Direction of Arrival (DOA) estimation or source localization by listening to the radiated acoustic signal from the target is of primal importance in underwater surveillance system. In general, the sensor array data vector is projected on a Complete Dictionary which is made up of a set of linearly independent basis vectors. In this work, the notion of Over-Complete Dictionary (OCD) is built for underwater source localization application. This is implemented by stacking multiple set of basis vectors. Each set of basis vectors are selected for a specific statistical properties of the signal and the ambient noise into consideration. In a dynamically changing ocean scenario, OCD implementation gives better results in comparison with the conventional or adaptive beamforming techniques. As expected, the simulation results also show significant performance improvement with OCD. Also, it is observed that the accuracy and bearing resolution improves as the dictionary size grows. The improved dictionary performance is demonstrated by Monte-Carlo simulations for various ocean scenarios which shows the effectiveness of the proposed technique.
{"title":"Source localization using Over-Complete Dictionary","authors":"Ashwin Srinath Sureshkumar, Harish Babu Kundhu Prabakaran","doi":"10.1109/ICAECC.2018.8479482","DOIUrl":"https://doi.org/10.1109/ICAECC.2018.8479482","url":null,"abstract":"Direction of Arrival (DOA) estimation or source localization by listening to the radiated acoustic signal from the target is of primal importance in underwater surveillance system. In general, the sensor array data vector is projected on a Complete Dictionary which is made up of a set of linearly independent basis vectors. In this work, the notion of Over-Complete Dictionary (OCD) is built for underwater source localization application. This is implemented by stacking multiple set of basis vectors. Each set of basis vectors are selected for a specific statistical properties of the signal and the ambient noise into consideration. In a dynamically changing ocean scenario, OCD implementation gives better results in comparison with the conventional or adaptive beamforming techniques. As expected, the simulation results also show significant performance improvement with OCD. Also, it is observed that the accuracy and bearing resolution improves as the dictionary size grows. The improved dictionary performance is demonstrated by Monte-Carlo simulations for various ocean scenarios which shows the effectiveness of the proposed technique.","PeriodicalId":106991,"journal":{"name":"2018 Second International Conference on Advances in Electronics, Computers and Communications (ICAECC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129161524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/ICAECC.2018.8479455
A. Shaji, Rakesh Kumar
Rotating point spread function (RPSF) is generated using a Fresnel zone type spiral phase mask, which encodes the axial position of a point source in the orientation of the point spread function. Microgrid polarimeter is an established technique to determine the polarization signature of an object. In this paper, we propose a new methodology which combines RPSF technique with microgrid polarimetry in order to obtain a joint polarimetric-three dimensional imaging capability. Simulation results are obtained for 3D localization of point sources and estimation of its linear polarization signature using data frames with and without additive white Gaussian noise.
{"title":"Joint Polarimetric-Three Dimensional Imaging Using Spiral Phase Mask and Microgrid Polarimeter","authors":"A. Shaji, Rakesh Kumar","doi":"10.1109/ICAECC.2018.8479455","DOIUrl":"https://doi.org/10.1109/ICAECC.2018.8479455","url":null,"abstract":"Rotating point spread function (RPSF) is generated using a Fresnel zone type spiral phase mask, which encodes the axial position of a point source in the orientation of the point spread function. Microgrid polarimeter is an established technique to determine the polarization signature of an object. In this paper, we propose a new methodology which combines RPSF technique with microgrid polarimetry in order to obtain a joint polarimetric-three dimensional imaging capability. Simulation results are obtained for 3D localization of point sources and estimation of its linear polarization signature using data frames with and without additive white Gaussian noise.","PeriodicalId":106991,"journal":{"name":"2018 Second International Conference on Advances in Electronics, Computers and Communications (ICAECC)","volume":"37 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117279055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/ICAECC.2018.8479419
Savita Choudhary, N. Singh, Sanjay Chichadwani
Detection and recognition of text from natural images is very important for extracting information from images but is an extensively challenging task. This paper proposes an approach for detection of text area from natural scene images using Maximally Stable Extremal Regions (MSER) and recognizing the text using a self-trained Neural Network. Some preprocessing is applied to the image then MSER and canny edge is used to locate the smaller areas that may more likely contain text. The text is individually isolated as single characters by simple algorithms on the binary image and then passed through the recognition model specially designed for hazy and unaligned characters.
