Pub Date : 2019-10-01DOI: 10.1109/ICOM47790.2019.8952056
C. M. M. Refat, N. Azlan
Deep learning is very popular methods for facial expression recognition (FER) and classification. Different types of deep learning algorithms have been used for FER such as deep belief network (DBN) and convolutional neural network (CNN). In this paper, we analyze various deep learning methods and their results. We have chosen Deep convolutional neural network as the best algorithms for facial expression detection and classification. In our study, we have tested the algorithm using Japanese Female facial expressions database (JAFFE) datasets by anaconda software. The deep convolution neural networks with JAFFE datasets accuracy rate around 97.01%.
{"title":"Deep Learning Methods for Facial Expression Recognition","authors":"C. M. M. Refat, N. Azlan","doi":"10.1109/ICOM47790.2019.8952056","DOIUrl":"https://doi.org/10.1109/ICOM47790.2019.8952056","url":null,"abstract":"Deep learning is very popular methods for facial expression recognition (FER) and classification. Different types of deep learning algorithms have been used for FER such as deep belief network (DBN) and convolutional neural network (CNN). In this paper, we analyze various deep learning methods and their results. We have chosen Deep convolutional neural network as the best algorithms for facial expression detection and classification. In our study, we have tested the algorithm using Japanese Female facial expressions database (JAFFE) datasets by anaconda software. The deep convolution neural networks with JAFFE datasets accuracy rate around 97.01%.","PeriodicalId":415914,"journal":{"name":"2019 7th International Conference on Mechatronics Engineering (ICOM)","volume":"315 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116382190","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 : 2019-10-01DOI: 10.1109/ICOM47790.2019.8952059
Peter Zechel, Ralph Streiter, K. Bogenberger, U. Göhner
This paper presents an analysis of the euroFot data set to determine limits for the typical lateral acceleration behavior of drivers. Since recent studies indicate that lateral accelerations close to the physically possible limit are rarely used by drivers, predictions tasks for autonomous driving could consider a smaller, so-called natural lateral acceleration interval (NLAI) instead of all physically possible lateral accelerations. This NLAI should be as small as possible while still fulfilling all safety aspects. Therefore, valid assumptions are required on which the interval can be derived. Since a valid assumption which leads to minimal NLAI is yet unknown, four different assumptions concerning the lateral acceleration behavior are derived and evaluated in this paper. Thereby, detailed examinations regarding the relative frequencies of violations are presented. Finally, two assumptions are recommended for introducing an NLAI, depending on prediction time and safety requirements. Additionally, the advantages of utilizing an NLAI instead of all physically possible lateral accelerations are highlighted by comparing the results of an occupancy prediction approach.
{"title":"Assumptions of Lateral Acceleration Behavior Limits for Prediction Tasks in Autonomous Vehicles","authors":"Peter Zechel, Ralph Streiter, K. Bogenberger, U. Göhner","doi":"10.1109/ICOM47790.2019.8952059","DOIUrl":"https://doi.org/10.1109/ICOM47790.2019.8952059","url":null,"abstract":"This paper presents an analysis of the euroFot data set to determine limits for the typical lateral acceleration behavior of drivers. Since recent studies indicate that lateral accelerations close to the physically possible limit are rarely used by drivers, predictions tasks for autonomous driving could consider a smaller, so-called natural lateral acceleration interval (NLAI) instead of all physically possible lateral accelerations. This NLAI should be as small as possible while still fulfilling all safety aspects. Therefore, valid assumptions are required on which the interval can be derived. Since a valid assumption which leads to minimal NLAI is yet unknown, four different assumptions concerning the lateral acceleration behavior are derived and evaluated in this paper. Thereby, detailed examinations regarding the relative frequencies of violations are presented. Finally, two assumptions are recommended for introducing an NLAI, depending on prediction time and safety requirements. Additionally, the advantages of utilizing an NLAI instead of all physically possible lateral accelerations are highlighted by comparing the results of an occupancy prediction approach.","PeriodicalId":415914,"journal":{"name":"2019 7th International Conference on Mechatronics Engineering (ICOM)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114487852","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 : 2019-10-01DOI: 10.1109/ICOM47790.2019.8952040
