Volume-10 Issue-5, January 2022 – International Journal of Recent Technology and Engineering (IJRTE)

E67100110522

IJRTE Journal — Fri, 04 Feb 2022 07:05:39 +0000

Social Distancing Detector using Deep Learning
Manthri Sriharsha¹, Lalith Sai Allani², Akhila Gandla³, Sowjanya Jindam⁴
¹Manthri Sriharsha*, Department of Information Technology, MVSR Engineering College, Osmania University, Hyderabad (Telangana), India.
²Sowjanya Jindam, Department of Information Technology, MVSR Engineering College, Osmania University, Hyderabad (Telangana), India.
³Akhila Gandla, Department of Information Technology, MVSR Engineering College, Osmania University, Hyderabad (Telangana), India.
⁴Lalith Sai Allani, Department of Information Technology, MVSR Engineering College, Osmania University, Hyderabad (Telangana), India.
Manuscript received on December 20, 2021. | Revised Manuscript received on January 30, 2022. | Manuscript published on March 30, 2022. | PP: 146-149 | Volume-10 Issue-5, January 2022. | Retrieval Number: 100.1/ijrte.E67100110522 | DOI: 10.35940/ijrte.E6710.0110522
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Social Distancing is the best possible way to detain the spread of Covid-19. Even though vaccine has been found and working effectively in saving the lives of people, social distancing is necessary to reduce the spread of virus to maximum extent which not only saves people from being infected but also reduces the impact of spreading of the disease. In our proposed system, we use Deep Learning with python to monitor social distancing in public places. This is a software tool that monitor if people are maintaining proper social distancing norms or not by analyzing real time video streams from CC camera. We use YOLO Model which is trained by COCO dataset.
Keywords: Social Distancing, Deep Learning, YOLO, COCO. Abbreviations and Acronyms, YOLO-You Only Look Once, COCO-Common Objects in Context, DNN- Deep Neural Network
Scope of the Article: Deep Learning

Download PDF

The post E67100110522 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E67290110522

IJRTE Journal — Sat, 29 Jan 2022 12:40:33 +0000

Mechanical and Durability Properties of Kernelrazzo Floor Finish: A Review
Ts. ABAS Noor Faisal¹, Olanrewaju Sharafadeen Babatunde Owolabi²
¹Dr. Ts ABAS Noor Faisal, School of Housing, Building and Planning, Universiti Sains Malaysia, Penang Island, Malaysia.
²OLANREWAJU Sharafadeen Babatunde Owolabi, School of Housing, Building and Planning, Universiti Sains Malaysia, Penang Island, Malaysia.
Manuscript received on December 28, 2021. | Revised Manuscript received on January 28, 2022. | Manuscript published on January 30, 2022. | PP: 134-145 | Volume-10 Issue-5, January 2022. | Retrieval Number: 100.1/ijrte.E67290110522 | DOI: 10.35940/ijrte.E6729.0110522
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: This writes up analyse earlier investigation on the major benefits and problems associated with the utilization of palm kernel shell as limited substitute of marble chippings as a local material in the production of kernelrazzo floor finish tiles. Although papers on kernelrazzo floor finish are few and one hundred and one (101) current related papers on palm kernel shell concrete were used to produce lightweight concretes and former literatures was assessed on the durability and strength of kernelrazzo floor finish. Rarely work has been done on incorporating palm kernel shell as incomplete substitute of marble in the production of kernelrazzo floor finish tiles. Palm kernel shell is one of the waste agricultural products obtained from production palm oil which is originating from the palm oil industry which common in Africa and Asia. Properties and characteristics of palm kernel shell (PKS) and marble chippings are summarized as specific gravity to include shape, thickness and texture include bulk density, water absorption and moisture content. Mechanical properties tests on palm kernel shell also include abrasion property and impact resistivity. Lightweight properties of concrete produced with palm kernel shell (PKS) have a limited substitute of coarse aggregate which include chemical and physical properties of granite dust were appraised. Mechanical properties of kernelrazzo floor finish tiles that were reviewed include compressive strength; curing and minimum requirement for Terrazzo floor finish and final for the area covered on this review is the consequence of acids, bases, and salts on the durability and strength of kernelrazzo floor finish.
Keywords: Mechanical properties, durability, palm kernel shell, kernelrazzo, marble chippings, granite dust
Scope of the Article: Civil Engineering

Download PDF

The post E67290110522 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E67830110522

