This paper mainly proposes a deep learning method-Stacked Denoising Auto Encoder (SDAE) to solve the problems of automatic feature extraction and dimension reduction in Braille recognition. In the construction of a network with deep architecture, a feature extractor was trained with unsupervised greedy layer-wise training algorithm to initialize the weights for extracting features from Braille images, and then a following classifier was set up for recognition. The experimental results show that by comparing to traditional methods, the constructed network based on the deep learning method can easily recognize Braille images with satisfied performance. The deep learning model can effectively solve the Braille recognition problem in automatic feature extraction and dimension reduction with a reduced preprocessing.
{"title":"A Deep Learning Method for Braille Recognition","authors":"Ting Li, Xiaoqin Zeng, Shoujing Xu","doi":"10.1109/CICN.2014.229","DOIUrl":"https://doi.org/10.1109/CICN.2014.229","url":null,"abstract":"This paper mainly proposes a deep learning method-Stacked Denoising Auto Encoder (SDAE) to solve the problems of automatic feature extraction and dimension reduction in Braille recognition. In the construction of a network with deep architecture, a feature extractor was trained with unsupervised greedy layer-wise training algorithm to initialize the weights for extracting features from Braille images, and then a following classifier was set up for recognition. The experimental results show that by comparing to traditional methods, the constructed network based on the deep learning method can easily recognize Braille images with satisfied performance. The deep learning model can effectively solve the Braille recognition problem in automatic feature extraction and dimension reduction with a reduced preprocessing.","PeriodicalId":6487,"journal":{"name":"2014 International Conference on Computational Intelligence and Communication Networks","volume":"13 1","pages":"1092-1095"},"PeriodicalIF":0.0,"publicationDate":"2014-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88750130","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}
Long Term Evolution LTE is developing as a major candidate for fourth generation (4G) cellular networks and is being modified by various cellular providers to increase the capacity and speed of mobile telephone networks. The major features that discriminate LTE from other technologies at the air interface are Orthogonal Frequency Division Multiple Access OFDMA for the downlink transmission. OFDMA run into the LTE requirement for spectrum flexibility and enables cost-efficient solutions for very wide carriers with high peak rates. In this paper a proposed novel method based on the Multiwavelet Transform MWT for applying the OFDMA in LTE. The proposed scheme is verified in two channels which are flat fading and selective Fading with other related parameters such as second path gain, Doppler frequency, and path delay. The results show that the proposed system overwhelms the traditional method based on the Fast Fourier Transform FFT and give lower Bit Error Rate BER compared with the system based on FFT.
{"title":"The Downlink 4G-LTE in Fading Channel Based on the Multiwavelet Transform","authors":"R. F. Chisab, C. Shukla","doi":"10.1109/CICN.2014.61","DOIUrl":"https://doi.org/10.1109/CICN.2014.61","url":null,"abstract":"Long Term Evolution LTE is developing as a major candidate for fourth generation (4G) cellular networks and is being modified by various cellular providers to increase the capacity and speed of mobile telephone networks. The major features that discriminate LTE from other technologies at the air interface are Orthogonal Frequency Division Multiple Access OFDMA for the downlink transmission. OFDMA run into the LTE requirement for spectrum flexibility and enables cost-efficient solutions for very wide carriers with high peak rates. In this paper a proposed novel method based on the Multiwavelet Transform MWT for applying the OFDMA in LTE. The proposed scheme is verified in two channels which are flat fading and selective Fading with other related parameters such as second path gain, Doppler frequency, and path delay. The results show that the proposed system overwhelms the traditional method based on the Fast Fourier Transform FFT and give lower Bit Error Rate BER compared with the system based on FFT.","PeriodicalId":6487,"journal":{"name":"2014 International Conference on Computational Intelligence and Communication Networks","volume":"1 1","pages":"233-236"},"PeriodicalIF":0.0,"publicationDate":"2014-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88916001","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}
Internet is an attractive cultural exchange platform in the language and literature intelligent teaching system, particularly for foreigner which is difficult to understanding cultural background. The process the traditional teaching system is suited to native culture background but because of the long time required, conventional Education facilities would require excessive student carrying capacity. The intelligent language and literature teaching modules in the network environment has been developed. Together with associated hardware system improvements, increased suitability of the language learners have been demonstrated for the learning effect of using and relay.