M. Z. Ahmed, A. M. Hassan, A. H. Alkali, A. H. Hashim, O. Khalifa, H. Ramli
A scenario-aware is a type of protocol designed to enable NDN applications have specific interest/data naming convention and specific message exchange. Location update and Handoff analysis are the two basic classes of managing network mobility in both IP and NDN. Location update focus mainly on updating producer's mobility/movement information while handoff focus mainly on ensuring network access as the mobile producer continues to relocate/change its (Point of Attachment) PoA to another. Thus, the frequent mobility of the NDN producer is one high significant features of network mobility in an NDN environment. In this paper, the mobile producer is anchorless and is required to frequently change its Care of Address (CoA) as it relocates between multiple NDN access networks. This then has absolute effect on network performance of the mobility management at mobile producer's handoff. Therefore, a performance analysis for the mobile producer handoff between different NDN access networks using NDN scenario-aware protocol is presented using analytical approach and to be supported with simulation. Simulations were carried out using ndnSim 2.1 NS3-based. Analysis were estimated for delay during handoff and packet loss for interest/data exchange between mobile producers.
场景感知是一种协议类型，旨在使NDN应用程序具有特定的兴趣/数据命名约定和特定的消息交换。位置更新和切换分析是IP和NDN中管理网络移动性的两个基本类别。位置更新主要关注更新制作人的移动/移动信息，而切换主要关注在移动制作人继续搬迁/更改其(附件点)PoA时确保网络访问。因此，NDN生产者的频繁移动性是NDN环境中网络移动性的一个重要特征。在本文中，移动生产者是无锚点的，当它在多个NDN接入网之间移动时，需要频繁地改变其CoA (Care of Address)。这对移动制造商移交时移动管理的网络性能有绝对影响。因此，本文采用分析方法对基于NDN场景感知协议的不同NDN接入网之间的移动生产者切换进行了性能分析，并提供了仿真支持。采用基于ns3的ndnSim 2.1进行仿真。分析估计了切换期间的延迟和移动生产者之间兴趣/数据交换的数据包丢失。
{"title":"Performance Evaluation of Scenerio-aware Protocol for Producer Mobility Support in NDN","authors":"M. Z. Ahmed, A. M. Hassan, A. H. Alkali, A. H. Hashim, O. Khalifa, H. Ramli","doi":"10.1109/ICOM47790.2019.8952040","DOIUrl":"https://doi.org/10.1109/ICOM47790.2019.8952040","url":null,"abstract":"A scenario-aware is a type of protocol designed to enable NDN applications have specific interest/data naming convention and specific message exchange. Location update and Handoff analysis are the two basic classes of managing network mobility in both IP and NDN. Location update focus mainly on updating producer's mobility/movement information while handoff focus mainly on ensuring network access as the mobile producer continues to relocate/change its (Point of Attachment) PoA to another. Thus, the frequent mobility of the NDN producer is one high significant features of network mobility in an NDN environment. In this paper, the mobile producer is anchorless and is required to frequently change its Care of Address (CoA) as it relocates between multiple NDN access networks. This then has absolute effect on network performance of the mobility management at mobile producer's handoff. Therefore, a performance analysis for the mobile producer handoff between different NDN access networks using NDN scenario-aware protocol is presented using analytical approach and to be supported with simulation. Simulations were carried out using ndnSim 2.1 NS3-based. Analysis were estimated for delay during handoff and packet loss for interest/data exchange between mobile producers.","PeriodicalId":415914,"journal":{"name":"2019 7th International Conference on Mechatronics Engineering (ICOM)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116812282","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 : 2019-10-01DOI: 10.1109/ICOM47790.2019.8952050
M. T. Ajala, M. R. Khan, M. Salami, A. Shafie, M. Oladokun, M. Nor
In recent times, the need for a self-powered, autonomous firefighting robot, which can cope in fire hot spots, is strongly required in fire emergencies. The obtainable firefighting robots lack efficient performance in such conditions due to less reliability of their electric-powered actuators in the high-temperature environment under fire emergency. Our previous study suggests a gas actuated propulsion system (GAPS) as an alternative to the identified limitations of the existing electric actuated propulsion system. The GAPS drives a carbon dioxide propelled autonomous firefighting robot (CAFFR), which uses dry ice as its power source. However, there still exists a lack of detailed understanding of the working principle of the proposed GAPS. Thus, this study provides a theoretical framework for the novel CAFFR. Upon establishing the working theory and the concept of the CAFFR, the research carried out an empirical analysis of the key influencing design parameters for the CAFFR pneumatic actuation. The study presents a mathematical model of the effects of the design parameters and after that, discusses its implications.
