Pub Date : 2022-12-17DOI: 10.1109/ICSPC55597.2022.10001800
Maricel L. Amit, Arnel C. Fajardo, Ruji P. Medina
This study used computer vision to capture real-time hand gestures using the MediaPipe Holistic Model and LSTM with MLP architecture to bridge the communication gap between the hearing majority and the deaf minority. The structure of LSTM architecture was consist of 84 neurons with a 30, 1662 input vector that will be transmitted to the MLP model. It has five layers with corresponding nodes of 84, 56, 28,14, and 7 and a dropout with rate values of 0.4 in the first, second, and third layers, while 0.5 in fourth layer. The proposed method was trained and validated with 1000 epoch which achieved a 100 percent accuracy rate in the recognition of real-time hand gesture. Additionally, the researchers envisioned to incorporate hand gesture detection into a number of real-world applications for human-computer interaction in the coming years.
{"title":"Recognition of Real-Time Hand Gestures using Mediapipe Holistic Model and LSTM with MLP Architecture","authors":"Maricel L. Amit, Arnel C. Fajardo, Ruji P. Medina","doi":"10.1109/ICSPC55597.2022.10001800","DOIUrl":"https://doi.org/10.1109/ICSPC55597.2022.10001800","url":null,"abstract":"This study used computer vision to capture real-time hand gestures using the MediaPipe Holistic Model and LSTM with MLP architecture to bridge the communication gap between the hearing majority and the deaf minority. The structure of LSTM architecture was consist of 84 neurons with a 30, 1662 input vector that will be transmitted to the MLP model. It has five layers with corresponding nodes of 84, 56, 28,14, and 7 and a dropout with rate values of 0.4 in the first, second, and third layers, while 0.5 in fourth layer. The proposed method was trained and validated with 1000 epoch which achieved a 100 percent accuracy rate in the recognition of real-time hand gesture. Additionally, the researchers envisioned to incorporate hand gesture detection into a number of real-world applications for human-computer interaction in the coming years.","PeriodicalId":334831,"journal":{"name":"2022 IEEE 10th Conference on Systems, Process & Control (ICSPC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129779646","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 : 2022-12-17DOI: 10.1109/ICSPC55597.2022.10001805
Rabab Alayham Abbas Helmi, S. Attalla, Muhammad Fareez Lutfi Bin Faizol, M. Johar
In recent decades, the utilization of autopsies as a teaching tool in undergraduate medical education is facing many challenges due to the nature of the medico legal issues. Aside from that, school closures and remote or hybrid learning environments manifested during Covid-19 pandemic have created more challenges for educators. Students are missing out the autopsy-based teaching, which provide various advantages. Moreover, it is difficult to assess students in ways that encourage and empower them to progress. Fortunately, the technology has the potential to provide a virtual museum with an interactive cadaver of several case studies, each with its own history and narrative beside, quizzes and assessments that give educational reasoning, analyze and track the user's learning. The objective of this research is to establish a virtual system for teaching the basis of Forensic medicine to medical students. The system is developed as a web based system, moreover this research uses Agile development approach as the methodology for this system development, the platform is developed to provide a single platform for material, assessment and feedback. Therefore, including 3 stages of the teaching and learning process, the system include scope for educators and learners as well.
