Pub Date : 2016-05-09DOI: 10.1109/TENCONSPRING.2016.7519433
Pimolrat Ounsrimuang, S. Nootyaskool
Particle Swarm Optimization (PSO) successfully finds a solution as shown in various literatures. In some problems creating on discrete space, adjustment control-parameter may be difficult to modify a reach of optimum solution. The paper proposes an approach applying roulette wheel selection to PSO, which can help PSO escape from a local solution. This approach tested on both continuous and discrete space by finding solution of 12-numerical functions and an engineering-problem. The experiment result showed that the proposed technique can help PSO getting the best result both problem spaces, the performance improvement but also maintain easily to implementation.
{"title":"Roulette wheel selection applied to PSO on numerical function in discrete and continuous space","authors":"Pimolrat Ounsrimuang, S. Nootyaskool","doi":"10.1109/TENCONSPRING.2016.7519433","DOIUrl":"https://doi.org/10.1109/TENCONSPRING.2016.7519433","url":null,"abstract":"Particle Swarm Optimization (PSO) successfully finds a solution as shown in various literatures. In some problems creating on discrete space, adjustment control-parameter may be difficult to modify a reach of optimum solution. The paper proposes an approach applying roulette wheel selection to PSO, which can help PSO escape from a local solution. This approach tested on both continuous and discrete space by finding solution of 12-numerical functions and an engineering-problem. The experiment result showed that the proposed technique can help PSO getting the best result both problem spaces, the performance improvement but also maintain easily to implementation.","PeriodicalId":166275,"journal":{"name":"2016 IEEE Region 10 Symposium (TENSYMP)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117322180","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 : 2016-05-09DOI: 10.1109/TENCONSPRING.2016.7519432
R. Swarnkar, P. Prasad, A. Keskar, N. C. Shivprakash
Single trial detection of P300 signal is one of the trending areas of Brain Computer Interface (BCI) research. We propose a new method with a high level of accuracy to detect P300 signals in a single trial. Features were obtained with a new technique making use of the wavelet coefficients. Reduced feature dimension was achieved using Principal Component Analysis (PCA). Support Vector Machine (SVM) was used as the classifier. The proposed method has achieved an accuracy of 98.47% for Subject A and 95.06% for Subject B. Thus a high degree of accuracy was obtained.
{"title":"A new approach to detect P300 in a single trial based on PCA and SVM classifier","authors":"R. Swarnkar, P. Prasad, A. Keskar, N. C. Shivprakash","doi":"10.1109/TENCONSPRING.2016.7519432","DOIUrl":"https://doi.org/10.1109/TENCONSPRING.2016.7519432","url":null,"abstract":"Single trial detection of P300 signal is one of the trending areas of Brain Computer Interface (BCI) research. We propose a new method with a high level of accuracy to detect P300 signals in a single trial. Features were obtained with a new technique making use of the wavelet coefficients. Reduced feature dimension was achieved using Principal Component Analysis (PCA). Support Vector Machine (SVM) was used as the classifier. The proposed method has achieved an accuracy of 98.47% for Subject A and 95.06% for Subject B. Thus a high degree of accuracy was obtained.","PeriodicalId":166275,"journal":{"name":"2016 IEEE Region 10 Symposium (TENSYMP)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115297934","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 : 2016-05-09DOI: 10.1109/TENCONSPRING.2016.7519401
Padma Nyoman Crisnapati, I Nyoman Kusuma Wardana, I. Aryanto
This paper presents Rudas, a low cost and energy efficient system that fully operational for IP-based network. The system comprised of few embedded sensors and networking devices in the house that connected to the Internet architecture. It can be used in many applications, leading to the emerging concept of the Internet of Things (IoT). The IoT describes the future where everyday things (or objects) will be connected to the internet and be able to communicate themselves to other devices. In order to well maintain those sensor devices, it is often necessary to evolve devices to function correctly by allowing device management (DM) entities to remotely monitor and control devices without consuming significant resources. In particular, it includes a single board computer, microcontrollers, responsive web technology, database system, environmentally sensitive devices, tornado server software, cameras and could computing. The system is also implanted a fuzzy logic artificial intelligence to adjust the intensity of light and air condition in a room. Information will be recorded and calculated so that home owners will be more efficient in managing and monitoring all home devices. A result from this study is a well-worked home management and other aspects including security, energy saving and monitoring.
