Pub Date : 2018-10-01DOI: 10.1109/TENCON.2018.8650428
H. Shu, Ying Song, Huan Zhou
Convolutional neural network (ConvNet) is a class of deep feed-forward neural network which exploits the strong spatially local correlation in natural images. It achieves successful performance in visual analyzing area. Recently, ConvNet has been employed in acoustic processing area and been proved to be able to learn the spectro-temporal pattern of sound and differential them for the classification purpose. In this manuscript, the time-frequency resolution of the input sound is studied for their efficiency in the classification accuracy when ConvNet is adopted. Simulation results shows that the data augment solution, which is called multi-width frequency-delta, presents little contribution for the performance improvement when the network is carefully designed. In addition, a suitable temporal resolution in acoustic sound segmentation can achieve good classification effect.
{"title":"Time-frequency Performance Study on Urban Sound Classification with Convolutional Neural Network","authors":"H. Shu, Ying Song, Huan Zhou","doi":"10.1109/TENCON.2018.8650428","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650428","url":null,"abstract":"Convolutional neural network (ConvNet) is a class of deep feed-forward neural network which exploits the strong spatially local correlation in natural images. It achieves successful performance in visual analyzing area. Recently, ConvNet has been employed in acoustic processing area and been proved to be able to learn the spectro-temporal pattern of sound and differential them for the classification purpose. In this manuscript, the time-frequency resolution of the input sound is studied for their efficiency in the classification accuracy when ConvNet is adopted. Simulation results shows that the data augment solution, which is called multi-width frequency-delta, presents little contribution for the performance improvement when the network is carefully designed. In addition, a suitable temporal resolution in acoustic sound segmentation can achieve good classification effect.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129915313","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650431
Jason L. Española, A. Bandala, R. R. Vicerra, E. Dadios
In this study, a fuzzy logic controller (FLC) was designed to manipulate an articulated robot gripper. An idea from a previous study was utilized to enhance the performance of the FLC using genetic algorithms by optimizing newly-introduced coefficients in the membership functions of the FLC. The proposed controller was applied on a robot gripper model in Simulink. All in all, the genetic algorithm was able to come up with optimized parameters after an average of at least eight (8) generations and the proposed controller was able to follow the reference trajectory more accurately than the simple fuzzy controller. Further research will be necessary for physical implementation and possible improvement of the utilized genetic algorithm.
{"title":"Design of a Fuzzy-Genetic Controller for an Articulated Robot Gripper","authors":"Jason L. Española, A. Bandala, R. R. Vicerra, E. Dadios","doi":"10.1109/TENCON.2018.8650431","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650431","url":null,"abstract":"In this study, a fuzzy logic controller (FLC) was designed to manipulate an articulated robot gripper. An idea from a previous study was utilized to enhance the performance of the FLC using genetic algorithms by optimizing newly-introduced coefficients in the membership functions of the FLC. The proposed controller was applied on a robot gripper model in Simulink. All in all, the genetic algorithm was able to come up with optimized parameters after an average of at least eight (8) generations and the proposed controller was able to follow the reference trajectory more accurately than the simple fuzzy controller. Further research will be necessary for physical implementation and possible improvement of the utilized genetic algorithm.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130400730","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650389
R. Tirupathi, S. Kar
This paper presents a switched capacitor based capacitive sensor interfacing circuit, which can sense the change in capacitance from differential capacitive sensor and produces differential voltage output. The proposed circuit has the ability to reduce the errors like offset and low frequency noise introduced by the circuit components. The main advantage of this interfacing circuit is, it utilizes a single differential capacitive sensor and a single feedback network to provide differential output. The gain of the interfacing circuit is programmable through the feedback capacitor of the charge amplifier configuration. The interfacing circuit comprises of a fully differential operational amplifier, offset reduction scheme, buffer and low pass filter. The proposed circuit is designed and simulated using UMC 0.18-μm CMOS process technology. Both schematic and post-layout simulation results are presented.
