Pub Date : 2013-12-01DOI: 10.1109/RAICS.2013.6745443
A. Yasodai, A. Ramprasad
A new technique for implementing low power FFTs based on memory less Z path eliminated CORDIC is proposed in this paper. The vector rotation in the x/y plane can be realized by rotating a vector through a series of elementary angles. These elementary angles are chosen such that the vector rotation through each of them may be approximated easily with a simple shift and add operation, and their algebraic sum approaches the required rotation angle. This can be exercised by CORDIC (CO-ordinate Rotation Digital Computer) algorithm in rotation mode. Pipelined architecture by pre computation of direction of micro rotation, radix-4 number representation, and the angle generator has been processed in terms of hardware complexity, iteration delay and memory reduction. The proposed algorithm also exercises an addressing scheme and the associated angle generator logic in order to eliminate the ROM usage for bottling the twiddle factors. It incorporates parallelism and pipe line processing. The latency of the system is n/2 clock cycles. The throughput rate is one valid result per eight clock cycles. The approached architecture for radix-4, 16-bit precision and 16-point FFT was implemented on FPGA platform virtex 5 and simulated to validate the results. This contributes to the minimization of the dynamic power consumption of the proposed system to 28.52mW at 100MHz and 5.70mW at 20MHz with the maximum operating frequency of 450.564MHZ.
{"title":"An efficient implementation of rotational radix-4 CORDIC based FFT processor","authors":"A. Yasodai, A. Ramprasad","doi":"10.1109/RAICS.2013.6745443","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745443","url":null,"abstract":"A new technique for implementing low power FFTs based on memory less Z path eliminated CORDIC is proposed in this paper. The vector rotation in the x/y plane can be realized by rotating a vector through a series of elementary angles. These elementary angles are chosen such that the vector rotation through each of them may be approximated easily with a simple shift and add operation, and their algebraic sum approaches the required rotation angle. This can be exercised by CORDIC (CO-ordinate Rotation Digital Computer) algorithm in rotation mode. Pipelined architecture by pre computation of direction of micro rotation, radix-4 number representation, and the angle generator has been processed in terms of hardware complexity, iteration delay and memory reduction. The proposed algorithm also exercises an addressing scheme and the associated angle generator logic in order to eliminate the ROM usage for bottling the twiddle factors. It incorporates parallelism and pipe line processing. The latency of the system is n/2 clock cycles. The throughput rate is one valid result per eight clock cycles. The approached architecture for radix-4, 16-bit precision and 16-point FFT was implemented on FPGA platform virtex 5 and simulated to validate the results. This contributes to the minimization of the dynamic power consumption of the proposed system to 28.52mW at 100MHz and 5.70mW at 20MHz with the maximum operating frequency of 450.564MHZ.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"56 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120870457","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745453
Jitesh Punjabi, Shekhar Parkhi, Gaurav Taneja, N. Giri
Context Aware Computing is a promising approach of developing mobile applications that provide experiences and services in a manner that is fine-tuned based on the user's preferences. Applications such as Google Now, Apple Siri learn the User's activities from context related information and subsequently provide suggestions to the users in real-time. However, in almost all cases, application developers have to develop the same set of mechanisms to consume the context information and storing it in an appropriate form rather than focusing on the parts of the application that consume the context information. This approach results in the repetition of the same task and multiple copies of data. This paper presents our work detailing the development of a middleware that handles context information collection and its storage. The work provides a framework that allows the developers to easily implement context aware applications that consume the services provided by the middleware. Applications will only have to react to context data (past and present) while the middleware takes care of everything else such as the background service for context information collection and storage, thus reducing the redundancy, increasing adaptability and flexibility, and simultaneously supporting developers in rapid prototyping of context-aware applications. Thus the paper presents our work towards building sustainable Android Framework which follows the principle of Reformat, Reduce, Regenerate, Reuse and Repurpose.
