Pub Date : 2019-04-01DOI: 10.1109/ISCAIE.2019.8743867
S. Najib, Norshahida Binti Hassan, Nur Tysha Atikah binti Mohd Shair, N. Rahim, N. Wahab
The purpose of the project is to develop an Intelligent Neonatal Monitoring System based on temperature and pulse rate data. In the Neonatal Intensive Care Unit (NICU), there are premature babies and other ill babies who need extra care from the doctors, nurses as well as medical supplies. Therefore, an intelligent neonatal monitoring system should be a good solution in order to help them to observe neonates frequently and consistently. This system transmits the vital signs of the neonate such as body temperature and pulse rate to the Internet of Things (IoT) called ThingSpeak. The body temperature and the pulse rate will be detected by LM35 temperature sensor and pulse sensor respectively. These information will be sent to the IoT via ESP8266 Wi-Fi Shield. IoT helps the doctors and nurses to be connected with the neonate’s vital signs and it is helpful in monitoring the neonates at anytime and anywhere through the internet. The percentage difference between LM35 temperature sensor and digital thermometer is less than 3% while the pulse rate can be varied according to the physical activity. This develops system will providing efficiency and reliability which will play a vital role for better care.
{"title":"Intelligent Neonatal Monitoring System Based on Android Application using Multi Sensors","authors":"S. Najib, Norshahida Binti Hassan, Nur Tysha Atikah binti Mohd Shair, N. Rahim, N. Wahab","doi":"10.1109/ISCAIE.2019.8743867","DOIUrl":"https://doi.org/10.1109/ISCAIE.2019.8743867","url":null,"abstract":"The purpose of the project is to develop an Intelligent Neonatal Monitoring System based on temperature and pulse rate data. In the Neonatal Intensive Care Unit (NICU), there are premature babies and other ill babies who need extra care from the doctors, nurses as well as medical supplies. Therefore, an intelligent neonatal monitoring system should be a good solution in order to help them to observe neonates frequently and consistently. This system transmits the vital signs of the neonate such as body temperature and pulse rate to the Internet of Things (IoT) called ThingSpeak. The body temperature and the pulse rate will be detected by LM35 temperature sensor and pulse sensor respectively. These information will be sent to the IoT via ESP8266 Wi-Fi Shield. IoT helps the doctors and nurses to be connected with the neonate’s vital signs and it is helpful in monitoring the neonates at anytime and anywhere through the internet. The percentage difference between LM35 temperature sensor and digital thermometer is less than 3% while the pulse rate can be varied according to the physical activity. This develops system will providing efficiency and reliability which will play a vital role for better care.","PeriodicalId":369098,"journal":{"name":"2019 IEEE 9th Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122685293","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 : 2019-04-01DOI: 10.1109/ISCAIE.2019.8743725
Farah Hijjawi, Rameen S. Anjum, A. Massoud
In this paper, the performance of two types of DC-DC converters namely Ćuk and Boost-Buck converters is assessed for battery charging systems. Operation with power factor correction for the input side AC current, and continuous input and output currents at the DC side of the converter are considered. The aforementioned system can be employed for many applications such as electric vehicles, data centers, etc. This paper focuses typically on data centers. Matlab/Simulink models for the two converters have been built to verify the claimed contributions.
