Pub Date : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123435
M. S. Fathillah, R. Jaafar, K. Chellappan, R. Remli, W. Zainal
Epileptologists use interictal epileptic discharge (lED) as a marker for epilepsy. The present conventional method to distinguish normal and I ED by an epileptologist's visual screening is tedious and operator dependent. The focus of this paper is to distinguish normal and IED in clinically recorded electroencephalogram (EEG) using discrete wavelet transform. Wavelet multiresolution analysis has been adopted in this study looking into wavelet energy, wavelet entropy and amplitude dispersion in every sub-band. The extracted features were classified using support vector machine (SVM). EEG data were obtained from both online database and Pusat Perubatan Universiti Kebangsaan Malaysia (PPUKM) Neurology database. The ability of the proposed algorithm in detecting the presence of IED is 96.5% of accuracy, 100% of sensitivity and 95.5% of specificity. The algorithm has good potential to be used in clinical practice for IED detection with validation against the present clinical detection method.
{"title":"Interictal epileptic discharge EEG detection based on wavelet and multiresolution analysis","authors":"M. S. Fathillah, R. Jaafar, K. Chellappan, R. Remli, W. Zainal","doi":"10.1109/ICSENGT.2017.8123435","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123435","url":null,"abstract":"Epileptologists use interictal epileptic discharge (lED) as a marker for epilepsy. The present conventional method to distinguish normal and I ED by an epileptologist's visual screening is tedious and operator dependent. The focus of this paper is to distinguish normal and IED in clinically recorded electroencephalogram (EEG) using discrete wavelet transform. Wavelet multiresolution analysis has been adopted in this study looking into wavelet energy, wavelet entropy and amplitude dispersion in every sub-band. The extracted features were classified using support vector machine (SVM). EEG data were obtained from both online database and Pusat Perubatan Universiti Kebangsaan Malaysia (PPUKM) Neurology database. The ability of the proposed algorithm in detecting the presence of IED is 96.5% of accuracy, 100% of sensitivity and 95.5% of specificity. The algorithm has good potential to be used in clinical practice for IED detection with validation against the present clinical detection method.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116794791","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123410
Suhaizal Hashim, Affero Ismail, A. Masek
School Based Assessment (SBA) has been in place since 2012 in Malaysia. Amongst the main purpose of it was to improve students' learning and assessment system. However, school still fails to explain and implement a broader assessment process that can improve teaching and learning and still using manual filing systems to manage and process the students result. Therefore, Collaborative Portfolio Assessment (CPA) learning system that use to scaffold students' knowledge was purposed as a solution. This paper presents the main characteristics of CPA learning system that was embedded with an interactive learning approach using group based activities to encourage students' active participation in their learning. The CPA learning system is a learning environment consuming the principle elements from knowledge management model, Computer Supported Collaborative Learning (CSCL) approaches and eportfolio as a learning documentation model. It also allows students to learn together through computer-mediated networks. CSCL learning strategies has been implemented with an eportfolio as a learning documentation model that expect to foster knowledge construction process by involving students to learn together through computer mediated networks. These process plans to help and manage the implementation of SBA in Malaysian school systematically. Assessment process conducted on this CPA learning system is hope to benefits teachers with emphasizing on assessment in the learning aspect and assisting to overcome issues of documentation filing, missing data, human negligence and to ensure that latest updates and information's about assessment is spread accordingly.
