Pub Date : 1900-01-01DOI: 10.1109/INTELSE.2016.7475168
Rida Gillani, Ali Nasir
There are many challenges involved in the realization of a shopping assistance robot (SAR). The specific challenge addressed in this paper is that of incorporating artificial intelligence or decision making capability in such robot. Markov Decision Process (MDP) based formulation of the problem has been presented for this purpose. The major advantage of the MDP based approach over simple search based artificial intelligence techniques is that it can incorporate uncertainty. The proposed MDP model has been solved for optimal policy using value iteration algorithm. Furthermore, it has been shown how the reward function influences the structure of the resulting policy. The results show encouraging potential in the use of MDP based formulation for SAR.
{"title":"Incorporating artificial intelligence in shopping assistance robot using Markov Decision Process","authors":"Rida Gillani, Ali Nasir","doi":"10.1109/INTELSE.2016.7475168","DOIUrl":"https://doi.org/10.1109/INTELSE.2016.7475168","url":null,"abstract":"There are many challenges involved in the realization of a shopping assistance robot (SAR). The specific challenge addressed in this paper is that of incorporating artificial intelligence or decision making capability in such robot. Markov Decision Process (MDP) based formulation of the problem has been presented for this purpose. The major advantage of the MDP based approach over simple search based artificial intelligence techniques is that it can incorporate uncertainty. The proposed MDP model has been solved for optimal policy using value iteration algorithm. Furthermore, it has been shown how the reward function influences the structure of the resulting policy. The results show encouraging potential in the use of MDP based formulation for SAR.","PeriodicalId":127671,"journal":{"name":"2016 International Conference on Intelligent Systems Engineering (ICISE)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133694295","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 : 1900-01-01DOI: 10.1109/INTELSE.2016.7475162
Waqar Farooq, N. Butt, Sameed Shukat, N. Baig, Sheikh Muhammad Ahmed
This paper demonstrates the problem and effects of landmines in defense fields. We are proposing a robot that has the aptitude to detect the buried mines and lets user control it wirelessly to avoid human causalities. The robot is equipped with special wheels controlled by H-Bridge module, allowing it to move in all possible directions. In this paper, we focus on the safety of humans and the robot; the robot is equipped with special range sensors that help in avoiding the obstacles in the field by specifically detecting the position of obstacles. For the fabrication of the project, a special type of prototype made of lightweight temperature resistant metal is used to carry all objects. A wireless camera is added to the robot, which captures and broadcasts the present location of the robot. Microcontroller commands the robot. This technique has the practical benefit of reducing the number of casualties, after the implementation of the technique, the robot can be controlled efficiently and it robustly determines the position of the obstacle.
{"title":"Wirelessly Controlled Mines Detection Robot","authors":"Waqar Farooq, N. Butt, Sameed Shukat, N. Baig, Sheikh Muhammad Ahmed","doi":"10.1109/INTELSE.2016.7475162","DOIUrl":"https://doi.org/10.1109/INTELSE.2016.7475162","url":null,"abstract":"This paper demonstrates the problem and effects of landmines in defense fields. We are proposing a robot that has the aptitude to detect the buried mines and lets user control it wirelessly to avoid human causalities. The robot is equipped with special wheels controlled by H-Bridge module, allowing it to move in all possible directions. In this paper, we focus on the safety of humans and the robot; the robot is equipped with special range sensors that help in avoiding the obstacles in the field by specifically detecting the position of obstacles. For the fabrication of the project, a special type of prototype made of lightweight temperature resistant metal is used to carry all objects. A wireless camera is added to the robot, which captures and broadcasts the present location of the robot. Microcontroller commands the robot. This technique has the practical benefit of reducing the number of casualties, after the implementation of the technique, the robot can be controlled efficiently and it robustly determines the position of the obstacle.","PeriodicalId":127671,"journal":{"name":"2016 International Conference on Intelligent Systems Engineering (ICISE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131281218","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 : 1900-01-01DOI: 10.1109/INTELSE.2016.7475157
Muhammad Faisal, Mohsin Jamil, S. Soomro, Abubaker Riaz, M. Luqman
In these days, three degree of freedom (3DOF) cranes are considered as backbone in most of industries. It is mostly used for picking and placing of heavy objects from one place to another place. The common part in mostly cranes is jib system. Two main tasks of jib system are movement of the trolley and loading/unloading of the payload. The safety of crane mostly depends upon these sub tasks. In most cases, number of unwanted vibrations due to undesirable initial jerks of trolley results uneven operation of crane. These jerks are usually happened during acceleration in the start and deceleration in the end of crane operation. So, it is desirable to develop a control technique that tries to reduce theses initial trolley jerks by providing a reasonable input to the trolley. Moreover, reduction of jerks reduce the payload vibrations. So, it results smooth operation of crane. In this research work, we have implemented PD control technique for payload vibration and trolley position control of jib system of three 3DOF crane. The gains of PD controllers have been found through two methods namely LQR and pole placement. The performance of controllers have been investigated on Matlab/Simulink. The results shows the effectiveness of PD tune by LQR as compared to PD tune by pole placement in context of settling time and rise time of both trolley position and payload vibrations. The former technique is also helpful in reduction of payload vibrations or payload load anti-swing. It has also improved the overshoot of the trolley.