{"title":"Power Factor Correction Converters with Continuous Input and Output Currents for Battery Chargers in Data Centers: Performance Assessment","authors":"Farah Hijjawi, Rameen S. Anjum, A. Massoud","doi":"10.1109/ISCAIE.2019.8743725","DOIUrl":"https://doi.org/10.1109/ISCAIE.2019.8743725","url":null,"abstract":"In this paper, the performance of two types of DC-DC converters namely Ćuk and Boost-Buck converters is assessed for battery charging systems. Operation with power factor correction for the input side AC current, and continuous input and output currents at the DC side of the converter are considered. The aforementioned system can be employed for many applications such as electric vehicles, data centers, etc. This paper focuses typically on data centers. Matlab/Simulink models for the two converters have been built to verify the claimed contributions.","PeriodicalId":369098,"journal":{"name":"2019 IEEE 9th Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114363470","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 : 2019-04-01DOI: 10.1109/ISCAIE.2019.8743998
M. Z. Zainal Arifin, M. Kassim, A. R. Mahmud, Saiful Izwan Suliman
This paper presents a development of a Home Automation Security with Laser Lights Alarm that interfaces with web pages and Mobile apps. This system is designed to improve the security of a large space area like the factory from the robbery. A new development system using Raspberry Pi controllers which interface with Windows Mobile users and web pages which comprised on design system, hardware and sensors connections with programmed coding. Laser beam module and passive infrared (PIR) sensor are installed at a selected area to be protected to detect the intruder. Alerts lights are installed in a selected area. Lights are ON followed by alert's area when the laser is crossed out by intruders and PIR sensor detects changes of infrared radiation. Installed buzzers also are alert with sounds. LED lights are used to save energy consumed by lights. The alert message is sent out to mobile users and webpage. Reminder features of security activated set are also designed on the mobile apps. The prototype system is successfully developed and tested. The analysis shows there are 148 incoming messages and 196 of outgoing messages has been sent and delivered in 5 tested days. A total of 1157 of requests has been made by this system's software to the server and the results show 100% of the connection is successful. This research is significant for recent security issues on high rated of burglars for a large area. A large area security system is beneficial by implementing this system's concept of lights alert built that interfaces with mobile and webpage.
{"title":"Automation Security System with Laser Lights Alarm on Web Pages and Mobile Apps","authors":"M. Z. Zainal Arifin, M. Kassim, A. R. Mahmud, Saiful Izwan Suliman","doi":"10.1109/ISCAIE.2019.8743998","DOIUrl":"https://doi.org/10.1109/ISCAIE.2019.8743998","url":null,"abstract":"This paper presents a development of a Home Automation Security with Laser Lights Alarm that interfaces with web pages and Mobile apps. This system is designed to improve the security of a large space area like the factory from the robbery. A new development system using Raspberry Pi controllers which interface with Windows Mobile users and web pages which comprised on design system, hardware and sensors connections with programmed coding. Laser beam module and passive infrared (PIR) sensor are installed at a selected area to be protected to detect the intruder. Alerts lights are installed in a selected area. Lights are ON followed by alert's area when the laser is crossed out by intruders and PIR sensor detects changes of infrared radiation. Installed buzzers also are alert with sounds. LED lights are used to save energy consumed by lights. The alert message is sent out to mobile users and webpage. Reminder features of security activated set are also designed on the mobile apps. The prototype system is successfully developed and tested. The analysis shows there are 148 incoming messages and 196 of outgoing messages has been sent and delivered in 5 tested days. A total of 1157 of requests has been made by this system's software to the server and the results show 100% of the connection is successful. This research is significant for recent security issues on high rated of burglars for a large area. A large area security system is beneficial by implementing this system's concept of lights alert built that interfaces with mobile and webpage.","PeriodicalId":369098,"journal":{"name":"2019 IEEE 9th Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129418990","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 : 2019-04-01DOI: 10.1109/ISCAIE.2019.8743751
A. Huong, X. Ngu
This study presented the use of Neural Network (NN) approach in the prediction of transcutaneous oxygen saturation level, StO2. This is to overcome the limitation of using conventional signal processing approaches that are computational exhaustive. The accuracy of the NN predictive model was tested on 35 sets of new noise-corrupted Monte Carlo simulation data. This study found mean absolute error of 2.91± 2.29 % in its predictions while the statistical test revealed a strong correlation between the considered features and the predictions (ρ = 0.000). This work concluded that the proposed technique could promote further advancement in the current technology specifically in the development of portable StO2 measurement system.
