2022 6th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)最新文献

{"title":"Predicting Undergraduates Stress Level Using Eye Tracking","authors":"Murugesh Sujan, Pradeesha L. S. Jayasinghe","doi":"10.1109/SLAAI-ICAI56923.2022.10002457","DOIUrl":"https://doi.org/10.1109/SLAAI-ICAI56923.2022.10002457","url":null,"abstract":"Stress is a feeling of emotional or physical tension, this makes a serious influence among undergraduates. There is a lack of stress prediction techniques that can detect what sort of stress level undergraduates are having from time to time. This research explored the prediction of undergraduate stress levels using eye-tracking. In this study, 306 PSS-10 data sets and 30600 eye-tracking data (Images) were collected from undergraduates at the University of Ruhuna using a questionnaire and a third-party eye-tracker application. PSS-10 (Perceived Stress Scale −10) and CNN (Convolutional Neural Network) was used to predict undergraduate stress levels. Stress levels are determined by the PSS-10 analysis, and divided into three classes: High, Moderate, and Low. Eye tracking data and stress classes are correlated in data pre-processing phase. The eye tracking images takes as input for well define eye tracking classification model; the model predict the stress level of the given undergraduate eye tracking data. According to the results, it was concluded that 19.7% of the undergraduates were in very high level of stress, 71.8% were in moderate level of stress and 8.5% were in low level of stress. However, it is certain that most of the undergraduates suffer from moderate levels of stress. The research will help predict undergraduate stress levels more accurately, and aid undergraduates managing their stress levels in academic life.","PeriodicalId":308901,"journal":{"name":"2022 6th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115114872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Deep Learning Based Approach for Janya Raga Classification in Carnatic Music","authors":"P. Kavitha, J. Charles, L. S. Lekamge","doi":"10.1109/SLAAI-ICAI56923.2022.10002700","DOIUrl":"https://doi.org/10.1109/SLAAI-ICAI56923.2022.10002700","url":null,"abstract":"Janya Ragas are Carnatic music ragas derived from the fundamental ragas called Melakarta Raga, by the permutation and combination of various ascending and descending swaras. Raga recognition is an important task, essential to research in Music Information Retrieval in Indian Classical Music. Even though the automatic raga recognition methods have been widely adopted in Carnatic music, most of the existing methods are restricted only to Melakarta Ragas. It is an important task to identify the Melakarta Raga of a Janya Raga, especially for improved music recommendation performance. In this study, we used deep learning-based approach to address this problem. Music files were collected for 65 Janya Ragas belonging to seven Melakarta Ragas. Classification-based supervised deep learning models: 1D CNN, LSTM and 1D CNN-LSTM were used in the study. The models were implemented to learn similarities from 1–20 mean values of Mel-Frequency Cepstral Coefficients (MFCCs) features of audio samples, by using TensorFlow and Keras APIs. The results revealed that the 1D CNN-LSTM model outperformed the other models with an accuracy of 82.0%. In the future, 1D CNN-LSTM based Siamese neural networks can be introduced to reduce the dependence on large amounts of labeled audio data.","PeriodicalId":308901,"journal":{"name":"2022 6th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"235 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121070971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SLAAI-ICAI 2022 Panel Discussion","authors":"","doi":"10.1109/slaai-icai56923.2022.10002639","DOIUrl":"https://doi.org/10.1109/slaai-icai56923.2022.10002639","url":null,"abstract":"","PeriodicalId":308901,"journal":{"name":"2022 6th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124539364","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using Machine Learning and Feedback Filters for Localization in Ambient Assisted Living (AAL) Applications","authors":"Mwp Maduranga, H.K.I.S. Lakmal, Rhns Jayathissa, Wmsrb Wijayarathne, Wamm Wanniarachchi","doi":"10.1109/SLAAI-ICAI56923.2022.10002492","DOIUrl":"https://doi.org/10.1109/SLAAI-ICAI56923.2022.10002492","url":null,"abstract":"Machine Learning (ML) based Indoor Positioning Systems (IPS) are more efficient than other classical localization algorithms developed. Rather, efficiency these ML based IPS are easy to deploy in real environments. ML-based IPS initiates cognitive Location Based Services (LBS) in IoT. Among these LBSs, Ambient Assisted Living applications are curtailed. In this paper, we experiment with how to use ML classifiers in such an AAL application. During the experiments supervised classifiers Linear Discriminant Analysis Model, Quadratic Discriminant Analysis