{"title":"Rudas: Energy and sensor devices management system in home automation","authors":"Padma Nyoman Crisnapati, I Nyoman Kusuma Wardana, I. Aryanto","doi":"10.1109/TENCONSPRING.2016.7519401","DOIUrl":"https://doi.org/10.1109/TENCONSPRING.2016.7519401","url":null,"abstract":"This paper presents Rudas, a low cost and energy efficient system that fully operational for IP-based network. The system comprised of few embedded sensors and networking devices in the house that connected to the Internet architecture. It can be used in many applications, leading to the emerging concept of the Internet of Things (IoT). The IoT describes the future where everyday things (or objects) will be connected to the internet and be able to communicate themselves to other devices. In order to well maintain those sensor devices, it is often necessary to evolve devices to function correctly by allowing device management (DM) entities to remotely monitor and control devices without consuming significant resources. In particular, it includes a single board computer, microcontrollers, responsive web technology, database system, environmentally sensitive devices, tornado server software, cameras and could computing. The system is also implanted a fuzzy logic artificial intelligence to adjust the intensity of light and air condition in a room. Information will be recorded and calculated so that home owners will be more efficient in managing and monitoring all home devices. A result from this study is a well-worked home management and other aspects including security, energy saving and monitoring.","PeriodicalId":166275,"journal":{"name":"2016 IEEE Region 10 Symposium (TENSYMP)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127643984","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 : 2016-05-09DOI: 10.1109/TENCONSPRING.2016.7519405
Abdulrahman Abdulkareem S. Al-Shanoon, S. A. Ahmad, M. K. Hassan
To develop an intelligent robotic hand, diverse approaches have been applied, including optimum gripping force and slippage analysis. In this study, a robotic hand was modeled with tactile pressure sensors. The slip detection sensor, which is represented as a rotary encoder device, was employed to indicate the slip situation features, distance and velocity. Empirical findings imply that the correlation between the distance that an object has slipped and the required re-gripping force was developed to be availed as an automatic feedback algorithm. The slippage events were revealed and analyzed to perform the control system mechanism of the re-gripping mission.
{"title":"Re-gripping analysis based on implementation of slip-detection device for robotic hand model","authors":"Abdulrahman Abdulkareem S. Al-Shanoon, S. A. Ahmad, M. K. Hassan","doi":"10.1109/TENCONSPRING.2016.7519405","DOIUrl":"https://doi.org/10.1109/TENCONSPRING.2016.7519405","url":null,"abstract":"To develop an intelligent robotic hand, diverse approaches have been applied, including optimum gripping force and slippage analysis. In this study, a robotic hand was modeled with tactile pressure sensors. The slip detection sensor, which is represented as a rotary encoder device, was employed to indicate the slip situation features, distance and velocity. Empirical findings imply that the correlation between the distance that an object has slipped and the required re-gripping force was developed to be availed as an automatic feedback algorithm. The slippage events were revealed and analyzed to perform the control system mechanism of the re-gripping mission.","PeriodicalId":166275,"journal":{"name":"2016 IEEE Region 10 Symposium (TENSYMP)","volume":"308 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116754883","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 : 2016-05-09DOI: 10.1109/TENCONSPRING.2016.7519425
P. Du, Pratama Putra, Shu Yamamoto, A. Nakao
Current host-centric Internet infrastructure is inefficient in supporting data-oriented Internet-of-Things (IoT) applications, where contextual information of data packet is desirable for performing in-network forwarding and processing. In this paper, we prototype a context-aware IoT architecture that can forward and process IoT traffic in data plane based on contextual information exposed from both high application-layer and low sensor-layer, to fill the gap between IoT and IP network leveraging SDN and NFV through software-defined data plane. We implemented the proposed IoT architecture including programmable MVNO switch on many-core processor and IoT gateway with Intel Edison board and show the feasibility of our proposal with example use cases.