{"title":"Design and Development of Virtual Autopsy System for Teaching Medical Undergraduates","authors":"Rabab Alayham Abbas Helmi, S. Attalla, Muhammad Fareez Lutfi Bin Faizol, M. Johar","doi":"10.1109/ICSPC55597.2022.10001805","DOIUrl":"https://doi.org/10.1109/ICSPC55597.2022.10001805","url":null,"abstract":"In recent decades, the utilization of autopsies as a teaching tool in undergraduate medical education is facing many challenges due to the nature of the medico legal issues. Aside from that, school closures and remote or hybrid learning environments manifested during Covid-19 pandemic have created more challenges for educators. Students are missing out the autopsy-based teaching, which provide various advantages. Moreover, it is difficult to assess students in ways that encourage and empower them to progress. Fortunately, the technology has the potential to provide a virtual museum with an interactive cadaver of several case studies, each with its own history and narrative beside, quizzes and assessments that give educational reasoning, analyze and track the user's learning. The objective of this research is to establish a virtual system for teaching the basis of Forensic medicine to medical students. The system is developed as a web based system, moreover this research uses Agile development approach as the methodology for this system development, the platform is developed to provide a single platform for material, assessment and feedback. Therefore, including 3 stages of the teaching and learning process, the system include scope for educators and learners as well.","PeriodicalId":334831,"journal":{"name":"2022 IEEE 10th Conference on Systems, Process & Control (ICSPC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127621074","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 : 2022-12-17DOI: 10.1109/ICSPC55597.2022.10001767
Nur Ulfah Maisurah Mohd Faiz, Muhaini Othman, M. N. Mohd Salleh, Yana Mazwin Mohmad Hassim, S. Marjudi, M. M. Yusof, Mohd Zaki bin Mohd Salikon, Tan Kang Leng
The exponential growth of social media data has been collected in today's F&B business. Simple and cost-effective to run high business performance result is critical and engage in successful marketing campaigns. It is necessary to understand different customer behaviour and make more strategically decisions to explore and analyze these data to target the appropriate customers in their business. Most of the profiling and segmentation consider as popular marketing approach to investigate customers based on their characteristics for targeted campaigns. In this paper, we use different clustering methods to get insight and reveal the trends in the mass of real-time collected datasets. K-Means, agglomerative clustering and farthest clustering algorithm is applied to segment the customers into the similar group and further dive into relating specific subset of given datasets. The result of the comparison study shows K-means clustering achieved the accuracy of seventy-five percent (75%) outperform to others. This study addresses the effective data mining approach has helped the F&B companies to make more branding in their promotion campaign and serve the customer better.
{"title":"Comparative Analysis for Customer Profiling and Segmentation in Food and Beverages Using Data Mining Techniques","authors":"Nur Ulfah Maisurah Mohd Faiz, Muhaini Othman, M. N. Mohd Salleh, Yana Mazwin Mohmad Hassim, S. Marjudi, M. M. Yusof, Mohd Zaki bin Mohd Salikon, Tan Kang Leng","doi":"10.1109/ICSPC55597.2022.10001767","DOIUrl":"https://doi.org/10.1109/ICSPC55597.2022.10001767","url":null,"abstract":"The exponential growth of social media data has been collected in today's F&B business. Simple and cost-effective to run high business performance result is critical and engage in successful marketing campaigns. It is necessary to understand different customer behaviour and make more strategically decisions to explore and analyze these data to target the appropriate customers in their business. Most of the profiling and segmentation consider as popular marketing approach to investigate customers based on their characteristics for targeted campaigns. In this paper, we use different clustering methods to get insight and reveal the trends in the mass of real-time collected datasets. K-Means, agglomerative clustering and farthest clustering algorithm is applied to segment the customers into the similar group and further dive into relating specific subset of given datasets. The result of the comparison study shows K-means clustering achieved the accuracy of seventy-five percent (75%) outperform to others. This study addresses the effective data mining approach has helped the F&B companies to make more branding in their promotion campaign and serve the customer better.","PeriodicalId":334831,"journal":{"name":"2022 IEEE 10th Conference on Systems, Process & Control (ICSPC)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127808921","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 : 2022-12-17DOI: 10.1109/ICSPC55597.2022.10001739
Muhamad Azizulhakim Mohamed Asseri, Mohd Hezri Fazalul Rahiman, Mohd Helmy Halim Abdul Majid
Motors and generators like other machineries, experience wear and ageing. The materials and components will deteriorate over time if nothing is done, and they will ultimately fail. Fortunately, most form of failures may be avoided with proper maintenances. To successfully schedule the maintenance, the plant operator must have reliable information on the current state of their machineries. This paper presents a technique and measuring system for PD monitoring of rotating machines using Phase Resolve Partial Discharge pattern. With this technique, the maintenance strategy and planning can be considerably improved. The proposed method was tested on asynchronous motor with 6.6 kV rated voltage. The measuring approach is based on the decoupling of PD pulses using inductive sensors mounted on terminals of the item to be tested and the handling of the sensor signals, which results in a measurement of the PD level in the test object. Since one of the most essential responsibilities of PD monitoring is to identify insulation degradation early, analyzing PRPD patterns is helpful for assessing the state of high voltage rotating machines so they may work reliably for a known period of time. The paper evaluates a case scenario of a machine and the PRPD results show the current condition of the inspected machine which is in good running condition.
