Browsing by Author "Wijekoon, J. L"

Now showing 1 - 6 of 6

Embargo
Deep Learning-Based Surveillance System for Coconut Disease and Pest Infestation Identification
(IEEE, 2021-12-07) Vidhanaarachchi, S. P.; Akalanka, P. K. G. C.; Gunasekara, R. P. T. I.; Rajapaksha, H. M. U.D; Aratchige, N. S.; Lunugalage, D; Wijekoon, J. L
The coconut industry which contributes 0.8% to the national GDP is severely affected by diseases and pests. Weligama coconut leaf wilt disease and coconut caterpillar infestation are the most devastating; hence early detection is essential to facilitate control measures. Management strategies must reach approximately 1.1 million coconut growers with a wide range of demographics. This paper reports a smart solution that assists the stakeholders by detecting and classifying the disease, infestation, and deficiency for the sustainable development of the coconut industry. It leads to the early detections and makes stakeholders aware about the dispersions to take necessary control measures to save the coconut lands from the devastation. The results obtained from the proposed method for the identifications of disease, pest, deficiency, and degree of diseased conditions are in the range of 88% - 97% based on the performance evaluations.
Embargo
Effective use of network device state information for network path selection
(IEEE, 2017-01-27) Abeygunawardhana, P. K. W; Wijekoon, J. L
Network path selection defines the methodology of selecting the best routes and forwarding traffic in a network service provider (NSP). NSPs use routing protocols that are optimized for a single arbitrary metric (i.e., administrative weight), which is commonly calculated according to the link state information, to select network paths. Despite the advantages, link-state protocols lack the ability to select network paths by considering the states of network devices such as the effect of routers for network path selection. Apparently, studying possible techniques for selecting network paths based on the state information of network devices, e.g., routers, has become obligatory. This paper hypothesis to calculate a composite path selection metric by employing the state information of network devices; the proposed method selects the network paths based on the cumulative packet traveling time. By simulating proposed method using an ISP topology, the proposed method is examined for the effectiveness of using network device state information for network path selection.
Embargo
On the effectiveness of using machine learning and Gaussian plume model for plant disease dispersion prediction and simulation
(IEEE, 2019-12-05) Miriyagalla, R; Samarawickrama, Y; Rathnaweera, D; Liyanage, L; Kasthurirathna, D; Nawinna, D; Wijekoon, J. L
Agriculture plays a vital role in the economic development of the entire world. Similarly, in Sri Lanka, 6.9% of the national GDP is contributed by the agricultural sector and more than 25% of Sri Lankans are employed in the field of agriculture. But the frequent fluctuations of climate conditions have caused the spread of diseases such as late blight which eventually has led to the devastation of entire plantations of Sri Lankans. To this end, this paper proposes to forecast the possible dispersion pattern and assist the farmers in identifying the possibility of the disease getting dispersed to nearby crops to provide early warning. Eventually, it leads the farmers to take precautions to save the plants before reaching a critical stage. The yielded results show that the proposed method successfully performed disease diagnosis and disease progression level identification with 90-94 % accuracy and dispersion pattern analysis.
Embargo
A Secure Corroboration Protocol for Internet of Things (IoT) Devices Using MQTT Version 5 and LDAP
(IEEE, 2021-01-13) Vithanage, N. N. N; Thanthrige, S. S. H; Paththini Kapuge, M. C. K; Malwenna, T. H; Liyanapathirana, C; Wijekoon, J. L
The world is now shifting from Industry 4.0 to Industry 5.0 enabling the automation of the human livelihood by using Internet of Things (IoT). IoT can be attributed as a network that connects many sensor devices to collect data to provide automated smart environments. However, with a huge number of connected devices already deployed worldwide and organizations resorting to IoT development services more frequently because IoT security issues remain a matter of concern. One of the main identified reasons is IoT devices possess limited memory capacity, energy, processing which cause difficulties to run complex security algorithms, hindering the security services such as privacy and authentication, although those are crucial factors of IoT services. Hence, the adoption of adequate security and authentication techniques are necessary for a broad IoT deployment. To this end, this study proposes an authentication platform to improve the security and efficiency of data transmission between the IoT devices using LDAP and MQTT technologies. The implementation complies with IEEE 1451 standardization to uplift the MQTT with the help of LDAP features and GZip compression.
Embargo
Smart Plant Disorder Identification using Computer Vision Technology
(IEEE, 2020-11-04) Manoharan, S; Sariffodeen, B; Ramasinghe, K. T; Rajaratne, L. H; Kasthurirathna, D; Wijekoon, J. L
The soil composition around the world is depleting at a rapid rate due to overexploitation by the unsustainable use of fertilizers. Streamlining the availability of nutrient deficiency and fertilizer related knowledge among impoverished farming communities would promoter environmentally and scientifically sustainable farming practices. Thus, contributing to several Sustainable Development Goals set out by the United Nations. The most direct solution to the inappropriate fertilizer usage is to add only the necessary amounts of fertilizer required by plants to produce a significant yield without nutrition deficiencies. To this end this paper proposes a Smart Nutrient Disorder Identification system employing computer vision and machine learning techniques for identification purposes and a decentralized blockchain platform to streamline a bias-less procurement system. The proposed system yielded 88% accuracy in disorder identification, while also enabling secure, transparent flow of verified information.
Embargo
Smart Snake Identification System using Video Processing
(IEEE, 2021-12-07) Deshan, P.D.R.; Pabasara, D. V. H.; Yapa, N. A.; Perera, D. S. R. C. V.; Lunugalage, D; Wijekoon, J. L
There is a common fact in the world that all snakes are venomous and dangerous to humans. This is due to a lack of awareness about snake species among the general public. However, based on the literature, the reality is that only 41 out of 108 reptiles are venomous and dangerous to humans. The challenge is specifically identifying the various snake species instead of considering all of them to be venomous. With the population growth frequency of snakebites reported in hospitals have arisen because of people attempt to harm snakes. This paper proposes an approach to help people in identifying snakes in panic situations using video processing, and then alert the nearest rescuer teams. This study has been carried in Sri Lanka, with a contribution to the scientific world to save both snakes and humans. The implemented system comprises of a mobile application with features including offline real-time snake identification, online real-time snake identification using video processing, manual snake detection, and alert nearest rescuers. The obtained results indicate that this application has an offline snake identification accuracy of 75%-80% and an online snake identification accuracy of 90%- 95%.