International Conference on Advancements in Computing [ICAC]
Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/312
The International Conference on Advancements in Computing (ICAC) is organized by the Faculty of Computing of the Sri Lanka Institute of Information Technology (SLIIT) as an open forum for academics along with industry professionals to present the latest findings and research output and practical deployments in computing.
The primary objective of ICAC is to promote innovative research that addresses real-world challenges and contributes to the social well-being of communities. The conference provides a dynamic platform for researchers from around the world to present groundbreaking findings, exchange ideas, and establish meaningful collaborations.
Browse
5 results
Search Results
Item Embargo Adaptive AI-Based Enhancement of Critical External Sounds in Insulated Vehicle Cabins for Improved Safety(Institute of Electrical and Electronics Engineers Inc., 2025-12-09) Rathnayaka D.B; Wickramasuriya L.H.N.Y; Walpalage J.V; Rathnayake, SThe increasing acoustic insulation in modern and electric vehicles improves passenger comfort but unintentionally suppresses critical external sounds such as ambulance sirens, car horns, and train alarms, creating potential safety risks. While existing research has explored sound detection or localization in isolation, few systems integrate both capabilities in a unified framework for real-time vehicular deployment. This research proposes an adaptive AI-based system that detects, classifies, and selectively enhances these critical sounds in real time while providing directional awareness. Using a convolutional recurrent neural network (CRNN) trained on the UrbanSound8K dataset, the system processes incoming audio from external microphones, extracts Mel-frequency cepstral coefficients (MFCCs), and distinguishes safety-relevant cues from non-essential background noise. A dual-microphone setup enables the estimation of sound direction (left or right), providing additional spatial awareness to the driver. Detected signals are isolated through spectral filtering and relayed into the cabin with sub-30 ms latency, ensuring timely driver and passenger awareness without compromising comfort. Experimental results achieved 91.2% classification accuracy and 87.4% directional accuracy,confirming the system's feasibility for enhancing safety in insulated vehicle cabins and supporting future autonomous driving environments.Item Embargo HCLIP: Beyond CLIP for Cost-Effective Multimodal Retrieval in Education(Institute of Electrical and Electronics Engineers Inc., 2025-12-09) Weerasinghe, S; Gunatunga, O; Dewpura, W; Fernando, S; Kasthurirathna, D; Rathnayake, SMultimodal retrieval systems have gained significant attention due to their ability to process and cross-retrieve data containing images and text. However, the factors such as high cost of development, limitation on resources, and the proper addressing of the modality gap, the inherent representational differences between modalities pose a challenge to building effective and efficient retrieval models. In this work, we propose a low-resource, cost-efficient hybrid multimodal retrieval model that integrates Contrastive Language-Image Pre-training (CLIP) and All-MiniLM-L6-v2 to create a shared embedding space while storing raw images in an unstructured database. Our primary contributions include (1) the development of a hybrid model that outperforms CLIP-native retrieval, (2) a novel bidirectional neural network alignment technique that brings textual and visual modalities closer together, and (3) a comprehensive analysis of the modality gap's impact on downstream retrieval performance. Through proper evaluation using transparent techniques such as Mean Reciprocal Rank (MRR) and Cosine-Weighted MRR, our method demonstrates improved retrieval accuracy over baseline approaches. Experimental results exhibit that a lower modality gap does not always prove to be efficient on the downstream retrieval. Our findings pave the way for more efficient, adaptable, and cost-effective multimodal retrieval methodologies in low-resource environments, not limited to the education domain.Item Embargo Object Detection Approach for Pure and Cross Chicken Breed Identification(Institute of Electrical and Electronics Engineers Inc., 2025-12-09) Jayarathna, N; Rathnayake, S; Panduwawala, PThe proposed system aims to identify different types of purebred and crossbred chicken breeds across ten categories. Traditional methods such as visual inspection are often subjective and inaccurate, making breed identification challenging. To address this, image processing and deep learning techniques were employed, with the YOLOv5 object detection algorithm trained on a custom data set of 1,310 images. The model achieved strong results, with an overall precision of 83.5%, recall of 81.8%, and mAP@0.5 of 89.3%. The Class-wise evaluation showed particularly high performance for the Brahma and Leghorn breeds. Based on these outcomes, a mobile application was designed to provide farmers with a fast, reliable, and cost-effective tool for breed identification. In addition to classification, the application provides detailed information on breed characteristics and commercial value, helping small-scale farmers improve productivity, efficiency, and animal welfareItem Embargo Adaptive Video Game Content Generation through Player Centered Modeling(Institute of Electrical and Electronics Engineers Inc., 2025-12-09) Hapuarachchi H.A.R.S; Herath H.M.N.R; Kaveesha B.G.S; Deheragoda D.M.L.M; Rathnayake, S; Chamara, DThis research introduces a novel, integrated AI system for Adaptive Video Game Content Generation Through Player Centered Modeling, designed to overcome the limitations of conventional static game mechanics by dynamically modifying gameplay elements (levels, quests, music, and enemy behavior) in real-time based on player biometric and behavioral data. Key contributions include the Personalized Quest Generation System, where the CatBoost model performed well in predicting player engagement, and shifting to the YOLO11X-CLS classification model substantially reduced computational lag for real-time emotional adaptation. For Level Generation, the implementation of a bootstrapping methodology during DCGAN training enabled continued refinement, resulting in lower Symmetry Error and Block Diversity Error, while the Intelligent Enemy Agent, trained using Dueling DQN, demonstrated a clear upward trend in Mean Rewards, successfully generalizing learned pursuit strategies to a real-time environment. Despite these successes, limitations include potential mild overfitting in the emotion recognition model, evidenced by a slight increase in validation loss after 20 epochs, and the CNN used for dynamic music adjustment struggled with low-resolution webcam inputs, leading to occasional minor misclassifications and slight delays in music transitions when multiple biometric parameters changed simultaneously.Item Embargo Human-Ai Cooperative Driving Through Emotion-Aware Decision Making and Driver Personalization(Institute of Electrical and Electronics Engineers, 2025-12-09) Wickramasuriya L.H.N.Y; Rathnayaka D.B; Walpalage J.V.; Rathnayake, SConventional in-vehicle safety systems often neglect real-time emotional monitoring, prediction, and passenger influence, leading to reactive rather than proactive interventions. This paper presents an emotion-aware cooperative driving system that combines facial emotion recognition, time-series emotion forecasting, and personalized music-based regulation. The system detects both driver and front-seat passenger emotions through a Vision Transformer (ViT) model, while a time-series model anticipates the driver's upcoming emotional state. A prioritization algorithm ensures driver emotions hold precedence, with passenger states considered when the driver is stable. Based on this prioritized emotional context, the system regulates the in-cabin atmosphere using music recommendations drawn from the driver's preferred artists via the Spotify API. Experimental results show robust real-time emotion classification (86.4% validation accuracy), proactive forecasting (81.6% predictive accuracy), and improved driver acceptance due to personalization. The proposed framework advances intelligent transportation by shifting from static monitoring toward predictive, human-centered, and non-intrusive emotional regulation, thereby enhancing both safety and user comfort.