Pub Date : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495890
Jessie R. Balbin, Irish Joy N. Maliban, Joshua Mark A. Marquez
This paper is about an automated waste bin that segregates waste into three divisions: wet, dry, and metal. The automated waste bin uses inductive, capacitive, proximity sensors and an Arduino Mega microcontroller board. Utilizing IoT (Internet of Things), the system will relay information to its user through a mobile application. The application shows if the bin is operating. It also indicates the bin's current level capacity, whether it is already full or not. The prototype was able to function as intended and has a 90% reading for accuracy and precision in its overall system.
{"title":"Automated Waste Segregation Bin with IoT-based Mobile Monitoring Application","authors":"Jessie R. Balbin, Irish Joy N. Maliban, Joshua Mark A. Marquez","doi":"10.1109/I2CACIS52118.2021.9495890","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495890","url":null,"abstract":"This paper is about an automated waste bin that segregates waste into three divisions: wet, dry, and metal. The automated waste bin uses inductive, capacitive, proximity sensors and an Arduino Mega microcontroller board. Utilizing IoT (Internet of Things), the system will relay information to its user through a mobile application. The application shows if the bin is operating. It also indicates the bin's current level capacity, whether it is already full or not. The prototype was able to function as intended and has a 90% reading for accuracy and precision in its overall system.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122968518","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}
Pub Date : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495898
Y. Alshebly, Marwan Nafea, H. Almurib, Mohamed Sultan Mohamed Ali, Ahmad Athif Mohd Faudzi, M. T. Tan
The field of four-dimensional (4D) printing is still in its prime and lacking in tools to help designers and researchers in creating applicable structures that are 4D printed. In order for these tools to be available for researchers, testing and simulation work must be done on 4D printing and the shape memory effect of printed materials. In this work, testing of 4D printed actuators that have an induced strain upon printing is performed. The strain is induced in the printing process of fused deposition modelling. The induced strain allows a shape change upon stimulation of the materials after printing, removing the need for a programming step at which force, and stimulation are needed to program the temporary shape of the print. Two actuators and an open-sided box reservoir for drug delivery applications are proposed. Printing and shape change of polylactic acid are achieved and measured for the degree of bending of the actuators. The designs are printed at speed values of 10 mm/s and 60 mm/s for the passive and active layers, respectively. The printed samples are heated, and their bending angles are measured for replication by simulation. Finite element analysis (FEA) of the actuators is carried out to replicate the induced strain by using the thermal expansion of materials. The settings of the FEA are used to create a more complex structure and simulate its shape change. Deformation is achieved with values of 7.81 mm, 6.06 mm, and 4.84 mm in the z-axis direction for Design 1, Design 2, and the reservoir, respectively.
{"title":"Development of 4D Printed PLA Actuators with an Induced Internal Strain Upon Printing","authors":"Y. Alshebly, Marwan Nafea, H. Almurib, Mohamed Sultan Mohamed Ali, Ahmad Athif Mohd Faudzi, M. T. Tan","doi":"10.1109/I2CACIS52118.2021.9495898","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495898","url":null,"abstract":"The field of four-dimensional (4D) printing is still in its prime and lacking in tools to help designers and researchers in creating applicable structures that are 4D printed. In order for these tools to be available for researchers, testing and simulation work must be done on 4D printing and the shape memory effect of printed materials. In this work, testing of 4D printed actuators that have an induced strain upon printing is performed. The strain is induced in the printing process of fused deposition modelling. The induced strain allows a shape change upon stimulation of the materials after printing, removing the need for a programming step at which force, and stimulation are needed to program the temporary shape of the print. Two actuators and an open-sided box reservoir for drug delivery applications are proposed. Printing and shape change of polylactic acid are achieved and measured for the degree of bending of the actuators. The designs are printed at speed values of 10 mm/s and 60 mm/s for the passive and active layers, respectively. The printed samples are heated, and their bending angles are measured for replication by simulation. Finite element analysis (FEA) of the actuators is carried out to replicate the induced strain by using the thermal expansion of materials. The settings of the FEA are used to create a more complex structure and simulate its shape change. Deformation is achieved with values of 7.81 mm, 6.06 mm, and 4.84 mm in the z-axis direction for Design 1, Design 2, and the reservoir, respectively.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124182882","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}
Pub Date : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495895
N. Hamzah, M. Ahmad, N. Zakaria, A. Ariffin, S. K. Rubani
The closure of Higher Education Institutions and Schools due to COVID-19 pandemic has affected the structure of Learning and Teaching (T&L) from direct method at institutions to Open and Distance Education (ODE) completely. All face-to-face T&L activities are not allowed except for certain categories of students who need to return to campus in stages to participante in T&L activities in full compliance of the Standard Operating Procedures (SOP) set by prioritizing safety measures and social distancing. This study used a quantitative approach by using online questionnaire as instrument (google form). A total of 73 Technical and Vocational Education (TVE) students from various backgrounds of respondents participated in the study. The findings of the study showed that there was a strong correlation between the aspects of interest and gender of TVE students in using learning videos during the COVID-19 pandemic period (r =.701). Therefore, all parties must prepare to face the new norm, namely the ODL method as a whole during the COVID-19 pandemic period to continue the T&L process for students.