{"title":"Partial Discharge Monitoring and Analysis using Phase Resolve Partial Discharge Pattern","authors":"Muhamad Azizulhakim Mohamed Asseri, Mohd Hezri Fazalul Rahiman, Mohd Helmy Halim Abdul Majid","doi":"10.1109/ICSPC55597.2022.10001739","DOIUrl":"https://doi.org/10.1109/ICSPC55597.2022.10001739","url":null,"abstract":"Motors and generators like other machineries, experience wear and ageing. The materials and components will deteriorate over time if nothing is done, and they will ultimately fail. Fortunately, most form of failures may be avoided with proper maintenances. To successfully schedule the maintenance, the plant operator must have reliable information on the current state of their machineries. This paper presents a technique and measuring system for PD monitoring of rotating machines using Phase Resolve Partial Discharge pattern. With this technique, the maintenance strategy and planning can be considerably improved. The proposed method was tested on asynchronous motor with 6.6 kV rated voltage. The measuring approach is based on the decoupling of PD pulses using inductive sensors mounted on terminals of the item to be tested and the handling of the sensor signals, which results in a measurement of the PD level in the test object. Since one of the most essential responsibilities of PD monitoring is to identify insulation degradation early, analyzing PRPD patterns is helpful for assessing the state of high voltage rotating machines so they may work reliably for a known period of time. The paper evaluates a case scenario of a machine and the PRPD results show the current condition of the inspected machine which is in good running condition.","PeriodicalId":334831,"journal":{"name":"2022 IEEE 10th Conference on Systems, Process & Control (ICSPC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116338893","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 : 2022-12-17DOI: 10.1109/ICSPC55597.2022.10001746
Rabab Alayham Abbas Helmi, Naveen A-L Baskaran, Arshad Jamal, M. N. Mohammed
The usage of web crawlers has been increasing over the years to retrieve data. A functional and accurate crawler is crucial of system that implements them, to increase the precision in result output. The advanced and flexible the web crawler is, the better the data scraping can get. Vitality of crawlers rises when it is being implemented in retrieving data from dark net. The paper emphasizes on the development web crawling application based on dark net. The aim of this system is to be able to retrieve data from dark net forums with given URL and keyword. To able to gain data accurately based on the expected output, the precision of data output has been increased by implementation of data filtering. The data obtained can be reserved in multiple file format for future research and development purposes.