{"title":"Digital control of trolley position and payload vibrations of non-linear Quanser three degree of freedom crane","authors":"Muhammad Faisal, Mohsin Jamil, S. Soomro, Abubaker Riaz, M. Luqman","doi":"10.1109/INTELSE.2016.7475157","DOIUrl":"https://doi.org/10.1109/INTELSE.2016.7475157","url":null,"abstract":"In these days, three degree of freedom (3DOF) cranes are considered as backbone in most of industries. It is mostly used for picking and placing of heavy objects from one place to another place. The common part in mostly cranes is jib system. Two main tasks of jib system are movement of the trolley and loading/unloading of the payload. The safety of crane mostly depends upon these sub tasks. In most cases, number of unwanted vibrations due to undesirable initial jerks of trolley results uneven operation of crane. These jerks are usually happened during acceleration in the start and deceleration in the end of crane operation. So, it is desirable to develop a control technique that tries to reduce theses initial trolley jerks by providing a reasonable input to the trolley. Moreover, reduction of jerks reduce the payload vibrations. So, it results smooth operation of crane. In this research work, we have implemented PD control technique for payload vibration and trolley position control of jib system of three 3DOF crane. The gains of PD controllers have been found through two methods namely LQR and pole placement. The performance of controllers have been investigated on Matlab/Simulink. The results shows the effectiveness of PD tune by LQR as compared to PD tune by pole placement in context of settling time and rise time of both trolley position and payload vibrations. The former technique is also helpful in reduction of payload vibrations or payload load anti-swing. It has also improved the overshoot of the trolley.","PeriodicalId":127671,"journal":{"name":"2016 International Conference on Intelligent Systems Engineering (ICISE)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130582650","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 : 1900-01-01DOI: 10.1109/INTELSE.2016.7475119
E. Aboadla, Sheroz Khan, M. H. Habaebi, T. Gunawan, B. A. Hamidah, Mashkuri Bin Yaacob
Knowing Total Harmonic Distortion (THD) content of voltage source inverter (VSI) is important and must be within the allowable range. Several schemes are suggested to mitigate THD and to produce as much a sinusoidal output signal as would be possible. One of such schemes is using a Sinusoidal Pulse Width Modulation SPWM-based inverter. SPWM is usually used in inverters for industrial applications. In this paper, a study of the performance of the SPWM technique is presented for a single phase H-bridge inverter. The SPWM scheme is modeled in MATLAB - Simulink. A bipolar and unipolar PWM technique are compared in this project as such techniques offer the features of effectively doubling the switching frequency of the output voltage. Under different conditions of modulation index, the pattern is utilized to estimate the harmonics. Simulation results for a full bridge single phase inverter using bipolar and unipolar SPWM schemes are presented.
{"title":"Effect of modulation index of pulse width modulation inverter on Total Harmonic Distortion for Sinusoidal","authors":"E. Aboadla, Sheroz Khan, M. H. Habaebi, T. Gunawan, B. A. Hamidah, Mashkuri Bin Yaacob","doi":"10.1109/INTELSE.2016.7475119","DOIUrl":"https://doi.org/10.1109/INTELSE.2016.7475119","url":null,"abstract":"Knowing Total Harmonic Distortion (THD) content of voltage source inverter (VSI) is important and must be within the allowable range. Several schemes are suggested to mitigate THD and to produce as much a sinusoidal output signal as would be possible. One of such schemes is using a Sinusoidal Pulse Width Modulation SPWM-based inverter. SPWM is usually used in inverters for industrial applications. In this paper, a study of the performance of the SPWM technique is presented for a single phase H-bridge inverter. The SPWM scheme is modeled in MATLAB - Simulink. A bipolar and unipolar PWM technique are compared in this project as such techniques offer the features of effectively doubling the switching frequency of the output voltage. Under different conditions of modulation index, the pattern is utilized to estimate the harmonics. Simulation results for a full bridge single phase inverter using bipolar and unipolar SPWM schemes are presented.","PeriodicalId":127671,"journal":{"name":"2016 International Conference on Intelligent Systems Engineering (ICISE)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122195867","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 : 1900-01-01DOI: 10.1109/INTELSE.2016.7475123
Ala Abdulhakim Alariki, Azizah Bt Abdul Manaf, S. Khan
With the increased popularity of touch screen mobile phones, touch gesture behavior is becoming more and more important. Due to increasing demand for safer access in touch screen mobile phones, old strategies like pins, tokens, or passwords have failed to stay abreast of the challenges. However, we study user authentication scheme based on these touch dynamics features for accurate user authentication. We developed the software needed to collect readings from touch screen of mobile phone running the android operation system. Based on these preliminary experiments we concentrated on the Random Forest classifier to differentiate multiple users. Our results show that combining all features such as touch direction, finger pressure, finger size and acceleration correctly classified touch behavior on an android phone with 98.14% accuracy.
