Research Papers - Dept of Computer Systems Engineering
Permanent URI for this collection https://rda.sliit.lk/handle/123456789/1253
Browse
7 results
Search Results
Publication 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. LThe 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.Publication Embargo A Deep Learning Model Optimized with Genetic Algorithms for Resource Allocation of Virtualized Network Functions(IEEE, 2021-12-01) Rankothge, W. H; Gamage, N. D. U; Suhail, S. A. A; Ariyawansa, M. M. T. R.; Dewwiman, H. G. H; Senevirathne, M. D. B. PSoftware Defined Networking (SDN) has gained a significant attention of Cloud Service providers (CSPs) for managing their network infrastructure. With the popularity of services such as virtualized applications and Virtualized Network Functions (VNFs), many organizations are outsourcing their entire data centers to the CSPs. From the perspective of CSPs, effective and efficient cloud resource management plays an important role, in terms of continuing a successful business model. This research focuses on proposing a resource allocation algorithm for a cloud platform where VNFs are offered as a service. It is a tier-based resource allocation approach, where different resource tiers are defined in terms of network bandwidth, processor speed, RAM, vCPUs and number of users. Once the client's request is submitted for VNFs, we have used a deep learning approach (a Keras model which was optimized using Genetic Algorithms) to forecast the most suitable resource tier. Our results show that the proposed resource allocation algorithms can forecasts the most suitable resource tier for given scenario, in the order of seconds, with high accuracy.Publication Embargo Deepfake Audio Detection: A Deep Learning Based Solution for Group Conversations(IEEE, 2020-12-10) Wijethunga, R. L. M. A. P. C; Matheesha, D. M. K; Noman, A. A; De Silva, K. H. V. T. A; Tissera, M; Rupasinghe, LThe recent advancements in deep learning and other related technologies have led to improvements in various areas such as computer vision, bio-informatics, and speech recognition etc. This research mainly focuses on a problem with synthetic speech and speaker diarization. The developments in audio have resulted in deep learning models capable of replicating natural-sounding voice also known as text-to-speech (TTS) systems. This technology could be manipulated for malicious purposes such as deepfakes, impersonation, or spoofing attacks. We propose a system that has the capability of distinguishing between real and synthetic speech in group conversations.We built Deep Neural Network models and integrated them into a single solution using different datasets, including but not limited to Urban-Sound8K (5.6GB), Conversational (12.2GB), AMI-Corpus (5GB), and FakeOrReal (4GB). Our proposed approach consists of four main components. The speech-denoising component cleans and preprocesses the audio using Multilayer- Perceptron and Convolutional Neural Network architectures, with 93% and 94% accuracies accordingly. The speaker diarization was implemented using two different approaches, Natural Language Processing for text conversion with 93% accuracy and Recurrent Neural Network model for speaker labeling with 80% accuracy and 0.52 Diarization-Error-Rate. The final component distinguishes between real and fake audio using a CNN architecture with 94 % accuracy. With these findings, this research will contribute immensely to the domain of speech analysis.Publication Embargo Deepfake audio detection: a deep learning based solution for group conversations(IEEE, 2020-12-10) Wijethunga, R. L. M. A. P. C; Matheesha, D. M. K; Noman, A. A; De Silva, K. H. V. T. A; Tissera, M; Rupasinghe, LThe recent advancements in deep learning and other related technologies have led to improvements in various areas such as computer vision, bio-informatics, and speech recognition etc. This research mainly focuses on a problem with synthetic speech and speaker diarization. The developments in audio have resulted in deep learning models capable of replicating natural-sounding voice also known as text-to-speech (TTS) systems. This technology could be manipulated for malicious purposes such as deepfakes, impersonation, or spoofing attacks. We propose a system that has the capability of distinguishing between real and synthetic speech in group conversations.We built Deep Neural Network models and integrated them into a single solution using different datasets, including but not limited to Urban-Sound8K (5.6GB), Conversational (12.2GB), AMI-Corpus (5GB), and FakeOrReal (4GB). Our proposed approach consists of four main components. The speech-denoising component cleans and preprocesses the audio using Multilayer- Perceptron and Convolutional Neural Network architectures, with 93% and 