IJRTE Journal — Sat, 29 Jan 2022 12:10:09 +0000

Performance Evaluation and Analysis of OFDM signal using Discretization
Geetha M N¹, U B Mahadevaswamy²
¹Mrs. Geetha M N*, Assistant Professor, Department of Electronics & Communication Engineering, Vidyavardhaka College of Engineering, Mysuru, India.
²Dr. U B Mahadevaswamy, Professor, Department of Electronics and Communication Engineering, Sri Jayachamarajendra college of Engineering, Mysuru, India.
Manuscript received on January 20, 2022. | Revised Manuscript received on January 20, 2022. | Manuscript published on January 30, 2022. | PP: 125-132 | Volume-10 Issue-5, January 2022. | Retrieval Number: 100.1/ijrte.E67830110522 | DOI: 10.35940/ijrte.E6783.0110522
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The Transmission of signals from one end to other end without intrusions and efficient manner is most hilarious task. Accordingly, OFDM method is utilized for transmission which has better resistance against the multipath fading and yields better efficiency among other wireless communication processes. Even though bounded with more advantages PAPR problem is undesirable for OFDM which in turn readily reduces the data rate. Hence, PAPR Problem reduction improves the quality of service. Thus the reduction of PAPR is done by utilizing adaptive clipping and windowing methods with interdependent discretization approach by utilizing CAIM algorithm, which arrange signal in equal discrete level and makes clipping with reduced BER and Planck-tapper window further yields renovated signal with amplitude varied linear signal which in turn mitigates the PAPR and also allows the signal to flow on exact discrete interval which readily improves the efficiency to a great extent. This proposed methodology is implemented in MATLAB software.
Keywords: Class-Attribute Interdependency Maximization, Quadrature Amplitude Modulation, Peak to average power ratio, Orthogonal frequency division multiplexing.
Scope of the Article: Analysis of OFDM signal

Download PDF

The post E67830110522 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E67820110522

IJRTE Journal — Sat, 29 Jan 2022 12:03:20 +0000

The Intuitive Supervision Model (ISM) using Convolution Neural Networks (CNN) and Unscented Kalman Filters (UKF)
Noopur Soni¹, Agya Mishra²
¹Noopur Soni*, Department of Electronics and Telecommunication, Jabalpur Engineering College, Jabalpur, (M.P), India.
²Dr. Agya Mishra, Department of Electronics and Telecommunication, Jabalpur Engineering College, Jabalpur (M.P), India.
Manuscript received on January 20, 2022. | Revised Manuscript received on January 27, 2022. | Manuscript published on January 30, 2022. | PP: 117-124 | Volume-10 Issue-5, January 2022. | Retrieval Number: 100.1/ijrte.E67820110522 | DOI: 10.35940/ijrte.E6782.0110522
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Radio frequency identification technology is one of the fastest-growing technologies in the realms of navigation, medical, robotics, communication system, logistics, security, safety, etc. Surveillance is one of the important fields where high accuracy and fast response are needed. In this research work, RFID sensors are used to track moving objects with an intelligent supervision model. The sophisticated surveillance model employs neural networks followed by an adaptive filtering technique based on an Unscented Kalman filter. A neural network is also one of the most efficient and powerful technology in the field of learning and data processing capability. A neural network has the capability of processing a mammoth amount of data because of this feature its efficiency and accuracy are quite high. This model localizes N number of objects/targets through an intelligent surveillance model, picks a random object from this pool of localized objects to track, categorizes their movement through a controlled checkpoint, and calculates the distance traveled by the moving object /target. Experimental results show that the proposed model can locate multiple-objects with the help of multiple input RFID antennas and tags and track them concerning to the RFID antennas with high accuracy and stability in the complex indoor environment and this intuitive model can be effectively implemented at the airport, railway station, shopping mall, retail management, as well as any other surveillance purpose. For this research work number of authors work, is reviewed and based on literature review this model is designed.
Keywords: Adaptive Filtering, Convolution Neural Network (CNN), Deep Neural Network, Gauss-Newton Algorithm, Intelligent system, Indoor Positioning and tracking, Radiofrequency Identification (RFID), Unscented Kalman Filter (UKF), Received Signal Strength Indication (RSSI)
Scope of the Article: Electronics and Telecommunication

Download PDF

The post E67820110522 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E67680110522