{"title":"A study of touching behavior for authentication in touch screen smart devices","authors":"Ala Abdulhakim Alariki, Azizah Bt Abdul Manaf, S. Khan","doi":"10.1109/INTELSE.2016.7475123","DOIUrl":"https://doi.org/10.1109/INTELSE.2016.7475123","url":null,"abstract":"With the increased popularity of touch screen mobile phones, touch gesture behavior is becoming more and more important. Due to increasing demand for safer access in touch screen mobile phones, old strategies like pins, tokens, or passwords have failed to stay abreast of the challenges. However, we study user authentication scheme based on these touch dynamics features for accurate user authentication. We developed the software needed to collect readings from touch screen of mobile phone running the android operation system. Based on these preliminary experiments we concentrated on the Random Forest classifier to differentiate multiple users. Our results show that combining all features such as touch direction, finger pressure, finger size and acceleration correctly classified touch behavior on an android phone with 98.14% accuracy.","PeriodicalId":127671,"journal":{"name":"2016 International Conference on Intelligent Systems Engineering (ICISE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129516572","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 : 1900-01-01DOI: 10.1109/INTELSE.2016.7475115
Shah Riaz, L. Khan
In this paper, effect of the vertical vibrations on biodynamic model of a 55 kg pregnant woman seated at the driver place is carried out. Investigation is based on eleven degrees of freedom biodynamic pregnant woman model and eight degree of freedom full-car nonlinear active suspension model. In the exiting literature, more emphasis is devoted towards the effect of vibrations on nonpregnant subject while little work is done on the biodynamic response of pregnant seated woman exposed to vertical vibrations. The mass increase due to pregnancy is incorporated in the biodynamic mathematical model. The lumped-parameter biodynamic model is implemented for vibration damping and frequency control. An advanced adaptive NeuroFuzzy Takagi Sugeno Kang (NFTSK) control technique is developed for ride quality improvement of the seated pregnant woman driver and to reduce the risk of damages both to fetus and mother. Performance of the advanced adaptive control technique is validated against the random gaussian external road profile and results are compared with passive and PID control for further validation of the performance.
{"title":"Adaptive soft computing algorithm for seated pregnant subject biodynamic vibrations damping control","authors":"Shah Riaz, L. Khan","doi":"10.1109/INTELSE.2016.7475115","DOIUrl":"https://doi.org/10.1109/INTELSE.2016.7475115","url":null,"abstract":"In this paper, effect of the vertical vibrations on biodynamic model of a 55 kg pregnant woman seated at the driver place is carried out. Investigation is based on eleven degrees of freedom biodynamic pregnant woman model and eight degree of freedom full-car nonlinear active suspension model. In the exiting literature, more emphasis is devoted towards the effect of vibrations on nonpregnant subject while little work is done on the biodynamic response of pregnant seated woman exposed to vertical vibrations. The mass increase due to pregnancy is incorporated in the biodynamic mathematical model. The lumped-parameter biodynamic model is implemented for vibration damping and frequency control. An advanced adaptive NeuroFuzzy Takagi Sugeno Kang (NFTSK) control technique is developed for ride quality improvement of the seated pregnant woman driver and to reduce the risk of damages both to fetus and mother. Performance of the advanced adaptive control technique is validated against the random gaussian external road profile and results are compared with passive and PID control for further validation of the performance.","PeriodicalId":127671,"journal":{"name":"2016 International Conference on Intelligent Systems Engineering (ICISE)","volume":"32 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134521607","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 : 1900-01-01DOI: 10.1109/INTELSE.2016.7475129
A. Rehman, Fahad Khan, Baber Khan Jadoon
Noise cancellation algorithms have been frequently applied in many fields including image/video processing. Adaptive noise cancellation algorithms exploit the correlation property of noise and remove the noise from the input signal more effectively than non-adaptive algorithms. In this paper different noise cancellation techniques are applied to de-noise a video frame. Three different variants of gradient based adaptive filtering algorithms and independent component analysis (ICA) procedure are implemented and compared on the basis of signal to noise ratio (SNR) and computational time. The common algorithms used in adaptive filters are least mean square (LMS), normalized least means square (NLMS), and recursive least mean square (RLS). The simulation results demonstrates that NLMS algorithm is computationally efficient but cannot handle impulsive noise whereas LMS and RLS can perform better for long duration noise signals. The comparative analysis of adaptive filtering algorithms and ICA shows that ICA can perform better then all three iterative gradient based algorithms because of its non-iterative nature. For testing and simulations, three variants of white Gaussian noise (WGN) are used to corrupt the video frame.