{"title":"Text Detection and Recognition from Scene Images using MSER and CNN","authors":"Savita Choudhary, N. Singh, Sanjay Chichadwani","doi":"10.1109/ICAECC.2018.8479419","DOIUrl":"https://doi.org/10.1109/ICAECC.2018.8479419","url":null,"abstract":"Detection and recognition of text from natural images is very important for extracting information from images but is an extensively challenging task. This paper proposes an approach for detection of text area from natural scene images using Maximally Stable Extremal Regions (MSER) and recognizing the text using a self-trained Neural Network. Some preprocessing is applied to the image then MSER and canny edge is used to locate the smaller areas that may more likely contain text. The text is individually isolated as single characters by simple algorithms on the binary image and then passed through the recognition model specially designed for hazy and unaligned characters.","PeriodicalId":106991,"journal":{"name":"2018 Second International Conference on Advances in Electronics, Computers and Communications (ICAECC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115686361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/ICAECC.2018.8479460
B. Vijayakumar
Presently, Computations traverse through several layers of hardware logic structures to perform the intended operation. This, amounts to a significant time delay and power consumption. In this paper, a memristor-based ALU architecture is proposed which is a combination of trained Memristor-based Neural Networks and hybrid CMOS circuits which together can form a promising solution to Implement High-Speed Logic. We will discuss a Neural Network to implement an N-Bit Full Adder. Further, an N-Bit Hybrid CMOS Fast Multiplier architecture is proposed; which uses an N-Bit Full Adder Neural Network as well as Memristor-based Hybrid CMOS Logic Circuits to implement the entire Functionality. Also a 2-Bit Neural full adder is trained using Back Propagation algorithm which gives a better insight into the Robustness of the architecture. The comparison analysis of the CMOS as well as the proposed Memristor-based Neural 2-Bit Full adder is shown. Systems which use repetitive logic computations; for instance, DSP processors can benefit highly from the proposed architecture by simply cutting down on the Time and Power spent on Complex Real-Time Calculations (matrix DFT-FFT computations).
{"title":"Memristor-Based Neuromorphic Hybrid CMOS Sub-Block Architecture for a High-Speed Arithmetic and Logic Unit","authors":"B. Vijayakumar","doi":"10.1109/ICAECC.2018.8479460","DOIUrl":"https://doi.org/10.1109/ICAECC.2018.8479460","url":null,"abstract":"Presently, Computations traverse through several layers of hardware logic structures to perform the intended operation. This, amounts to a significant time delay and power consumption. In this paper, a memristor-based ALU architecture is proposed which is a combination of trained Memristor-based Neural Networks and hybrid CMOS circuits which together can form a promising solution to Implement High-Speed Logic. We will discuss a Neural Network to implement an N-Bit Full Adder. Further, an N-Bit Hybrid CMOS Fast Multiplier architecture is proposed; which uses an N-Bit Full Adder Neural Network as well as Memristor-based Hybrid CMOS Logic Circuits to implement the entire Functionality. Also a 2-Bit Neural full adder is trained using Back Propagation algorithm which gives a better insight into the Robustness of the architecture. The comparison analysis of the CMOS as well as the proposed Memristor-based Neural 2-Bit Full adder is shown. Systems which use repetitive logic computations; for instance, DSP processors can benefit highly from the proposed architecture by simply cutting down on the Time and Power spent on Complex Real-Time Calculations (matrix DFT-FFT computations).","PeriodicalId":106991,"journal":{"name":"2018 Second International Conference on Advances in Electronics, Computers and Communications (ICAECC)","volume":"322 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132338137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/ICAECC.2018.8479512
A. M. George, S. Y Kulkarni
In the new era of Internet of Things (IOT) where 50 billion devices are projected to be linked to the internet, different challenges like system integration, low power design, security are imposed on the semiconductor industry. The rapid increase in the demand for battery-operated IOT devices and the scaling of Complementary Metal Oxide Semiconductor (CMOS) devices has gained the attention of ultra-low power design approaches. Most IOT devices are active for a short amount of time and are in sleep or standby mode for a long time. Systems require different power levels as they combine Intellectual Property from analog, digital and mixed signal vendors thereby necessitating efficient power management circuits. This paper reviews different power converters and energy harvesting systems with low power architectures and circuit level optimizations.
