computer vision applications. This advancement has the potential to improve the trustworthiness of AI models in real-world machine vision applications, thereby increasing their reliability and effectiveness.

Suphanut Jamonnak, Ye Zhao, Xinyi Huang et al.

Vision-based deep learning (DL) methods have made great progress in learning autonomous driving models from large-scale crowd-sourced video datasets. They are trained to predict instantaneous driving behaviors from video data captured by on-vehicle cameras. In this paper, we develop a geo-context aware visualization system for the study of Autonomous Driving Model (ADM) predictions together with large-scale ADM video data. The visual study is seamlessly integrated with the geographical environment by combining DL model performance with geospatial visualization techniques. Model performance measures can be studied together with a set of geospatial attributes over map views. Users can also discover and compare prediction behaviors of multiple DL models in both city-wide and street-level analysis, together with road images and video contents. Therefore, the system provides a new visual exploration platform for DL model designers in autonomous driving. Use cases and domain expert evaluation show the utility and effectiveness of the visualization system.

Mahnaz Rafia Islam, Israt Jahan Jenny, Moniruzzaman Nayon et al.

Selecting an appropriate clustering method as well as an optimal number of clusters in road accident data is at times confusing and difficult. This paper analyzes shortcomings of different existing techniques applied to cluster accident-prone areas and recommends using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Ordering Points To Identify the Clustering Structure (OPTICS) to overcome them. Comparative performance analysis based on real-life data on the recorded cases of road accidents in North Carolina also show more effectiveness and efficiency achieved by these algorithms.

Asif Bhat, Rizal Mohd Nor, Md Amiruzzaman et al.

Blokchain is used in a variety of applications where trustworthy computing is re-quired. Trade finance is one of these areas that would benefit immensely from a decentralized way of doing transactions. This paper presents the preliminary as-sessment of Accepire-BT, a software platform developed for the practice of col-laborative Trade Finance. The proposed solution is enforced by smart contracts using Solidity, the underlying programming language for the Ethereum block-chain. We evaluated the performance in the Rinkeby test network by using Remix and MetaMask. The results of the preliminary trial show that smart contracts take less than one minute per cycle. Also, we present a discussion about costs for us-ing the public Ethereum Rinkeby network.

Hassnain ul hassan, Rizal Mohd Nor, Md Amiruzzaman et al.

The Domain Name System (DNS) is essential for the Internet, giving a mechanism to resolve hostnames into Internet Protocol (IP) addresses. DNS is known as the world's largest distributed database that manages hostnames and Internet Protocol. By having the DNS, only simple names that can be easily memorized will be used and then the domain name system will map it into the numeric Internet Protocol addresses that are used by computers to communicate. This research aims to propose a model for the development of a private cloud infrastructure to host DNS. The cloud infrastructure will be created using the OpenStack software platform where each server will be hosted separately in a different virtual machine. Virtual network architecture will be created using the Software Defined Networking (SDN) approach and it will be secured using Firewall as a Service (FWaaS). By hosting DNS in private cloud infrastructure, the DNS servers will be out of reach by attackers which will prevent DNS attacks. Besides, available research had proven that the cloud is the best choice for DNS. A prototype had been implemented and evaluated for its efficiencies. The findings from the evaluation carried out shown a positive result.

Md Mashfiq Rizvee, Md Amiruzzaman, Md Rajibul Islam

In this study, we present both data mining and information visualization techniques to identify accident-prone areas, most accident-prone time, day, and month. Also, we surveyed among volunteers to understand which visualization techniques help non-expert users to understand the findings better. Findings of this study suggest that most accidents occur in the dusk (i.e., between 6 to 7 pm), and on Fridays. Results also suggest that most accidents occurred in October, which is a popular month for tourism. These findings are consistent with social information and can help policymakers, residents, tourists, and other law enforcement agencies. This study can be extended to draw broader implications.

Md Amiruzzaman, Rizal Mohd Nor

In this paper, a new steganographic method is presented that provides minimum distortion in the stego image. The proposed encoding algorithm focuses on DCT rounding error and optimizes that in a way to reduce distortion in the stego image, and the proposed algorithm produces less distortion than existing methods (e.g., F5 algorithm). The proposed method is based on DCT rounding error which helps to lower distortion and higher embedding capacity.