{"title":"Technical and Vocational Education Students’ Perception of Using Learning Videos during Covid-19 Pandemic Period","authors":"N. Hamzah, M. Ahmad, N. Zakaria, A. Ariffin, S. K. Rubani","doi":"10.1109/I2CACIS52118.2021.9495895","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495895","url":null,"abstract":"The closure of Higher Education Institutions and Schools due to COVID-19 pandemic has affected the structure of Learning and Teaching (T&L) from direct method at institutions to Open and Distance Education (ODE) completely. All face-to-face T&L activities are not allowed except for certain categories of students who need to return to campus in stages to participante in T&L activities in full compliance of the Standard Operating Procedures (SOP) set by prioritizing safety measures and social distancing. This study used a quantitative approach by using online questionnaire as instrument (google form). A total of 73 Technical and Vocational Education (TVE) students from various backgrounds of respondents participated in the study. The findings of the study showed that there was a strong correlation between the aspects of interest and gender of TVE students in using learning videos during the COVID-19 pandemic period (r =.701). Therefore, all parties must prepare to face the new norm, namely the ODL method as a whole during the COVID-19 pandemic period to continue the T&L process for students.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115908661","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}
Pub Date : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495905
Aung Khant Maw, P. Somboon, W. Srituravanich, A. Teeramongkonrasmee
Commercial metal-oxide semiconductor (MOS) gas sensors have been widely used by recent studies as detection units of electronic noses (e-nose) in various applications including disease diagnosis. However, the enoses employing the MOS sensors can only discriminate a limited number of odor groups due to their poor selectivity. Preliminary studies have shown that the selectivity of the MOS sensors can be enhanced by jointly integrating with other sensory units such as QCM or potentiometric sensors, which, however, involves complex interface circuitry and measurement procedures. In contrast, this paper presents a hybrid electronic nose that combines olfactory information from an MOS sensor array together with a compact paperbased colorimetric sensor array which is simpler and easier to utilize. The proposed system employs total 8 MOS sensors, and the compact paper-based colorimetric sensors are fabricated with indicator dyes such as phenol red, methyl red, and methylene blue. Color profiles of the paper-based sensors are captured using a USB-microscope and the alterations of the dyes during the gas exposure are monitored. The improvement of the system performance in classifying six volatile organic compounds (VOC) are investigated by comparing the classification results of the system with and without the colorimetric sensors. The measurement data from both sensor arrays are mapped to the feature space using principal component analysis (PCA) for pattern extraction. It was confirmed that pattern separation among the target VOCs could be improved based on data fusion of these two sensor arrays. This hybrid e-nose system may be useful for improvement of VOC classification performance.