IJRTE Journal — Fri, 28 Jan 2022 11:38:58 +0000

Implementation of Machine Learning Model to Predict Heart Problem
Shruti Patil¹, Mrunal Annadate²
¹Shruti Gurudas Patil*, Department of Electronics and Telecommunication Engineering, Prof. Dr. Vishwanath Karad MIT World Peace University, Pune (MH), India.
²Dr. Mrunal Ninad Annadate, Department of Electronics and Telecommunication Engineering, Prof. Dr. Vishwanath Karad MIT World Peace University, Pune (MH), India.
Manuscript received on January 16, 2022. | Revised Manuscript received on January 23, 2022. | Manuscript published on January 30, 2022. | PP: 117-122 | Volume-10 Issue-5, January 2022. | Retrieval Number: 100.1/ijrte.E67680110522 | DOI: 10.35940/ijrte.E6768.0110522
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: With the rapid growth of technology and data, the healthcare domain has emerged as one of the most important research areas in the modern period. Machine Learning is a novel method for disease prediction and diagnosis. This study demonstrates how machine learning can be used to forecast disease based on symptoms. Techniques of Machine learning such as Bayes, Random Forest, and SVM are used to forecast the disease on the supplied dataset. The research determines which algorithm is the best based on its accuracy. The accuracy of an algorithm is determined by its performance on a particular dataset. One of the most significant disorders is heart disease. We discovered machine learning models to predict heart problems in order to lower the incidence of death caused by heart disease. In this paper, we used a dataset from 1988 that included four databases: Cleveland, Hungary, Switzerland, and Long Beach V., and applied an algorithms to it to obtain the results. Previous studies had lower accuracy, therefore we focused on this research to enhance accuracy rate, precision, and recall which are very crucial parameters in medical field, in order to forecast heart problems and rescue patients. In this paper, we worked on different algorithms such as SVM, Random Forest, Naïve Bayes, Neural Network and Decision Tree. The model was implemented using the Python programming language. Analysis result indicates that SVM and Decision Tree algorithms have achieved highest accuracy which is 98.05%.
Keywords: Heart Disease, Random Forest, Machine Learning, Naïve Bayes, Pre-processing.
Scope of the Article: Electronics and Telecommunication

Download PDF

The post E67680110522 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E67810110522

IJRTE Journal — Fri, 28 Jan 2022 11:33:29 +0000

Synthesis of Magnetic Eggshell Modified with Polyethyleneimine for Aspirin Removal
Noor Fathiah Haziqah Othman¹, Norzita Ngadi², Abu Hassan Nordin³, Nur Aien Fatini Abd Latif⁴, Amir Asyraf Nasarudin⁵
¹Noor Fathiah Haziqah Othman*, Faculty of Chemical Engineering, Universiti Technologi Malaysia, Johor, Malaysia.
²Norzita Ngadi, Faculty of Chemical Engineering, Universiti Technologi Malaysia, Johor, Malaysia.
³Abu Hassan Nordin, Faculty of Chemical Engineering, Universiti Technologi Malaysia, Johor, Malaysia.
⁴Nur Aien Fatini Abd Latif, Faculty of Chemical Engineering, Universiti Technologi Malaysia, Johor, Malaysia.
⁵Amir Asyraf Nasarudin, Faculty of Chemical Engineering, Universiti Technologi Malaysia, Johor, Malaysia.
Manuscript received on January 19, 2022. | Revised Manuscript received on January 24, 2022. | Manuscript published on January 30, 2022. | PP: 113-116 | Volume-10 Issue-5, January 2022. | Retrieval Number: 100.1/ijrte.E67810110522 | DOI: 10.35940/ijrte.E6781.0110522
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The application of domestic waste as an economical and eco-friendly adsorbent has emerged among the most promising options for pharmaceutical remediation due to its high performance. Nonetheless, one of the most significant challenges of modified adsorbents is the difficulty in their recovery process, which includes separating adsorbents from cleaned water. This study synthesized and investigated a magnetic adsorbent derived from chicken eggshell (CE) modified with polyethyleneimine (PEI) for aspirin removal to address this issue. The chosen variables for the adsorbent synthesized were the ratio of CE:PEI (1:1, 1:2, 2:1, 2:0.5), the ratio of CE-PEI: magnet powder (2:1:2, 2:1:1, 2:1:0.5, 2:1:0.25). Adsorption studies were carried out to remove 0.1 g/l of aspirin. The results indicated that the optimal synthesis conditions for the magnetic chicken eggshell modified with polyethyleneimine (MCEP) are 2:1 for CE: PEI ratio, 2:1:1 ratio for CE-PEI to magnet particles and 120 minutes of crosslinking time.
Keywords: Adsorption, Polyethyleneimine, Chicken Eggshell, Aspirin, Pharmaceutical Waste.
Scope of the Article: Pharmaceutical Waste.