{"title":"The characteristics of collaborative portfolio assessment learning system as a tools in school based assessment environment","authors":"Suhaizal Hashim, Affero Ismail, A. Masek","doi":"10.1109/ICSENGT.2017.8123410","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123410","url":null,"abstract":"School Based Assessment (SBA) has been in place since 2012 in Malaysia. Amongst the main purpose of it was to improve students' learning and assessment system. However, school still fails to explain and implement a broader assessment process that can improve teaching and learning and still using manual filing systems to manage and process the students result. Therefore, Collaborative Portfolio Assessment (CPA) learning system that use to scaffold students' knowledge was purposed as a solution. This paper presents the main characteristics of CPA learning system that was embedded with an interactive learning approach using group based activities to encourage students' active participation in their learning. The CPA learning system is a learning environment consuming the principle elements from knowledge management model, Computer Supported Collaborative Learning (CSCL) approaches and eportfolio as a learning documentation model. It also allows students to learn together through computer-mediated networks. CSCL learning strategies has been implemented with an eportfolio as a learning documentation model that expect to foster knowledge construction process by involving students to learn together through computer mediated networks. These process plans to help and manage the implementation of SBA in Malaysian school systematically. Assessment process conducted on this CPA learning system is hope to benefits teachers with emphasizing on assessment in the learning aspect and assisting to overcome issues of documentation filing, missing data, human negligence and to ensure that latest updates and information's about assessment is spread accordingly.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116958906","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123419
Muhammad Hafiz Allias, Z. Muhammad, Z. Yusoff, M. Rahiman
This paper presents the performance of proportional-integral-derivative (PID) controller and Model Reference Adaptive Controller (MRAC) on regulating essential oil extraction process. The quality of essential oil will reduce if the extraction process expose to overheating of temperature. AutoRegressive with Exogenous Input (ARX) model represent as heating process plant. Heating process is important thing in the essential oil extraction and became challenging for industrial to control the temperature at the desired temperature. Besides, quality of essential oil will reduce if the extraction process expose to overheating of temperature. Generally, conventional PID controller that commonly used in control system is not provided a desired output performance. Implementation of MRAC by using Lyapunov approach in the system gives better response than conventional PID controller. Model reference of the system was developed based on first order plus dead time (FOPDT). In addition, ±0.1 is the best selection for adaptation gain of MRAC system. Result shows that MRAC controller was able to minimize its overshoot and robust in performance better than conventional PID controller. Conventional PID controller provided faster time taken in rise time, 1760 sec to initially reach the set point compared to MRAC, 2500 sec but MRAC takes in short time to settle the response, 4460 sec compared to PID, 7220 sec. The comparison of output response between both controllers was obtained by using transient analysis and performance indices in MATLAB/Simulink.
{"title":"Implementation of first order model reference adaptive control (MRAC) on regulating temperature of essential oil extraction process","authors":"Muhammad Hafiz Allias, Z. Muhammad, Z. Yusoff, M. Rahiman","doi":"10.1109/ICSENGT.2017.8123419","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123419","url":null,"abstract":"This paper presents the performance of proportional-integral-derivative (PID) controller and Model Reference Adaptive Controller (MRAC) on regulating essential oil extraction process. The quality of essential oil will reduce if the extraction process expose to overheating of temperature. AutoRegressive with Exogenous Input (ARX) model represent as heating process plant. Heating process is important thing in the essential oil extraction and became challenging for industrial to control the temperature at the desired temperature. Besides, quality of essential oil will reduce if the extraction process expose to overheating of temperature. Generally, conventional PID controller that commonly used in control system is not provided a desired output performance. Implementation of MRAC by using Lyapunov approach in the system gives better response than conventional PID controller. Model reference of the system was developed based on first order plus dead time (FOPDT). In addition, ±0.1 is the best selection for adaptation gain of MRAC system. Result shows that MRAC controller was able to minimize its overshoot and robust in performance better than conventional PID controller. Conventional PID controller provided faster time taken in rise time, 1760 sec to initially reach the set point compared to MRAC, 2500 sec but MRAC takes in short time to settle the response, 4460 sec compared to PID, 7220 sec. The comparison of output response between both controllers was obtained by using transient analysis and performance indices in MATLAB/Simulink.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"229 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124536767","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123430
N. Ya'acob, Ainnur Eiza Azhar, A. L. Yusof, S. S. Sarnin, D. Ali, A. Anuar
Vehicle accidents are one of the most leading causes of fatality. The time between an accident occurrence and the emergency medical personnel are dispatched to the location of accident is the critical factor in the survival rate after an accident. By minimizing the gap time, mortality rate can be reduced. One approach to reduce the delay time is to use the Real Time Wireless Accident Tracker Using Mobile Phone, a system which automatically senses the occurrence of an accident of a vehicle and immediately notify central emergency dispatch server of the location of accident using Global Positioning System (GPS). The main purpose of this research is as an early accident detection. This system uses PIC 16F microcontroller, piezoelectric sensors, GPS and Global System for Mobile (GSM) modules to detect traffic accidents. When an accident occurs, the piezoelectric sensor detects and measures the severity of the force impacted on the vehicle and sends out a help message to central emergency server. Upon acknowledgement from the server, the system sends out another message containing GPS coordinate of the location.