{"title":"A Hybrid E-nose System based on Metal Oxide Semiconductor Gas Sensors and Compact Colorimetric Sensors","authors":"Aung Khant Maw, P. Somboon, W. Srituravanich, A. Teeramongkonrasmee","doi":"10.1109/I2CACIS52118.2021.9495905","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495905","url":null,"abstract":"Commercial metal-oxide semiconductor (MOS) gas sensors have been widely used by recent studies as detection units of electronic noses (e-nose) in various applications including disease diagnosis. However, the enoses employing the MOS sensors can only discriminate a limited number of odor groups due to their poor selectivity. Preliminary studies have shown that the selectivity of the MOS sensors can be enhanced by jointly integrating with other sensory units such as QCM or potentiometric sensors, which, however, involves complex interface circuitry and measurement procedures. In contrast, this paper presents a hybrid electronic nose that combines olfactory information from an MOS sensor array together with a compact paperbased colorimetric sensor array which is simpler and easier to utilize. The proposed system employs total 8 MOS sensors, and the compact paper-based colorimetric sensors are fabricated with indicator dyes such as phenol red, methyl red, and methylene blue. Color profiles of the paper-based sensors are captured using a USB-microscope and the alterations of the dyes during the gas exposure are monitored. The improvement of the system performance in classifying six volatile organic compounds (VOC) are investigated by comparing the classification results of the system with and without the colorimetric sensors. The measurement data from both sensor arrays are mapped to the feature space using principal component analysis (PCA) for pattern extraction. It was confirmed that pattern separation among the target VOCs could be improved based on data fusion of these two sensor arrays. This hybrid e-nose system may be useful for improvement of VOC classification performance.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116773038","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}
Pub Date : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495859
Surapong Kokkrathoke, Xu Xu
This paper presents a nonlinear freezing optimal control (NFOC) technique combined with an extended Kalman filter (EKF) for stabilising a two-wheel robot (TWR). The balancing LEGO EV3 Robot is utilised as a prototype for simulation and practical implementation to test the performance of the NFOC with EKF, compared against the well-known linear optimal control, i.e., the linear quadratic regulator (LQR) and the stand-alone NFOC. The stabilisation of the TWR system when starting from various ranges of initial pitch angles with different types of controllers are investigated and discussed. The MATLAB simulation result demonstrates wider operation ranges from both nonlinear optimal controllers over the linear one when simulated with a high-performance motor. In the case of implementation, the two nonlinear methods also displayed slightly more comprehensive initial pitch angle ranges than the linear control. Significantly, the precision of state variable estimation from the EKF technique removes the signal drift problem in the gyro sensor, which is used to measure the pitch angle of the TWR. The effectiveness of the NFOC controller combined with EKF is demonstrated by results from MATLAB simulation and implementation on the LEGO TWR.
{"title":"Implementation of Nonlinear Optimal Control of Two-wheel Robot with Extended Kalman Filter","authors":"Surapong Kokkrathoke, Xu Xu","doi":"10.1109/I2CACIS52118.2021.9495859","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495859","url":null,"abstract":"This paper presents a nonlinear freezing optimal control (NFOC) technique combined with an extended Kalman filter (EKF) for stabilising a two-wheel robot (TWR). The balancing LEGO EV3 Robot is utilised as a prototype for simulation and practical implementation to test the performance of the NFOC with EKF, compared against the well-known linear optimal control, i.e., the linear quadratic regulator (LQR) and the stand-alone NFOC. The stabilisation of the TWR system when starting from various ranges of initial pitch angles with different types of controllers are investigated and discussed. The MATLAB simulation result demonstrates wider operation ranges from both nonlinear optimal controllers over the linear one when simulated with a high-performance motor. In the case of implementation, the two nonlinear methods also displayed slightly more comprehensive initial pitch angle ranges than the linear control. Significantly, the precision of state variable estimation from the EKF technique removes the signal drift problem in the gyro sensor, which is used to measure the pitch angle of the TWR. The effectiveness of the NFOC controller combined with EKF is demonstrated by results from MATLAB simulation and implementation on the LEGO TWR.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115362179","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}
Pub Date : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495897
Sandy Victor Amanoul, A. Abdulazeez, Diyar Qader Zeebare, F. Y. Ahmed
Networks are important today in the world and data security has become a crucial area of study. An IDS monitors the status of the software and hardware of the network. Curing problems for current IDSs remain they improve detection precision, decrease false alarm rates and track unknown attacks after decades of advancement. Many researchers have focused on the development of IDSs using machine learning approaches to solve the above-described problems. With the high precision of computer teachings, the basic distinctions between usual and irregular data can be recognized automatically. Unknown threats may also be detected because of their generalizability via machine learning system. This paper suggests a taxonomy of IDS, which uses the primary dimension of data objects to classify and sum up IDS literatures based on and dependent on deep learning. We assume this kind of taxonomy is sufficient for researchers in cyber security. We selected three algorithms from machine learning (Bayes Net, Random Forest, Neural Network) and two algorithms of deep learning (RNN, LSTM), and we tested them on KDD cup 99 and evaluated accuracy algorithms, and we used a program WEKA To calculate the accuracy.
