Pub Date : 2018-04-01DOI: 10.1109/ISCAIE.2018.8405494
Chi Qin Lai, H. Ibrahim, M. Abdullah, J. Abdullah, S. A. Suandi, A. Azman
Electroencephalogram (EEG) is used to study the activity of human brain using instrument named electroen-cephalograph. The application of EEG is now widened to many fields due to its great temporal resolution and other advantages. To utilize the advantage of EEG, the correct setup need to be done for recording the EEG. This is to ensure the EEG recorded is informative enough to serve the targeting application. In this paper, a literature study has been done to explore parameters of EEG recording used for different application. The parameters are number of channels, sampling rate and recording duration. It was found that for medical applications, the number of channel used ranging from two to 100 channels, sampling rate of 100Hz to 3000Hz, and recording duration from 3000 seconds to 21600 seconds. For BCI and neuromarketing, the number of channels used is from one up to 256 channels, 100Hz to 1000Hz sampling rate, and recording duration from five seconds onwards and some researches used continuous recording.
{"title":"Literature survey: Recording set up for electroencephalography (EEG) acquisition","authors":"Chi Qin Lai, H. Ibrahim, M. Abdullah, J. Abdullah, S. A. Suandi, A. Azman","doi":"10.1109/ISCAIE.2018.8405494","DOIUrl":"https://doi.org/10.1109/ISCAIE.2018.8405494","url":null,"abstract":"Electroencephalogram (EEG) is used to study the activity of human brain using instrument named electroen-cephalograph. The application of EEG is now widened to many fields due to its great temporal resolution and other advantages. To utilize the advantage of EEG, the correct setup need to be done for recording the EEG. This is to ensure the EEG recorded is informative enough to serve the targeting application. In this paper, a literature study has been done to explore parameters of EEG recording used for different application. The parameters are number of channels, sampling rate and recording duration. It was found that for medical applications, the number of channel used ranging from two to 100 channels, sampling rate of 100Hz to 3000Hz, and recording duration from 3000 seconds to 21600 seconds. For BCI and neuromarketing, the number of channels used is from one up to 256 channels, 100Hz to 1000Hz sampling rate, and recording duration from five seconds onwards and some researches used continuous recording.","PeriodicalId":333327,"journal":{"name":"2018 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114335863","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 : 2018-04-01DOI: 10.1109/ISCAIE.2018.8405507
Z. Iqbal, R. Ilyas, W. Shahzad, Irum Inayat
New technologies are being adapted to made progress in healthcare especially for independent livings. Medication at distance is leading to integrate technologies with medical. Machine learning methods in collaboration with wearable sensor network technology are used to find hidden patterns in data, detect patient movements, observe habits of patient, analyze clinical data of patient, find intention of patients and make decision on the bases of gathered data. This research performs comparative study on non-clinical systems in healthcare for independent livings. In this study, these systems are sub-divided w.r.t their working into two types: single purpose systems and multi-purpose systems. Systems that are built for single specific purpose (e.g. detect fall, detect emergent state of chronic disease patient) and cannot support healthcare generically are known as single purpose systems, where multi-purpose systems are built to serve for multiple problems (e.g. heart attack, fall detection etc.) by using single system. This study analyzes usages of machine learning techniques in healthcare systems for independent livings. Answer Set Programming (ASP), Artificial Neural Networks, Classification, Sampling and Rule Based Reasoning etc. are some state of art techniques used to determine emergent situations and observe changes in patient data. Among all methods, ASP logic is used most widely, it is due to its feature to deal with incomplete data. It is also observed that system using ANN shows better accuracy than other systems. It is observed that most of the systems created are for single purpose. In this work, 10 single purpose systems and 5 multi-purpose systems are studied. There is need to create more generic systems that can be used for patients with multiple diseases. Furthermore, most of the systems created are prototypical. There is need to create systems that can serve healthcare services in real world. Some systems are hard to be used in real life due to large hardware requirements. Although, good systems are created but still there is need to build more efficient, affordable, adoptive and generic systems.
