Pub Date : 2007-12-12DOI: 10.1109/SCORED.2007.4451370
S. Kamal, B. Issac
Over the last decade, computer networks have been subject to widespread security attacks. Some are spoofing attacks, Denial of service (DoS) attacks and its various forms (like ping attacks, smurfing etc), password sniffing, packet capturing along with traffic analysis and other wireless key cracking attacks. Many of these attacks steal someone's identity and use it for exploiting the victim or others by masquerading or forgery, made the network or computer system inoperable by interrupting normal services, created a back door for re-visits etc. In this paper we analyze some of these attacks and evaluate its effectiveness, concluding with some security recommendations.
{"title":"Analysis of Network Communication Attacks","authors":"S. Kamal, B. Issac","doi":"10.1109/SCORED.2007.4451370","DOIUrl":"https://doi.org/10.1109/SCORED.2007.4451370","url":null,"abstract":"Over the last decade, computer networks have been subject to widespread security attacks. Some are spoofing attacks, Denial of service (DoS) attacks and its various forms (like ping attacks, smurfing etc), password sniffing, packet capturing along with traffic analysis and other wireless key cracking attacks. Many of these attacks steal someone's identity and use it for exploiting the victim or others by masquerading or forgery, made the network or computer system inoperable by interrupting normal services, created a back door for re-visits etc. In this paper we analyze some of these attacks and evaluate its effectiveness, concluding with some security recommendations.","PeriodicalId":443652,"journal":{"name":"2007 5th Student Conference on Research and Development","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115530391","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 : 2007-12-11DOI: 10.1109/SCORED.2007.4451430
N. F. A. Aziz, L. Hao, Paul Lewin
This paper investigates the recognition of partial discharge sources by using a statistical learning theory, support vector machine (SVM). SVM provides a new approach to pattern classification and has been proven to be successful in fields such as image identification and face recognition. To apply SVM learning in partial discharge classification, data input is very important. The input should be able to fully represent different patterns in an effective way. The determination of features that describe the characteristics of partial discharge signals and the extraction of reliable information from the raw data are the key to acquiring valuable patterns of partial discharge signals. In this paper, data obtained from experiment is carried out in both time and frequency domain. By using appropriate combination of kernel functions and parameters, it is concluded that the frequency domain approach gives a better classification rate.
{"title":"Analysis of Partial Discharge Measurement Data Using a Support Vector Machine","authors":"N. F. A. Aziz, L. Hao, Paul Lewin","doi":"10.1109/SCORED.2007.4451430","DOIUrl":"https://doi.org/10.1109/SCORED.2007.4451430","url":null,"abstract":"This paper investigates the recognition of partial discharge sources by using a statistical learning theory, support vector machine (SVM). SVM provides a new approach to pattern classification and has been proven to be successful in fields such as image identification and face recognition. To apply SVM learning in partial discharge classification, data input is very important. The input should be able to fully represent different patterns in an effective way. The determination of features that describe the characteristics of partial discharge signals and the extraction of reliable information from the raw data are the key to acquiring valuable patterns of partial discharge signals. In this paper, data obtained from experiment is carried out in both time and frequency domain. By using appropriate combination of kernel functions and parameters, it is concluded that the frequency domain approach gives a better classification rate.","PeriodicalId":443652,"journal":{"name":"2007 5th Student Conference on Research and Development","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130827433","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 : 2007-12-11DOI: 10.1109/SCORED.2007.4451371
A.Z. Ghavidel, B. Issac
A technical solution has been proposed in this paper to secure transport protocol communication in the case of DDoS (distributed denial of service) attacks. The recent papers about DDoS attacks, especially the amplification attack looks for abnormal transaction that signals and eventually reports them. These methods may generate false positives or negatives and in turn can be quite dismal in its performance, in the wake of a real DDoS attack. This paper suggests a symmetric key exchange and hiding of a secret code in the UDP (user datagram protocol) packets. Any packet that has the secret code missing would be rejected. At first, the secure UDP protocol will be discussed and later, a similar method for the TCP (transmission control protocol) will be discussed. Finally the performance analysis is done to compare the overhead incurred.