94% accuracies accordingly. The speaker diarization was implemented using two different approaches, Natural Language Processing for text conversion with 93% accuracy and Recurrent Neural Network model for speaker labeling with 80% accuracy and 0.52 Diarization-Error-Rate. The final component distinguishes between real and fake audio using a CNN architecture with 94 % accuracy. With these findings, this research will contribute immensely to the domain of speech analysis.Publication Embargo A Geophone Based Surveillance System Using Neural Networks and IoT(2020 2nd International Conference on Advancements in Computing (ICAC), SLIIT, 2020-12-10) Supun Hettigoda, Chamath Jayaminda; Amarathunga, U.; Wijesundara, M.; Wijekoon, J.; Thaha, S.Securing our assets and properties from intruders and thieves has become increasingly challenging as intruders become technology aware. The most common approach to monitor physical assets is CCTV. However, this approach has a number of technical limitations in addition to the cost. The CCTV camera location is visible to the intruder and intruder can also identify possible blind spots in the CCTV coverage area. In this paper, we introduce a novel method to secure physical assets using Geophones, Neural Networks, and IoT Platforms. This can either be used stand alone or to complement existing CCTV systems. In this approach, the system monitors vibrations on ground to detect intruders. We have achieved up to 93.90% overall accuracy for person identification. The system is invisible to intruders and covers a large area with a smaller number of nodes, thereby reducing the cost of ownership.Publication Embargo Smart Office Automation System for Covid Prevention(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Rajapaksha, R.A.D.S.; Costa, L.S.; Prasanna, P.L.U.S.C.; Disanayaka, A.P.D.; Senarathne, A. N.; Wijekoon, Janaka L.Today, this coronavirus is spread all around the world. Most organizations and businesses start to think about how to continue their business in a situation like COVID-19 and their employees’ health and business security. To avoid and be safe from this type of disease, there are some common rules to follow. Keeping a distance, wearing a mask, cleaning our hands, are some health guidelines from them. According to the current situation, many inventors are trying and have already given some solutions to avoid these kinds of situations aligning with health guidance’ provided by WHO. With the advantage of advanced modern-day technologies and ideas, researchers started to think about how to face situations like these with the new technologies and found that many users are highly interested and motivated with automated systems. Thus, from this study, we aim to provide a fully automated office management system to prevent corona with advanced technology in combination with IoT technologies, Machine learning, Cloud technologies, and sensor technologies. Considering the security aspect, Controlling the main entrance, identifying, ensuring user’s authentication before entering the building, and monitoring employee activities are very significant aspects of the study. As the result of the study, the combination of IoT technologies and Machine Learning with deep learning mechanisms have guaranteed organizational business continuity, employees' health, and security.Publication Embargo Career Aura – Smart Resume and Employment Recommender(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Dissanayake, K.; Mendis, S.; Subasinghe, R.; Geethanjana, D.; Kasthurirathna, D.Recruitment and Job seeking are two major factors that are directly proportional to each other. Due to the competitive nature of the present world, the process of acquiring the best resource effectively and efficiently has become a challenging aspect for the companies. As a result, modern job portals have become increasingly popular to address the challenges identified in the early recruitment and job search process. The purpose of this research is to introduce an optimal solution to address the ineffective areas identified in the job and recruitment domain which can further enhance the recruitment and job seeking decisions by utilizing deep learning and sentiment analytic approach along with descriptive analysis. The proposed system recommends the relevant job opportunities by omitting the irrelevant job advertisements for job hunters who are interested in the IT job domain while they input their resume to the system and additionally, they can improve their career decisions by adhering to the prediction schemes. Moreover, the system facilitates recruiters to headhunt top talents efficiently once they input job requirements to the system and candidate suggestions are not only made depending on their resume information but also analyzing their LinkedIn endorsements.