Pub Date : 2012-11-01DOI: 10.1504/IJISTA.2014.068828
L. Butler, G. Bright
The current economic climate spurred by growing customer demands are placing more and more pressure on manufacturing enterprises to improve efficiency and productivity even further than before. Opportunities exist for implementing novel optimisation techniques to improve the capabilities of modern advanced manufacturing systems. Computational Intelligence (CI) is not a new topic of research, however recent advances in available computing power and new paradigms in the field have given rise to this research. This paper investigates the extent of CI applications in manufacturing system management, and undertakes to identify the latest CI paradigms which are applicable to manufacturing system management optimisation. The paper also summarises these applicable CI paradigms in such a way as to form the basis for future work in simulation and experimentation.
{"title":"Computational intelligence for advanced manufacturing system management: A review","authors":"L. Butler, G. Bright","doi":"10.1504/IJISTA.2014.068828","DOIUrl":"https://doi.org/10.1504/IJISTA.2014.068828","url":null,"abstract":"The current economic climate spurred by growing customer demands are placing more and more pressure on manufacturing enterprises to improve efficiency and productivity even further than before. Opportunities exist for implementing novel optimisation techniques to improve the capabilities of modern advanced manufacturing systems. Computational Intelligence (CI) is not a new topic of research, however recent advances in available computing power and new paradigms in the field have given rise to this research. This paper investigates the extent of CI applications in manufacturing system management, and undertakes to identify the latest CI paradigms which are applicable to manufacturing system management optimisation. The paper also summarises these applicable CI paradigms in such a way as to form the basis for future work in simulation and experimentation.","PeriodicalId":328187,"journal":{"name":"2012 19th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)","volume":"179 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132136071","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 : 2012-11-01DOI: 10.1504/IJCAT.2014.063913
K. Mutib, M. Emaduddin, M. Alsulaiman, R. Hedjar, E. Mattar
A novel method is proposed that adapts a previously proposed LADAR based pedestrian detection and tracking technique by introducing a stereo-vision based segmentation technique for the purpose of pedestrian detection and tracking. The proposed method detects the harmonic motions of limbs and body during a typical human walk and temporally propagates the position, stride, direction and phase using a particle filter. The particle-filter uses a human limb-motion model and is able to track the walking pedestrians in a heavily occluded environment. Potential 3D point clusters belonging to arms and feet are extracted employing an adapted version of RANSAC based segmentation algorithm. A Fourier-transform based periodogram confirms the periodicity for each point-cluster representing limbs. Since RGB or intensity data from the stereo-vision input is ignored and the proposed method completely relies upon 3D data produced by the stereo-vision sensor, reliable illumination invariant pedestrian detection and tracking results are achieved using Daimler-Stereo-Pedestrian-Detection-Dataset. Further lab experiments also confirm the viability of the method within the indoor environment.
{"title":"Motion periodicity based pedestrian detection and particle filter based pedestrian tracking using stereo vision camera","authors":"K. Mutib, M. Emaduddin, M. Alsulaiman, R. Hedjar, E. Mattar","doi":"10.1504/IJCAT.2014.063913","DOIUrl":"https://doi.org/10.1504/IJCAT.2014.063913","url":null,"abstract":"A novel method is proposed that adapts a previously proposed LADAR based pedestrian detection and tracking technique by introducing a stereo-vision based segmentation technique for the purpose of pedestrian detection and tracking. The proposed method detects the harmonic motions of limbs and body during a typical human walk and temporally propagates the position, stride, direction and phase using a particle filter. The particle-filter uses a human limb-motion model and is able to track the walking pedestrians in a heavily occluded environment. Potential 3D point clusters belonging to arms and feet are extracted employing an adapted version of RANSAC based segmentation algorithm. A Fourier-transform based periodogram confirms the periodicity for each point-cluster representing limbs. Since RGB or intensity data from the stereo-vision input is ignored and the proposed method completely relies upon 3D data produced by the stereo-vision sensor, reliable illumination invariant pedestrian detection and tracking results are achieved using Daimler-Stereo-Pedestrian-Detection-Dataset. Further lab experiments also confirm the viability of the method within the indoor environment.","PeriodicalId":328187,"journal":{"name":"2012 19th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121673836","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 : 2012-11-01DOI: 10.1504/IJBBR.2013.058722
X. Zhu, H. Qiu, Z. Dong, Z. Qi, Y. Zhang
The paper puts forward a novel vehicle-network architecture of the power system based on the 4WIDIS EV. And then, the steering coordination control system's design of the 4WIDIS EV based on the novel vehicle-network architecture is focused on the analysis. Finally, the experimental data shows that the system can meet the actual steering requirements of synchronicity, accuracy and real-time.