网络在当今世界非常重要，数据安全已经成为一个重要的研究领域。IDS监视网络的软件和硬件状态。经过几十年的发展，目前的ids仍然可以提高检测精度，降低误报率并跟踪未知攻击。许多研究人员专注于使用机器学习方法开发ids来解决上述问题。利用计算机教学的高精度，可以自动识别正常和不规则数据的基本区别。未知的威胁也可以通过机器学习系统检测到，因为它们的通用性。本文提出了一种基于深度学习和依赖深度学习的IDS分类方法，该方法利用数据对象的初级维度对IDS文献进行分类和总结。我们认为这种分类法对网络安全研究人员来说是足够的。我们从机器学习中选择了三种算法(Bayes Net、Random Forest、Neural Network)和两种深度学习算法(RNN、LSTM)，在KDD cup 99上进行了测试并评估了准确率算法，并使用WEKA程序计算了准确率。
{"title":"Intrusion Detection Systems Based on Machine Learning Algorithms","authors":"Sandy Victor Amanoul, A. Abdulazeez, Diyar Qader Zeebare, F. Y. Ahmed","doi":"10.1109/I2CACIS52118.2021.9495897","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495897","url":null,"abstract":"Networks are important today in the world and data security has become a crucial area of study. An IDS monitors the status of the software and hardware of the network. Curing problems for current IDSs remain they improve detection precision, decrease false alarm rates and track unknown attacks after decades of advancement. Many researchers have focused on the development of IDSs using machine learning approaches to solve the above-described problems. With the high precision of computer teachings, the basic distinctions between usual and irregular data can be recognized automatically. Unknown threats may also be detected because of their generalizability via machine learning system. This paper suggests a taxonomy of IDS, which uses the primary dimension of data objects to classify and sum up IDS literatures based on and dependent on deep learning. We assume this kind of taxonomy is sufficient for researchers in cyber security. We selected three algorithms from machine learning (Bayes Net, Random Forest, Neural Network) and two algorithms of deep learning (RNN, LSTM), and we tested them on KDD cup 99 and evaluated accuracy algorithms, and we used a program WEKA To calculate the accuracy.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126878736","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}
Pub Date : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495858
Elbren Antonio, Cyrus Rael, Elmer Buenavides
In computer vision, transfer learning is a common method because it helps us to quickly create accurate models. In this work, consider the outcome of the convolutional network depth with VGG16 on its accuracy in the large-scale image recognition setting. Rather than using a Convolutional Neural Network, Transfer Learning can be used on images with different image dimension inputs (CNN) and was originally trained on by using Keras to fine-tune the input from tensor dimensions. In this paper, we demonstrate how the VGG16 network handles new image input dimensions of 128x128x3 pixels from eligible VGG16 224x224x3 pixels images that are cut before the recognition is implemented. Our results show that Convolutional Neural Network can manage small datasets and can produce ideal validation accuracy of 93% from small images and better results from higher resolution images.
