EAI Endorsed Transactions on Context-aware Systems and Applications https://publications.eai.eu/index.php/casa <p>EAI Endorsed Transactions on Context-aware Systems and Applications (CASA) is a place for highly original ideas about how context-aware systems are going to shape networked computing systems of the future. Hence, it focuses on rigorous approaches and cutting-edge solutions which break new ground in dealing with the properties of context-awareness.</p> <p> </p> en-US <p>This is an open-access article distributed under the terms of the Creative Commons Attribution <a href="https://creativecommons.org/licenses/by/3.0/" target="_blank" rel="noopener">CC BY 3.0</a> license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.</p> publications@eai.eu (EAI Publications Department) publications@eai.eu (EAI Support) Wed, 29 Mar 2023 12:24:15 +0000 OJS http://blogs.law.harvard.edu/tech/rss 60 Predicting Breast Cancer with Ensemble Methods on Cloud https://publications.eai.eu/index.php/casa/article/view/2788 <p class="ICST-abstracttext"><span lang="EN-GB">There are many dangerous diseases and high mortality rates for women (including breast cancer). If the disease is detected early, correctly diagnosed and treated at the right time, the likelihood of illness and death is reduced. Previous disease prediction models have mainly focused on methods for building individual models. However, these predictive models do not yet have high accuracy and high generalization performance. In this paper, we focus on combining these individual models together to create a combined model, which is more generalizable than the individual models. Three ensemble techniques used in the experiment are: Bagging; Boosting and Stacking (Stacking include three models: Gradient Boost, Random Forest, Logistic Regression) to deploy and apply to breast cancer prediction problem. The experimental results show the combined model with the ensemble methods based on the Breast Cancer Wisconsin dataset; this combined model has a higher predictive performance than the commonly used individual prediction models.</span></p> Au Pham, Tu Tran, Phuc Tran, Hiep Huynh Copyright (c) 2023 EAI Endorsed Transactions on Context-aware Systems and Applications https://creativecommons.org/licenses/by/3.0/ https://publications.eai.eu/index.php/casa/article/view/2788 Wed, 29 Mar 2023 00:00:00 +0000 IoT based Human Activity Recognition using Deep learning https://publications.eai.eu/index.php/casa/article/view/2682 <p>Artificial intelligence and the Internet of things (IoT) are the fastest and latest growing technologies that can handle a huge amount of data in computing services. This paper presents a smart human activity recognition system based on IoT that can be used for surveillance purposes working as IoT-based armour. Pose estimation model viz. MoveNet has been employed to extract the anatomical key points from RGB video frames. Different subjects from different camera angles were employed to make the approach person-independent. Diverse Machine learning models such as Decision tree, support vector machines, XGboost, and random forest classifiers were employed using extracted keypoints for training the model for estimating human activity during posture estimation monitoring. SMS are sent to the designated person with the raising of buzzer alarm in case of anomalous behaviour detection.</p> Salman Siddiqui, Anwar Ahmad, Ankur Varshney Copyright (c) 2023 EAI Endorsed Transactions on Context-aware Systems and Applications https://creativecommons.org/licenses/by/3.0/ https://publications.eai.eu/index.php/casa/article/view/2682 Thu, 20 Apr 2023 00:00:00 +0000 Linear Quadratic Gaussian with noise signals for lateral and longitudinal of F-16 https://publications.eai.eu/index.php/casa/article/view/2781 <p>Today, classical control methods are still widely used because of their excellent performance in a working enviroment with noise signals. Besides, they are suitble for functiions of the system : operations to control a machine are more flexible, easy to perform, less unwanted risks occur, the efficiency of controlling a system better. In the early years of the 21<sup>st</sup> century, traditional algorithms still promote their effects. Besides the traditional control methods, the author has applied more moderm and smarter algorithms such as adjusting Linear Quadratic Gaussian&nbsp; (LQG) to control a system on the ground or a system moving in the air. In the paper, LQG regulator is applied to a flight model to demonstrate its effectiveness in all cases. LQG regulator has not been applied before for this model. Results are as expected by the author for the working enviroment with noise signals affecting the system. Kalman filter used in this paper has shown its usefulness in the problem of dealing with unwanted signals. Simulation is done by Matlab.</p><p>&nbsp;</p> Nguyen Danh Copyright (c) 2023 EAI Endorsed Transactions on Context-aware Systems and Applications https://creativecommons.org/licenses/by/3.0/ https://publications.eai.eu/index.php/casa/article/view/2781 Thu, 20 Apr 2023 00:00:00 +0000 Deep Biased Matrix Factorization for Student Performance Prediction https://publications.eai.eu/index.php/casa/article/view/3147 <p>In universities that use the academic credit system, selecting elective courses is a crucial task that can have a significant impact on a student's academic performance. Students who perform poorly in their courses may receive formal warnings or even face expulsion from the university. Thus, a well-designed study plan from a course recommendation system can play an essential role in achieving good academic performance. Additionally, early warnings regarding challenging courses can help students better prepare and improve their chances of success. Therefore, predicting student performance is a vital component of both the course recommendation system and the academic advisor's role. To this end, numerous studies have addressed the prediction of student performance using various approaches such as association rules, machine learning, and recommender systems. More recently, personalized machine learning approaches, particularly the matrix factorization technique, have been used in the course recommendation system. However, the accuracy of these approaches in predicting student performance still needs improvement. To address this issue, this study proposes an approach called Deep Biased Matrix Factorization, which carries out deep factorization via multi-layer to enhance prediction accuracy. Experimental results on an educational dataset have demonstrated that the proposed approach can significantly improve the accuracy of student performance prediction. By using this approach, universities can better recommend elective courses to their students as well as predict student performance, which can help them make informed decisions and achieve better academic outcomes.</p> Thanh-Nhan Huynh-Ly, Huy-Thap Le, Nguyen Thai-Nghe Copyright (c) 2023 EAI Endorsed Transactions on Context-aware Systems and Applications https://creativecommons.org/licenses/by/3.0/ https://publications.eai.eu/index.php/casa/article/view/3147 Thu, 20 Apr 2023 00:00:00 +0000 Polarity assignment method (PAM), ANN, Neural networks strategy for the data of PAM for the single degree of freedom flexible joint robot https://publications.eai.eu/index.php/casa/article/view/2783 <p>This paper “describes” the investigation of the stability of a single Degree of Freedom (DOF) flexible robotic arm by the diagrams shown below. The derived model is based on Euler- Lagrange approach. Exploration of a flexible robotic arm with using state-of-the-art controllers is essential for intelligent applications. These robot arms have joints that work independently of each other in order to create a smooth connection between joints. They still ensures the natural properties like a real human arm. The use of polarity assignment method&nbsp; “helps” the system to achieve desired output signals which has not been thoroughtly studied before for this system. The author can also compare the effectiveness of control methods for this system to find the most effective method for control strategies. In particular, ANN ( artificial neural network) is the most modern technique currently&nbsp; applied to this system to investigate the security and stability of the system through this program. This is new and it has never been used before for a system of this type. Neural networks strategy has been implemented in this paper as an application of artificial intelligence. It has successfully performed a mission in re-simulating functions of another control method: Polarity assignment method. Simulation results are done by Matlab.</p> Nguyen Danh Copyright (c) 2023 EAI Endorsed Transactions on Context-aware Systems and Applications https://creativecommons.org/licenses/by/3.0/ https://publications.eai.eu/index.php/casa/article/view/2783 Thu, 20 Apr 2023 00:00:00 +0000