{"title":"A Differential Output Switched Capacitor based Capacitive Sensor Interfacing Circuit","authors":"R. Tirupathi, S. Kar","doi":"10.1109/TENCON.2018.8650389","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650389","url":null,"abstract":"This paper presents a switched capacitor based capacitive sensor interfacing circuit, which can sense the change in capacitance from differential capacitive sensor and produces differential voltage output. The proposed circuit has the ability to reduce the errors like offset and low frequency noise introduced by the circuit components. The main advantage of this interfacing circuit is, it utilizes a single differential capacitive sensor and a single feedback network to provide differential output. The gain of the interfacing circuit is programmable through the feedback capacitor of the charge amplifier configuration. The interfacing circuit comprises of a fully differential operational amplifier, offset reduction scheme, buffer and low pass filter. The proposed circuit is designed and simulated using UMC 0.18-μm CMOS process technology. Both schematic and post-layout simulation results are presented.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129116945","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650445
Bharath A. Kartha, B. Goutham, Parvathi S. Nair, Vishnu S. Nair
The hearing impaired community faces many challenges during their daily life and communication is the most talked about problem out of them. A conclusion based on some research suggests that rather than one on one communication with their fellow hearing impaired friends, what they find more difficult is to capture their peers attention when they are in a group, at class or at work. Differently abled students in class struggle to capture the attention of their fellow friends and teachers struggle to capture the attention of the students. The current solution for which is flickering the classroom lights which is very rudimentary and ineffective in places other than the classroom. Hard of hearing working professionals go through the same struggle every day to capture their nearby colleagues attention.The conceptualised solution is a wearable device called ACVA( Assistive Communicative Vibrating Aid). It is a wearable wristband which contains an OLED display and a vibrating module. The aim is to transform natural communicative gestures into a form that can be sensed by the differently abled, helping them with effective communication and mainstreaming their communicative conducts. By converting clap gesture into a broadcast signal using Wifi technology, the device can bridge the gap between Augmentative and Alternative Communication (AAC) and general human behavioural communication.ACVA proposes to achieve an interface that allows the differently abled to culminate natural communicative gestures to provide ease in attention capturing during interpersonal or group level communications.
{"title":"Assistive Communicative Vibrating Aid for Differently Abled","authors":"Bharath A. Kartha, B. Goutham, Parvathi S. Nair, Vishnu S. Nair","doi":"10.1109/TENCON.2018.8650445","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650445","url":null,"abstract":"The hearing impaired community faces many challenges during their daily life and communication is the most talked about problem out of them. A conclusion based on some research suggests that rather than one on one communication with their fellow hearing impaired friends, what they find more difficult is to capture their peers attention when they are in a group, at class or at work. Differently abled students in class struggle to capture the attention of their fellow friends and teachers struggle to capture the attention of the students. The current solution for which is flickering the classroom lights which is very rudimentary and ineffective in places other than the classroom. Hard of hearing working professionals go through the same struggle every day to capture their nearby colleagues attention.The conceptualised solution is a wearable device called ACVA( Assistive Communicative Vibrating Aid). It is a wearable wristband which contains an OLED display and a vibrating module. The aim is to transform natural communicative gestures into a form that can be sensed by the differently abled, helping them with effective communication and mainstreaming their communicative conducts. By converting clap gesture into a broadcast signal using Wifi technology, the device can bridge the gap between Augmentative and Alternative Communication (AAC) and general human behavioural communication.ACVA proposes to achieve an interface that allows the differently abled to culminate natural communicative gestures to provide ease in attention capturing during interpersonal or group level communications.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130578830","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650369
Glenn Paul P. Gara, M. P. B. Pacot, R. Uy
The longest common subsequence (LCS) is an essential technique in the sequence alignment. By deleting zero or more symbols, it determines one of the longest subsequences in a sequence. This paper described a simulation of the algorithm using the EduMIPS64 and MIPSers simulators where the latter implements the most recent developments of MIPS64 instruction sets. The method applied to solve the LCS in this study was the first known solution invented by Wagner and Fischer. The authors programmed the LCS on a RISC architecture and evaluated the results of the test cases by observing the number of clock cycles performed through the simulators. Results show that the MIPSers executed the least number of clock cycles compared to the EduMIPS64 simulator.
