Browsing by Author "Dilhara, A"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationEmbargo
    Bridging tradition and innovation: exploring vegetable harvest loss reduction strategies in Sri Lanka
    (Emerald Publishing, 2026-01-15) Jayasuriya, N; Yapa, C.G; Rathnayake, T.A; Dilhara, A; Rathnayake, I.D; Mathangadeera, R
    Purpose – This study aims to address a significant gap in the literature regarding vegetable harvest loss reduction methods, exploring both traditional and modern perspectives in Sri Lanka, which is largely driven by an agricultural economy. This study explores the diverse strategies employed and how they are going to be integrated by Sri Lankan vegetable farmers, highlighting both traditional and modern pre- and post-harvest practices aimed at improving productivity, sustainability and resilience in agricultural systems. Design/methodology/approach – The study was conducted across key agricultural districts in Sri Lanka, with data collected through semi-structured interviews with vegetable farmers using the snowball sampling method. Thematic analysis was employed to identify patterns and themes in the data. Findings – The findings emphasize the importance of traditional methods, including cultural practices such as cultivating at auspicious times, established pest control and irrigation techniques. These are complemented by advanced agricultural innovations, modern harvest protection methods and improved packing and transportation techniques. This integrated approach showcases farmers' adaptability in reducing vegetable losses despite the challenges they face. Originality/value – Post- and pre-harvest loss reduction in Asian countries can be considered an understudied area. Furthermore, the focus on traditional methods is rare in the field. Therefore, this study provides a clear understanding of traditional and modern methods that are suitable for farmers in developing countries
  • No Thumbnail Available
    ItemEmbargo
    Project HyperAdapt: An Agent-Based Intelligent Sandbox Design to Deceive and Analyze Sophisticated Malware
    (Institute of Electrical and Electronics Engineers Inc., 2025) Perera, S; Dias, S; Vithanage, V; Dilhara, A; Senarathne, A; Siriwardana, D; Liyanapathirana, C
    Malware increasingly employs sophisticated evasion techniques to bypass sandbox-based analysis, rendering traditional detection methods ineffective. This research presents Project HyperAdapt: Agent-Based Intelligent Sandbox, a framework that integrates both offensive and defensive machine learning models to enhance malware detection, deception, and behavioral analysis. The offensive RL model generates evasive malware samples, challenging the sandbox, while the defensive models including hybrid evasion detection, GAN-based behavior simulation, and a dynamically adapting RL agent work collectively to improve sandbox resilience. By continuously learning from evasive malware behavior, the defensive RL agent adapts in real-time, strengthening detection capabilities. Experimental results demonstrate that this approach enhances sandbox effectiveness, ensuring long-term adaptability against evolving malware threats.