{"title":"A context-aware IoT architecture through software-defined data plane","authors":"P. Du, Pratama Putra, Shu Yamamoto, A. Nakao","doi":"10.1109/TENCONSPRING.2016.7519425","DOIUrl":"https://doi.org/10.1109/TENCONSPRING.2016.7519425","url":null,"abstract":"Current host-centric Internet infrastructure is inefficient in supporting data-oriented Internet-of-Things (IoT) applications, where contextual information of data packet is desirable for performing in-network forwarding and processing. In this paper, we prototype a context-aware IoT architecture that can forward and process IoT traffic in data plane based on contextual information exposed from both high application-layer and low sensor-layer, to fill the gap between IoT and IP network leveraging SDN and NFV through software-defined data plane. We implemented the proposed IoT architecture including programmable MVNO switch on many-core processor and IoT gateway with Intel Edison board and show the feasibility of our proposal with example use cases.","PeriodicalId":166275,"journal":{"name":"2016 IEEE Region 10 Symposium (TENSYMP)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131264903","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 : 2016-05-09DOI: 10.1109/TENCONSPRING.2016.7519381
U. Prathap, P. D. Shenoy, K. Venugopal
Security in wireless sensor networks is critical due to its way of open communication. In this paper we have considered suite of attacks - packet modification, packet dropping, sybil attack, packet misrouting, and bad mouthing attack, and provided a solution to detect attacks. In literature, many schemes have been proposed to mitigate such attacks but very few detect the malicious nodes effectively and also no single solution detects all attacks. In the proposed approach, each node chooses the parent node for forwarding the packet towards sink. Each node adds its identity and trust on parent as a routing path marker and encrypts only the bytes added by node in packet before forwarding to parent. Sink can identify the malicious node based on trust value and node identities marked in packet. Child node observes the parent and decides the trust on parent based on successful and unsuccessful transactions. Data transmission is divided into multiple rounds of equal time duration. Each node chooses the parent node at the beginning of a round based on its own observation on parent. Simulated the algorithm in NS-3 and performance analysis is discussed by comparing the results with other two recently proposed approaches. With the combination of trust factor and fixed path routing to detect malicious activity, simulation results show that proposed method detect malicious nodes efficiently and early, and also with low percentage of false detection.
{"title":"CMNTS: Catching malicious nodes with trust support in wireless sensor networks","authors":"U. Prathap, P. D. Shenoy, K. Venugopal","doi":"10.1109/TENCONSPRING.2016.7519381","DOIUrl":"https://doi.org/10.1109/TENCONSPRING.2016.7519381","url":null,"abstract":"Security in wireless sensor networks is critical due to its way of open communication. In this paper we have considered suite of attacks - packet modification, packet dropping, sybil attack, packet misrouting, and bad mouthing attack, and provided a solution to detect attacks. In literature, many schemes have been proposed to mitigate such attacks but very few detect the malicious nodes effectively and also no single solution detects all attacks. In the proposed approach, each node chooses the parent node for forwarding the packet towards sink. Each node adds its identity and trust on parent as a routing path marker and encrypts only the bytes added by node in packet before forwarding to parent. Sink can identify the malicious node based on trust value and node identities marked in packet. Child node observes the parent and decides the trust on parent based on successful and unsuccessful transactions. Data transmission is divided into multiple rounds of equal time duration. Each node chooses the parent node at the beginning of a round based on its own observation on parent. Simulated the algorithm in NS-3 and performance analysis is discussed by comparing the results with other two recently proposed approaches. With the combination of trust factor and fixed path routing to detect malicious activity, simulation results show that proposed method detect malicious nodes efficiently and early, and also with low percentage of false detection.","PeriodicalId":166275,"journal":{"name":"2016 IEEE Region 10 Symposium (TENSYMP)","volume":"31 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132295409","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 : 2016-05-09DOI: 10.1109/TENCONSPRING.2016.7519376
S. Ohta
This paper presents a communication protocol for an ad hoc network constructed with 429 MHz data transmission modems. It is expected that the signal attenuation caused by rainfall is smaller for the 429 MHz band than for the 2.4 or 5 GHz band, which is used in wireless LANs and ZigBee. Additionally, since the signal diffraction is greater for this frequency than for higher frequencies, the signal is less attenuated by obstacles. Hence, the 429 MHz modem is suitable for networks with long-distance wireless transmission. However, the modem does not support network functions such as packet collision avoidance and routing. Thus, the paper presents a new simple protocol that avoids packet collisions and performs routing. The proposed protocol is essentially a token passing method that utilizes a rooted tree structure in a mesh network. In this method, the order of token passing is determined by a depth-first search in the tree. With this scheme, it is possible for the protocol to avoid packet collisions. In addition, routing is performed with very limited information stored at each node. This paper details the proposed token-based protocol and describes how the token and data packets circulate in the network. It also presents a distributed algorithm that finds a rooted tree in a mesh network. The proposed method was implemented on a prototype network. The feasibility of the method was confirmed through an experiment. The characteristic of a tree obtained by the tree construction algorithm is also clarified.