{"title":"Neural Network approach for rapid prediction of transcutaneous oxygen saturation","authors":"A. Huong, X. Ngu","doi":"10.1109/ISCAIE.2019.8743751","DOIUrl":"https://doi.org/10.1109/ISCAIE.2019.8743751","url":null,"abstract":"This study presented the use of Neural Network (NN) approach in the prediction of transcutaneous oxygen saturation level, StO2. This is to overcome the limitation of using conventional signal processing approaches that are computational exhaustive. The accuracy of the NN predictive model was tested on 35 sets of new noise-corrupted Monte Carlo simulation data. This study found mean absolute error of 2.91± 2.29 % in its predictions while the statistical test revealed a strong correlation between the considered features and the predictions (ρ = 0.000). This work concluded that the proposed technique could promote further advancement in the current technology specifically in the development of portable StO2 measurement system.","PeriodicalId":369098,"journal":{"name":"2019 IEEE 9th Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131201443","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 : 2019-04-01DOI: 10.1109/ISCAIE.2019.8743805
Ezmin Abdullah, Eber Lazareen Anak Ignatius, N. Hidayat, N. I. Shuhaimi, R. Mohamad
Energy audit is a systematic process to understand how and where the energy is being used. From the audits, energy auditor can identify the energy saving potential and can decide energy management tasks base on the report. However, there are several important challenges need to be considered in conducting energy audits especially in collecting field data at the multiple locations with various parameters. Previously, energy auditors need some number of data loggers in order to log the data from different parameters such as voltage, current, temperature, humidity and lux. The loggers come from various brands, software’s and purposes. This inefficient process cause the unsynchronized date and time, different logging period and logging time interval which consequently leads to high cost of equipment used, manpower, time consuming and low accuracy of data taken. The aims of this project was to develop a tool dedicated to energy auditor to improve the energy audit process during field data collection named variable input/output data logger that combined various parameters under one tool. This project utilized Field Programmable Gate Array board (FPGA) on the design part using platform designer software (QSYS) to generate the Verilog coding in the Quartus Prime Lite software and Altera DE1-Soc development board for the prototype. In this project, the developed data logger had the ability to measure and logged three essential parameters that would be used for energy analysis which were voltage, current and temperature. The results showed all the parameters worked concurrently and time synchronized controlled by only one data logger. The time interval for each parameter can be easily set to the any other counting at the clock set in the Qsys software. Lastly, the logged data from the logger could be displayed in real time when connected to computer for immediate observation and also could be saved systematically in Excel format for energy report analysis. This project benefits energy auditor for their auditing works and report preparation in term of time consume, cost and increase data reliability due to synchronization of date and time.
能源审计是一个了解能源使用方式和地点的系统过程。从审计中，能源审计员可以识别节能潜力，并根据报告确定能源管理任务。然而，在进行能源审计时，需要考虑几个重要的挑战，特别是在收集多个地点的不同参数的现场数据时。以前，能源审计人员需要一定数量的数据记录器，以便记录来自不同参数的数据，如电压、电流、温度、湿度和勒克斯。这些记录器来自不同的品牌、软件和用途。这种低效率的过程造成了日期和时间不同步，测井周期和测井时间间隔不同，从而导致使用的设备成本高，人力，耗时，数据准确性低。该项目的目的是开发一种专用于能源审计员的工具，以改善现场数据收集过程中的能源审计过程，该工具名为可变输入/输出数据记录器，将各种参数组合在一个工具下。本项目在设计部分使用现场可编程门阵列板(FPGA)，使用平台设计软件(QSYS)在Quartus Prime Lite软件和Altera DE1-Soc开发板中生成Verilog编码。在这个项目中，开发的数据记录仪能够测量和记录三个基本参数，这些参数将用于能量分析，即电压，电流和温度。结果表明，所有参数同时工作，时间同步，仅由一个数据记录器控制。每个参数的时间间隔可以很容易地设置为在Qsys软件中设置的时钟上的任何其他计数。最后，记录仪记录的数据与计算机连接后可实时显示，便于即时观察，并可系统保存成Excel格式，供能源报表分析使用。该项目为能源审计人员的审计工作和报告编制节省了时间和成本，同时由于日期和时间的同步，提高了数据的可靠性。