{"title":"Dark Net Forum Analyzer Using Meta Data Search Bots","authors":"Rabab Alayham Abbas Helmi, Naveen A-L Baskaran, Arshad Jamal, M. N. Mohammed","doi":"10.1109/ICSPC55597.2022.10001746","DOIUrl":"https://doi.org/10.1109/ICSPC55597.2022.10001746","url":null,"abstract":"The usage of web crawlers has been increasing over the years to retrieve data. A functional and accurate crawler is crucial of system that implements them, to increase the precision in result output. The advanced and flexible the web crawler is, the better the data scraping can get. Vitality of crawlers rises when it is being implemented in retrieving data from dark net. The paper emphasizes on the development web crawling application based on dark net. The aim of this system is to be able to retrieve data from dark net forums with given URL and keyword. To able to gain data accurately based on the expected output, the precision of data output has been increased by implementation of data filtering. The data obtained can be reserved in multiple file format for future research and development purposes.","PeriodicalId":334831,"journal":{"name":"2022 IEEE 10th Conference on Systems, Process & Control (ICSPC)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125997883","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 : 2022-12-17DOI: 10.1109/ICSPC55597.2022.10001808
N. Shamsudin, A. H. Razak, M. H. A. Ghafar, A. Halim, M. Idros, F. N. Osman, S. A. Al Junid
In this paper, a monitoring system device that analyses kidney conditions through urine pH was developed. This monitoring device provides a simple solution for people to keep updated on their kidney condition that could be implemented in the toilet either in public or personal via mobile apps wirelessly. It has been suggested that a person's urine pH that is not in the range are likely to suffer from kidney problem either kidney disease or kidney stone. An interview with a medical physician was performed to get a confirmation of the relationship between the pH level of urine and kidney condition. Urine samples of a total of 8 subjects were examined to observe the differences in pH levels for each subject. Factors that affect the pH level of urine, which are intake of medicine/supplement, fasting urine, health condition, and foods have been considered during the analysis. An experiment was conducted to compare the accuracy of our system compared to a standard urinalysis strip doctor used in a clinical test. The results show that our system manages to record accuracy in the range of 90% to 97% as compared to the urinalysis strip. This developed device is believed could help people to monitor their kidney condition easily and increase their awareness of kidneys' health.
{"title":"Preliminary Kidney Disease Diagnostic System based on Concentration of Hydrogen Ions in Urine","authors":"N. Shamsudin, A. H. Razak, M. H. A. Ghafar, A. Halim, M. Idros, F. N. Osman, S. A. Al Junid","doi":"10.1109/ICSPC55597.2022.10001808","DOIUrl":"https://doi.org/10.1109/ICSPC55597.2022.10001808","url":null,"abstract":"In this paper, a monitoring system device that analyses kidney conditions through urine pH was developed. This monitoring device provides a simple solution for people to keep updated on their kidney condition that could be implemented in the toilet either in public or personal via mobile apps wirelessly. It has been suggested that a person's urine pH that is not in the range are likely to suffer from kidney problem either kidney disease or kidney stone. An interview with a medical physician was performed to get a confirmation of the relationship between the pH level of urine and kidney condition. Urine samples of a total of 8 subjects were examined to observe the differences in pH levels for each subject. Factors that affect the pH level of urine, which are intake of medicine/supplement, fasting urine, health condition, and foods have been considered during the analysis. An experiment was conducted to compare the accuracy of our system compared to a standard urinalysis strip doctor used in a clinical test. The results show that our system manages to record accuracy in the range of 90% to 97% as compared to the urinalysis strip. This developed device is believed could help people to monitor their kidney condition easily and increase their awareness of kidneys' health.","PeriodicalId":334831,"journal":{"name":"2022 IEEE 10th Conference on Systems, Process & Control (ICSPC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133498651","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 : 2022-12-17DOI: 10.1109/ICSPC55597.2022.10001824