{"title":"Steering coordination control of front wheels for a four in-wheel-motor drive electric vehicle","authors":"X. Zhu, H. Qiu, Z. Dong, Z. Qi, Y. Zhang","doi":"10.1504/IJBBR.2013.058722","DOIUrl":"https://doi.org/10.1504/IJBBR.2013.058722","url":null,"abstract":"The paper puts forward a novel vehicle-network architecture of the power system based on the 4WIDIS EV. And then, the steering coordination control system's design of the 4WIDIS EV based on the novel vehicle-network architecture is focused on the analysis. Finally, the experimental data shows that the system can meet the actual steering requirements of synchronicity, accuracy and real-time.","PeriodicalId":328187,"journal":{"name":"2012 19th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130599901","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}
Street lighting system as one of the foremost facilities used in the cities plays a pivotal role in reducing nocturnal car accidents and enhancing individual and social security. Therefore, one of the main priorities in Electrical Distribution Companies is the timely repair and maintenance of the street lightening which should be regularly checked. The common mechanized monitoring of the street lighting is based on measuring the consumed current of each lamp and comparing it with the lamp nominal current. In this way, the error in network is identified. Monitoring street lighting in Iran is presently conducted by traditional inspection and check-out method. This paper suggests a new method for monitoring and remote sensing of the street lighting system which is completely isolated from electricity network and applies picture shooting of the street lighting network, image processing, and computer vision techniques and separating the light source method in the picture. The system performance was simulated and verified by MATLAB software. The results indicate the ability and effectiveness of this method and led to closing a research contract with Tehran Electrical Distribution Company for pilot implementation of the plan in one of the passageways in Tehran.
{"title":"Monitoring and remote sensing of the street lighting system using computer vision and image processing techniques for the purpose of mechanized blackouts","authors":"P. N. Zanjani, V. Ghods, M. Bahadori","doi":"10.1049/CP.2013.1016","DOIUrl":"https://doi.org/10.1049/CP.2013.1016","url":null,"abstract":"Street lighting system as one of the foremost facilities used in the cities plays a pivotal role in reducing nocturnal car accidents and enhancing individual and social security. Therefore, one of the main priorities in Electrical Distribution Companies is the timely repair and maintenance of the street lightening which should be regularly checked. The common mechanized monitoring of the street lighting is based on measuring the consumed current of each lamp and comparing it with the lamp nominal current. In this way, the error in network is identified. Monitoring street lighting in Iran is presently conducted by traditional inspection and check-out method. This paper suggests a new method for monitoring and remote sensing of the street lighting system which is completely isolated from electricity network and applies picture shooting of the street lighting network, image processing, and computer vision techniques and separating the light source method in the picture. The system performance was simulated and verified by MATLAB software. The results indicate the ability and effectiveness of this method and led to closing a research contract with Tehran Electrical Distribution Company for pilot implementation of the plan in one of the passageways in Tehran.","PeriodicalId":328187,"journal":{"name":"2012 19th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121435215","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 : 2012-11-01DOI: 10.1504/IJISTA.2014.059300
S. S. Shamsudin, Xiaoqi Chen
This paper presents a recursive Gauss-Newton based training algorithm to model the dynamics of a small scale helicopter system using neural network modelling approach. It focuses on selection of optimized network for recursive algorithm that offers good generalization performance with the aid of the cross validation method proposed. The recursive method is then compared with off-line Levenberg-Marquardt (LM) training method to evaluate the generalization performance and adaptability of the model prediction. The results indicate that the recursive Gauss-Newton method gives slightly lower generalization performance compared to its off-line counterpart but adapts well to the dynamic changes that occur during flight. The proposed recursive algorithm was found effective in representing coupled helicopter dynamics with acceptable accuracy within the available computational timing constraint.