{"title":"Changing Input Shape Dimension Using VGG16 Network Model","authors":"Elbren Antonio, Cyrus Rael, Elmer Buenavides","doi":"10.1109/I2CACIS52118.2021.9495858","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495858","url":null,"abstract":"In computer vision, transfer learning is a common method because it helps us to quickly create accurate models. In this work, consider the outcome of the convolutional network depth with VGG16 on its accuracy in the large-scale image recognition setting. Rather than using a Convolutional Neural Network, Transfer Learning can be used on images with different image dimension inputs (CNN) and was originally trained on by using Keras to fine-tune the input from tensor dimensions. In this paper, we demonstrate how the VGG16 network handles new image input dimensions of 128x128x3 pixels from eligible VGG16 224x224x3 pixels images that are cut before the recognition is implemented. Our results show that Convolutional Neural Network can manage small datasets and can produce ideal validation accuracy of 93% from small images and better results from higher resolution images.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126437957","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}
Pub Date : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495920
Aiesha Zoe Elevado, Elaine Sagao, Angela Faye Sales, Joseph Byran Ibarra, Leonardo D. Valiente
A wide variety of wheelchairs are already available in the market. However, discomfort monitoring is also not a standard feature for it. There are several types of discomfort that wheelchair users experience. This study mainly focuses on feelings of distress, such as wetness discomfort due to human wastes like urine. It also focuses on the uneven distribution of pressure on the surface, resulting in pressure sores and monitoring the user's stress through heart rate analysis and skin conductance. The discomfort monitoring system uses ECG, GSR, Wetness, and Pressure Sensors. With the ReLU activation function, the design used a neural network to predict the discomfort level felt by the user. IoT applications in the system include user detection, an LED indicator for the discomfort level, SMS alerts, and the execution of emergency calls. Based on the results, all the features extracted from the four sensors exhibited correlation to the discomfort felt by the user. The most correlated parameter to the discomfort level is from the ECG, next is pressure, followed by wetness, and lastly, GSR.
{"title":"Discomfort Monitoring System using IoT applied to a Wheelchair","authors":"Aiesha Zoe Elevado, Elaine Sagao, Angela Faye Sales, Joseph Byran Ibarra, Leonardo D. Valiente","doi":"10.1109/I2CACIS52118.2021.9495920","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495920","url":null,"abstract":"A wide variety of wheelchairs are already available in the market. However, discomfort monitoring is also not a standard feature for it. There are several types of discomfort that wheelchair users experience. This study mainly focuses on feelings of distress, such as wetness discomfort due to human wastes like urine. It also focuses on the uneven distribution of pressure on the surface, resulting in pressure sores and monitoring the user's stress through heart rate analysis and skin conductance. The discomfort monitoring system uses ECG, GSR, Wetness, and Pressure Sensors. With the ReLU activation function, the design used a neural network to predict the discomfort level felt by the user. IoT applications in the system include user detection, an LED indicator for the discomfort level, SMS alerts, and the execution of emergency calls. Based on the results, all the features extracted from the four sensors exhibited correlation to the discomfort felt by the user. The most correlated parameter to the discomfort level is from the ECG, next is pressure, followed by wetness, and lastly, GSR.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129932425","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}
Technology devices, such as smartphone, have become a part of communication skills development in objective to help in understanding Autism Spectrum Disorder (ASD). Emotion-learning applications that are available in smartphones and tablets help to assist individuals with ASD and their guardians and caregivers in their learning and social skills. Recent studies show that user interface / user experience (UI/UX) is an important part of the smartphone application design. Differences in application functions and design guidelines are reviewed and compare to recognize how individuals with ASD express their emotion and learning experience to their guardians. Besides that, human emotions are also associated with colors. This gives positive and negative perception in differentiating emotions. Previous studies found that human basic emotions are associated with certain colors, for example angry (red), sad (blue), happy (yellow), disgust (green), fear (purple) and joyful (orange). Meanwhile, some other colors would reflect more complex emotions, such as boredom (gray), innocence (white) and mourn (black). This paper discusses related literature review on this topic.