{"title":"Variable Input/Output Data Logging System Using FPGA for Energy Audit","authors":"Ezmin Abdullah, Eber Lazareen Anak Ignatius, N. Hidayat, N. I. Shuhaimi, R. Mohamad","doi":"10.1109/ISCAIE.2019.8743805","DOIUrl":"https://doi.org/10.1109/ISCAIE.2019.8743805","url":null,"abstract":"Energy audit is a systematic process to understand how and where the energy is being used. From the audits, energy auditor can identify the energy saving potential and can decide energy management tasks base on the report. However, there are several important challenges need to be considered in conducting energy audits especially in collecting field data at the multiple locations with various parameters. Previously, energy auditors need some number of data loggers in order to log the data from different parameters such as voltage, current, temperature, humidity and lux. The loggers come from various brands, software’s and purposes. This inefficient process cause the unsynchronized date and time, different logging period and logging time interval which consequently leads to high cost of equipment used, manpower, time consuming and low accuracy of data taken. The aims of this project was to develop a tool dedicated to energy auditor to improve the energy audit process during field data collection named variable input/output data logger that combined various parameters under one tool. This project utilized Field Programmable Gate Array board (FPGA) on the design part using platform designer software (QSYS) to generate the Verilog coding in the Quartus Prime Lite software and Altera DE1-Soc development board for the prototype. In this project, the developed data logger had the ability to measure and logged three essential parameters that would be used for energy analysis which were voltage, current and temperature. The results showed all the parameters worked concurrently and time synchronized controlled by only one data logger. The time interval for each parameter can be easily set to the any other counting at the clock set in the Qsys software. Lastly, the logged data from the logger could be displayed in real time when connected to computer for immediate observation and also could be saved systematically in Excel format for energy report analysis. This project benefits energy auditor for their auditing works and report preparation in term of time consume, cost and increase data reliability due to synchronization of date and time.","PeriodicalId":369098,"journal":{"name":"2019 IEEE 9th Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134501165","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 : 2019-04-01DOI: 10.1109/ISCAIE.2019.8743672
Chengqian Ma, W. Hu, Yayin Deng
Software engineering & Integrated project includes both software development and hardware construction processes ,while its progress control is one of the main problems faced by construction units and owners. Critical chain project management minimized the risk of progress through setting a Buffer, managed stratification of the software and hardware processes of the software engineering and integrated project, compared with traditional progress management methods , which owned natural advantages. Based on the critical chain management methods, this paper proposed an improved technique which combined critical chain with the traditional earned value technique. Drawn references from the PERT Methods, this method determined the scheduled duration in three situations: unconsumed buffer, completely consumed buffer and most likely consumed buffer, transformed the critical chain project duration into traditional earned value project duration, and then carried out the earned value analysis, at the same time, the monitoring of buffer consumption was improved. The method controlled the project schedule at both external and internal levels, which improved the accuracy and flexibility of duration monitoring and conducted an empirical research by taking a software engineering and integrated project as an example.