{"title":"Recursive Gauss-Newton based training algorithm for neural network modelling of an unmanned helicopter dynamics","authors":"S. S. Shamsudin, Xiaoqi Chen","doi":"10.1504/IJISTA.2014.059300","DOIUrl":"https://doi.org/10.1504/IJISTA.2014.059300","url":null,"abstract":"This paper presents a recursive Gauss-Newton based training algorithm to model the dynamics of a small scale helicopter system using neural network modelling approach. It focuses on selection of optimized network for recursive algorithm that offers good generalization performance with the aid of the cross validation method proposed. The recursive method is then compared with off-line Levenberg-Marquardt (LM) training method to evaluate the generalization performance and adaptability of the model prediction. The results indicate that the recursive Gauss-Newton method gives slightly lower generalization performance compared to its off-line counterpart but adapts well to the dynamic changes that occur during flight. The proposed recursive algorithm was found effective in representing coupled helicopter dynamics with acceptable accuracy within the available computational timing constraint.","PeriodicalId":328187,"journal":{"name":"2012 19th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122856918","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 : 2012-11-01DOI: 10.1504/IJBBR.2013.058720
S. Liang, Z. Qi, Z. Dong, H. Qiu, S. Hu
Since the four-in-wheel-motors drive (FWMD) Electric Vehicle (EV) has a 4-wheel independent steering, this paper presents a novel control method for an electric power steering system with a dead-zone execution mechanism. A mathematical model was derived for execution mechanisms from the empirical data. A “Dead-zone Inverse Transforming Compensation” was designed to eliminate ill effects caused by dead-zone. The experiment in a real car environment proves that the proposed method.
{"title":"A novel control method for electric power steering system based on dead-zone Inverse Transforming Compensation in a four-in-wheel-motor drive Electric Vehicle","authors":"S. Liang, Z. Qi, Z. Dong, H. Qiu, S. Hu","doi":"10.1504/IJBBR.2013.058720","DOIUrl":"https://doi.org/10.1504/IJBBR.2013.058720","url":null,"abstract":"Since the four-in-wheel-motors drive (FWMD) Electric Vehicle (EV) has a 4-wheel independent steering, this paper presents a novel control method for an electric power steering system with a dead-zone execution mechanism. A mathematical model was derived for execution mechanisms from the empirical data. A “Dead-zone Inverse Transforming Compensation” was designed to eliminate ill effects caused by dead-zone. The experiment in a real car environment proves that the proposed method.","PeriodicalId":328187,"journal":{"name":"2012 19th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122917325","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 : 2012-11-01DOI: 10.1504/IJCAT.2014.063914
Kouhei Shimizu, H. Iyatomi, K. Norton, M. E. Celebi
In this paper, we present an automated melanoma screening system that supports not only melanocytic skin lesions (MSLs) but also non-melanocytic skin lesions (NoMSLs). Melanoma is known as the most fatal skin cancer. Therefore, early detection is highly desired. However, melanoma diagnosis is not easy even for expert dermatologists. In such a background, several researchers have developed automated methods for melanoma detection but they mostly focused only on MSLs while NoMSLs have been almost neglected. To expand the scope to NoMSLs, we developed two melanoma classification models, namely the single-shot and the double-shot. The single-shot model differentiates melanomas from all the other skin lesions including NoMSLs. The double-shot model divides the task into two subtasks. Firstly, it differentiates MSLs from NoMSLs and then differentiates melanomas from the other MSLs. The single-shot achieved a sensitivity (SE) of 92.9% and a specificity (SP) of 83.9%, while the double-shot achieved an SE of 97.6% and an SP of 92.2% when 10 image features were used. The double-shot showed superior detection performance to the single-shot except when their constituent image features were limited.