{"title":"Real time wireless accident tracker using mobile phone","authors":"N. Ya'acob, Ainnur Eiza Azhar, A. L. Yusof, S. S. Sarnin, D. Ali, A. Anuar","doi":"10.1109/ICSENGT.2017.8123430","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123430","url":null,"abstract":"Vehicle accidents are one of the most leading causes of fatality. The time between an accident occurrence and the emergency medical personnel are dispatched to the location of accident is the critical factor in the survival rate after an accident. By minimizing the gap time, mortality rate can be reduced. One approach to reduce the delay time is to use the Real Time Wireless Accident Tracker Using Mobile Phone, a system which automatically senses the occurrence of an accident of a vehicle and immediately notify central emergency dispatch server of the location of accident using Global Positioning System (GPS). The main purpose of this research is as an early accident detection. This system uses PIC 16F microcontroller, piezoelectric sensors, GPS and Global System for Mobile (GSM) modules to detect traffic accidents. When an accident occurs, the piezoelectric sensor detects and measures the severity of the force impacted on the vehicle and sends out a help message to central emergency server. Upon acknowledgement from the server, the system sends out another message containing GPS coordinate of the location.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"41 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113974788","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123450
R. Ristiana, A. S. Rohman, A. Purwadi, C. Machbub
This paper validates the advantage of using an integrated electric vehicle-battery model in torque control application. In the integrated electric vehicle-battery model, battery dynamics is explicitly included in the model. A well-known linear quadratic integral (LQI) design is adopted here to have an optimal controller with zero tracking error. The energy consumption is, however, observed through several energy consumption formulations. The performance index of the LQI is set to include input-state multiplication, i.e. representing one usual form of energy formulation. The controller designs are performed using linearized model of the integrated electric vehicle-battery model. By applying the linear LQI control to the non-linear integrated electric vehicle battery model, simulations are then taken. The simulation result shows that torque motor control with the inclusion of input-state multiplication in the LQI's performance index present a more energy efficient control in comparison to LQI design without such inclusion in its performance index. This may lead to a potential use of integrated electric vehicle battery model to have an efficient battery usage in controlling an electric vehicle.
{"title":"Energy efficient torque control using integrated battery-electric vehicle model","authors":"R. Ristiana, A. S. Rohman, A. Purwadi, C. Machbub","doi":"10.1109/ICSENGT.2017.8123450","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123450","url":null,"abstract":"This paper validates the advantage of using an integrated electric vehicle-battery model in torque control application. In the integrated electric vehicle-battery model, battery dynamics is explicitly included in the model. A well-known linear quadratic integral (LQI) design is adopted here to have an optimal controller with zero tracking error. The energy consumption is, however, observed through several energy consumption formulations. The performance index of the LQI is set to include input-state multiplication, i.e. representing one usual form of energy formulation. The controller designs are performed using linearized model of the integrated electric vehicle-battery model. By applying the linear LQI control to the non-linear integrated electric vehicle battery model, simulations are then taken. The simulation result shows that torque motor control with the inclusion of input-state multiplication in the LQI's performance index present a more energy efficient control in comparison to LQI design without such inclusion in its performance index. This may lead to a potential use of integrated electric vehicle battery model to have an efficient battery usage in controlling an electric vehicle.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124420238","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123441
M. Teow
The contribution of this paper is to bridge the gap on understanding the mathematical structure and the computational implementation of a convolutional neural network using a minimal model. The proposed minimal convolutional neural network is presented using a layering approach. This approach provides a clear understanding of the main mathematical operations in a convolutional neural network. Hence, it benefits beginners and non-mathematical prolific researchers to understand the operation of a convolutional neural network without having an intimidating experience. A handwritten digit recognition using MNIST handwritten digit dataset is used to experiment the performance of the proposed minimal convolutional neural network.