上下文感知计算是开发移动应用程序的一种很有前途的方法，它可以根据用户的偏好进行微调，以提供体验和服务。谷歌等应用程序现在，苹果Siri从上下文相关信息中了解用户的活动，随后实时向用户提供建议。然而，在几乎所有情况下，应用程序开发人员都必须开发相同的机制集来使用上下文信息并将其以适当的形式存储，而不是专注于使用上下文信息的应用程序部分。这种方法导致重复相同的任务和数据的多个副本。本文详细介绍了我们开发处理上下文信息收集及其存储的中间件的工作。该工作提供了一个框架，允许开发人员轻松实现使用中间件提供的服务的上下文感知应用程序。应用程序只需要对上下文数据(过去的和现在的)做出反应，而中间件则负责其他一切，比如上下文信息收集和存储的后台服务，从而减少冗余，增加适应性和灵活性，同时支持开发人员快速构建上下文感知应用程序的原型。因此，本文介绍了我们为构建可持续的Android框架所做的工作，该框架遵循Reformat, Reduce, Regenerate, Reuse and Repurpose原则。
{"title":"Relaxed context-aware machine learning midddleware (RCAMM) for Android","authors":"Jitesh Punjabi, Shekhar Parkhi, Gaurav Taneja, N. Giri","doi":"10.1109/RAICS.2013.6745453","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745453","url":null,"abstract":"Context Aware Computing is a promising approach of developing mobile applications that provide experiences and services in a manner that is fine-tuned based on the user's preferences. Applications such as Google Now, Apple Siri learn the User's activities from context related information and subsequently provide suggestions to the users in real-time. However, in almost all cases, application developers have to develop the same set of mechanisms to consume the context information and storing it in an appropriate form rather than focusing on the parts of the application that consume the context information. This approach results in the repetition of the same task and multiple copies of data. This paper presents our work detailing the development of a middleware that handles context information collection and its storage. The work provides a framework that allows the developers to easily implement context aware applications that consume the services provided by the middleware. Applications will only have to react to context data (past and present) while the middleware takes care of everything else such as the background service for context information collection and storage, thus reducing the redundancy, increasing adaptability and flexibility, and simultaneously supporting developers in rapid prototyping of context-aware applications. Thus the paper presents our work towards building sustainable Android Framework which follows the principle of Reformat, Reduce, Regenerate, Reuse and Repurpose.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130875206","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745492
Aarti Singh, P. Anand
Ontologies play vital role in agent communication in present semantic web. Manual construction of ontology is very complex and time consuming process. Thus it is mandatory to automate this task. A number of tools have been created to help the ontology generation in a semi automatic or manual way. But there is no standard framework for complete automation of this process. Though ontologies are highly reusable so based on a basic ontology other ontologies may be built for specific application domain. This work attempts to present a mechanism for automatic construction of ontology using intelligent agents.
{"title":"Automatic domain ontology construction mechanism","authors":"Aarti Singh, P. Anand","doi":"10.1109/RAICS.2013.6745492","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745492","url":null,"abstract":"Ontologies play vital role in agent communication in present semantic web. Manual construction of ontology is very complex and time consuming process. Thus it is mandatory to automate this task. A number of tools have been created to help the ontology generation in a semi automatic or manual way. But there is no standard framework for complete automation of this process. Though ontologies are highly reusable so based on a basic ontology other ontologies may be built for specific application domain. This work attempts to present a mechanism for automatic construction of ontology using intelligent agents.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131309350","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745473
G. P. Acharya, M. A. Rani
Today's submicron VLSI technology has been emerged as integration of many VLSI ICs into a single Si Chip called System-on-Chip (SoC). The SoC architecture normally contains multiple processors along with either separate or centralized memory blocks as its core elements as well as many noncore elements, e.g., Cache/DRAM controllers, I/O Controllers. Due to the increased demands for high data storage, the integration of on-chip memories ranging from Gigabytes to Terrabytes is becoming essential for the latest SoC technology. To improve the reliability and performance of SoCs due to technology miniaturization and increased memory density, there is a need to incorporate on-chip self-testing unit for testing these memory units. Further, to improve the yield and fault tolerance of on-chip memories without degradation on its performance, self repair mechanism may be integrated on chip. Apart from memory self test and repair., another biggest challenge in SoC testing is the testing of logic blocks (core elements) as well as the noncore elements as specified earlier. This paper brings out the reviews of BIST strategies from various literatures that are being applied for testing of embedded memories and IP cores along with associated noncore elements.