Siti Nur Sarah Abu Bakar, Noor Hafizah Mahamarowi, Safinaz Mustapha
This paper presents a design of a 2D digital-game-based learning application for dyslexic children in primary school age between 7 to 12 years old. The purpose of digital game-based learning is to offer a new learning alternative that caters to the needs of dyslexic children. Based on a current finding, there is a lack of game-based learning that focuses on dyslexia children. An ADDIE model method was used to develop 2D games as teaching and learning tools. The results showshowt the use of special elements is hoped to help ease reading and learning for these children especially in helping them to learn and get familiar with new words in these developments that used as teachina g and learning tools for dyslexic children
{"title":"Game-Based Learning as a Teaching and Learning Tool for Dyslexic Children","authors":"Siti Nur Sarah Abu Bakar, Noor Hafizah Mahamarowi, Safinaz Mustapha","doi":"10.1109/ICSPC55597.2022.10001824","DOIUrl":"https://doi.org/10.1109/ICSPC55597.2022.10001824","url":null,"abstract":"This paper presents a design of a 2D digital-game-based learning application for dyslexic children in primary school age between 7 to 12 years old. The purpose of digital game-based learning is to offer a new learning alternative that caters to the needs of dyslexic children. Based on a current finding, there is a lack of game-based learning that focuses on dyslexia children. An ADDIE model method was used to develop 2D games as teaching and learning tools. The results showshowt the use of special elements is hoped to help ease reading and learning for these children especially in helping them to learn and get familiar with new words in these developments that used as teachina g and learning tools for dyslexic children","PeriodicalId":334831,"journal":{"name":"2022 IEEE 10th Conference on Systems, Process & Control (ICSPC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133618653","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 : 2022-12-17DOI: 10.1109/ICSPC55597.2022.10001814
Muhammad Asyraf Bin Mustaffa, Husna Binti Zainol Abidin, Lucyantie Mazalan, Fadhlan Hafizhelmi Kamaru Zaman, N. K. Mun, Syahrul Afzal Bin Che Abdullah
The development of 5G cellular networks has enabled the implementation of autonomous and self-driving vehicles, as the technology supports higher data speeds up to 1 Gbps with a reduction of network latency down to until several milliseconds by using Cellular Vehicle-to-Everything (C-V2X) network communications. The 3rd Generation Partnership Project (3GPP) entrusted to develop a protocol for the 5G New Radio Access Network (NR RAN) access technology and its associated technical specifications. 3GPP has introduced Service Data Adaptation Protocol (SDAP) that is responsible for Quality of Service (QoS) flow handling network. Malaysia's 5G network is currently operational, but it is only limited to end devices that are supported by telecom service providers. The end devices are expensive, and researchers may acquire a large number of them in order to understand the limitations, usage, and constraints of SDAP when deploying using 5G applications. Hence, a discrete event software simulator called OMNeT++ and the 5G-Sim-V2I/N framework were used to simulate and to evaluate a prioritized resource allocation algorithm for provisioning of Quality of Service (QoS) in Cellular Vehicle-to-Network (C-V2N) communication. Each application (i.e., Voice over Internet Protocol (VoIP), video streaming, data transmission, and V2X messaging) is allocated a QoS value, named 5G QoS Flow Identifier (5QI). The values of Signal Noise with Interference Ratio (SNIR), packet delay in each application, and the throughput of several cars, set randomly up to 254 cars were collected. The MAX C/I scheduling algorithm was adopted as the scheduler because the user with the highest SNIR will be prioritized and served first, which will instantly maximize the system throughput. The result of this experiment showed how 5QI affects transmission, notably when the network is congested, because of the large number of cars were connected to the 5G base station, as the value of SNIR decreases.