{"title":"Performance of Power Converters for Ultra Low Power Systems: A Review","authors":"A. M. George, S. Y Kulkarni","doi":"10.1109/ICAECC.2018.8479512","DOIUrl":"https://doi.org/10.1109/ICAECC.2018.8479512","url":null,"abstract":"In the new era of Internet of Things (IOT) where 50 billion devices are projected to be linked to the internet, different challenges like system integration, low power design, security are imposed on the semiconductor industry. The rapid increase in the demand for battery-operated IOT devices and the scaling of Complementary Metal Oxide Semiconductor (CMOS) devices has gained the attention of ultra-low power design approaches. Most IOT devices are active for a short amount of time and are in sleep or standby mode for a long time. Systems require different power levels as they combine Intellectual Property from analog, digital and mixed signal vendors thereby necessitating efficient power management circuits. This paper reviews different power converters and energy harvesting systems with low power architectures and circuit level optimizations.","PeriodicalId":106991,"journal":{"name":"2018 Second International Conference on Advances in Electronics, Computers and Communications (ICAECC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125379858","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}
The automatic system for classification of healthy and pathological voices has received a significant attention in the research of early detection and diagnosis of voice disorders. In this work, we propose a method to classify the healthy and pathological voices. To implement this system, we use audio recordings of normal and pathological voices. We extract Mel Frequency Cepstral Coefficients (MFCC) from the voice signals and use a visualization technique to explore the capability of these features in discriminating healthy and pathological voices. In this study, we use Artificial Neural Network (ANN) to classify the extracted features. Here, we present the results of experiments with varying number of neurons in the hidden layer and also with various frame sizes. The best obtained accuracy is 99.96%.
{"title":"Classification of Healthy and Pathological voices using MFCC and ANN","authors":"Smitha, Surendra Shetty, Sarika Hegde, Thejaswi Dodderi","doi":"10.1109/ICAECC.2018.8479441","DOIUrl":"https://doi.org/10.1109/ICAECC.2018.8479441","url":null,"abstract":"The automatic system for classification of healthy and pathological voices has received a significant attention in the research of early detection and diagnosis of voice disorders. In this work, we propose a method to classify the healthy and pathological voices. To implement this system, we use audio recordings of normal and pathological voices. We extract Mel Frequency Cepstral Coefficients (MFCC) from the voice signals and use a visualization technique to explore the capability of these features in discriminating healthy and pathological voices. In this study, we use Artificial Neural Network (ANN) to classify the extracted features. Here, we present the results of experiments with varying number of neurons in the hidden layer and also with various frame sizes. The best obtained accuracy is 99.96%.","PeriodicalId":106991,"journal":{"name":"2018 Second International Conference on Advances in Electronics, Computers and Communications (ICAECC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114302842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/ICAECC.2018.8479517
Shahmustafa Mujawar, D. Kiran, Hariharan Ramasangu
Image classification finds its suitability in applications ranging from medical diagnostics to autonomous vehicles. The existing architectures are computationally exhaustive, complex and less accurate. An accurate, simple and hardware efficient architecture is required to be developed for image classification. In this paper, Convolutional Neural Network (CNN) architecture has been proposed and validated using MNIST handwritten dataset. The adopted approaches of sliding-filter for convolution and parallel computation of Multiplication and Accumulation (MAC) operations resulted in optimized hardware architecture with reduced arithmetic operations and faster computations. The developed architecture has been implemented on Artix-7 FPGA and attained a significant improvement in speed compared to existing architecture working at 300MHz maximum operating frequency.