Model, Naïve Bayes Classifier Model, Decision Tree Classifier Model, and K-Nearest Neighbor Model were trained using an available Received Strength Indicator (RSSI) dataset to predict the location of a human. Algorithm Quadratic Discriminant Analysis provides a 25.88% misclassification error and 25.86% generalization error.","PeriodicalId":308901,"journal":{"name":"2022 6th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127561114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SLAAI-ICAI 2022 Cover Page","authors":"","doi":"10.1109/slaai-icai56923.2022.10002427","DOIUrl":"https://doi.org/10.1109/slaai-icai56923.2022.10002427","url":null,"abstract":"","PeriodicalId":308901,"journal":{"name":"2022 6th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115407574","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ruminations and Bioethics on AI for Humanity – A Review","authors":"Anuradha Kurunayakage, Dpm Lakshan, R. Kathriarachchi","doi":"10.1109/SLAAI-ICAI56923.2022.10002590","DOIUrl":"https://doi.org/10.1109/SLAAI-ICAI56923.2022.10002590","url":null,"abstract":"The implications of AI on human culture are intensely contested. There are people who believe that AI has a positive impact on people’s daily lives because it can perform mundane and even complex activities more efficiently and effectively than humans. Although AI has many potential applications, it also raises important public policy questions, and more work needs to be done to create safe human-centred AI systems. While recognizing the progress made in the field of artificial intelligence, this review contributes to the ongoing conversation about how the law interacts with emerging technologies, what effect this has on society, and why it’s important to ensure openness, privacy, and protection of all parties that stand to benefit from these developments as the objectives. Human rights, democratic principles, and the risks of bringing one’s own prejudices into one’s digital interactions are among the most pressing concerns. Unlike humans, AI has no emotions or character of its own, hence it’s vital to highlight the bioethics of the arena of AI. However, contemporary AI has a huge effect on peoples’ daily lives and interpersonal interactions. To meet this new challenge, people need to think about and build new principles of AI bioethics to provide standards for AI technology to follow so that humanity can reap the benefits of AI advancements. Because of the unique challenges posed by these developing technologies, bioethical frameworks must be adapted to deal with them, and the development of these automated systems also needs to be tailored to incorporate bioethical principles. As AI develops, people will have to learn how to interact with something that isn’t human. However, now humans must contend with something that is also unnatural and unnaturally created: AI. Experts in the field of artificial intelligence were surveyed via the Delphi method to focus on the human rights and legal implications, bioethics of AI and how it is now being discussed, argued, addressed, and how human rights concepts are being impacted.","PeriodicalId":308901,"journal":{"name":"2022 6th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127359825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi Agent Based Intelligent Personal Research Assistant","authors":"A. Karunananda, Thushari P. Silva, Dewmal Handapangoda, Sadika Sumanapala","doi":"10.1109/SLAAI-ICAI56923.2022.10002662","DOIUrl":"https://doi.org/10.1109/SLAAI-ICAI56923.2022.10002662","url":null,"abstract":"Since the very early days, developments of mankind have been energized by research. Despite people having developed many research methods, including Scientific Method, Milestone Approach, and IMRD, research conduct remains a challenge. We have examined various research methods and discovered reading and writing as the foundation of all research methods regardless of a novice or an experienced researcher. This was practised even before formally acknowledging what we called research methods today. We developed an Intelligent Personal Research Assistant, InPRA, which guides a researcher in systematically reading past research papers and, more importantly, developing research proposals, progress reports, thesis, and papers while doing the research, without waiting for the last moment. While InPRA is based on the reading-writing model of research, within InPRA, a researcher can access research management tools, scientific writing tools, specific research methods and other resources. InPRA has been developed as Multi Agent System to enable interaction among the steps in the research process beyond sequential processing. Research students and experienced researchers like supervisors have evaluated the guidance of InPRA to generate material for a project proposal, which is the first document in a research process. According to the evaluation results, the multi-agent-based