{"title":"RISC-Based Simulation of Longest Common Subsequence Algorithm in MIPS64 Simulators","authors":"Glenn Paul P. Gara, M. P. B. Pacot, R. Uy","doi":"10.1109/TENCON.2018.8650369","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650369","url":null,"abstract":"The longest common subsequence (LCS) is an essential technique in the sequence alignment. By deleting zero or more symbols, it determines one of the longest subsequences in a sequence. This paper described a simulation of the algorithm using the EduMIPS64 and MIPSers simulators where the latter implements the most recent developments of MIPS64 instruction sets. The method applied to solve the LCS in this study was the first known solution invented by Wagner and Fischer. The authors programmed the LCS on a RISC architecture and evaluated the results of the test cases by observing the number of clock cycles performed through the simulators. Results show that the MIPSers executed the least number of clock cycles compared to the EduMIPS64 simulator.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116334915","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650169
S. Shah, Hong Ping Zhao, Hoon Kim
Mobile edge computing (MEC) is the future of wireless communications and an alternative to cloud computing. It is a decentralized computing infrastructure, in which some signal processing, storage, control and computing applications are distributed in a most efficient and logical way between data source and cloud. Mobile edge computing extends cloud computing concept by bringing the advantages of the cloud closer to the users in the form of network edge, this results in less end to end delay. In this paper, we emphasize the importance of mobile computing by providing real-life scenarios and classifying the current research efforts in the domain of edge computing. We also discuss the key requirements for enabling edge computing and open research challenges in realizing the vision of future computing tendency.
{"title":"Mobile Edge Computing: A Promising Paradigm for Future Communication Systems","authors":"S. Shah, Hong Ping Zhao, Hoon Kim","doi":"10.1109/TENCON.2018.8650169","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650169","url":null,"abstract":"Mobile edge computing (MEC) is the future of wireless communications and an alternative to cloud computing. It is a decentralized computing infrastructure, in which some signal processing, storage, control and computing applications are distributed in a most efficient and logical way between data source and cloud. Mobile edge computing extends cloud computing concept by bringing the advantages of the cloud closer to the users in the form of network edge, this results in less end to end delay. In this paper, we emphasize the importance of mobile computing by providing real-life scenarios and classifying the current research efforts in the domain of edge computing. We also discuss the key requirements for enabling edge computing and open research challenges in realizing the vision of future computing tendency.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127707307","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650182
T. Deng
This paper generalizes the dented stability triangles for the second-order recursive digital system such that the borderlines of the dented stability triangles are included in the stability-margined (SM) region. This generalization enables the system designer to formulate the second-order system design more easily. More specifically, the existing inequalities for guaranteeing a specified stability margin are the inequalities that exclude the boundaries (borderlines) of the dented SM-regions, while this paper presents two sets of new inequalities that include the borderlines of the SM-regions and thus such inequalities produce a closed SM-region. In other words, the existing SM-regions are defined by using "less than" inequalities, while the new inequalities are "less than or equal to" inequalities. The added "equal to" constraints produces a closed region that includes borderlines in the SM-region. It is found that the resulting closed SM-regions are more convenient and more suitable for designing the second-order recursive system with robust stability.
{"title":"Closed Stability-Margined Regions for the Second-Order System with Robust Stability","authors":"T. Deng","doi":"10.1109/TENCON.2018.8650182","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650182","url":null,"abstract":"This paper generalizes the dented stability triangles for the second-order recursive digital system such that the borderlines of the dented stability triangles are included in the stability-margined (SM) region. This generalization enables the system designer to formulate the second-order system design more easily. More specifically, the existing inequalities for guaranteeing a specified stability margin are the inequalities that exclude the boundaries (borderlines) of the dented SM-regions, while this paper presents two sets of new inequalities that include the borderlines of the SM-regions and thus such inequalities produce a closed SM-region. In other words, the existing SM-regions are defined by using \"less than\" inequalities, while the new inequalities are \"less than or equal to\" inequalities. The added \"equal to\" constraints produces a closed region that includes borderlines in the SM-region. It is found that the resulting closed SM-regions are more convenient and more suitable for designing the second-order recursive system with robust stability.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"os-40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127780190","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650232
Qurat ul ain Ali, M. Yousaf
This paper presents a solution for incorporating the structural information along with local features to enhance the recognition accuracy of human-vehicle interaction activities. Proposed system aims to exploit Bag of Words for extracting structural information both spatial and temporal relationship between features from video data to help achieve better recognition accuracy for complex interaction scenes. Traditional Bag of Words (BOW) approach is inefficient in representing structural information, feature positions and their temporal relationships which makes it difficult for the classifier to recognise interaction and complex scenes. The classifier uses BOW along with spatial and temporal positions of features. Random Forest and kNN are used as classifiers to compare classification results and to find a trade-off between recognition accuracy and computational complexity. We have used state of the art dataset VIRAT (Video and Image Retrieval and Analysis Tool) for validation of our scheme. Random Forest and modified BOW (RF+mBOW) gives better recognition accuracy at the cost of higher computational time whereas kNN and modified BOW (kNN+mBOW) takes less time for computations while giving remarkable recognition results. We observed that Random Forest and modified BOW (RF+mBOW) outperforms all state of art methodologies.