{"title":"A comparative study of machine learning techniques used in non-clinical systems for continuous healthcare of independent livings","authors":"Z. Iqbal, R. Ilyas, W. Shahzad, Irum Inayat","doi":"10.1109/ISCAIE.2018.8405507","DOIUrl":"https://doi.org/10.1109/ISCAIE.2018.8405507","url":null,"abstract":"New technologies are being adapted to made progress in healthcare especially for independent livings. Medication at distance is leading to integrate technologies with medical. Machine learning methods in collaboration with wearable sensor network technology are used to find hidden patterns in data, detect patient movements, observe habits of patient, analyze clinical data of patient, find intention of patients and make decision on the bases of gathered data. This research performs comparative study on non-clinical systems in healthcare for independent livings. In this study, these systems are sub-divided w.r.t their working into two types: single purpose systems and multi-purpose systems. Systems that are built for single specific purpose (e.g. detect fall, detect emergent state of chronic disease patient) and cannot support healthcare generically are known as single purpose systems, where multi-purpose systems are built to serve for multiple problems (e.g. heart attack, fall detection etc.) by using single system. This study analyzes usages of machine learning techniques in healthcare systems for independent livings. Answer Set Programming (ASP), Artificial Neural Networks, Classification, Sampling and Rule Based Reasoning etc. are some state of art techniques used to determine emergent situations and observe changes in patient data. Among all methods, ASP logic is used most widely, it is due to its feature to deal with incomplete data. It is also observed that system using ANN shows better accuracy than other systems. It is observed that most of the systems created are for single purpose. In this work, 10 single purpose systems and 5 multi-purpose systems are studied. There is need to create more generic systems that can be used for patients with multiple diseases. Furthermore, most of the systems created are prototypical. There is need to create systems that can serve healthcare services in real world. Some systems are hard to be used in real life due to large hardware requirements. Although, good systems are created but still there is need to build more efficient, affordable, adoptive and generic systems.","PeriodicalId":333327,"journal":{"name":"2018 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123005248","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 : 2018-04-01DOI: 10.1109/ISCAIE.2018.8405452
G. Ang, Wei Ze Lim, C. Lim
An effective and computationally less intensive method for the stabilization of a Two-Input Two-Output, TITO, system is presented. The Input-Output (IO) models of the TITO under study are each described by a discrete-time model with its parameters estimated once every sample time. The discrete-time models are used in conjunction with two proposed performance indices to yield control signals to improve the overall system performance. The ability of the proposed self-tuning control scheme to reject small and large disturbances, and to overcome strong couplings in Multi-Input Multi-Output, MIMO, systems are investigated and presented in this study. Simulation tests show that the proposed enhanced self-tuning control scheme is suitable for Single-Input Single-Output (SISO) and MIMO systems.
{"title":"A proposed two-input two-output self-tuning control scheme","authors":"G. Ang, Wei Ze Lim, C. Lim","doi":"10.1109/ISCAIE.2018.8405452","DOIUrl":"https://doi.org/10.1109/ISCAIE.2018.8405452","url":null,"abstract":"An effective and computationally less intensive method for the stabilization of a Two-Input Two-Output, TITO, system is presented. The Input-Output (IO) models of the TITO under study are each described by a discrete-time model with its parameters estimated once every sample time. The discrete-time models are used in conjunction with two proposed performance indices to yield control signals to improve the overall system performance. The ability of the proposed self-tuning control scheme to reject small and large disturbances, and to overcome strong couplings in Multi-Input Multi-Output, MIMO, systems are investigated and presented in this study. Simulation tests show that the proposed enhanced self-tuning control scheme is suitable for Single-Input Single-Output (SISO) and MIMO systems.","PeriodicalId":333327,"journal":{"name":"2018 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132478575","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 : 2018-04-01DOI: 10.1109/ISCAIE.2018.8405491
R. A. Hamzah, M. S. Hamid, A. F. Kadmin, S. Ghani, S. S. Fakulti, Teknologi Kejuruteraan, Kampus Teknologi
This paper proposes a new stereo matching algorithm which uses Sum of Absolute RGB Differences. Generally, stereo matching algorithm is sensitive to low texture areas and high noise on images with high different brightness and contrast. To get over these problems, the proposed algorithm utilizes the RGB channels at the matching stage and edge-preserving filter at the second and final stage. The filter is known as Bilateral Filter (BF). The BF kernel well-recovered low texture areas which is able to reduce noise and sharpen the images. Additionally, BF is strong against the distortions due to high brightness and contrast. The propose algorithm produces accurate results on the disparity map for the low textured regions. The proposed work in this paper produces accurate results and performs much better compared to some established algorithms based on the quantitative and qualitative measurements using standard stereo benchmarking evaluation from the Middlebury.