{"title":"Secure Transport Protocols for DDoS Attack Resistant Communication","authors":"A.Z. Ghavidel, B. Issac","doi":"10.1109/SCORED.2007.4451371","DOIUrl":"https://doi.org/10.1109/SCORED.2007.4451371","url":null,"abstract":"A technical solution has been proposed in this paper to secure transport protocol communication in the case of DDoS (distributed denial of service) attacks. The recent papers about DDoS attacks, especially the amplification attack looks for abnormal transaction that signals and eventually reports them. These methods may generate false positives or negatives and in turn can be quite dismal in its performance, in the wake of a real DDoS attack. This paper suggests a symmetric key exchange and hiding of a secret code in the UDP (user datagram protocol) packets. Any packet that has the secret code missing would be rejected. At first, the secure UDP protocol will be discussed and later, a similar method for the TCP (transmission control protocol) will be discussed. Finally the performance analysis is done to compare the overhead incurred.","PeriodicalId":443652,"journal":{"name":"2007 5th Student Conference on Research and Development","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125439784","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 : 2007-12-01DOI: 10.1109/SCORED.2007.4451384
H. Abu Bakar, Z. Awang, W.A.A. Wan Razali
Preventing and monitoring of Cu cross contamination become critical for the semiconductor industries since most of them are converting to mass-producing chips with copper (Cu), rather than aluminium (Al) as an interconnect element. Cu is a superior conductor of electricity, making it possible to shrink the electronic devices while further increasing performance. Presently, most of the Cu contamination emphasis on a wafer surface only using various methodologies. This in turn requires the need to improve the performance of analytical tool and to develop a new analytical measurement methodology for evaluating the levels of Cu contamination that might come from many sources in a wafer fab. In order to solve this problem, a new assessment methodology of using vapor phase decomposition and total X-ray fluorescence (VPD-TXRF) was introduced with the aim of establishing a trace elemental analysis. Currently, VPD-TXRF is mainly used as an analyzing tool to monitor Cu contamination on a wafer surface. However in this research, the same methodology is proof to be useful for measuring traces of Cu element induced from the other sources of contamination which is not necessarily from a wafer itself but also from the other sources in the whole fab. Gauge repeatability and reproducibility (GR&R) including component of variations study was applied in this research and the finding shows a positive results. A standard procedure and comparable sample also has been used which is ICPMS analyzing in purpose to set up a correlation with VPD-TXRF measurement data. Then this study aid to develop a valid procedure for Cu traces analysis, which served as a reference procedure to measure, monitor and control a Cu contamination. The final results validate this methodology as a distinguish method to measure a Cu contamination that come from many sources. Beside that, this methodology offers a cost saving since it uses a reclaim wafer as a sample preparation. Thus, this methodology is a key and can be used as process knowledge in accelerating advanced Cu interconnects development.
{"title":"Ascertaining of Copper Contamination from Various Sources in the Wafer Fab by Using VPD-TXRF Methodology","authors":"H. Abu Bakar, Z. Awang, W.A.A. Wan Razali","doi":"10.1109/SCORED.2007.4451384","DOIUrl":"https://doi.org/10.1109/SCORED.2007.4451384","url":null,"abstract":"Preventing and monitoring of Cu cross contamination become critical for the semiconductor industries since most of them are converting to mass-producing chips with copper (Cu), rather than aluminium (Al) as an interconnect element. Cu is a superior conductor of electricity, making it possible to shrink the electronic devices while further increasing performance. Presently, most of the Cu contamination emphasis on a wafer surface only using various methodologies. This in turn requires the need to improve the performance of analytical tool and to develop a new analytical measurement methodology for evaluating the levels of Cu contamination that might come from many sources in a wafer fab. In order to solve this problem, a new assessment methodology of using vapor phase decomposition and total X-ray fluorescence (VPD-TXRF) was introduced with the aim of establishing a trace elemental analysis. Currently, VPD-TXRF is mainly used as an analyzing tool to monitor Cu contamination on a wafer surface. However in this research, the same methodology is proof to be useful for measuring traces of Cu element induced from the other sources of contamination which is not necessarily from a wafer itself but also from the other sources in the whole fab. Gauge repeatability and reproducibility (GR&R) including component of variations study was applied in this research and the finding shows a positive results. A standard procedure and comparable sample also has been used which is ICPMS analyzing in purpose to set up a correlation with VPD-TXRF measurement data. Then this study aid to develop a valid procedure for Cu traces analysis, which served as a reference procedure to measure, monitor and control a Cu contamination. The final results validate this methodology as a distinguish method to measure a Cu contamination that come from many sources. Beside that, this methodology offers a cost saving since it uses a reclaim wafer as a sample preparation. Thus, this methodology is a key and can be used as process knowledge in accelerating advanced Cu interconnects development.","PeriodicalId":443652,"journal":{"name":"2007 5th Student Conference on Research and Development","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129534683","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 : 2007-12-01DOI: 10.1109/SCORED.2007.4451364