{"title":"User Experience / User Interface (UX/UI) Design for Autistic Spectrum Disorder (ASD) Color Based Emotion Detection System: A Review","authors":"Ummi Umniah Ismail, Rusyaizila Ramli, Nabilah Rozzani","doi":"10.1109/I2CACIS52118.2021.9495855","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495855","url":null,"abstract":"Technology devices, such as smartphone, have become a part of communication skills development in objective to help in understanding Autism Spectrum Disorder (ASD). Emotion-learning applications that are available in smartphones and tablets help to assist individuals with ASD and their guardians and caregivers in their learning and social skills. Recent studies show that user interface / user experience (UI/UX) is an important part of the smartphone application design. Differences in application functions and design guidelines are reviewed and compare to recognize how individuals with ASD express their emotion and learning experience to their guardians. Besides that, human emotions are also associated with colors. This gives positive and negative perception in differentiating emotions. Previous studies found that human basic emotions are associated with certain colors, for example angry (red), sad (blue), happy (yellow), disgust (green), fear (purple) and joyful (orange). Meanwhile, some other colors would reflect more complex emotions, such as boredom (gray), innocence (white) and mourn (black). This paper discusses related literature review on this topic.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131156678","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}
Pub Date : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495877
Toya Acharya, Ishan Khatri, A. Annamalai, M. Chouikha
The internet-based services undoubtedly led the worldwide revolution with exponential growth, but security breaches resulting personal digital asset losses which need for a comprehensive cybersecurity solution. Traditionally, signature-based network intrusion detection is employed to capture attributes of normal and abnormal traffics in a network, but it fails to detect the zero-day attack. The machine learning-based approach is attractive among various known NIDS methods to circumvent the shortcoming because machine learning based approach can efficiently analyze the big network traffic data and efficiently detect the zero-day attack. The imbalanced NIDS dataset does not provide better performance on practical implementation scenarios. Reducing the number of target classes into a new target class creates a balanced NIDS and improved classifier performance. In this paper, we present the efficacy of several machine learning algorithms, including Random forest (RF), J48, Naïve Bayes, Bayesian Network, Bagging, AdaBoost, and Support Vector Machine (SVM) using network logs traffic (KDD99, UNSW-NB15, and CIC-IDS2017) using WEKA. This paper examined the impact of changing the number of output classes of the publicly available network intrusion datasets on sensitivity (True Positive Rate), False Positive Rate (FPR), Area under the ROC curve (AUC) and incorrectly identified percentage. Interestingly, the efficiency of these classifiers has increased, adding strongly correlated features to the target classes. The experimented results reveal that the machine learning classifiers performance improved when the number of target classes decreased. The addition of a highly correlated feature to the output class increases the performance of the classifiers.
{"title":"Efficacy of Machine Learning-Based Classifiers for Binary and Multi-Class Network Intrusion Detection","authors":"Toya Acharya, Ishan Khatri, A. Annamalai, M. Chouikha","doi":"10.1109/I2CACIS52118.2021.9495877","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495877","url":null,"abstract":"The internet-based services undoubtedly led the worldwide revolution with exponential growth, but security breaches resulting personal digital asset losses which need for a comprehensive cybersecurity solution. Traditionally, signature-based network intrusion detection is employed to capture attributes of normal and abnormal traffics in a network, but it fails to detect the zero-day attack. The machine learning-based approach is attractive among various known NIDS methods to circumvent the shortcoming because machine learning based approach can efficiently analyze the big network traffic data and efficiently detect the zero-day attack. The imbalanced NIDS dataset does not provide better performance on practical implementation scenarios. Reducing the number of target classes into a new target class creates a balanced NIDS and improved classifier performance. In this paper, we present the efficacy of several machine learning algorithms, including Random forest (RF), J48, Naïve Bayes, Bayesian Network, Bagging, AdaBoost, and Support Vector Machine (SVM) using network logs traffic (KDD99, UNSW-NB15, and CIC-IDS2017) using WEKA. This paper examined the impact of changing the number of output classes of the publicly available network intrusion datasets on sensitivity (True Positive Rate), False Positive Rate (FPR), Area under the ROC curve (AUC) and incorrectly identified percentage. Interestingly, the efficiency of these classifiers has increased, adding strongly correlated features to the target classes. The experimented results reveal that the machine learning classifiers performance improved when the number of target classes decreased. The addition of a highly correlated feature to the output class increases the performance of the classifiers.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134466923","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：