{"title":"Application of Improved Critical Chain and Earned Value Technique in Software Engineering & Integrated Project Progress Control","authors":"Chengqian Ma, W. Hu, Yayin Deng","doi":"10.1109/ISCAIE.2019.8743672","DOIUrl":"https://doi.org/10.1109/ISCAIE.2019.8743672","url":null,"abstract":"Software engineering & Integrated project includes both software development and hardware construction processes ,while its progress control is one of the main problems faced by construction units and owners. Critical chain project management minimized the risk of progress through setting a Buffer, managed stratification of the software and hardware processes of the software engineering and integrated project, compared with traditional progress management methods , which owned natural advantages. Based on the critical chain management methods, this paper proposed an improved technique which combined critical chain with the traditional earned value technique. Drawn references from the PERT Methods, this method determined the scheduled duration in three situations: unconsumed buffer, completely consumed buffer and most likely consumed buffer, transformed the critical chain project duration into traditional earned value project duration, and then carried out the earned value analysis, at the same time, the monitoring of buffer consumption was improved. The method controlled the project schedule at both external and internal levels, which improved the accuracy and flexibility of duration monitoring and conducted an empirical research by taking a software engineering and integrated project as an example.","PeriodicalId":369098,"journal":{"name":"2019 IEEE 9th Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130784495","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 : 2019-04-01DOI: 10.1109/ISCAIE.2019.8743665
J. Abdullah, M. K. Hussien, N. Alduais, M. Husni, A. Jamil
Wireless sensor networks (WSN) are critically resource constrained due to small memory, limited power supply, low processing capability and narrow communication bandwidth. Tremendous researches are geared towards optimizing some aspects of packet transmissions to mitigate those constraints. The energy efficiency of a sensor node is affected by the process of data packet transmission from the sensor board to the fusion center (FC) and also by its packet size. An effective technique to reduce data transmission within the WSN, is to locally reduce the number of packets before transmission. In this paper, the performance of different computational intelligence based algorithms that reduce the data packet traffic is presented. These methods are data reduction based on artificial neural networks (DR-ANN); data reduction methods based on Independent Component Analysis (DR-ICA) and one that is based on regression utilizing deep learning method (DR-GDMLR). These algorithms have been applied to different applications and datasets type. The simulation results with best performance is shown by the DR-ANN algorithm that reduced the size of transmitted data by 66%, while the other two algorithms only reduced the size by 33% only.
{"title":"Data Reduction Algorithms based on Computational Intelligence for Wireless Sensor Networks Applications","authors":"J. Abdullah, M. K. Hussien, N. Alduais, M. Husni, A. Jamil","doi":"10.1109/ISCAIE.2019.8743665","DOIUrl":"https://doi.org/10.1109/ISCAIE.2019.8743665","url":null,"abstract":"Wireless sensor networks (WSN) are critically resource constrained due to small memory, limited power supply, low processing capability and narrow communication bandwidth. Tremendous researches are geared towards optimizing some aspects of packet transmissions to mitigate those constraints. The energy efficiency of a sensor node is affected by the process of data packet transmission from the sensor board to the fusion center (FC) and also by its packet size. An effective technique to reduce data transmission within the WSN, is to locally reduce the number of packets before transmission. In this paper, the performance of different computational intelligence based algorithms that reduce the data packet traffic is presented. These methods are data reduction based on artificial neural networks (DR-ANN); data reduction methods based on Independent Component Analysis (DR-ICA) and one that is based on regression utilizing deep learning method (DR-GDMLR). These algorithms have been applied to different applications and datasets type. The simulation results with best performance is shown by the DR-ANN algorithm that reduced the size of transmitted data by 66%, while the other two algorithms only reduced the size by 33% only.","PeriodicalId":369098,"journal":{"name":"2019 IEEE 9th Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130830490","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 : 2019-04-01DOI: 10.1109/ISCAIE.2019.8743904
Jackson Teh Ka Sing, Usman Ullah Sheikh, M. Mokji, N. Alias
High Efficiency Video Coding (HEVC) doubles the data compression ratio compared to previous generation compression technology, Moving Picture Expert Group-Advanced Video Codec (MPEG-AVC/H.264) without sacrificing the image quality. However, this superior compression comes at the cost of more computation payload resulting in longer time for encoding and decoding. This work proposes the vectorization on HEVC data heavy computation algorithm, Hadamard Transform or Sum of Absolute Transform Difference (SATD) and Sum of Absolute Difference (SAD) to achieve optimized compression performance. Single Instruction Multiple Data (SIMD) acceleration will be based on the Intel AVX-512 (Advanced Vector Extension) Instruction Set Architecture (ISA). Since HEVC supports more coding tree block (CTB) sizes, SATD and SAD algorithms eventually become more complex compared to AVC. As a result, SATD and SAD algorithms with various block sizes will be subjected to SIMD acceleration. We provide performance evaluation based on different SIMD ISA and without SIMD implementation on HEVC SATD and SAD and found that AVX-512 optimized implementation performed faster when compared to non- optimized SATD and SAD but showed signs of reduced performance when compared to SSE optimized SATD and SAD.