Download PDF

The post E67810110522 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E67750110522

IJRTE Journal — Fri, 28 Jan 2022 11:25:44 +0000

Fault Detection in Smart Grid Networks by Optimizing the Sensor Network for Distributed Decision Guided by Machine Learning
Rekha M N¹, U B Mahadevaswamy²
¹Mrs. Rekha M N*, Assistant Professor, Department of Electrical & Electronics Engineering, SJCE, JSS Science and Technology University, Mysuru, India.
²Dr. U B Mahadevaswamy, Professor, Department of Electronics and Communication Engineering, Sri Jayachamarajendra College of Engineering, Mysuru, India.
Manuscript received on January 19, 2022. | Revised Manuscript received on January 24, 2022. | Manuscript published on January 30, 2022. | PP: 106-112 | Volume-10 Issue-5, January 2022. | Retrieval Number: 100.1/ijrte.E67750110522 | DOI: 10.35940/ijrte.E6775.0110522
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: A smart grid network allows the existence of distributed power generation units. These units generate power through renewable or non-renewable means and supply it through the distribution networks. A major problem with these distributed power generation units is that they introduce harmonic components and affect power flow, creating high impedance faults (HIF) in the distribution network. HIF detection is difficult because the associated current has a low amplitude, rendering overcurrent safety devices ineffective. Wireless communication is one of the solutions for fault detection and feeder reconfiguration. This proposed work has an effective sensor network employed to determine and localize the HIF faults in the distribution network supporting distribution generation units. Fast Independent Component features are clustered in each area, and a SVM classifier is constructed to recognize faults. The learnt knowledge represented in SVM is converted to decision rules and disseminated into the sensor network nodes for effective distributed detection and localization of faults. Due to distributed detection, faults can be localized in less time. This improves the accuracy of fault detection as well as improves the network performance.
Keywords: Smart Grid, Sensor Network, High Impedance Faults, Support Vector Machine Classifier
Scope of the Article: Electrical and Electronics Engineering

Download PDF

The post E67750110522 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E67700110522

IJRTE Journal — Sat, 22 Jan 2022 08:39:30 +0000

A New Perception of Activated Flux Tungsten Inert Gas (A-TIG) Welding Techniques for Various Materials
J. Sivakumar¹, Karthik Babu N.B², M.P. Mohanraj³, E. Hariharan⁴, M. Ranjithkumar⁵
¹J. Sivakumar*, Department of Mechanical Engineering, Annapoorana Engineering College, Salem (Tamil Nadu), India.
²Karthik Babu N.B, Department of Mechanical Engineering, Assam Energy Institute, Centre of Rajiv Gandhi Institute of Petroleum Technology, Sivasagar, Assam.
³M.P. Mohanraj, Department of Mechanical Engineering, Annapoorana Engineering College, Salem (Tamil Nadu), India.
⁴E. Hariharan, Department of Mechanical Engineering, Annapoorana Engineering College, Salem (Tamil Nadu), India.
⁵M. Ranjithkumar, Department of Mechanical Engineering, Annapoorana Engineering College, Salem (Tamil Nadu), India.
Manuscript received on January 17, 2022. | Revised Manuscript received on January 20, 2022. | Manuscript published on January 30, 2022. | PP: 92-105 | Volume-10 Issue-5, January 2022. | Retrieval Number: 100.1/ijrte.E67700110522 | DOI: 10.35940/ijrte.E6770.0110522
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Tungsten inert gas welding (TIG) is more stable and allows for more precise control than most other arc welding processes. TIG welding is desired in the aerospace sector when thin parts have been welded with accuracy. However, when welding thick sections, autogenous TIG welding is not commonly recommended due to the limited depth of penetration required. It is in effective for joining the thick parts in a particular pass. Welding with activated flux tungsten inert gas (A-TIG) enhances weld penetration by four times in a single pass. This process will improve penetration depth, depth/width ratio and also, minimize angular distortion and residual stresses. A-TIG is the topic of investigation among researchers due to its deep penetration capacity. Properties of A-TIG welding in diverse materials was investigated in this study which also discusses the mechanisms, varied forces like lorentz force, buoyancy force, shear stress prompted by plasma jet, shear stress prompted by surface tension gradient, reverse marangoni force and aerodynamic drag force induced in the weld pool. The impact of activated fluxes on various materials of A-TIG weld was also investigated in this study. Recent advancements in TIG welding methods were also explored. According to the findings, A-TIG welding improves weld penetration significantly, but there is a lot of slug on the weld surface. This constraint can be addressed by using new versions of the A-TIG welding progression, such as flux bounded and the flux zone.
Keywords: A-TIG welding. TIG welding. Mechanisms. Various forces. Various materials.
Scope of the Article: Mechanical Engineering.