{"title":"Extension of automated melanoma screening for non-melanocytic skin lesions","authors":"Kouhei Shimizu, H. Iyatomi, K. Norton, M. E. Celebi","doi":"10.1504/IJCAT.2014.063914","DOIUrl":"https://doi.org/10.1504/IJCAT.2014.063914","url":null,"abstract":"In this paper, we present an automated melanoma screening system that supports not only melanocytic skin lesions (MSLs) but also non-melanocytic skin lesions (NoMSLs). Melanoma is known as the most fatal skin cancer. Therefore, early detection is highly desired. However, melanoma diagnosis is not easy even for expert dermatologists. In such a background, several researchers have developed automated methods for melanoma detection but they mostly focused only on MSLs while NoMSLs have been almost neglected. To expand the scope to NoMSLs, we developed two melanoma classification models, namely the single-shot and the double-shot. The single-shot model differentiates melanomas from all the other skin lesions including NoMSLs. The double-shot model divides the task into two subtasks. Firstly, it differentiates MSLs from NoMSLs and then differentiates melanomas from the other MSLs. The single-shot achieved a sensitivity (SE) of 92.9% and a specificity (SP) of 83.9%, while the double-shot achieved an SE of 97.6% and an SP of 92.2% when 10 image features were used. The double-shot showed superior detection performance to the single-shot except when their constituent image features were limited.","PeriodicalId":328187,"journal":{"name":"2012 19th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114504358","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 : 2012-11-01DOI: 10.1504/IJISTA.2014.059302
Kevin Hughes, Heshan A. Fernando, Greg Szkilnyk, B. Surgenor, M. Greenspan
A major goal of many manufacturers is to minimize production downtime caused by machine faults and equipment breakdowns. This goal is typically achieved using sensor-based systems that can quickly detect and diagnose machine faults of various types. This paper proposes the use of a video event detection method based on spatiotemporal volumes (STVs) in a fault monitoring application to complement and improve upon existing systems. To detect faults, a set of image sequences are captured using a single web cam from the part dispensing region of an assembly machine testbed. The motion is segmented in each image creating binary frames which are stacked to build a STV. Normal operation of the machine is modeled by building a STV from several training sequences. New STVs are compared to the model and classified as either normal or faulty behaviour based on a calculated similarity measure. Both full-STV and partial-STV matching methods are tested. Test results show that the system is very effective on the data set collected. Recommendations for further exploration of this concept are made that include alternative video event detection techniques and different testbeds.
{"title":"Spatiotemporal volume video event detection for fault monitoring in assembly automation","authors":"Kevin Hughes, Heshan A. Fernando, Greg Szkilnyk, B. Surgenor, M. Greenspan","doi":"10.1504/IJISTA.2014.059302","DOIUrl":"https://doi.org/10.1504/IJISTA.2014.059302","url":null,"abstract":"A major goal of many manufacturers is to minimize production downtime caused by machine faults and equipment breakdowns. This goal is typically achieved using sensor-based systems that can quickly detect and diagnose machine faults of various types. This paper proposes the use of a video event detection method based on spatiotemporal volumes (STVs) in a fault monitoring application to complement and improve upon existing systems. To detect faults, a set of image sequences are captured using a single web cam from the part dispensing region of an assembly machine testbed. The motion is segmented in each image creating binary frames which are stacked to build a STV. Normal operation of the machine is modeled by building a STV from several training sequences. New STVs are compared to the model and classified as either normal or faulty behaviour based on a calculated similarity measure. Both full-STV and partial-STV matching methods are tested. Test results show that the system is very effective on the data set collected. Recommendations for further exploration of this concept are made that include alternative video event detection techniques and different testbeds.","PeriodicalId":328187,"journal":{"name":"2012 19th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133545029","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 : 2012-11-01DOI: 10.1504/IJBBR.2013.058721
Z. Deng, Z. Qi, Z. Dong, P. He, C. Han, S. Ren
A four in-wheel-motors drive electric vehicle need to identify the road surface in order to optimise the slip-ratio control. This paper builds a four in-wheel-motor drive electric vehicle dynamic model and estimates the vehicle speed and driving forces of four wheels by the method of adaptive filtering. According to the calculated tyre adhesion coefficient and slip ratio, the paper employs the method of combining fuzzy inference with Slope determination to evaluate the road type and determine the target slip ratio, and obtains a better slip ratio regulation effect through timely and precise adjustment of output torque of the in-wheel motors. The simulation and experiment results confirm that it is a reliable design.
{"title":"A road surface identification method for a four in-wheel-motor drive electric vehicle","authors":"Z. Deng, Z. Qi, Z. Dong, P. He, C. Han, S. Ren","doi":"10.1504/IJBBR.2013.058721","DOIUrl":"https://doi.org/10.1504/IJBBR.2013.058721","url":null,"abstract":"A four in-wheel-motors drive electric vehicle need to identify the road surface in order to optimise the slip-ratio control. This paper builds a four in-wheel-motor drive electric vehicle dynamic model and estimates the vehicle speed and driving forces of four wheels by the method of adaptive filtering. According to the calculated tyre adhesion coefficient and slip ratio, the paper employs the method of combining fuzzy inference with Slope determination to evaluate the road type and determine the target slip ratio, and obtains a better slip ratio regulation effect through timely and precise adjustment of output torque of the in-wheel motors. The simulation and experiment results confirm that it is a reliable design.","PeriodicalId":328187,"journal":{"name":"2012 19th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129160085","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：