{"title":"Survey of test strategies for System-on Chip and it's embedded memories","authors":"G. P. Acharya, M. A. Rani","doi":"10.1109/RAICS.2013.6745473","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745473","url":null,"abstract":"Today's submicron VLSI technology has been emerged as integration of many VLSI ICs into a single Si Chip called System-on-Chip (SoC). The SoC architecture normally contains multiple processors along with either separate or centralized memory blocks as its core elements as well as many noncore elements, e.g., Cache/DRAM controllers, I/O Controllers. Due to the increased demands for high data storage, the integration of on-chip memories ranging from Gigabytes to Terrabytes is becoming essential for the latest SoC technology. To improve the reliability and performance of SoCs due to technology miniaturization and increased memory density, there is a need to incorporate on-chip self-testing unit for testing these memory units. Further, to improve the yield and fault tolerance of on-chip memories without degradation on its performance, self repair mechanism may be integrated on chip. Apart from memory self test and repair., another biggest challenge in SoC testing is the testing of logic blocks (core elements) as well as the noncore elements as specified earlier. This paper brings out the reviews of BIST strategies from various literatures that are being applied for testing of embedded memories and IP cores along with associated noncore elements.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126555798","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745484
Burni George, S. S. Kumar
Conventional monopole antennas have narrow bandwidth and this bandwidth can slightly be improved by using dual arms for the monopole structure. Folding both ends of the dual monopole antenna can result in further improvement of bandwidth of the dual monopole structure. Spiral antennas have large bandwidth. This paper proposes an optimal symmetric antenna combining spiral geometry with a dual monopole structure. Modeling of the proposed antenna is done using the number of turns, segment lengths and spiral geometrical parameters. The antenna parameters, gain and input impedance, are calculated using NEC2 and the proposed structure is optimized using Particle Swarm Optimization(PSO). The proposed structure is optimized for maximizing gain subject to the prescribed input impedance. Simulated results of the proposed antenna shows better gain, impedance and bandwidth characteristics compared to L-shape folded dual monopole.
{"title":"Optimal design of a symmetric monopole antenna with spiral geometry","authors":"Burni George, S. S. Kumar","doi":"10.1109/RAICS.2013.6745484","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745484","url":null,"abstract":"Conventional monopole antennas have narrow bandwidth and this bandwidth can slightly be improved by using dual arms for the monopole structure. Folding both ends of the dual monopole antenna can result in further improvement of bandwidth of the dual monopole structure. Spiral antennas have large bandwidth. This paper proposes an optimal symmetric antenna combining spiral geometry with a dual monopole structure. Modeling of the proposed antenna is done using the number of turns, segment lengths and spiral geometrical parameters. The antenna parameters, gain and input impedance, are calculated using NEC2 and the proposed structure is optimized using Particle Swarm Optimization(PSO). The proposed structure is optimized for maximizing gain subject to the prescribed input impedance. Simulated results of the proposed antenna shows better gain, impedance and bandwidth characteristics compared to L-shape folded dual monopole.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"IA-15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126556423","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745460
R. Palaniappan, K. Sundaraj
Respiratory sound analysis provides vital information of the present condition of the Lungs. It can be used to assist medical professionals in differential diagnosis. In this paper, we intend to distinguish between normal (without any pathological condition), airway obstruction pathology and parenchymal pathology using respiratory sound recordings taken from RALE database. The proposed method uses Mel-frequency cepstral coefficients (MFCC) as features extracted from respiratory sounds. The extracted features are distinguished using support vector machine classifier (SVM). The classifier performance is analysed by using confusion matrix technique. A mean classification accuracy of 90.77% was reported using the proposed method. The performance analysis of the SVM classifier using confusion matrix revealed that normal, airway obstruction and parenchymal pathology are classified at 94.11%, 92.31% and 88.00% classification accuracy respectively. The analysis reveals that the proposed method shows promising outcome in distinguishing between the normal, airway obstruction and parenchymal pathology.