{"title":"An Efficient CNN Architecture for Image Classification on FPGA Accelerator","authors":"Shahmustafa Mujawar, D. Kiran, Hariharan Ramasangu","doi":"10.1109/ICAECC.2018.8479517","DOIUrl":"https://doi.org/10.1109/ICAECC.2018.8479517","url":null,"abstract":"Image classification finds its suitability in applications ranging from medical diagnostics to autonomous vehicles. The existing architectures are computationally exhaustive, complex and less accurate. An accurate, simple and hardware efficient architecture is required to be developed for image classification. In this paper, Convolutional Neural Network (CNN) architecture has been proposed and validated using MNIST handwritten dataset. The adopted approaches of sliding-filter for convolution and parallel computation of Multiplication and Accumulation (MAC) operations resulted in optimized hardware architecture with reduced arithmetic operations and faster computations. The developed architecture has been implemented on Artix-7 FPGA and attained a significant improvement in speed compared to existing architecture working at 300MHz maximum operating frequency.","PeriodicalId":106991,"journal":{"name":"2018 Second International Conference on Advances in Electronics, Computers and Communications (ICAECC)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124052225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/ICAECC.2018.8479496
N. Abdul Haq, Mrinal Sarvagya
Wireless data traffic is expected to increase 10000 fold in next 20 years. To meet this ever increasing demand of increased wireless traffic, the fifth-generation (5G) cellular systems are getting prepared to be deployed by 2020. 5G cellular systems are most likely to operate in millimeter wave (mm-wave)frequency bands. Communication at mm-wave is setting a new era of wireless communication. The mm-wave frequencies offer higher bandwidth channels up to 2 GHz. Signal processing techniques are critical for implementing in the next generation mm-wave communication systems. Millimeter wave technology enables the use of large antenna arrays at the transmitter (Tx) and receiver (Rx). Along with high operating frequency and mixed signal power constraints, incipient multiple-input multiple-output (MIMO) communication signal processing methods are essential. Due to large bandwidths, designing low complexity transceiver algorithms becomes critical. Millimeter wave technique provides enough opportunities to utilize the signal processing techniques such as compressed sensing technique in channel estimation and beamforming (BF). This article presents an overview of efficacious signal processing methods and challenges in using mm-wave technique, with an incremented fixate on MIMO technology in achieving larger data rates and issues with limited availability of frequency spectrum. There is an immense interest in mm-wave BF predicated for 5G networks. An important aspect in mm-wave communications is to exploit the increased number of deployable antennas at both Tx and Rx to combat high path loss, to tackle increased interference due to higher user density and to tackle multipath effects in frequency selective channels.
{"title":"Analysis on Channel Parameters and Signal Processing methods at mm-wave for 5G networks","authors":"N. Abdul Haq, Mrinal Sarvagya","doi":"10.1109/ICAECC.2018.8479496","DOIUrl":"https://doi.org/10.1109/ICAECC.2018.8479496","url":null,"abstract":"Wireless data traffic is expected to increase 10000 fold in next 20 years. To meet this ever increasing demand of increased wireless traffic, the fifth-generation (5G) cellular systems are getting prepared to be deployed by 2020. 5G cellular systems are most likely to operate in millimeter wave (mm-wave)frequency bands. Communication at mm-wave is setting a new era of wireless communication. The mm-wave frequencies offer higher bandwidth channels up to 2 GHz. Signal processing techniques are critical for implementing in the next generation mm-wave communication systems. Millimeter wave technology enables the use of large antenna arrays at the transmitter (Tx) and receiver (Rx). Along with high operating frequency and mixed signal power constraints, incipient multiple-input multiple-output (MIMO) communication signal processing methods are essential. Due to large bandwidths, designing low complexity transceiver algorithms becomes critical. Millimeter wave technique provides enough opportunities to utilize the signal processing techniques such as compressed sensing technique in channel estimation and beamforming (BF). This article presents an overview of efficacious signal processing methods and challenges in using mm-wave technique, with an incremented fixate on MIMO technology in achieving larger data rates and issues with limited availability of frequency spectrum. There is an immense interest in mm-wave BF predicated for 5G networks. An important aspect in mm-wave communications is to exploit the increased number of deployable antennas at both Tx and Rx to combat high path loss, to tackle increased interference due to higher user density and to tackle multipath effects in frequency selective channels.","PeriodicalId":106991,"journal":{"name":"2018 Second International Conference on Advances in Electronics, Computers and Communications (ICAECC)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126659309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/ICAECC.2018.8479445