{"title":"Hadamard Transform Improvement for HEVC using Intel AVX-512","authors":"Jackson Teh Ka Sing, Usman Ullah Sheikh, M. Mokji, N. Alias","doi":"10.1109/ISCAIE.2019.8743904","DOIUrl":"https://doi.org/10.1109/ISCAIE.2019.8743904","url":null,"abstract":"High Efficiency Video Coding (HEVC) doubles the data compression ratio compared to previous generation compression technology, Moving Picture Expert Group-Advanced Video Codec (MPEG-AVC/H.264) without sacrificing the image quality. However, this superior compression comes at the cost of more computation payload resulting in longer time for encoding and decoding. This work proposes the vectorization on HEVC data heavy computation algorithm, Hadamard Transform or Sum of Absolute Transform Difference (SATD) and Sum of Absolute Difference (SAD) to achieve optimized compression performance. Single Instruction Multiple Data (SIMD) acceleration will be based on the Intel AVX-512 (Advanced Vector Extension) Instruction Set Architecture (ISA). Since HEVC supports more coding tree block (CTB) sizes, SATD and SAD algorithms eventually become more complex compared to AVC. As a result, SATD and SAD algorithms with various block sizes will be subjected to SIMD acceleration. We provide performance evaluation based on different SIMD ISA and without SIMD implementation on HEVC SATD and SAD and found that AVX-512 optimized implementation performed faster when compared to non- optimized SATD and SAD but showed signs of reduced performance when compared to SSE optimized SATD and SAD.","PeriodicalId":369098,"journal":{"name":"2019 IEEE 9th Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":"8 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130327688","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 : 2019-04-01DOI: 10.1109/ISCAIE.2019.8743995
Ka‐Wing Tse, K. Hung
Due to the explosive growth of mobile devices worldwide, authentication is receiving increasing attention. Conventionally, explicit authentication methods such as password is employed. However, the system would be breached if the password is stolen. Therefore, there is a continual search for ways to strengthen authentication for mobile platforms. Behavioral biometric information such as keystroke and swipe dynamics can be used for enhancing security. This paper presents an authentication scheme which employs a combination of password, keystroke dynamics, and swipe dynamics for touchscreen mobile devices. Features extracted from swiping pattern and typing pattern were evaluated. Accuracy of the system was enhanced by using combined behavioral biometrics features, as compared with using only a single set of features. The identification accuracies increased significantly from the range of 63.03% - 88.30% to 86.59% -94.05%; while the F1 scores increased from the range of 60.42% - 85.96% to 85.43% - 93.15%.
{"title":"Behavioral Biometrics Scheme with Keystroke and Swipe Dynamics for User Authentication on Mobile Platform","authors":"Ka‐Wing Tse, K. Hung","doi":"10.1109/ISCAIE.2019.8743995","DOIUrl":"https://doi.org/10.1109/ISCAIE.2019.8743995","url":null,"abstract":"Due to the explosive growth of mobile devices worldwide, authentication is receiving increasing attention. Conventionally, explicit authentication methods such as password is employed. However, the system would be breached if the password is stolen. Therefore, there is a continual search for ways to strengthen authentication for mobile platforms. Behavioral biometric information such as keystroke and swipe dynamics can be used for enhancing security. This paper presents an authentication scheme which employs a combination of password, keystroke dynamics, and swipe dynamics for touchscreen mobile devices. Features extracted from swiping pattern and typing pattern were evaluated. Accuracy of the system was enhanced by using combined behavioral biometrics features, as compared with using only a single set of features. The identification accuracies increased significantly from the range of 63.03% - 88.30% to 86.59% -94.05%; while the F1 scores increased from the range of 60.42% - 85.96% to 85.43% - 93.15%.","PeriodicalId":369098,"journal":{"name":"2019 IEEE 9th Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132385012","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：