{"title":"Matching cost computation based on sum of absolute RGB differences","authors":"R. A. Hamzah, M. S. Hamid, A. F. Kadmin, S. Ghani, S. S. Fakulti, Teknologi Kejuruteraan, Kampus Teknologi","doi":"10.1109/ISCAIE.2018.8405491","DOIUrl":"https://doi.org/10.1109/ISCAIE.2018.8405491","url":null,"abstract":"This paper proposes a new stereo matching algorithm which uses Sum of Absolute RGB Differences. Generally, stereo matching algorithm is sensitive to low texture areas and high noise on images with high different brightness and contrast. To get over these problems, the proposed algorithm utilizes the RGB channels at the matching stage and edge-preserving filter at the second and final stage. The filter is known as Bilateral Filter (BF). The BF kernel well-recovered low texture areas which is able to reduce noise and sharpen the images. Additionally, BF is strong against the distortions due to high brightness and contrast. The propose algorithm produces accurate results on the disparity map for the low textured regions. The proposed work in this paper produces accurate results and performs much better compared to some established algorithms based on the quantitative and qualitative measurements using standard stereo benchmarking evaluation from the Middlebury.","PeriodicalId":333327,"journal":{"name":"2018 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129510993","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 : 2018-04-01DOI: 10.1109/ISCAIE.2018.8405461
Asmaa Elekhtiar, Lobna Eltagy, Tassneem Zamzam, A. Massoud
Electric Vehicles (EV) nowadays are an attractive means of transportation, as they do not emit harmful gasses. Charging of EVs can be achieved through either direct contact or contactless approaches. Contactless charging approach, as Inductive Power Transfer (IPT) system, provides several merits. Yet, the IPT system has several problems; the most severe one is that it causes health issues, since it is based on electromagnetic induction. The alternative method of transferring power wirelessly is the Capacitive Power Transfer (CPT). The basic concept of a CPT system is based on the power transferal via electric fields between the plates. In this paper, a 5kW CPT system is designed with SiC MOSFET-based inverter. A compensating network, connected to the coupling capacitor, is used. The system is then connected to a rectifier to feed a battery. CPT different aspects are studied in this paper. The system is simulated using MATLAB/Simulink and tested experimentally to examine the performance.
{"title":"Design of a capacitive power transfer system for charging of electric vehicles","authors":"Asmaa Elekhtiar, Lobna Eltagy, Tassneem Zamzam, A. Massoud","doi":"10.1109/ISCAIE.2018.8405461","DOIUrl":"https://doi.org/10.1109/ISCAIE.2018.8405461","url":null,"abstract":"Electric Vehicles (EV) nowadays are an attractive means of transportation, as they do not emit harmful gasses. Charging of EVs can be achieved through either direct contact or contactless approaches. Contactless charging approach, as Inductive Power Transfer (IPT) system, provides several merits. Yet, the IPT system has several problems; the most severe one is that it causes health issues, since it is based on electromagnetic induction. The alternative method of transferring power wirelessly is the Capacitive Power Transfer (CPT). The basic concept of a CPT system is based on the power transferal via electric fields between the plates. In this paper, a 5kW CPT system is designed with SiC MOSFET-based inverter. A compensating network, connected to the coupling capacitor, is used. The system is then connected to a rectifier to feed a battery. CPT different aspects are studied in this paper. The system is simulated using MATLAB/Simulink and tested experimentally to examine the performance.","PeriodicalId":333327,"journal":{"name":"2018 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125051461","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 : 2018-04-01DOI: 10.1109/ISCAIE.2018.8405489
K. Chew, Ching Yee Yong, R. Sudirman, Syvester Tan Chiang Wei
The paper discussed on the bio-signal processing and 2D representation of a near-field radar microwave analysis system using a mono-static ultra-wideband fabric antenna for brain tumor detection. Simulation of a brain tumor was done by developing a brain phantom with tumor using a new composition of agar-agar, sugar and water based on the relative permittivity, ∊r of the real human brain. In the simulation environment, the antenna travelled along planar y-axis and the reflected signals, S11 from the phantom were collected for processing. Five regular window functions and a proposed superposition technique function were applied to determine the reflection point. Following that, the linear interpolation and contrast enhancement technique were applied for a 2-dimensional (2D) representation enhancement.