D. V. Viswacheda, P.Y.V. Lisa, M. S. Arifianto, E. Husni, L. Barukang
This paper describes the development of pervasive computing application implemented in Smart Tele-medicine System as part of the researches done in University Malaysia Sabah in order to deliver medical assistance to victims in hazardous situations and residents in the rural areas of Sabah. Issues discussed including Smart Tele-medicine System; software architecture and hardware architecture of the system; Bluetooth framework for the system and portlet development. Pervasive computing devices tend to be small and tiny is choosen in this research. In a tele-medicine environment smart devices are connected to the servers by employing Bluetooth wireless connection. Bluetooth is chosen for its convenience and mobility offered to users. It is low cost, low power consumption as well as secured. As device with WEME application installed detects the availability of Bluetooth transmission, it will attempt to build a PPP connection with request for WAS servlet which contains location information, which WAS will respond with a servlet containing the location information to the requesting WEME through which the users in the hospital emvironment can have all the facilities regarding their queries.
{"title":"On the Development of Pervasive Computing Application in Telemedicine System","authors":"D. V. Viswacheda, P.Y.V. Lisa, M. S. Arifianto, E. Husni, L. Barukang","doi":"10.1109/SCORED.2007.4451364","DOIUrl":"https://doi.org/10.1109/SCORED.2007.4451364","url":null,"abstract":"This paper describes the development of pervasive computing application implemented in Smart Tele-medicine System as part of the researches done in University Malaysia Sabah in order to deliver medical assistance to victims in hazardous situations and residents in the rural areas of Sabah. Issues discussed including Smart Tele-medicine System; software architecture and hardware architecture of the system; Bluetooth framework for the system and portlet development. Pervasive computing devices tend to be small and tiny is choosen in this research. In a tele-medicine environment smart devices are connected to the servers by employing Bluetooth wireless connection. Bluetooth is chosen for its convenience and mobility offered to users. It is low cost, low power consumption as well as secured. As device with WEME application installed detects the availability of Bluetooth transmission, it will attempt to build a PPP connection with request for WAS servlet which contains location information, which WAS will respond with a servlet containing the location information to the requesting WEME through which the users in the hospital emvironment can have all the facilities regarding their queries.","PeriodicalId":443652,"journal":{"name":"2007 5th Student Conference on Research and Development","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116244914","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 : 2007-12-01DOI: 10.1109/SCORED.2007.4451375
K. Salleh, H. Seki, Y. Kamiya, M. Hikizu
Deformable object manipulation is important for robots, especially home service robots. This is because unlike factory robots that handle rigid objects most of the time, these robots also need to be able to handle soft objects like clothes, rubber, paper etc. This paper proposes a unique tracing method for clothes manipulation by robots. The tracing method is used to reveal a second corner of a rectangular towel for spreading purposes, assuming that a first corner has been successfully grasped. Tracing in this paper's context is tracing the towel's edge, with the robot movement based on feedback from sensors. Using tracing method to find a second corner has been proven to be efficient in finding a second corner next to the first corner and not apposite it, resulting in the robot properly spreading the towel. The clothes manipulation system consists of two robot arms equipped with robot grippers, a CCD camera and an image processing board. Passive tracing is a method where the tracing gripper is static while the gripper holding the first corner maneuvers according to the feedback from sensors inside the static gripper so that it pulls the towel appropriately for the static gripper to trace the edge of the towel. Movement pattern is based on the sensors feedback inside the static gripper. Basically, the movement pattern is divided into two: inward the towel when the static gripper is too near to the edge of the towel and away from the towel when the gripper is too deep inside the towel. Force control is also applied to the static gripper during tracing so that it doesn't grip the towel too hard or vice versa. The CCD camera is used from time to time to check whether the static gripper has reached the second corner or not. Tracing experiments were conducted to evaluate the proposed method.