S. Z. N. Dar, M. Mufti
There has been a paradigm shift in incorporation of wind energy into the conventional grid. The power electronic interface decoupling the inertial response in the event of contingency is a challenging issue. In this paper a control loop based upon linearized delta torque model DFIG system is incorporated in a pragmatic two area power system including steam reheat constraints and governor dead band nonlinearity. From the exhaustive simulation studies carried out in Matlab Simulink Environment it is found that there is 93% reduction in peak frequency deviation and 75% decrease in tie power deviation, thus improving the reliability of power system considerably
{"title":"Inertial Response Support in LFC by Linearized Delta Torque Model Based DFIG","authors":"S. Z. N. Dar, M. Mufti","doi":"10.1109/ICAECC.2018.8479445","DOIUrl":"https://doi.org/10.1109/ICAECC.2018.8479445","url":null,"abstract":"There has been a paradigm shift in incorporation of wind energy into the conventional grid. The power electronic interface decoupling the inertial response in the event of contingency is a challenging issue. In this paper a control loop based upon linearized delta torque model DFIG system is incorporated in a pragmatic two area power system including steam reheat constraints and governor dead band nonlinearity. From the exhaustive simulation studies carried out in Matlab Simulink Environment it is found that there is 93% reduction in peak frequency deviation and 75% decrease in tie power deviation, thus improving the reliability of power system considerably","PeriodicalId":106991,"journal":{"name":"2018 Second International Conference on Advances in Electronics, Computers and Communications (ICAECC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126925258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/ICAECC.2018.8479468
Lekshmi R Pillai, V. G, Deepa Gupta
Most question answering systems are used to predict an expected answer type given a question. In this work, we present a Question Answering System based on the combined approach of Word Sense Disambiguation (WSD) and Semantic Role Labeling (SRL). Our motivation is to generate reasonable questions and solve co-referencing problem extracted from the answer. The proposed model of work is factoid sense based question generation system. We have used Lesk algorithm for WSD and Senna tool for SRL. Based on the sense associated with the sentence, the system generates questions of semantically resolvable. Using deep syntax and semantics analysis, we have extracted an answer from the given question. Hobbs algorithm resolved co-reference problem generated in answer extraction. The experimental results show promising results for the proposed approach.
{"title":"A Combined Approach Using Semantic Role Labelling and Word Sense Disambiguation for Question Generation and Answer Extraction","authors":"Lekshmi R Pillai, V. G, Deepa Gupta","doi":"10.1109/ICAECC.2018.8479468","DOIUrl":"https://doi.org/10.1109/ICAECC.2018.8479468","url":null,"abstract":"Most question answering systems are used to predict an expected answer type given a question. In this work, we present a Question Answering System based on the combined approach of Word Sense Disambiguation (WSD) and Semantic Role Labeling (SRL). Our motivation is to generate reasonable questions and solve co-referencing problem extracted from the answer. The proposed model of work is factoid sense based question generation system. We have used Lesk algorithm for WSD and Senna tool for SRL. Based on the sense associated with the sentence, the system generates questions of semantically resolvable. Using deep syntax and semantics analysis, we have extracted an answer from the given question. Hobbs algorithm resolved co-reference problem generated in answer extraction. The experimental results show promising results for the proposed approach.","PeriodicalId":106991,"journal":{"name":"2018 Second International Conference on Advances in Electronics, Computers and Communications (ICAECC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132143997","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：