Institutional Repository

U n i v e r s i t y of P e r a d e n i y a

The Institutional Repository of the University of Peradeniya is the University's digital gateway to scholarly knowledge and research excellence. Established as the next phase of the Digital Library initiative launched by the University Library in 2011, it preserves, showcases, and provides open access to the intellectual output of the University community.

Through a rich collection of research articles, conference proceedings, theses, dissertations, and other scholarly works, the repository enhances the visibility, accessibility, and long-term preservation of knowledge, extending the global reach and impact of the University of Peradeniya’s academic and research contributions.

Photo by @ITD,Main Library

Communities in DSpace

Select a community to browse its collections.

Now showing 1 - 5 of 5

Recent Submissions

A wireless soft PLC architecture for scalable and cost-efficient intelligent automation platform for precision agriculture
(University of Peradeniya, Sri Lanka, 2026-08-20) Siriwardena, S. J.; Bandara, A. S.; Ekanayake, J. B.; Samaranayake, B. G. L. T.
Intelligent automation in precision agriculture demands scalable, adaptive, and cost-effective control architectures capable of reliable operation across distributed environments. Conventional Programmable Logic Controllers (PLCs), while deterministic and robust, are limited by high cost, hardware dependency, and poor scalability in geographically dispersed applications. This work proposes a software-defined Soft Programmable Logic Controller (Soft-PLC) architecture that virtualizes traditional PLC functionality while maintaining deterministic execution and hierarchical organization. A unified cyber-physical framework is introduced using a single long-range LoRa communication network to support sensing, closed-loop control, and actuation over distances up to 1 km. Wireless sensor nodes, each powered by a dedicated solar panel with a backup battery pack, measure nitrogen, phosphorus, potassium, pH, temperature, humidity, and electrical conductivity. Data are transmitted to a centralized control hub at intervals ranging from 30 seconds to 5 minutes, depending on agronomic requirements. The unified bidirectional LoRa infrastructure replaces the multiple communication gateways and multi-network infrastructure of conventional PLC-based precision agriculture systems, reducing system complexity and communication hardware by 30– 50%. Control logic is executed on a Raspberry Pi-based hub using a deterministic scan-cycle paradigm (input acquisition, logic execution, output update) aligned with IEC 61131-3 standards, achieving local controller scan times of 40–80 ms. End-to-end communication performance is evaluated separately through LoRa network latency and packet loss. The system follows ISA-95 layered design principles to ensure structured interaction between field devices, control processes, and supervisory systems, supporting integration with existing industrial automation frameworks. The key contribution is the integration of Soft-PLC virtualization, unified LoRa communication, and ISA-95 architecture into a scalable, hardware-independent automation platform for precision agriculture. Field validation over 72 hours in an open agriculture field with node–hub distances from 200 m to 1 km demonstrates the feasibility and stable short-term operation of the proposed architecture, with an average communication latency of 180 ms (range: 150–250 ms) and a packet loss rate of 2.3% (below 5% across all nodes). The system achieves a 40–50% cost reduction compared to conventional PLC-based precision agriculture setups while maintaining comparable control performance, providing a scalable automation and communication platform capable of supporting future AI-driven precision agriculture applications.
A unified comparative analysis of attention mechanisms for pneumonia detection in chest X-ray images
(University of Peradeniya, Sri Lanka, 2026-08-20) Selvarasa, T.; Ramanan, A.
Lower respiratory tract infections continue to represent a significant global health burden, particularly among children in low-resource settings. Limited access to expert radiological interpretation further increases the need for reliable automated diagnostic systems using chest X-ray (CXR) imaging. This study presents a systematic and controlled comparative analysis of three widely used attention mechanisms: Squeeze-and-Excitation (SE), Spatial Attention (SA), and Convolutional Block Attention Module (CBAM) within a unified deep learning framework for pediatric pneumonia detection. Unlike existing studies, many approaches report results using inconsistent datasets, preprocessing methods, and training strategies, making fair comparison difficult. To address this limitation, the present study ensures fairness and reproducibility