{"title":"Respiratory sound classification using cepstral features and support vector machine","authors":"R. Palaniappan, K. Sundaraj","doi":"10.1109/RAICS.2013.6745460","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745460","url":null,"abstract":"Respiratory sound analysis provides vital information of the present condition of the Lungs. It can be used to assist medical professionals in differential diagnosis. In this paper, we intend to distinguish between normal (without any pathological condition), airway obstruction pathology and parenchymal pathology using respiratory sound recordings taken from RALE database. The proposed method uses Mel-frequency cepstral coefficients (MFCC) as features extracted from respiratory sounds. The extracted features are distinguished using support vector machine classifier (SVM). The classifier performance is analysed by using confusion matrix technique. A mean classification accuracy of 90.77% was reported using the proposed method. The performance analysis of the SVM classifier using confusion matrix revealed that normal, airway obstruction and parenchymal pathology are classified at 94.11%, 92.31% and 88.00% classification accuracy respectively. The analysis reveals that the proposed method shows promising outcome in distinguishing between the normal, airway obstruction and parenchymal pathology.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"457 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122893520","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745485
C. K. Manikandtan, S. Resmi, S. Sibi, R. Kumar, G. S. Harikumaran Nair
Surface generation from high resolution datasets using triangulation algorithms like marching cubes require large amounts of computational time for the generation and interpolation of vertices. Here we propose a templated method of generating triangles which has far less computation involved and saves on CPU cycles and memory. Each cube orientation corresponding to the boundary cases in the original algorithm is listed in a prebuilt table of templated triangles. The template created using binary input may be further smoothened using cost functions related to input image data.
{"title":"Templated marching cubes — A low computation approach to surface rendering","authors":"C. K. Manikandtan, S. Resmi, S. Sibi, R. Kumar, G. S. Harikumaran Nair","doi":"10.1109/RAICS.2013.6745485","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745485","url":null,"abstract":"Surface generation from high resolution datasets using triangulation algorithms like marching cubes require large amounts of computational time for the generation and interpolation of vertices. Here we propose a templated method of generating triangles which has far less computation involved and saves on CPU cycles and memory. Each cube orientation corresponding to the boundary cases in the original algorithm is listed in a prebuilt table of templated triangles. The template created using binary input may be further smoothened using cost functions related to input image data.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133130823","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745452
M. Geetha, P. Aswathi
Sign language is the most natural way of expression for the deaf community. Indian Sign Language (ISL) is a visual-spatial language which provides linguistic information using hands, arms, facial expressions, and head/body postures. In this paper we propose a new method for, vision-based recognition of dynamic signs corresponding to Indian Sign Language words. A new method is proposed for key frame extraction which is more accurate than the existing methods. The frames corresponding to the Maximum Curvature Points (MCPs) of the global trajectory are taken as the keyframes. The method accomodates the spatio temporal variability that may occur when different persons perform the same gesture. We are also proposing a new method based on spatial location of the Key Maximum Curvature Points of the boundary for shape feature extraction of key frames. Our method when compared with three other exisiting methods has given better performance. The method has considered the local as well as global trajectory information for recognition. The feature extraction method has proved to be scale invariant and translation invariant.