{"title":"Deformable Object Manipulation - Study on Passive Tracing by Robot","authors":"K. Salleh, H. Seki, Y. Kamiya, M. Hikizu","doi":"10.1109/SCORED.2007.4451375","DOIUrl":"https://doi.org/10.1109/SCORED.2007.4451375","url":null,"abstract":"Deformable object manipulation is important for robots, especially home service robots. This is because unlike factory robots that handle rigid objects most of the time, these robots also need to be able to handle soft objects like clothes, rubber, paper etc. This paper proposes a unique tracing method for clothes manipulation by robots. The tracing method is used to reveal a second corner of a rectangular towel for spreading purposes, assuming that a first corner has been successfully grasped. Tracing in this paper's context is tracing the towel's edge, with the robot movement based on feedback from sensors. Using tracing method to find a second corner has been proven to be efficient in finding a second corner next to the first corner and not apposite it, resulting in the robot properly spreading the towel. The clothes manipulation system consists of two robot arms equipped with robot grippers, a CCD camera and an image processing board. Passive tracing is a method where the tracing gripper is static while the gripper holding the first corner maneuvers according to the feedback from sensors inside the static gripper so that it pulls the towel appropriately for the static gripper to trace the edge of the towel. Movement pattern is based on the sensors feedback inside the static gripper. Basically, the movement pattern is divided into two: inward the towel when the static gripper is too near to the edge of the towel and away from the towel when the gripper is too deep inside the towel. Force control is also applied to the static gripper during tracing so that it doesn't grip the towel too hard or vice versa. The CCD camera is used from time to time to check whether the static gripper has reached the second corner or not. Tracing experiments were conducted to evaluate the proposed method.","PeriodicalId":443652,"journal":{"name":"2007 5th Student Conference on Research and Development","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121577990","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 : 2007-12-01DOI: 10.1109/SCORED.2007.4451365
A. Taib, R. Budiarto
Transition from IPv4 to IPv6 has been made possible through various transition mechanisms, categorized as dual-stack, tunneling and translation. However, period of transition may take years to complete which both protocols will coexist due to Internet services deployed are widely in IPv4. So, a successful IPv6 transition is depended on the compatibility with the large installed base of IPv4 hosts and routers, as well as maintaining security of the network from potential threats and vulnerabilities of both Internet protocols. This paper classifies potential security issues in the transition period and identifies prevention mechanisms to the problems identified. As dual-stacked host or network is the most simple IPv6 deployment any enterprise can settle for now, this paper focuses on possible implementation of distributed firewall in a dual-stacked environment which involves packet filtering at the edge router as well as the host-based firewall.
{"title":"Security Mechanisms for the IPv4 to IPv6 Transition","authors":"A. Taib, R. Budiarto","doi":"10.1109/SCORED.2007.4451365","DOIUrl":"https://doi.org/10.1109/SCORED.2007.4451365","url":null,"abstract":"Transition from IPv4 to IPv6 has been made possible through various transition mechanisms, categorized as dual-stack, tunneling and translation. However, period of transition may take years to complete which both protocols will coexist due to Internet services deployed are widely in IPv4. So, a successful IPv6 transition is depended on the compatibility with the large installed base of IPv4 hosts and routers, as well as maintaining security of the network from potential threats and vulnerabilities of both Internet protocols. This paper classifies potential security issues in the transition period and identifies prevention mechanisms to the problems identified. As dual-stacked host or network is the most simple IPv6 deployment any enterprise can settle for now, this paper focuses on possible implementation of distributed firewall in a dual-stacked environment which involves packet filtering at the edge router as well as the host-based firewall.","PeriodicalId":443652,"journal":{"name":"2007 5th Student Conference on Research and Development","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127764426","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 : 2007-12-01DOI: 10.1109/SCORED.2007.4451422
M. Salem, M. Ismail, N. Misran
The type of the construction materials of the interior walls of the indoor environments plays a great role in the propagation of the transmitted signals inside the buildings. A comparison of calculated and simulated Fresnel reflection and transmitted coefficients at 2.4 GHz and 900 MHz for a variety of typical exterior building surfaces has been achieved. The effect of the different types of wall on the path loss prediction had been conducted by using a ray tracing program with real time reflection and refraction phenomena.