by integrating each attention mechanism into the same ResNet50 backbone architecture and training all models under identical experimental conditions. The study utilises a publicly available Chest X-ray dataset (https://tinyurl.com/kaggle-CXR) comprising 5,856 pediatric CXR images, categorised into pneumonia and normal classes, using the predefined patient-wise train, validation, and test splits to prevent data leakage and ensure fair evaluation. Consistent preprocessing and data augmentation techniques are applied to improve model generalisation. Each attention module is incorporated across all hierarchical stages of the network, enabling progressive refinement of feature representations from low-level visual patterns to high-level disease-specific characteristics. Model evaluation is conducted using accuracy, precision, recall, and F1-score, along with Grad-CAM visualisations to assess interpretability and highlight clinically relevant lung regions. An ablation study is conducted to analyse the contribution of attention placement across network stages and evaluate the impact of channel and spatial attention components. The experimental findings indicate that all attention-based models outperform the ResNet50 models, confirming the effectiveness of attention mechanisms in improving classification performance. ResNet50 achieved an accuracy of 91.03%, while ResNet50+SE, ResNet50+SA, and ResNet50+CBAM achieved 91.99%, 92.31%, and 92.95%, respectively. ResNet50+CBAM improved accuracy by 1.92 percentage points over ResNet50. Test results confirm this gain stems specifically from combined channel-spatial refinement across all stages, not either component alone. These findings offer the first controlled evidence that CBAM's advantage holds specifically for pediatric pneumonia detection.
A regenerative braking system for an open wheeled single seater rear wheel drive formula-type race car
(University of Peradeniya, Sri Lanka, 2026-08-20) Pilapitiya, P. K. W. R. M. T. R. B.; Wedisinghe, W. A. T. A.; Thajudeeen, M. T. M. M.; Weerakoon, W. M. A. A. B.; Ampitithanne, A. T. G. S. K.; Illankoon, H. M. D.; Herath, H. M. A. D. K.
Braking systems in high-performance race cars must deliver consistent stopping power, precise modulation, and high thermal resistance under extreme operating conditions. Modern motorsport increasingly emphasizes energy efficiency and sustainability, driving the adoption of regenerative braking technologies. Regenerative braking converts kinetic energy, generally lost as heat during deceleration, into electrical energy that can be stored and reused, improving vehicle efficiency. Consequently, regenerative braking has become vital in motorsport for improving efficiency and reducing energy losses. This project presents the design, development, integration, and validation of a combined conventional hydraulic and regenerative braking system for a single-seater rear-wheel- drive race car named Diablo XI, developed for Formula motor sports competitions in Sri Lanka. The project focused on advanced engineering integration, improved efficiency, and cost-effective safety enhancements. A novel belt-driven, generator-based regenerative braking mechanism is proposed, enabling energy recovery in a cost-effective manner suitable for internal combustion engine-powered race vehicles. SolidWorks, the computer-aided design and simulation tool, was used to model the system prior to physical implementation. The project used conventional braking system consists of ventilated disc brakes on all four wheels, a vacuum-assisted brake booster, a dual-line master cylinder, semi-metallic brake pads, production-based calipers, steel brake lines, and DOT 3 brake fluid. The regenerative braking system utilizes a modified alternator operating as a generator, driven via a belt connected to the engine crankshaft. Generator engagement is controlled through an overrunning clutch activated during braking events. The recovered electrical energy is stored in a 12V lithium-ion battery pack equipped with a battery management system (BMS). The hydraulic braking system was validated through static inspections and dynamic testing at speeds of up to 100 km/h. Braking performance under repeated racing conditions was evaluated, and the test results confirmed reliable braking performance, consistent generator engagement during braking events, and successful battery charging while maintaining vehicle safety, stability, and handling characteristics. Future work will focus on comprehensive track testing and further optimization of the regenerative braking strategy to maximize energy recovery and braking performance under competitive racing conditions. Overall, this study demonstrates the feasibility of implementing a low-cost regenerative braking system for student-level and grassroots motorsport applications.