{"title":"Pneumatic actuation of a firefighting robot: A theoretical Foundation and an Empirical study","authors":"M. T. Ajala, M. R. Khan, M. Salami, A. Shafie, M. Oladokun, M. Nor","doi":"10.1109/ICOM47790.2019.8952050","DOIUrl":"https://doi.org/10.1109/ICOM47790.2019.8952050","url":null,"abstract":"In recent times, the need for a self-powered, autonomous firefighting robot, which can cope in fire hot spots, is strongly required in fire emergencies. The obtainable firefighting robots lack efficient performance in such conditions due to less reliability of their electric-powered actuators in the high-temperature environment under fire emergency. Our previous study suggests a gas actuated propulsion system (GAPS) as an alternative to the identified limitations of the existing electric actuated propulsion system. The GAPS drives a carbon dioxide propelled autonomous firefighting robot (CAFFR), which uses dry ice as its power source. However, there still exists a lack of detailed understanding of the working principle of the proposed GAPS. Thus, this study provides a theoretical framework for the novel CAFFR. Upon establishing the working theory and the concept of the CAFFR, the research carried out an empirical analysis of the key influencing design parameters for the CAFFR pneumatic actuation. The study presents a mathematical model of the effects of the design parameters and after that, discusses its implications.","PeriodicalId":415914,"journal":{"name":"2019 7th International Conference on Mechatronics Engineering (ICOM)","volume":"10 14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116212493","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 : 2019-10-01DOI: 10.1109/ICOM47790.2019.8952051
Z. M. Yasin, N. A. Salim, N. F. Ab Aziz
This paper presents a new technique namely Grey Wolf Optimizer- Artificial Neural Network (GWO-ANN) as a technique to forecast electrical load. GWO is a meta heuristic technique inspired by the hierarchy of leadership of the grey wolf hunting mechanism in nature. Four types of grey wolves such as alpha, beta, delta, and omega are employed for simulating the leadership hierarchy. In addition, the three main steps of hunting, searching for prey, encircling are also imitated in the algorithm. GWO is utilized to determine the optimal momentum rate and learning rate of ANN for accurate prediction. In the ANN configuration, the temperature, humidity, wind speed, maximum power, and average power were used as the input data. While total power was used as the output data. ANN is trained by adjusting the parameters of momentum rate and learning rate until the output data matches the actual data. The performance of GWO-ANN was compared to the performance of ANN and Particle Swarm Optimization - Artificial Neural Network (PSO-ANN). The results showed GWO-ANN provide better result in terms of the Mean Absolute Percentage Error (MAPE) and coefficients of determination (R2) as compared to other methods.