{"title":"A minimal convolutional neural network for handwritten digit recognition","authors":"M. Teow","doi":"10.1109/ICSENGT.2017.8123441","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123441","url":null,"abstract":"The contribution of this paper is to bridge the gap on understanding the mathematical structure and the computational implementation of a convolutional neural network using a minimal model. The proposed minimal convolutional neural network is presented using a layering approach. This approach provides a clear understanding of the main mathematical operations in a convolutional neural network. Hence, it benefits beginners and non-mathematical prolific researchers to understand the operation of a convolutional neural network without having an intimidating experience. A handwritten digit recognition using MNIST handwritten digit dataset is used to experiment the performance of the proposed minimal convolutional neural network.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130797602","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123438
Banphatree Khomkham, A. Wattanathum, R. Lipikorn
This paper aims to classify a peripheral pulmonary lesion whether it is malignant or benign by proposing the new method to select a window of interest (WOI) using window slicing and the new feature called the "weight-sum of upper and lower gray level co-occurrence matrix (GLCM)" of an endobronchial ultrasound (EBUS) image. The proposed feature can be used to determine the heterogeneity of pulmonary lesion which is one of the most important characteristics of lung cancer. The proposed feature is used as input into three different feature selection methods and three different classifiers for lesion classification. In order to evaluate the classification, a set of 89 EBUS images were used as a sample set. The classifications were performed three times with three different sets of features that were extracted from sample images using the same classification process. The first set of features consists of only standard features which are mean, contrast, homogeneity, correlation, entropy, and energy. The second set of features consists of the proposed feature, and the last set of features consists of both standard features and the proposed feature. The classification results show that using genetic selection as feature selection method with support vector machine as classifier with only the proposed features as input data gives the highest accuracy rate. The statistical results show that the accuracy, the sensitivity, and the specificity are 84.27%, 82.53%, and 88.46%, respectively.
{"title":"Peripheral pulmonary lesion classification from endobronchial ultrasonography images using weight-sum of upper and lower GLCM feature","authors":"Banphatree Khomkham, A. Wattanathum, R. Lipikorn","doi":"10.1109/ICSENGT.2017.8123438","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123438","url":null,"abstract":"This paper aims to classify a peripheral pulmonary lesion whether it is malignant or benign by proposing the new method to select a window of interest (WOI) using window slicing and the new feature called the \"weight-sum of upper and lower gray level co-occurrence matrix (GLCM)\" of an endobronchial ultrasound (EBUS) image. The proposed feature can be used to determine the heterogeneity of pulmonary lesion which is one of the most important characteristics of lung cancer. The proposed feature is used as input into three different feature selection methods and three different classifiers for lesion classification. In order to evaluate the classification, a set of 89 EBUS images were used as a sample set. The classifications were performed three times with three different sets of features that were extracted from sample images using the same classification process. The first set of features consists of only standard features which are mean, contrast, homogeneity, correlation, entropy, and energy. The second set of features consists of the proposed feature, and the last set of features consists of both standard features and the proposed feature. The classification results show that using genetic selection as feature selection method with support vector machine as classifier with only the proposed features as input data gives the highest accuracy rate. The statistical results show that the accuracy, the sensitivity, and the specificity are 84.27%, 82.53%, and 88.46%, respectively.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127771754","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123448
A. S. Rohman, Hanif F. Prasetyo
Many physical process systems have performance limitation regardless the input. This limitation usually occurs in the form of input saturation of actuator as the constraint of the system. To overcome this problem, Model Predictive Control (MPC) may be used due to its capability to compute optimal control signal in the presence of input saturation. The optimal control signal is obtained by solving a quadratic programming (QP) problem with variables' constraints at each time instants. QP problem with lower and upper constraint is known to be equivalent to an algebraic loop involving diagonal upper and lower saturation. Hence, QP can be iteratively computed until its solution converges. A slow computation of QP, however, limits its applications for fast systems with simple digital processor. Therefore, in order to be able to be implemented in real-time embedded applications, a fast algorithm of QP solver is in need. In this paper, a comparison study of two QP implementation, i.e. Projected Gauss Seidel (PGS) and so called Algorithm-2, using Arduino Mega 2560 is presented. In this case, MPC with QP solver using both algorithms is implemented to control the speed of lightly loaded BLDC motor. Before implementation, system modeling, controller designing, and simulation are undertaken. The performance of both iterative algorithms are then compared in terms of average computation time in the simulation and implementation. It can be observed from the results that Algorithm-2 gives a bit faster computation than PGS under same conditions.