A multi-agent AI framework for real-time flood disaster response using satellite imagery and geospatial analysis
(University of Peradeniya, Sri Lanka, 2026-08-20) Abeywardena, M. B.; Dilshan, R. W. V. I.; Tharaka, A. L. S.; Iddamalgoda, I. H. R. P.
Flood disasters demand rapid situational awareness spanning hazard detection, infrastructure disruption, evacuation planning, and community coordination, yet conventional GIS workflows depend on manual tools and specialist intervention, delaying critical decisions for first responders in resource-constrained emergency environments. This study aimed to design, implement, and evaluate an autonomous multi-agent AI framework that converts satellite imagery and geospatial data into actionable, near-real-time flood-response intelligence usable by non-GIS-expert responders, integrating vision-language modelling, multi-agent orchestration, and geospatial analytics into a single decision-support pipeline. The system employed four specialized agents orchestrated through CrewAI with a Llama 3.2 reasoning backbone. A Qwen2-VL-7B vision-language model was finetuned using Low-Rank Adaptation on an AMD Instinct MI300X GPU with the Cyclone Ditwah 2025 Sentinel-1 SAR dataset (50,000 samples; 45,000/5,000 train/validation split) for damage-zone classification and GeoJSON generation, while live precipitation from the Open-Meteo API and OpenStreetMap road networks processed via GeoPandas and NetworkX supported blocked-road detection, shelter identification, and hazard-avoidant routing. Evaluation used 5,000 validation scenes and 50 routing scenarios. The fine-tuned model achieved 83.70% mAP@0.5 (82.51% precision, 86.77% recall) for damage-zone detection, generating valid GeoJSON outputs in under five seconds per image; the pipeline produced complete situational reports in under sixty seconds, and the routing module generated topologically valid evacuation paths in 41 of 50 cases. Supporting modules delivered early warning alerts, seven-day forecasting, geotagged incident reporting, missing-person tracking, SOS dispatch, and offline HTML map export. These results show that combining fine-tuned vision-language models, multi-agent orchestration, and geospatial analytics can consolidate fragmented flood-response workflows into a unified, near-real-time decision-support process suitable for resource-constrained emergency environments.
A comparative analysis of the energy demands and runtime of Large Language Models when deployed on user-side devices
(University of Peradeniya, Sri Lanka, 2026-08-20) Ahamed, H. U.; Aturusinghe, A. L. A. D. T. T.; Dewmini, D. M. K. N.; Jayarathne, M. G. S. K.
Large Language Models (LLMs) are statistical algorithms trained on massive amounts of data to predict the most appropriate response to a user prompt. LLMs requires a substantial supply of resources to function and despite the increase in the number of LLMs locally deployed, studies about LLM energy consumption are limited to those run at data centers, with research on locally deployed LLM energy consumption lacking. This study aims to bridge that gap by providing important information on the energy consumption and runtime of LLMs deployed on user-side devices via a comparison of the energy consumption and runtime efficiency of selected locally deployed LLMs across different prompt categories on consumer-grade hardware. For this task, a personal laptop having 16.0GB RAM and an Intel(R) UHD Graphics GPU was configured with Ollama for local LLM deployment and HWiNFO64 for hardware monitoring. To ensure the relevancy of the research, the study uses the 5 prompt categories most used in locally deployed LLMs (Factual, Reasoning, Long Generation, Code Generation and summarization), however future studies will use more novel prompts with increasing complexity. For proper evaluation we chose models developed by different companies (DeepSeek-R1(7B), Gemma 3(4B), and Phi-4 Mini (3.8B)). Using Ollama, each model was run 45 times, with 3 tests per prompt. During each test, HWiNFO64 recorded average power use and runtime, and these average values were compared across models and categories. The findings indicate that throughout the test cases, an overall average of 23.34 Watts (W) was consumed by all three LLMs at a mean runtime of 37.81 seconds. Furthermore, results reveal that DeepSeek-R1 (7B) had the greatest power demand with an average of 29.89 W, while Gemma 3(4B) recording the lowest demand for power with an average of 18.72 W needed. The results denote that there exists a relationship between model architecture, prompt category and PC system specifications that affects energy usage. By elaborating on this relationship and offering key insights, this study provides opportunities for future LLM development in consideration of user-device capabilities and to propose a reproducible LLM benchmark for consumer grade hardware to support future research.