{"title":"Performance Analysis of Heterogeneous Data Transmission in 5G C-V2N Communication","authors":"Muhammad Asyraf Bin Mustaffa, Husna Binti Zainol Abidin, Lucyantie Mazalan, Fadhlan Hafizhelmi Kamaru Zaman, N. K. Mun, Syahrul Afzal Bin Che Abdullah","doi":"10.1109/ICSPC55597.2022.10001814","DOIUrl":"https://doi.org/10.1109/ICSPC55597.2022.10001814","url":null,"abstract":"The development of 5G cellular networks has enabled the implementation of autonomous and self-driving vehicles, as the technology supports higher data speeds up to 1 Gbps with a reduction of network latency down to until several milliseconds by using Cellular Vehicle-to-Everything (C-V2X) network communications. The 3rd Generation Partnership Project (3GPP) entrusted to develop a protocol for the 5G New Radio Access Network (NR RAN) access technology and its associated technical specifications. 3GPP has introduced Service Data Adaptation Protocol (SDAP) that is responsible for Quality of Service (QoS) flow handling network. Malaysia's 5G network is currently operational, but it is only limited to end devices that are supported by telecom service providers. The end devices are expensive, and researchers may acquire a large number of them in order to understand the limitations, usage, and constraints of SDAP when deploying using 5G applications. Hence, a discrete event software simulator called OMNeT++ and the 5G-Sim-V2I/N framework were used to simulate and to evaluate a prioritized resource allocation algorithm for provisioning of Quality of Service (QoS) in Cellular Vehicle-to-Network (C-V2N) communication. Each application (i.e., Voice over Internet Protocol (VoIP), video streaming, data transmission, and V2X messaging) is allocated a QoS value, named 5G QoS Flow Identifier (5QI). The values of Signal Noise with Interference Ratio (SNIR), packet delay in each application, and the throughput of several cars, set randomly up to 254 cars were collected. The MAX C/I scheduling algorithm was adopted as the scheduler because the user with the highest SNIR will be prioritized and served first, which will instantly maximize the system throughput. The result of this experiment showed how 5QI affects transmission, notably when the network is congested, because of the large number of cars were connected to the 5G base station, as the value of SNIR decreases.","PeriodicalId":334831,"journal":{"name":"2022 IEEE 10th Conference on Systems, Process & Control (ICSPC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131273554","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 : 2022-12-17DOI: 10.1109/ICSPC55597.2022.10001796
Laily Azyan Ramlan, W. Zaki, H. A. Mutalib, A. B. Huddin, A. Hussain
In the digital age, the use of smartphone digital camera images as an imaging modality for early eye disease screening and detection has been widely explored. Nevertheless, the process of taking pictures often raises some issues that may be related to the dynamic range limitations of cameras and uneven lighting, which may cause uneven illumination in the images. Therefore, image enhancement is further needed to improve the visual quality of the images and to provide sufficient detail for basic computer vision tasks including segmentation. This work studies the effect of image enhancement methods on the segmentation results of anterior segment photographed image (ASPI) ocular regions with nonuniform illumination. During the pre-processing stage, the image enhancement methods are performed on the nonuniform illumination ASPI. Those images are later trained using a deep learning approach for semantic segmentation. Based on the network performance, the Multiscale Retinex with Chromaticity Preservation (MSRCP) method gives the best segmentation results for all classes with mean accuracy of 0.921, mean IoU of 0.805 and mean BFScore of 0.717. In addition, the image quality assessment is performed on the ASPI with image enhancement methods. It is found that the images using MSRCP method had the lowest values for Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE), Naturalness Image Quality Evaluator (NIQE), and Perception-based Image Quality Evaluator (PIQE), indicating the highest image quality compared to the other methods. For future work, the segmented region of the eyes, including the sclera, iris, and pupil, can be utilized as a region of interest (ROI) to detect various anterior eye diseases.