无论输入是什么，许多物理进程系统都有性能限制。这种限制通常以执行器输入饱和的形式出现，作为系统的约束。为了克服这个问题，模型预测控制(MPC)可以在输入饱和的情况下计算出最优的控制信号。通过求解具有变量约束的二次规划(QP)问题，得到各时刻的最优控制信号。已知具有上下约束的QP问题等价于一个包含对角上下饱和的代数环。因此，QP可以迭代计算，直到其解收敛为止。然而，由于QP的计算速度较慢，限制了它在具有简单数字处理器的快速系统中的应用。因此，为了能够在实时嵌入式应用中实现，需要一种快速的QP求解算法。本文对使用Arduino Mega 2560的两种QP实现，即投影高斯塞德尔(PGS)和所谓的Algorithm-2进行了比较研究。在这种情况下，实现MPC与QP求解器同时使用这两种算法来控制轻载无刷直流电机的速度。在实现之前，进行了系统建模、控制器设计和仿真。然后比较了两种迭代算法在仿真和实现中的平均计算时间。从结果可以看出，在相同条件下，算法-2的计算速度比PGS略快。
{"title":"Quadratic programming implementations of model predictive control on arduino for BLDC speed control","authors":"A. S. Rohman, Hanif F. Prasetyo","doi":"10.1109/ICSENGT.2017.8123448","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123448","url":null,"abstract":"Many physical process systems have performance limitation regardless the input. This limitation usually occurs in the form of input saturation of actuator as the constraint of the system. To overcome this problem, Model Predictive Control (MPC) may be used due to its capability to compute optimal control signal in the presence of input saturation. The optimal control signal is obtained by solving a quadratic programming (QP) problem with variables' constraints at each time instants. QP problem with lower and upper constraint is known to be equivalent to an algebraic loop involving diagonal upper and lower saturation. Hence, QP can be iteratively computed until its solution converges. A slow computation of QP, however, limits its applications for fast systems with simple digital processor. Therefore, in order to be able to be implemented in real-time embedded applications, a fast algorithm of QP solver is in need. In this paper, a comparison study of two QP implementation, i.e. Projected Gauss Seidel (PGS) and so called Algorithm-2, using Arduino Mega 2560 is presented. In this case, MPC with QP solver using both algorithms is implemented to control the speed of lightly loaded BLDC motor. Before implementation, system modeling, controller designing, and simulation are undertaken. The performance of both iterative algorithms are then compared in terms of average computation time in the simulation and implementation. It can be observed from the results that Algorithm-2 gives a bit faster computation than PGS under same conditions.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133247297","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123418
H. A. Nugroho, Yuli Triyani, M. Rahmawaty, I. Ardiyanto
Breast cancer is the leading cause of death in women worldwide. Ultrasonography (USG) is one of the imaging modalities which is widely used to detect and classify the mass abnormalities of the breast nodule. The use of image processing in the development a computer aided diagnosis (CADx) can assist the radiologists in analysing and interpreting the abnormalities of ultrasound nodules. This paper proposes an approach to classify the characteristics of breast nodule into circumscribed and not circumscribed classes. The proposed approach is implemented on 102 breast nodule images comprising of 57 circumscribed and 45 not circumscribed margins. Seven relevant features are extracted from nodule which is automatically segmented by combination neutrosophic set and watershed methods. The classification process based on multi-layer perceptron (MLP) classifier obtains the sensitivity of 96.49%, NPV of 95.35% and AUC of 0.972. These results indicate that the proposed approach successfully classify the margin characteristics of breast ultrasound nodule.