{"title":"An Investigation on the Effects of Wall Parameters on the Indoor Wireless Propagations","authors":"M. Salem, M. Ismail, N. Misran","doi":"10.1109/SCORED.2007.4451422","DOIUrl":"https://doi.org/10.1109/SCORED.2007.4451422","url":null,"abstract":"The type of the construction materials of the interior walls of the indoor environments plays a great role in the propagation of the transmitted signals inside the buildings. A comparison of calculated and simulated Fresnel reflection and transmitted coefficients at 2.4 GHz and 900 MHz for a variety of typical exterior building surfaces has been achieved. The effect of the different types of wall on the path loss prediction had been conducted by using a ray tracing program with real time reflection and refraction phenomena.","PeriodicalId":443652,"journal":{"name":"2007 5th Student Conference on Research and Development","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114551888","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 : 2007-12-01DOI: 10.1109/SCORED.2007.4451379
S. W. Nawawi, M. N. Ahmad, J. Osman
The research on two-wheeled inverted pendulum (T-WIP) mobile robots or commonly known as balancing robots have gained momentum over the last decade in a number of robotic laboratories around the world. This paper describes the hardware design of such a robot. The objective of the design is to develop a T-WIP mobile robot to be used as flexible platform comprises of embedded unstable linear plant intended for research and teaching purposes. Issues such as selection of actuators and sensors, signal processing units, modeling and control scheme was addressed and discussed. The system is then tested using a well-known pole-placement state feedback controller to verify its functionality.
{"title":"Development of a Two-Wheeled Inverted Pendulum Mobile Robot","authors":"S. W. Nawawi, M. N. Ahmad, J. Osman","doi":"10.1109/SCORED.2007.4451379","DOIUrl":"https://doi.org/10.1109/SCORED.2007.4451379","url":null,"abstract":"The research on two-wheeled inverted pendulum (T-WIP) mobile robots or commonly known as balancing robots have gained momentum over the last decade in a number of robotic laboratories around the world. This paper describes the hardware design of such a robot. The objective of the design is to develop a T-WIP mobile robot to be used as flexible platform comprises of embedded unstable linear plant intended for research and teaching purposes. Issues such as selection of actuators and sensors, signal processing units, modeling and control scheme was addressed and discussed. The system is then tested using a well-known pole-placement state feedback controller to verify its functionality.","PeriodicalId":443652,"journal":{"name":"2007 5th Student Conference on Research and Development","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121969912","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 : 2007-12-01DOI: 10.1109/SCORED.2007.4451425
Syed Abdul Rahman Al-Haddad, S. Samad, Aini Hussain, K. A. Ishak, Hamid Mirvaziri
This paper is focused on Malay speech recognition with the intention to introduce a decision fusion technique for isolated Malay digit recognition using Dynamic Time Warping (DTW) and Hidden Markov Model (HMM). This study proposes an algorithm for decision fusion of the recognition models. The endpoint detection, framing, normalization, Mel Frequency Cepstral Coefficient (MFCC) and vector quantization techniques are used to process speech samples to accomplish the recognition. Decision fusion technique is then used to combine the results of DTW and HMM. The algorithm is tested on speech samples that is a part of a Malay corpus.
{"title":"Decision Fusion for Isolated Malay Digit Recognition Using Dynamic Time Warping (DTW) and Hidden Markov Model (HMM)","authors":"Syed Abdul Rahman Al-Haddad, S. Samad, Aini Hussain, K. A. Ishak, Hamid Mirvaziri","doi":"10.1109/SCORED.2007.4451425","DOIUrl":"https://doi.org/10.1109/SCORED.2007.4451425","url":null,"abstract":"This paper is focused on Malay speech recognition with the intention to introduce a decision fusion technique for isolated Malay digit recognition using Dynamic Time Warping (DTW) and Hidden Markov Model (HMM). This study proposes an algorithm for decision fusion of the recognition models. The endpoint detection, framing, normalization, Mel Frequency Cepstral Coefficient (MFCC) and vector quantization techniques are used to process speech samples to accomplish the recognition. Decision fusion technique is then used to combine the results of DTW and HMM. The algorithm is tested on speech samples that is a part of a Malay corpus.","PeriodicalId":443652,"journal":{"name":"2007 5th Student Conference on Research and Development","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124745313","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：