approach in InPRA could outperform traditional text-based search approaches. Moreover, based on survey results, the system is very useful for researchers as it generates more relevant results.","PeriodicalId":308901,"journal":{"name":"2022 6th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"44 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131435543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generative Adversarial Neural Networks based Oversampling Technique for Imbalanced Credit Card Dataset","authors":"S. El Kafhali, Mohammed Tayebi","doi":"10.1109/SLAAI-ICAI56923.2022.10002630","DOIUrl":"https://doi.org/10.1109/SLAAI-ICAI56923.2022.10002630","url":null,"abstract":"The imbalanced dataset is a challenging issue in many classification tasks. Because it leads a machine learning algorithm to poor generalization and performance. The imbalanced dataset is characterized as having a huge difference between the number of samples that contain each class. Unfortunately, various resampling methods are proposed to solve this problem. In our work, we target enhancing the handling of the imbalanced dataset using a new oversampling technique based on generative adversarial neural networks. Our method is benchmarked against the widely used oversampling technique including the synthetic minority oversampling technique (SMOTE), random oversampling technique (ROS), and the adaptive synthetic sampling approach(ADSYN). Additionally, three machine learning algorithms are used for evaluation. The outcome of our experiments on a real-world credit card dataset shows the strong ability of the proposed solution against the competitive oversampling techniques to overcome the imbalanced problem in the European credit card dataset.","PeriodicalId":308901,"journal":{"name":"2022 6th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128014225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic Sri Lankan Traditional Musical Instruments Recognition In Soundtracks","authors":"K.E. Nirozika, S. Thulasiga, T. Krishanthi, M. Ramashini, N. Gamachchige","doi":"10.1109/SLAAI-ICAI56923.2022.10002483","DOIUrl":"https://doi.org/10.1109/SLAAI-ICAI56923.2022.10002483","url":null,"abstract":"Musical instrument recognition is an essential aspect of music information retrieval, and nowadays, audio signal processing is an active research domain. Automatic identification of traditional music instruments from the soundtracks is one of the applications which combines signal processing and machine learning techniques. So, this paper presents an application to automatically recognise the Sri Lankan traditional music instruments from long music tracks. Soundtracks of Ten (10) instruments were collected from various domain experts to demonstrate the proposed method. Four different features are extracted and compared from collected soundtracks to find the most suitable feature for Sri Lankan traditional musical instrument sounds. Using Principal Component Analysis (PCA), the six (06) most significant features were selected from twenty (20) Mel Frequency Cepstral Coefficients (MFCC) features. Then two (02) machine learning algorithms (K-NN, SVM) are used to classify the traditional instruments’ soundtracks separately and classified. By outperforming other models, the SVM model with MFCC features provided 86.8% of the highest accuracy.","PeriodicalId":308901,"journal":{"name":"2022 6th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130558173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dynamic Ontology Generation using Relational Schema","authors":"Hansika Gunasekara, Thushari P. Silva","doi":"10.1109/SLAAI-ICAI56923.2022.10002666","DOIUrl":"https://doi.org/10.1109/SLAAI-ICAI56923.2022.10002666","url":null,"abstract":"The ontology is one of the best methods of defining the semantic model of the data combined with the associated domain knowledge. It can be used in formulating some data searching strategies. Ontologies can also define links between different types of semantic knowledge. However, ontology building is a time-consuming and complicated task that needs expert participation. Therefore, the automatic generation of ontology is a crucial topic among researchers. Furthermore, to take the maximum output of the semantic systems needs a dynamic update of not only the data but relationships accordingly. This paper proposes a method of automatic generation of the dynamic ontology using a relational database and expanding dynamically when a new concept is needed to add. As per the knowledge, this is the first approach to updating the ontology by dynamically using the updated relational schema. The proposed method shows higher accuracy in the evaluation when generating and updating all ontology components dynamically.","PeriodicalId":308901,"journal":{"name":"2022 6th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131039514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}