{"title":"Dynamic gesture recognition of Indian sign language considering local motion of hand using spatial location of Key Maximum Curvature Points","authors":"M. Geetha, P. Aswathi","doi":"10.1109/RAICS.2013.6745452","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745452","url":null,"abstract":"Sign language is the most natural way of expression for the deaf community. Indian Sign Language (ISL) is a visual-spatial language which provides linguistic information using hands, arms, facial expressions, and head/body postures. In this paper we propose a new method for, vision-based recognition of dynamic signs corresponding to Indian Sign Language words. A new method is proposed for key frame extraction which is more accurate than the existing methods. The frames corresponding to the Maximum Curvature Points (MCPs) of the global trajectory are taken as the keyframes. The method accomodates the spatio temporal variability that may occur when different persons perform the same gesture. We are also proposing a new method based on spatial location of the Key Maximum Curvature Points of the boundary for shape feature extraction of key frames. Our method when compared with three other exisiting methods has given better performance. The method has considered the local as well as global trajectory information for recognition. The feature extraction method has proved to be scale invariant and translation invariant.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"2 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114105222","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745476
Sreeja S, M Wilscy
In this paper we address the problem of super resolution in remote sensing images from a single low resolution image without using an external database. This method uses the techniques of Compressive Sensing (CS), Structural Self Similarity and Total Variation (TV) Minimization. The approach is based on sparse and redundant representations over trained dictionaries. The method involves identifying a dictionary that represents high resolution patches in a sparse manner. Extra information from similar structures that exist in remote sensing images can be introduced to dictionary in the CS framework. K-SVD method is used for finding the dictionary and TV Minimization method is used for finding the sparse representation coefficients. Instead of using the HR patches from an external database, the proposed method uses the patches from the interpolated version of the LR image for training the dictionary. The method is compared with other single image super resolution algorithms that use sparse recovery methods such as Orthogonal Matching Pursuit algorithm. The proposed method is tested with satellite images from USC_SIPI database. The method gives better results than other methods both visually and quantitatively. Performance of the method is evaluated using the metrics: PSNR, MSSIM, FSIM and Blur Metric.
{"title":"Single image super-resolution based on compressive sensing and TV minimization sparse recovery for remote sensing images","authors":"Sreeja S, M Wilscy","doi":"10.1109/RAICS.2013.6745476","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745476","url":null,"abstract":"In this paper we address the problem of super resolution in remote sensing images from a single low resolution image without using an external database. This method uses the techniques of Compressive Sensing (CS), Structural Self Similarity and Total Variation (TV) Minimization. The approach is based on sparse and redundant representations over trained dictionaries. The method involves identifying a dictionary that represents high resolution patches in a sparse manner. Extra information from similar structures that exist in remote sensing images can be introduced to dictionary in the CS framework. K-SVD method is used for finding the dictionary and TV Minimization method is used for finding the sparse representation coefficients. Instead of using the HR patches from an external database, the proposed method uses the patches from the interpolated version of the LR image for training the dictionary. The method is compared with other single image super resolution algorithms that use sparse recovery methods such as Orthogonal Matching Pursuit algorithm. The proposed method is tested with satellite images from USC_SIPI database. The method gives better results than other methods both visually and quantitatively. Performance of the method is evaluated using the metrics: PSNR, MSSIM, FSIM and Blur Metric.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132699606","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745494
U. Nagarsekar, A. Mhapsekar, P. Kulkarni, D. Kalbande
Due to the sudden eruption of activity in the social networking domain, analysts, social media as well as general public are drawn to Sentiment Analysis domain to gain invaluable information. In this paper, we go beyond basic sentiment classification (positive, negative and neutral) and target deeper emotion classification of Twitter data. We have focused on emotion identification into Ekman's six basic emotions i.e. JOY, SURPRISE, ANGER, DISGUST, FEAR and SADNESS. We have employed two diverse machine learning algorithms with three varied datasets and analyzed their outcomes. We show how equal distribution of emotions in training tweets results in better learning accuracies and hence better performance in the classification task.
{"title":"Emotion detection from “the SMS of the internet”","authors":"U. Nagarsekar, A. Mhapsekar, P. Kulkarni, D. Kalbande","doi":"10.1109/RAICS.2013.6745494","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745494","url":null,"abstract":"Due to the sudden eruption of activity in the social networking domain, analysts, social media as well as general public are drawn to Sentiment Analysis domain to gain invaluable information. In this paper, we go beyond basic sentiment classification (positive, negative and neutral) and target deeper emotion classification of Twitter data. We have focused on emotion identification into Ekman's six basic emotions i.e. JOY, SURPRISE, ANGER, DISGUST, FEAR and SADNESS. We have employed two diverse machine learning algorithms with three varied datasets and analyzed their outcomes. We show how equal distribution of emotions in training tweets results in better learning accuracies and hence better performance in the classification task.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129025962","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：