{"title":"Bio-signal processing and 2D representation for brain tumor detection using microwave signal analysis","authors":"K. Chew, Ching Yee Yong, R. Sudirman, Syvester Tan Chiang Wei","doi":"10.1109/ISCAIE.2018.8405489","DOIUrl":"https://doi.org/10.1109/ISCAIE.2018.8405489","url":null,"abstract":"The paper discussed on the bio-signal processing and 2D representation of a near-field radar microwave analysis system using a mono-static ultra-wideband fabric antenna for brain tumor detection. Simulation of a brain tumor was done by developing a brain phantom with tumor using a new composition of agar-agar, sugar and water based on the relative permittivity, ∊r of the real human brain. In the simulation environment, the antenna travelled along planar y-axis and the reflected signals, S11 from the phantom were collected for processing. Five regular window functions and a proposed superposition technique function were applied to determine the reflection point. Following that, the linear interpolation and contrast enhancement technique were applied for a 2-dimensional (2D) representation enhancement.","PeriodicalId":333327,"journal":{"name":"2018 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126670308","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 : 2018-04-01DOI: 10.1109/ISCAIE.2018.8405487
Hong Ning Choo, N. A. A. Latiff, P. Varahram, B. Ali
The non-linear characteristic of the Power Amplifier (PA) causes system inefficiency and signal distortion when operating in the non-linear region. High Peak to Average Power Ratio (PAPR) in recent high speed wireless communications technology causes Memory Effects, where the PA output signal deteriorates with unwanted scattering and distortion against the ideal signal value. To solve the PA non-linearity effects, Digital Pre-distortion (DPD) is chosen among other linearization methods due to its attractive strengths on ease of implementation, supported bandwidth, flexibility, efficiency and cost. A precise modeling of the PA is required in order to compliment the effectiveness of DPD in terms of resources and performance. Memory Polynomial (MP) has been employed widely in the industry and academia on PA modeling due to its significant resource reduction from Volterra Series. The Memory Polynomial with Binomial Reduction method (MPB-imag-2k) was developed where similar performance is achieved using lesser resources compared to MP. MPB-imag-2k was enhanced into MPB on its Normalized Mean Square Error (NMSE). This paper exhibits the resource optimization in terms of calculation and multiplication operations by using the Calculation Complexity Reduction Ratio (CCRR). CCRR is derived into Multiplications Operations Reduction Ratio (MORR) together with Addition Operations Reduction Ratio (aORR) for both MPB and MP. A modeled ZVE-8G PA and sampled 4G (LTE) signals are used in the simulation. MPB is compared with MP in the non-linearity order range of 1 to 4, pre-amplifier gain (PAG) of 2 to 4, with up to 36dB improvement in NMSE, 57% of MORR and 87.5% of AORR.
{"title":"Operations optimization of memory polynomial with binomial reduction in digital pre-distortion for wireless communication systems","authors":"Hong Ning Choo, N. A. A. Latiff, P. Varahram, B. Ali","doi":"10.1109/ISCAIE.2018.8405487","DOIUrl":"https://doi.org/10.1109/ISCAIE.2018.8405487","url":null,"abstract":"The non-linear characteristic of the Power Amplifier (PA) causes system inefficiency and signal distortion when operating in the non-linear region. High Peak to Average Power Ratio (PAPR) in recent high speed wireless communications technology causes Memory Effects, where the PA output signal deteriorates with unwanted scattering and distortion against the ideal signal value. To solve the PA non-linearity effects, Digital Pre-distortion (DPD) is chosen among other linearization methods due to its attractive strengths on ease of implementation, supported bandwidth, flexibility, efficiency and cost. A precise modeling of the PA is required in order to compliment the effectiveness of DPD in terms of resources and performance. Memory Polynomial (MP) has been employed widely in the industry and academia on PA modeling due to its significant resource reduction from Volterra Series. The Memory Polynomial with Binomial Reduction method (MPB-imag-2k) was developed where similar performance is achieved using lesser resources compared to MP. MPB-imag-2k was enhanced into MPB on its Normalized Mean Square Error (NMSE). This paper exhibits the resource optimization in terms of calculation and multiplication operations by using the Calculation Complexity Reduction Ratio (CCRR). CCRR is derived into Multiplications Operations Reduction Ratio (MORR) together with Addition Operations Reduction Ratio (aORR) for both MPB and MP. A modeled ZVE-8G PA and sampled 4G (LTE) signals are used in the simulation. MPB is compared with MP in the non-linearity order range of 1 to 4, pre-amplifier gain (PAG) of 2 to 4, with up to 36dB improvement in NMSE, 57% of MORR and 87.5% of AORR.","PeriodicalId":333327,"journal":{"name":"2018 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129846636","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 : 2018-04-01DOI: 10.1109/ISCAIE.2018.8405500
J. Jali, Ahmad Fuzi Md Ajis
E-Learning Maturity Model (eMM) is one of the tool to assess the current practices of Virtual Learning Environment (VLE) in Malaysia's Public University. The study assesses major processes which require critical improvement based on specific dimensions to enhance VLE operations in higher education institutions. The study compares findings from instructors and administrators of VLE practices to identify processes which require better enhancement to bring up parallel evaluation on the extent of practices of VLE within the institution. A parallel comparison was made to ensure integrity of the execution of VLE by both parties to identify which dimensions require critical improvements.
