19c96fd517d854497e8-247f 20220216013418513 beie:beie director@blueeyesintelligence.org WEB-FORM International Journal of Innovative Technology and Exploring Engineering IJITEE 22783075 10.35940/ijitee https://www.ijitee.org/ 03 30 2021 10 5 IRF-SIC Laboratory, Faculty of Science, Ibn Zohr University, Agadir-Morocco. Ali El mezouary Brahim Hmedna IRF-SIC Laboratory, Faculty of Science, Ibn Zohr University, Agadir-Morocco. Omar Baz Department, IRF-SIC Laboratory, Faculty of Science, Department, Ibn Zohr University, Agadir-Morocco. Massive Open Online Course (MOOC) seems to expand access to education and it present too many advantages as: democratization of learning, openness to all and accessibility on a large scale, etc. However, this new phenomenon of open learning suffers from the lack of personalization; it is not easy to identify learners’ characteristics because their heterogeneous masse. Following the increasing adoption of learning styles as personalization criteria, it is possible to make learning process easier for learners. In this paper, we extracted features from learners’ traces when they interact with the MOOC platform in order to identify learning styles in an automatic way. For this purpose, we adopted the Felder-Silverman Learning Style Model (FSLSM) and used an unsupervised clustering method. Finally, this solution was implemented to clustered learners based on their level of preference for the sequential/global dimension of FSLSM. Results indicated that, first: k-means is the best performing algorithm when it comes to the identification of learning styles; second: the majority of learners show strong and moderate sequential learning style preferences. 03 30 2021 40 49 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijitee.org true 10.35940/ijitee.E8673.0310521 https://www.ijitee.org/portfolio-item/E86730310521/ Department of Mechanical Engineering, D.N. Patel College of Engineering, Shahada (Maharashtra), India. Mr. Sandeep Suresh Patil Prof. Harichandra K. Chavhan Assistant Professor, D.N. Patel College of Engineering, Shahada (Maharashtra), India. Prof. Umesh U Patil Assistant Professor, D.N. Patel College of Engineering, Shahada (Maharashtra), India. Prof. Nilesh Damodar Patel Assistant Professor, D.N. Patel College of Engineering, Shahada (Maharashtra), India. Metal matrix composite is used in engineering applications due to its superior mechanical properties. MMC’s are reinforced with particle fiber, whisker, and particulate. The size of particulates used is classified as micro, nano, and macro. The particulate reinforced MMC’s have excellent form-ability compared to fiber and whisker composite. Metal matrix composite has outstanding wear, heat resistance, and excellent mechanical properties. Many authors have been stated the property as its ability of workpiece material to be machined or it refers to workpiece response to machining or it is normally applied to the machining properties of work material or it indicates how easily and fast a material can be machined. MMC materials are difficult to machine with a superior surface finish. In this study Al6061 with Silicon Carbide and Graphite are fabricated with 5 weight % using squeeze casting route. Tensile strength and hardness are tested according to ASTM standards and as a result, there was an increase in tensile strength and hardness of MMC. Machining process parameters plays a vital role in defining surface roughness. This machining parameters are to be optimized to get the better surface finish results. Taguchi techniques is used. To optimized the machining parameters affecting machining of MMC for surface roughness are identified. Orthogonal array L9 was selected based on three parameters with three levels. There is a vital role played by the feed rate in increasing the surface roughness of the material. Relevant process parameters considered for a better roughness of the surface are, cutting speed 300RPM, the rate of feed 0.13 mm/rev, and the depth of cut 0.4mm. 03 30 2021 93 96 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijitee.org true 10.35940/ijitee.E8683.0310521 https://www.ijitee.org/portfolio-item/E86830310521/ Ph. D Research Scholar, Tiruppur Kumaran College for Women, PG and Research Department of Computer Science, Tiruppur. V. Deepa Dr. K. Rajeswari Associate Professor, PG and Research Department of Computer Science, Tirppur Kumaran College for Women, Tiruppur. Internet of Things (IoT) technology helped the development of healthcare from face-to-face consulting to the telemedicine. Smart healthcare system in IoT environment monitored the patient basic health signs such as heart rate, body temperature, and hospital room condition in real-time applications. The IoT