{"title":"Analysis of adaptive filter and ICA for noise cancellation from a video frame","authors":"A. Rehman, Fahad Khan, Baber Khan Jadoon","doi":"10.1109/INTELSE.2016.7475129","DOIUrl":"https://doi.org/10.1109/INTELSE.2016.7475129","url":null,"abstract":"Noise cancellation algorithms have been frequently applied in many fields including image/video processing. Adaptive noise cancellation algorithms exploit the correlation property of noise and remove the noise from the input signal more effectively than non-adaptive algorithms. In this paper different noise cancellation techniques are applied to de-noise a video frame. Three different variants of gradient based adaptive filtering algorithms and independent component analysis (ICA) procedure are implemented and compared on the basis of signal to noise ratio (SNR) and computational time. The common algorithms used in adaptive filters are least mean square (LMS), normalized least means square (NLMS), and recursive least mean square (RLS). The simulation results demonstrates that NLMS algorithm is computationally efficient but cannot handle impulsive noise whereas LMS and RLS can perform better for long duration noise signals. The comparative analysis of adaptive filtering algorithms and ICA shows that ICA can perform better then all three iterative gradient based algorithms because of its non-iterative nature. For testing and simulations, three variants of white Gaussian noise (WGN) are used to corrupt the video frame.","PeriodicalId":127671,"journal":{"name":"2016 International Conference on Intelligent Systems Engineering (ICISE)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125427321","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 : 1900-01-01DOI: 10.1109/INTELSE.2016.7475176
Muddasir Ahmad, M. Aqil
Electroencephalography (EEG) has potential medical, military and industrial applications. To date, no method is said to be a standardized EEG estimator. The aim of this study is to realize QR decomposition based recursive least square estimator for EEG feature extraction. The features are modeled as adaptive autoregressive model. Linear discriminant analysis is performed to classify the extracted features for a dual class experiment. For validation, right- and left-hand movement imaginations based EEG experiments are conducted. Further validation, carried out by a comparative study with other adaptive (least mean squares and recursive least squares) algorithms, demonstrates the effectiveness of the proposed method.
{"title":"QR decomposition based recursive least square adaptation of autoregressive EEG features","authors":"Muddasir Ahmad, M. Aqil","doi":"10.1109/INTELSE.2016.7475176","DOIUrl":"https://doi.org/10.1109/INTELSE.2016.7475176","url":null,"abstract":"Electroencephalography (EEG) has potential medical, military and industrial applications. To date, no method is said to be a standardized EEG estimator. The aim of this study is to realize QR decomposition based recursive least square estimator for EEG feature extraction. The features are modeled as adaptive autoregressive model. Linear discriminant analysis is performed to classify the extracted features for a dual class experiment. For validation, right- and left-hand movement imaginations based EEG experiments are conducted. Further validation, carried out by a comparative study with other adaptive (least mean squares and recursive least squares) algorithms, demonstrates the effectiveness of the proposed method.","PeriodicalId":127671,"journal":{"name":"2016 International Conference on Intelligent Systems Engineering (ICISE)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125211824","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 : 1900-01-01DOI: 10.1109/INTELSE.2016.7475130
M. Alfaqawi, M. H. Habaebi, M. Siddiqi, M. R. Islam, Sheroz Khan, Dinesh Datla
The concept of wireless distributed computing (WDC), proposed recently, is used to distribute and allocate computational tasks wirelessly. Despite various benefits of WDC, such as distributing the workload efficiently among cooperating nodes, WDC concept is facing enormous challenges. Proposing an efficient task allocation algorithm is one of the key challenges in WDC network. The work reported here proposes a novel task allocation algorithm called as adaptive load balancing (ALB). The ALB algorithm nominates the cooperating nodes in WDC network adaptively based on the channel conditions among the cooperating nodes. Then, it balances the workload amongst the cooperating nodes based on the available energy in each node. Herein, the validity of the proposed novel ALB algorithm is proved first. Then, ALB algorithm is applied to an application in cognitive radio network (CRN). Furthermore, the channel impact on the distributed tasks by ALB algorithm, in WDC-CRN, is investigated and benchmarked. Accordingly, the probability of detection results in case of applying the novel ALB algorithm is found to be enhanced.