本文提出了一种结合结构信息和局部特征的方法，以提高人车交互活动的识别精度。本系统旨在利用Bag of Words从视频数据中提取特征之间的时空关系结构信息，以提高对复杂交互场景的识别精度。传统的词袋(BOW)方法在表示结构信息、特征位置及其时间关系方面效率低下，使得分类器难以识别交互和复杂场景。分类器使用BOW以及特征的时空位置。使用随机森林和kNN作为分类器来比较分类结果，并在识别精度和计算复杂度之间找到权衡。我们使用了最先进的数据集VIRAT(视频和图像检索和分析工具)来验证我们的方案。随机森林和改进的BOW (RF+mBOW)以较高的计算时间为代价获得了更好的识别精度，而kNN和改进的BOW (kNN+mBOW)计算时间更少，识别效果显著。我们观察到随机森林和改进的BOW (RF+mBOW)优于所有最先进的方法。
{"title":"Role of Spatio-Temporal Feature Position in Recognition of Human Vehicle Interaction","authors":"Qurat ul ain Ali, M. Yousaf","doi":"10.1109/TENCON.2018.8650232","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650232","url":null,"abstract":"This paper presents a solution for incorporating the structural information along with local features to enhance the recognition accuracy of human-vehicle interaction activities. Proposed system aims to exploit Bag of Words for extracting structural information both spatial and temporal relationship between features from video data to help achieve better recognition accuracy for complex interaction scenes. Traditional Bag of Words (BOW) approach is inefficient in representing structural information, feature positions and their temporal relationships which makes it difficult for the classifier to recognise interaction and complex scenes. The classifier uses BOW along with spatial and temporal positions of features. Random Forest and kNN are used as classifiers to compare classification results and to find a trade-off between recognition accuracy and computational complexity. We have used state of the art dataset VIRAT (Video and Image Retrieval and Analysis Tool) for validation of our scheme. Random Forest and modified BOW (RF+mBOW) gives better recognition accuracy at the cost of higher computational time whereas kNN and modified BOW (kNN+mBOW) takes less time for computations while giving remarkable recognition results. We observed that Random Forest and modified BOW (RF+mBOW) outperforms all state of art methodologies.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126223010","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650399
Seoung-hee Lee, C. Lee, H. Yoon
This paper proposed increase 2VIN+VCLK voltage series charge pump. Recently, trend of low power circuit designs a lower input voltage. But several circuit require high voltage. In this case, charge pump solves a problem with small area and cheap cost. Many Conventional charge pumps are connected parallel each capacitor. So many capacitors are required for high voltage. However proposed charge pump can supply high voltage easily and design less capacitors. Proposed circuit are comprised 2-stages with 5 capacitors. To compare with conventional charge pumps, proposed circuit design same component units.
{"title":"A New Charge Pump Switch Parallel to Series Connection","authors":"Seoung-hee Lee, C. Lee, H. Yoon","doi":"10.1109/TENCON.2018.8650399","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650399","url":null,"abstract":"This paper proposed increase 2VIN+VCLK voltage series charge pump. Recently, trend of low power circuit designs a lower input voltage. But several circuit require high voltage. In this case, charge pump solves a problem with small area and cheap cost. Many Conventional charge pumps are connected parallel each capacitor. So many capacitors are required for high voltage. However proposed charge pump can supply high voltage easily and design less capacitors. Proposed circuit are comprised 2-stages with 5 capacitors. To compare with conventional charge pumps, proposed circuit design same component units.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126441489","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：