在数字时代，使用智能手机数码相机图像作为早期眼病筛查和检测的成像方式已被广泛探索。然而，在拍照的过程中经常会出现一些问题，这些问题可能与相机的动态范围限制和不均匀的光线有关，这可能会导致图像中的照明不均匀。因此，需要进一步进行图像增强，以提高图像的视觉质量，并为分割等基本计算机视觉任务提供足够的细节。本文研究了不同图像增强方法对非均匀光照下前段拍摄图像(ASPI)眼部区域分割结果的影响。在预处理阶段，对非均匀光照的ASPI进行了图像增强。这些图像随后使用深度学习方法进行语义分割训练。基于网络性能，Multiscale Retinex with Chromaticity Preservation (MSRCP)方法对所有类别的分割结果最好，平均准确率为0.921，平均IoU为0.805，平均BFScore为0.717。此外，采用图像增强方法对ASPI进行了图像质量评估。结果发现，采用MSRCP方法的图像在无参考/盲图像空间质量评价器(BRISQUE)、自然图像质量评价器(NIQE)和基于感知的图像质量评价器(PIQE)上的值最低，表明与其他方法相比，使用MSRCP方法的图像质量最高。在未来的工作中，眼睛的分割区域，包括巩膜、虹膜和瞳孔，可以作为感兴趣区域(ROI)来检测各种眼前疾病。
{"title":"Image Enhancement Methods for Anterior Segment Photographed Images","authors":"Laily Azyan Ramlan, W. Zaki, H. A. Mutalib, A. B. Huddin, A. Hussain","doi":"10.1109/ICSPC55597.2022.10001796","DOIUrl":"https://doi.org/10.1109/ICSPC55597.2022.10001796","url":null,"abstract":"In the digital age, the use of smartphone digital camera images as an imaging modality for early eye disease screening and detection has been widely explored. Nevertheless, the process of taking pictures often raises some issues that may be related to the dynamic range limitations of cameras and uneven lighting, which may cause uneven illumination in the images. Therefore, image enhancement is further needed to improve the visual quality of the images and to provide sufficient detail for basic computer vision tasks including segmentation. This work studies the effect of image enhancement methods on the segmentation results of anterior segment photographed image (ASPI) ocular regions with nonuniform illumination. During the pre-processing stage, the image enhancement methods are performed on the nonuniform illumination ASPI. Those images are later trained using a deep learning approach for semantic segmentation. Based on the network performance, the Multiscale Retinex with Chromaticity Preservation (MSRCP) method gives the best segmentation results for all classes with mean accuracy of 0.921, mean IoU of 0.805 and mean BFScore of 0.717. In addition, the image quality assessment is performed on the ASPI with image enhancement methods. It is found that the images using MSRCP method had the lowest values for Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE), Naturalness Image Quality Evaluator (NIQE), and Perception-based Image Quality Evaluator (PIQE), indicating the highest image quality compared to the other methods. For future work, the segmented region of the eyes, including the sclera, iris, and pupil, can be utilized as a region of interest (ROI) to detect various anterior eye diseases.","PeriodicalId":334831,"journal":{"name":"2022 IEEE 10th Conference on Systems, Process & Control (ICSPC)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125231583","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 : 2022-12-17DOI: 10.1109/ICSPC55597.2022.10001813
Rabab Alayham Abbas Helmi, Chua Shang Ren
The aim of the research study for securing digital payment by using blockchain technology, is to understand the rapid growth of technology which affects digital payment’s security. Without proper digital security, there will be a lot of issues when users make digital transactions. Therefore, it will also affect user’s trust while using digital transactions. To overcome these issues that users face in digital transactions, a new method that has been proposed in this research is to establish a two-way trust by storing user information under blockchain technology. Face recognition authentication has been developed to store inside blockchain technology. This research includes the framework, data collection, and testing of systems. Data collection was done by using different types of method to collect sampling data.
{"title":"Securing Digital Payment by using Blockchain Technology","authors":"Rabab Alayham Abbas Helmi, Chua Shang Ren","doi":"10.1109/ICSPC55597.2022.10001813","DOIUrl":"https://doi.org/10.1109/ICSPC55597.2022.10001813","url":null,"abstract":"The aim of the research study for securing digital payment by using blockchain technology, is to understand the rapid growth of technology which affects digital payment’s security. Without proper digital security, there will be a lot of issues when users make digital transactions. Therefore, it will also affect user’s trust while using digital transactions. To overcome these issues that users face in digital transactions, a new method that has been proposed in this research is to establish a two-way trust by storing user information under blockchain technology. Face recognition authentication has been developed to store inside blockchain technology. This research includes the framework, data collection, and testing of systems. Data collection was done by using different types of method to collect sampling data.","PeriodicalId":334831,"journal":{"name":"2022 IEEE 10th Conference on Systems, Process & Control (ICSPC)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128391280","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：