{"title":"Long Term Load Forecasting using Grey Wolf Optimizer - Artificial Neural Network","authors":"Z. M. Yasin, N. A. Salim, N. F. Ab Aziz","doi":"10.1109/ICOM47790.2019.8952051","DOIUrl":"https://doi.org/10.1109/ICOM47790.2019.8952051","url":null,"abstract":"This paper presents a new technique namely Grey Wolf Optimizer- Artificial Neural Network (GWO-ANN) as a technique to forecast electrical load. GWO is a meta heuristic technique inspired by the hierarchy of leadership of the grey wolf hunting mechanism in nature. Four types of grey wolves such as alpha, beta, delta, and omega are employed for simulating the leadership hierarchy. In addition, the three main steps of hunting, searching for prey, encircling are also imitated in the algorithm. GWO is utilized to determine the optimal momentum rate and learning rate of ANN for accurate prediction. In the ANN configuration, the temperature, humidity, wind speed, maximum power, and average power were used as the input data. While total power was used as the output data. ANN is trained by adjusting the parameters of momentum rate and learning rate until the output data matches the actual data. The performance of GWO-ANN was compared to the performance of ANN and Particle Swarm Optimization - Artificial Neural Network (PSO-ANN). The results showed GWO-ANN provide better result in terms of the Mean Absolute Percentage Error (MAPE) and coefficients of determination (R2) as compared to other methods.","PeriodicalId":415914,"journal":{"name":"2019 7th International Conference on Mechatronics Engineering (ICOM)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124472915","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 : 2019-10-01DOI: 10.1109/ICOM47790.2019.8952006
Mozamil Ebnauf, W. Abdelmoez, H. Ammar, Aisha Hassan, M. Abdelhamid
The safety is considered one of the most critical issues in the design of cyber-physical systems (CPS). The Software Product-Line (SPL) and reusable software components are suitable approaches for CPS, which are often re-engineered from existing systems. Currently, the influence of architecture in assurance of software safety is being increasingly recognized. However, the safety-based architectural design methods are limited in SPLs because of the complexity and variabilities existing in SPL architectures. A new statechart-based safety pattern and adaptation of our previous SPL Architecture design method are presented in this paper. Also the paper describes a simplified safety assessment model which is used to evaluate the safety improvement in the design of the SPLA after using the proposed safety design pattern. Finally, to illustrate the effect of the design pattern in the PLA design, a simplified automated Electromechanical Braking System (EBS) product line is used as a running example. The results show that there is a considerable improvement in the system safety design after using the proposed safety pattern.
{"title":"State-driven Architecture Design for Safety-critical Software Product Lines","authors":"Mozamil Ebnauf, W. Abdelmoez, H. Ammar, Aisha Hassan, M. Abdelhamid","doi":"10.1109/ICOM47790.2019.8952006","DOIUrl":"https://doi.org/10.1109/ICOM47790.2019.8952006","url":null,"abstract":"The safety is considered one of the most critical issues in the design of cyber-physical systems (CPS). The Software Product-Line (SPL) and reusable software components are suitable approaches for CPS, which are often re-engineered from existing systems. Currently, the influence of architecture in assurance of software safety is being increasingly recognized. However, the safety-based architectural design methods are limited in SPLs because of the complexity and variabilities existing in SPL architectures. A new statechart-based safety pattern and adaptation of our previous SPL Architecture design method are presented in this paper. Also the paper describes a simplified safety assessment model which is used to evaluate the safety improvement in the design of the SPLA after using the proposed safety design pattern. Finally, to illustrate the effect of the design pattern in the PLA design, a simplified automated Electromechanical Braking System (EBS) product line is used as a running example. The results show that there is a considerable improvement in the system safety design after using the proposed safety pattern.","PeriodicalId":415914,"journal":{"name":"2019 7th International Conference on Mechatronics Engineering (ICOM)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116398962","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 : 2019-10-01DOI: 10.1109/ICOM47790.2019.8952005
Nur Farahana Mohd Suhaimi, Z. Htike
Machine learning has opened up the opportunity for understanding how the brain works. In this paper, functional magnetic resonance imaging (fMRI) data are analyzed with reduced dimension. We have carried out a performance comparison of random projection (RP) and principal component analysis (PCA) with different number of components of fMRI data. In addition to that, six different types of machine learning algorithm have been used. In particular, the Haxby dataset is chosen for our experiment. The dataset comprises 9 classes for object recognition. 10-fold cross validation step has been employed. We have discovered that RP outperforms PCA when the former is paired with logistic regression, Gaussian Naive Bayes and linear support vector machine. The best pair for this study was found to be PCA and k-nearest neighbors. Nevertheless, each algorithm was found to have its own strengths for fMRI classification approach.