{"title":"Tree-based protocol for ad hoc networks constructed with data transmission modems","authors":"S. Ohta","doi":"10.1109/TENCONSPRING.2016.7519376","DOIUrl":"https://doi.org/10.1109/TENCONSPRING.2016.7519376","url":null,"abstract":"This paper presents a communication protocol for an ad hoc network constructed with 429 MHz data transmission modems. It is expected that the signal attenuation caused by rainfall is smaller for the 429 MHz band than for the 2.4 or 5 GHz band, which is used in wireless LANs and ZigBee. Additionally, since the signal diffraction is greater for this frequency than for higher frequencies, the signal is less attenuated by obstacles. Hence, the 429 MHz modem is suitable for networks with long-distance wireless transmission. However, the modem does not support network functions such as packet collision avoidance and routing. Thus, the paper presents a new simple protocol that avoids packet collisions and performs routing. The proposed protocol is essentially a token passing method that utilizes a rooted tree structure in a mesh network. In this method, the order of token passing is determined by a depth-first search in the tree. With this scheme, it is possible for the protocol to avoid packet collisions. In addition, routing is performed with very limited information stored at each node. This paper details the proposed token-based protocol and describes how the token and data packets circulate in the network. It also presents a distributed algorithm that finds a rooted tree in a mesh network. The proposed method was implemented on a prototype network. The feasibility of the method was confirmed through an experiment. The characteristic of a tree obtained by the tree construction algorithm is also clarified.","PeriodicalId":166275,"journal":{"name":"2016 IEEE Region 10 Symposium (TENSYMP)","volume":"9 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114120591","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 : 2016-05-09DOI: 10.1109/TENCONSPRING.2016.7519392
M. Rathore, Awais Ahmad, Anand Paul, Uthra Kunathur Thikshaja
The growing population in the metropolitan areas in this modern age requires more smart services of transportation. Achieving smart and intelligent transportation requires the use of millions of devices equipped with Internet of things (IoT) technology. On the other hand, graphs are the better way to represent the transportation infrastructure. The use of millions of IoT devices generates a huge volume of data, termed as Big Data, which results in the generation of big graphs. The processing of big graphs using current technology while taking the present real-time traffic information in order to generate graphs for real-time decision making is a challenging task. Therefore, in this paper, we proposed smart and intelligent transportation based on real-time traffic circumstances using graphs. It supports the municipalities to manage the traffic efficiently and facilitate the travelers' queries anytime, anywhere intelligently based on current traffic scenarios. The road sensor deployment and vehicular network are used to generate real-time traffic information producing Big Data. In addition, an architecture is proposed to efficiently process the real-time vehicular Big Data by using parallel processing systems and big graph processing technology. Various graph algorithms are used to respond the user queries smartly. Vehicular data of Madrid highway and Aarhus city of Denmark is used for analysis and evaluation by implementing the system using Giraph on top of Hadoop ecosystem. The results show the proposed system is efficient and cable to work in the real-time environment.