{"title":"Breast ultrasound image segmentation based on neutrosophic set and watershed method for classifying margin characteristics","authors":"H. A. Nugroho, Yuli Triyani, M. Rahmawaty, I. Ardiyanto","doi":"10.1109/ICSENGT.2017.8123418","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123418","url":null,"abstract":"Breast cancer is the leading cause of death in women worldwide. Ultrasonography (USG) is one of the imaging modalities which is widely used to detect and classify the mass abnormalities of the breast nodule. The use of image processing in the development a computer aided diagnosis (CADx) can assist the radiologists in analysing and interpreting the abnormalities of ultrasound nodules. This paper proposes an approach to classify the characteristics of breast nodule into circumscribed and not circumscribed classes. The proposed approach is implemented on 102 breast nodule images comprising of 57 circumscribed and 45 not circumscribed margins. Seven relevant features are extracted from nodule which is automatically segmented by combination neutrosophic set and watershed methods. The classification process based on multi-layer perceptron (MLP) classifier obtains the sensitivity of 96.49%, NPV of 95.35% and AUC of 0.972. These results indicate that the proposed approach successfully classify the margin characteristics of breast ultrasound nodule.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123647655","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123440
N. M. Isa, N. Irawati, H. A. Rahman, M. H. M. Yusoff, S. Harun, F. Ahmad
A relative humidity sensor based on Multi Walled Carbon Nanotubes (MWCNTs) doped with polymer Poly(methyl methacryate) was proposed in this paper. The fabrication technique applied in this paper is a simple direct drawing method that was able to produce a uniform waist microfiber with a minimum diameter of 5 μm with a length of 5 mm. This microfiber was tested on a different range of relative humidity from 45% to 80%. Performance of the fabricated sensor were then analyzed, focusing at the sensitivity of undoped and MWCNTs-doped polymer microfiber. Based on the results, MWCNTs-doped polymer microfiber exhibits higher sensitivities and better resolution compared to undoped polymer microfiber, with sensitivity and resolution obtained at 0.3341 dBm/% and 1.649% respectively. Indeed, the sensor exhibited a high reliability as well as repeatability. Therefore, this study provides a good platform for enhancing the concept of doping nanomaterials like MWCNTs into PMMA for a chemical and biosensor application.
{"title":"Relative humidity sensor based on MWCNTs-doped polymer microfiber","authors":"N. M. Isa, N. Irawati, H. A. Rahman, M. H. M. Yusoff, S. Harun, F. Ahmad","doi":"10.1109/ICSENGT.2017.8123440","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123440","url":null,"abstract":"A relative humidity sensor based on Multi Walled Carbon Nanotubes (MWCNTs) doped with polymer Poly(methyl methacryate) was proposed in this paper. The fabrication technique applied in this paper is a simple direct drawing method that was able to produce a uniform waist microfiber with a minimum diameter of 5 μm with a length of 5 mm. This microfiber was tested on a different range of relative humidity from 45% to 80%. Performance of the fabricated sensor were then analyzed, focusing at the sensitivity of undoped and MWCNTs-doped polymer microfiber. Based on the results, MWCNTs-doped polymer microfiber exhibits higher sensitivities and better resolution compared to undoped polymer microfiber, with sensitivity and resolution obtained at 0.3341 dBm/% and 1.649% respectively. Indeed, the sensor exhibited a high reliability as well as repeatability. Therefore, this study provides a good platform for enhancing the concept of doping nanomaterials like MWCNTs into PMMA for a chemical and biosensor application.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116629310","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：