{"title":"Comparison of Machine Learning Classifiers for dimensionally reduced fMRI data using Random Projection and Principal Component Analysis","authors":"Nur Farahana Mohd Suhaimi, Z. Htike","doi":"10.1109/ICOM47790.2019.8952005","DOIUrl":"https://doi.org/10.1109/ICOM47790.2019.8952005","url":null,"abstract":"Machine learning has opened up the opportunity for understanding how the brain works. In this paper, functional magnetic resonance imaging (fMRI) data are analyzed with reduced dimension. We have carried out a performance comparison of random projection (RP) and principal component analysis (PCA) with different number of components of fMRI data. In addition to that, six different types of machine learning algorithm have been used. In particular, the Haxby dataset is chosen for our experiment. The dataset comprises 9 classes for object recognition. 10-fold cross validation step has been employed. We have discovered that RP outperforms PCA when the former is paired with logistic regression, Gaussian Naive Bayes and linear support vector machine. The best pair for this study was found to be PCA and k-nearest neighbors. Nevertheless, each algorithm was found to have its own strengths for fMRI classification approach.","PeriodicalId":415914,"journal":{"name":"2019 7th International Conference on Mechatronics Engineering (ICOM)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130415996","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 : 2019-10-01DOI: 10.1109/ICOM47790.2019.8952061
M. M. Hashim, Mustafa Sabah Taha, A. Aman, A. H. Hashim, M. Rahim, S. Islam
The awareness to secure medical data has significantly increased. Steganographic has binged an important topic especially in this area since it has the capability to avoid medical data breach. This paper proposes a new steganography scheme based on Bit Invert System (BIS) using three control random parameters. The random selection process is performed based on Henon Map Function (HMF). In order to increase the security level, affine cipher and Huffman method is used for encryption as well as to minimize the encrypt data prior to the embedding for high payload ability. This integration is effective due to two main reasons: first, checking, and mapping to determine 0- and 1-bits during embedding, and second, segmenting the secret data to track and map every bit in stego image. The results showed that the presented scheme can assure confidentiality and security of the medical data while maintaining the image quality.
确保医疗数据安全的意识已大大提高。隐写术已经成为一个重要的话题，特别是在这一领域，因为它有能力避免医疗数据泄露。提出了一种基于比特反转系统(BIS)的隐写新方案，该方案采用三个控制随机参数。随机选择过程基于Henon Map Function (HMF)。为了提高安全级别，采用仿射密码和霍夫曼方法进行加密，并尽量减少嵌入前的加密数据，提高有效载荷能力。这种集成之所以有效，主要有两个原因:首先，在嵌入过程中检查和映射以确定0位和1位;其次，分割秘密数据以跟踪和映射隐写图像中的每个位。结果表明，该方案在保证图像质量的前提下，保证了医疗数据的保密性和安全性。
{"title":"Securing Medical Data Transmission Systems Based on Integrating Algorithm of Encryption and Steganography","authors":"M. M. Hashim, Mustafa Sabah Taha, A. Aman, A. H. Hashim, M. Rahim, S. Islam","doi":"10.1109/ICOM47790.2019.8952061","DOIUrl":"https://doi.org/10.1109/ICOM47790.2019.8952061","url":null,"abstract":"The awareness to secure medical data has significantly increased. Steganographic has binged an important topic especially in this area since it has the capability to avoid medical data breach. This paper proposes a new steganography scheme based on Bit Invert System (BIS) using three control random parameters. The random selection process is performed based on Henon Map Function (HMF). In order to increase the security level, affine cipher and Huffman method is used for encryption as well as to minimize the encrypt data prior to the embedding for high payload ability. This integration is effective due to two main reasons: first, checking, and mapping to determine 0- and 1-bits during embedding, and second, segmenting the secret data to track and map every bit in stego image. The results showed that the presented scheme can assure confidentiality and security of the medical data while maintaining the image quality.","PeriodicalId":415914,"journal":{"name":"2019 7th International Conference on Mechatronics Engineering (ICOM)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126390497","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：