Download PDF

The post E67700110522 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

D66131110421

IJRTE Journal — Sat, 22 Jan 2022 07:45:01 +0000

Automatic Street Lighting Controller with Anti-Theft Alarm
Fullitan, Ric Vincent T.¹, Jason F. Mamac², Joshua T. Palma³, Jestone C. Labastida⁴, Michael P. Garay⁵, Maria Danesa S. Rabia⁶
¹Ric Vincent T. Fullitan, CTAS, Bohol Island State University, Calape, Bohol, Philippines. CTAS, Bohol Island State University, Calape, Bohol, Philippines.
²Jason F. Mamac, CTAS, Bohol Island State University, Calape, Bohol, Philippines.
³Joshua T. Palma, CTAS, Bohol Island State University, Calape, Bohol, Philippines.
⁴Jestone C. Labastida, CTAS, Bohol Island State University, Calape, Bohol, Philippines.
⁵Michael P. Garay, CTAS, Bohol Island State University, Calape, Bohol, Philippines.
⁶Maria Danesa S. Rabia*, CTAS, Bohol Island State University, Calape, Bohol, Philippines.
Manuscript received on November 16, 2021. | Revised Manuscript received on January 09, 2022. | Manuscript published on January 30, 2021. | PP: 87-91 | Volume-10 Issue-5, January 2022. | Retrieval Number: 100.1/ijrte.D66131110421 | DOI: 10.35940/ijrte.D6613.0110522
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: In times when security is the topmost priority of every community, the provision of adequate and functional streetlights is deemed necessary as one of the measures to protect life and property. In this study, the researchers designed and constructed a prototype device Automatic Streetlight Controller with anti-theft alarm using a Light-dependent resistor (LDR) and Photodiode – Infrared LED tandem. This study was conducted to assess the qualitative description, functionality, and level of acceptability regarding the constructed Automatic Streetlight Controller with Anti-theft device in terms of its performance as to device and simulator/trainer, the convenience of use, safety, assembly of parts, and cost. A mixed research design was used that includes both qualitative and quantitative research design. The qualitative description of the device was presented in narrative form and assessed using a focused-group discussion. Quantitative research design is done using quasi-experimental in testing the functionality, trials were made to assess its functionality and descriptive survey method was used to assess the level of acceptability. Probability sampling was also used thru the lottery method to get the two (2) selected groups of respondents: the 3rd year BSIT- Electricity block B students and community barangay officials of Calunasan, Calape, Bohol. T-test was used to test its significance using the 0.05α. Results have shown that on testing the device has 100% good performance and is rated as it functions well. The acceptability level was rated “very high” which means highly acceptable by both respondents. Therefore, the device can be used if implanted in existing street lights or newly built ones to improve the condition of our street lights to properly illuminate the streets for an improved security system.
Keywords: Acceptability, Anti-Thief Alarm, Controller, Functionality
Scope of the Article: Electrical and Electronics Engineering.

Download PDF

The post D66131110421 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E67620110522

IJRTE Journal — Sat, 15 Jan 2022 06:25:39 +0000

A Study on Reinforcement of Self Directed Learning using Controlling Face Emotion
Dong Hwa Kim¹, Young Sung Kim²
¹Prof. Dr. Dong Hwa Kim*, Researcher, Seoul National University of Science and Technology, Seoul, South Korea.
²Prof. Dr. Young Sung Kim, Graduating School of Nano Science, Information, Design and Engineering, Seoul National University of Science and Technology, Seoul, South Korea.
Manuscript received on January 13, 2022. | Revised Manuscript received on January 15, 2022. | Manuscript published on January 30, 2022. | PP: 76-83 | Volume-10 Issue-5, January 2022. | Retrieval Number: 100.1/ijrte.E67620110522 | DOI: 10.35940/ijrte.E6762.0110522
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: This paper deals with emotion-based self-directed teaching and learning in online education. Teachers and learners cannot understand how much their communication exchanges well with each other. So, their teaching and learning efficiency decreases than their expectation. To increase teaching and learning efficiency, this paper analyzes face emotional patterns to figure out which emotion segments have dominant facts in teaching and learning through Korean women’s face data. These dominant factors are sent to control for improving self-directed learning. In the control system, deep learning compares face data with reference data and finally decides the control signal to improve self-directed learning.
Keywords: Face Emotion, Online Education, Self-Directed Teaching and Learning, Emotion Reinforcement.
Scope of the Article: Computer Science and Engineering.

Download PDF

The post E67620110522 appeared first on International Journal of Recent Technology and Engineering (IJRTE).