{"title":"VLE in Malaysia's Public University: Instructors VS administrators eMM outlook","authors":"J. Jali, Ahmad Fuzi Md Ajis","doi":"10.1109/ISCAIE.2018.8405500","DOIUrl":"https://doi.org/10.1109/ISCAIE.2018.8405500","url":null,"abstract":"E-Learning Maturity Model (eMM) is one of the tool to assess the current practices of Virtual Learning Environment (VLE) in Malaysia's Public University. The study assesses major processes which require critical improvement based on specific dimensions to enhance VLE operations in higher education institutions. The study compares findings from instructors and administrators of VLE practices to identify processes which require better enhancement to bring up parallel evaluation on the extent of practices of VLE within the institution. A parallel comparison was made to ensure integrity of the execution of VLE by both parties to identify which dimensions require critical improvements.","PeriodicalId":333327,"journal":{"name":"2018 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132730665","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 : 2018-04-01DOI: 10.1109/ISCAIE.2018.8405481
N. H. Noordin, L. B. Hwa, N. Hassan, R. Samad, Z. Ibrahim
This paper discusses the design of an RF switching using PIN diode for a 2.4GHz polarization reconfigurable antenna. The PIN diode in a switching circuit requires an accompanying PIN diode driver or switch driver that provides a controlled forward bias current and a reverse bias voltage. The 2.4GHz polarization reconfigurable antenna is able to switch between Linear Polarization (LP), Left Hand Circular Polarization (LHCP) and Right Hand Circular Polarization (RHCP). The RF switching circuit includes PIN diode, RF choke inductor and DC block capacitor. The antenna also demonstrates good matching performance between the result of axial ratio and frequency for all polarization modes.
{"title":"An RF switching circuit using PIN diode for a 2.4GHz frequency reconfigurable antenna","authors":"N. H. Noordin, L. B. Hwa, N. Hassan, R. Samad, Z. Ibrahim","doi":"10.1109/ISCAIE.2018.8405481","DOIUrl":"https://doi.org/10.1109/ISCAIE.2018.8405481","url":null,"abstract":"This paper discusses the design of an RF switching using PIN diode for a 2.4GHz polarization reconfigurable antenna. The PIN diode in a switching circuit requires an accompanying PIN diode driver or switch driver that provides a controlled forward bias current and a reverse bias voltage. The 2.4GHz polarization reconfigurable antenna is able to switch between Linear Polarization (LP), Left Hand Circular Polarization (LHCP) and Right Hand Circular Polarization (RHCP). The RF switching circuit includes PIN diode, RF choke inductor and DC block capacitor. The antenna also demonstrates good matching performance between the result of axial ratio and frequency for all polarization modes.","PeriodicalId":333327,"journal":{"name":"2018 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123663495","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 : 2018-04-01DOI: 10.1109/ISCAIE.2018.8405503
S. Ismail, Nik Intan Areena Nik Azlan, A. Mustapha
This paper is set to perform a comparative experiment on prediction of alcohol consumption among secondary school students. Data set used in this project contained 34 attribute was gathered from two Portuguese secondary schools in the year 2005–2006. Four classification algorithms are proposed and implemented, which include the Decision Tree, k-Nearest Neighbour (k-NN), Random Forest and Naïve Bayes. These methods were trained and tested using 10-fold cross validation. The results showed that the Decision Tree algorithm produced highest values for accuracy, recall and precision compared to other classification algorithms. Besides, it is observed that Naïve Bayes methods combined with Interquartile normalization provides a promising alternative classification technique in the area.
{"title":"Prediction of alcohol consumption among Portuguese secondary school students: A data mining approach","authors":"S. Ismail, Nik Intan Areena Nik Azlan, A. Mustapha","doi":"10.1109/ISCAIE.2018.8405503","DOIUrl":"https://doi.org/10.1109/ISCAIE.2018.8405503","url":null,"abstract":"This paper is set to perform a comparative experiment on prediction of alcohol consumption among secondary school students. Data set used in this project contained 34 attribute was gathered from two Portuguese secondary schools in the year 2005–2006. Four classification algorithms are proposed and implemented, which include the Decision Tree, k-Nearest Neighbour (k-NN), Random Forest and Naïve Bayes. These methods were trained and tested using 10-fold cross validation. The results showed that the Decision Tree algorithm produced highest values for accuracy, recall and precision compared to other classification algorithms. Besides, it is observed that Naïve Bayes methods combined with Interquartile normalization provides a promising alternative classification technique in the area.","PeriodicalId":333327,"journal":{"name":"2018 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124732781","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}