and big data is an important challenge in many fields including smart healthcare systems due to its significance. Big data is employed to analyse the huge volume of data. Big data are significantly used in healthcare technique to determine the normal and abnormal patient condition. The doctors are easily analysed the patient condition in a short time. This system is very easy to design and use. It is employed to enhance the present healthcare system which preserves the lot of lives from death. Healthcare monitoring system in hospitals has experienced large development and portable healthcare monitoring systems with new technologies. Connected healthcare is an essential solution for hospital to record and analyse the patient data and to save money. The clustering and classification methods are used in existing methods. The clustering method is employed to group the similar data. The classification method is utilized to classify the patient data. A lot of healthcare technique was introduced by many researchers ranging from diagnosis to treatment and prevention on efficient e-health monitoring system. But, the accuracy level was not improved and time consumption was not reduced by existing techniques. In order to address these problems, different methods and techniques were reviewed for performing the e-healthcare monitoring system with big data. The machine learning techniques are used for efficient diseased patient health monitoring through the effective performance of feature selection, clustering and patient classification with increase the accuracy and minimum time consumption. The results are is performed using on different factors such as clustering accuracy, clustering time, classification accuracy, classification time, and error rate with respect to number of patient data. 03 30 2021 97 102 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijitee.org true 10.35940/ijitee.E8685.0310521 https://www.ijitee.org/portfolio-item/E86850310521/ PG Student, Faculty of Architecture and Planning, Dr. A.P.J. Abdul Kalam Technical University, Lucknow, India. Lalit Akash Verma Farheen Bano Associate Professor, Faculty of Architecture and Planning, Dr. A.P.J. Abdul Kalam Technical University, Lucknow, India. Studies have shown the relevance of the courtyard houses and passive strategy that plays a significant role in energy reduction, providing thermal comfort and visual comfort. Generally, designing the courtyards was considered suitable for thermal comfort. North India lies in the composite climatic zone, and courtyard houses in this region have a distinctly vernacular style. Many studies all around the world were conducted to analyse courtyard houses and followed different methodologies. The aim of this paper is to uncover and formulate a research methodology to analyse effective daylighting in courtyard houses of composite climate; approximately forty research papers were reviewed to find out the research methodology. The year of publication, climate zone, sky models used, weather file, building type, verifying method, simulation tools, daylight matrices, and methodology adopted were studied in the reviewed literature to formulating the methodology. The study concludes that experimental models were commonly used for daylight analysis, moreover climate-based sky can be used for detailed simulation instead of the Daylight factor with overcast sky conditions. 03 30 2021 103 116 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijitee.org true 10.35940/ijitee.E8687.0310521 https://www.ijitee.org/portfolio-item/E86870310521/ Dept. of Electronics and Communications Eng, Kwangwoon Univ, Seoul, Korea. Hyung-Hwa Ko GeunTae Kim ABH Inc, Ulsan, Republic of Korea. Hyunmin Kim Telecons Inc, Seoul, Republic of Korea. Since deep learning applications in object recogni-tion, object detection, segmentation, and image generation are needed increasingly, related research has been actively conducted. In this paper, using segmentation and style transfer together, a method of producing desired images in the desired area in real-time video is proposed. Two deep neural networks were used to enable as possible as in real-time with the trade-off relationship between speed and accuracy. Modified BiSe Net for segmentation and Cycle GAN for style transfer were processed on a desktop PC equipped with two RTX-2080-Ti GPU boards. This enables real-time processing over SD video in decent level. We obtained good results in subjective quality to segment Road area in city street video and change into the Grass style at no less than 6(fps). 03 30 2021 50 56 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijitee.org true 10.35940/ijitee.E8689.0310521 https://www.ijitee.org/portfolio-item/E86890310521/