{"title":"Exploiting real-time big data to empower smart transportation using big graphs","authors":"M. Rathore, Awais Ahmad, Anand Paul, Uthra Kunathur Thikshaja","doi":"10.1109/TENCONSPRING.2016.7519392","DOIUrl":"https://doi.org/10.1109/TENCONSPRING.2016.7519392","url":null,"abstract":"The growing population in the metropolitan areas in this modern age requires more smart services of transportation. Achieving smart and intelligent transportation requires the use of millions of devices equipped with Internet of things (IoT) technology. On the other hand, graphs are the better way to represent the transportation infrastructure. The use of millions of IoT devices generates a huge volume of data, termed as Big Data, which results in the generation of big graphs. The processing of big graphs using current technology while taking the present real-time traffic information in order to generate graphs for real-time decision making is a challenging task. Therefore, in this paper, we proposed smart and intelligent transportation based on real-time traffic circumstances using graphs. It supports the municipalities to manage the traffic efficiently and facilitate the travelers' queries anytime, anywhere intelligently based on current traffic scenarios. The road sensor deployment and vehicular network are used to generate real-time traffic information producing Big Data. In addition, an architecture is proposed to efficiently process the real-time vehicular Big Data by using parallel processing systems and big graph processing technology. Various graph algorithms are used to respond the user queries smartly. Vehicular data of Madrid highway and Aarhus city of Denmark is used for analysis and evaluation by implementing the system using Giraph on top of Hadoop ecosystem. The results show the proposed system is efficient and cable to work in the real-time environment.","PeriodicalId":166275,"journal":{"name":"2016 IEEE Region 10 Symposium (TENSYMP)","volume":"197 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122382978","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 : 2016-05-09DOI: 10.1109/TENCONSPRING.2016.7519440
Maricor Y. Ingal, Ralph Louisse T. Tolentino, M. J. Valencia, Francis F. Balahadia, Arlene Caballero
Fires have become a concern in recent years in the city of Manila, posing a threat to the entire community. Manila Fire District is facing problems in their internal transactions between different sub-stations. The study served as an automated fire incidents management system that can provide a chart and a summary based on the input data of each sub-station and can provide a map of all the fire incidents through geo-mapping in districts of Manila. This study, Manila Fire District could implement appropriate programs and lead awareness campaign to the community to help lessen fire incidents and mitigate its damages.
{"title":"Fire incidents management system in the city of Manila through geo-mapping","authors":"Maricor Y. Ingal, Ralph Louisse T. Tolentino, M. J. Valencia, Francis F. Balahadia, Arlene Caballero","doi":"10.1109/TENCONSPRING.2016.7519440","DOIUrl":"https://doi.org/10.1109/TENCONSPRING.2016.7519440","url":null,"abstract":"Fires have become a concern in recent years in the city of Manila, posing a threat to the entire community. Manila Fire District is facing problems in their internal transactions between different sub-stations. The study served as an automated fire incidents management system that can provide a chart and a summary based on the input data of each sub-station and can provide a map of all the fire incidents through geo-mapping in districts of Manila. This study, Manila Fire District could implement appropriate programs and lead awareness campaign to the community to help lessen fire incidents and mitigate its damages.","PeriodicalId":166275,"journal":{"name":"2016 IEEE Region 10 Symposium (TENSYMP)","volume":"198 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123172053","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 : 2016-05-09DOI: 10.1109/TENCONSPRING.2016.7519416
Saad Hameed, O. Hasan
Surgical robots provide various advantages, like improved precision and dexterity, over conventional surgical procedures and have been extensively studied in the last decade. However, safety is still a major concern mainly due to the unreliable or no haptic feedback to the surgeon and the shaky movements (tremors) in the surgeons hands. These issues may result in unwanted collisions between the robotic arm tips and the soft tissues of the human body or between the robotic arm tips inside the human body causing non-repairable damage. In this paper, we propose to overcome this problem by using image segmentation techniques, on the real-time video of the robotic surgery, along with genetic algorithms to avoid possible collisions. The main idea is to introduce an automatic collision avoidance mechanism upon detecting a threat for a possible collision. For illustration, some preliminary results on using image segmentation on a video of the cholecystectomy surgical procedure are presented.
{"title":"Towards autonomous collision avoidance in surgical robots using image segmentation and genetic algorithms","authors":"Saad Hameed, O. Hasan","doi":"10.1109/TENCONSPRING.2016.7519416","DOIUrl":"https://doi.org/10.1109/TENCONSPRING.2016.7519416","url":null,"abstract":"Surgical robots provide various advantages, like improved precision and dexterity, over conventional surgical procedures and have been extensively studied in the last decade. However, safety is still a major concern mainly due to the unreliable or no haptic feedback to the surgeon and the shaky movements (tremors) in the surgeons hands. These issues may result in unwanted collisions between the robotic arm tips and the soft tissues of the human body or between the robotic arm tips inside the human body causing non-repairable damage. In this paper, we propose to overcome this problem by using image segmentation techniques, on the real-time video of the robotic surgery, along with genetic algorithms to avoid possible collisions. The main idea is to introduce an automatic collision avoidance mechanism upon detecting a threat for a possible collision. For illustration, some preliminary results on using image segmentation on a video of the cholecystectomy surgical procedure are presented.","PeriodicalId":166275,"journal":{"name":"2016 IEEE Region 10 Symposium (TENSYMP)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114708520","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：