{"title":"Adaptive load balancing algorithm for wireless distributed computing networks","authors":"M. Alfaqawi, M. H. Habaebi, M. Siddiqi, M. R. Islam, Sheroz Khan, Dinesh Datla","doi":"10.1109/INTELSE.2016.7475130","DOIUrl":"https://doi.org/10.1109/INTELSE.2016.7475130","url":null,"abstract":"The concept of wireless distributed computing (WDC), proposed recently, is used to distribute and allocate computational tasks wirelessly. Despite various benefits of WDC, such as distributing the workload efficiently among cooperating nodes, WDC concept is facing enormous challenges. Proposing an efficient task allocation algorithm is one of the key challenges in WDC network. The work reported here proposes a novel task allocation algorithm called as adaptive load balancing (ALB). The ALB algorithm nominates the cooperating nodes in WDC network adaptively based on the channel conditions among the cooperating nodes. Then, it balances the workload amongst the cooperating nodes based on the available energy in each node. Herein, the validity of the proposed novel ALB algorithm is proved first. Then, ALB algorithm is applied to an application in cognitive radio network (CRN). Furthermore, the channel impact on the distributed tasks by ALB algorithm, in WDC-CRN, is investigated and benchmarked. Accordingly, the probability of detection results in case of applying the novel ALB algorithm is found to be enhanced.","PeriodicalId":127671,"journal":{"name":"2016 International Conference on Intelligent Systems Engineering (ICISE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114194079","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 : 1900-01-01DOI: 10.1109/INTELSE.2016.7475163
Atif Khan, N. Salim, Haleem Farman
Multi-document summarization aims to produce a compressed version of numerous online text documents and preserves the salient information. A particular challenge for multi-document summarization is that there is an inevitable overlap in the information stored in different documents. Thus, effective summarization methods that merge similar information across the documents are desirable. This paper introduces a clustered genetic semantic graph approach for multi-document abstractive summarization. The semantic graph from the document set is constructed in such a way that the graph vertices represent the predicate argument structures (PASs), extracted automatically by employing semantic role labeling (SRL); and the edges of graph correspond to semantic similarity weight determined from PAS-to-PAS semantic similarity, and PAS-to-document relationship. The PAS-to-document relationship is expressed by different features, weighted and optimized by genetic algorithm. The salient graph nodes (PASs) are ranked based on modified weighted graph based ranking algorithm. The clustering algorithm is performed to eliminate redundancy in such a way that representative PAS with the highest salience score from each cluster is chosen, and fed to language generation to generate summary sentences. Experiment of this study is performed using DUC-2002, a standard corpus for text summarization. Experimental results indicate that the proposed approach outperforms other summarization systems.
{"title":"Clustered genetic semantic graph approach for multi-document abstractive summarization","authors":"Atif Khan, N. Salim, Haleem Farman","doi":"10.1109/INTELSE.2016.7475163","DOIUrl":"https://doi.org/10.1109/INTELSE.2016.7475163","url":null,"abstract":"Multi-document summarization aims to produce a compressed version of numerous online text documents and preserves the salient information. A particular challenge for multi-document summarization is that there is an inevitable overlap in the information stored in different documents. Thus, effective summarization methods that merge similar information across the documents are desirable. This paper introduces a clustered genetic semantic graph approach for multi-document abstractive summarization. The semantic graph from the document set is constructed in such a way that the graph vertices represent the predicate argument structures (PASs), extracted automatically by employing semantic role labeling (SRL); and the edges of graph correspond to semantic similarity weight determined from PAS-to-PAS semantic similarity, and PAS-to-document relationship. The PAS-to-document relationship is expressed by different features, weighted and optimized by genetic algorithm. The salient graph nodes (PASs) are ranked based on modified weighted graph based ranking algorithm. The clustering algorithm is performed to eliminate redundancy in such a way that representative PAS with the highest salience score from each cluster is chosen, and fed to language generation to generate summary sentences. Experiment of this study is performed using DUC-2002, a standard corpus for text summarization. Experimental results indicate that the proposed approach outperforms other summarization systems.","PeriodicalId":127671,"journal":{"name":"2016 International Conference on Intelligent Systems Engineering (ICISE)","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114312131","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：