{"title":"Research and Implementation of Intelligent Linguistics and Language Teaching Module Based on Network Environment","authors":"Du Hongyan","doi":"10.1109/CICN.2014.114","DOIUrl":"https://doi.org/10.1109/CICN.2014.114","url":null,"abstract":"Internet is an attractive cultural exchange platform in the language and literature intelligent teaching system, particularly for foreigner which is difficult to understanding cultural background. The process the traditional teaching system is suited to native culture background but because of the long time required, conventional Education facilities would require excessive student carrying capacity. The intelligent language and literature teaching modules in the network environment has been developed. Together with associated hardware system improvements, increased suitability of the language learners have been demonstrated for the learning effect of using and relay.","PeriodicalId":6487,"journal":{"name":"2014 International Conference on Computational Intelligence and Communication Networks","volume":"18 1","pages":"492-495"},"PeriodicalIF":0.0,"publicationDate":"2014-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86699429","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}
In today's era of drastically improved technology and increasing scalability for large number of users, need for a secure system has grown immensely. To protect networks from unauthorized entries and hackers, intrusion detection systems provides improved monitoring of malicious entries and provides integrity to the system. This growing problem has motivated widespread research in particular field. Till now, many approaches has been defined by various researchers to improve the detection rate of intrusions over networks. This paper provides a brief study on significance of evolutionary approach genetic algorithm for intrusion detection to classify and detect intrusions. Methodology of genetic algorithm based intrusion detection systems and review on different approaches introduced in the field has been illustrated with the help of flowcharts for easy interpretation. This paper will provide a helpful review to the promising researchers on the relevant topic.
{"title":"A Study on Intrusion Detection in Wireless Networks by Using Genetic Algorithm Applications","authors":"Shubhangi Singh, R. S. Kushwah","doi":"10.1109/CICN.2014.162","DOIUrl":"https://doi.org/10.1109/CICN.2014.162","url":null,"abstract":"In today's era of drastically improved technology and increasing scalability for large number of users, need for a secure system has grown immensely. To protect networks from unauthorized entries and hackers, intrusion detection systems provides improved monitoring of malicious entries and provides integrity to the system. This growing problem has motivated widespread research in particular field. Till now, many approaches has been defined by various researchers to improve the detection rate of intrusions over networks. This paper provides a brief study on significance of evolutionary approach genetic algorithm for intrusion detection to classify and detect intrusions. Methodology of genetic algorithm based intrusion detection systems and review on different approaches introduced in the field has been illustrated with the help of flowcharts for easy interpretation. This paper will provide a helpful review to the promising researchers on the relevant topic.","PeriodicalId":6487,"journal":{"name":"2014 International Conference on Computational Intelligence and Communication Networks","volume":"1 1","pages":"749-752"},"PeriodicalIF":0.0,"publicationDate":"2014-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78763263","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}
In this paper, a three-level model of micro bolometer was established by intellisuit software. The total heat capacity, resistance and device thermal conductance Gdev (lower limit) was obtained by theoretical calculation, resistance extraction and dynamic thermal finite element simulation respectively. According to the relationship among of the bias current, effective thermal conductance and device thermal conductance, the range of current is got. Different current and the same amount of heat radiation were loaded on the devices for dynamic thermoelectric coupling finite element simulation. Considering the thermal time constant, effective thermal conductance and power consumption, the optimal current can be drawn.
{"title":"The Optimal Bias Current of Microbolometer under Self-Heating Effect","authors":"Chao Chen, Long Zhang, Yadong Jiang, Tao Wang","doi":"10.1109/CICN.2014.37","DOIUrl":"https://doi.org/10.1109/CICN.2014.37","url":null,"abstract":"In this paper, a three-level model of micro bolometer was established by intellisuit software. The total heat capacity, resistance and device thermal conductance Gdev (lower limit) was obtained by theoretical calculation, resistance extraction and dynamic thermal finite element simulation respectively. According to the relationship among of the bias current, effective thermal conductance and device thermal conductance, the range of current is got. Different current and the same amount of heat radiation were loaded on the devices for dynamic thermoelectric coupling finite element simulation. Considering the thermal time constant, effective thermal conductance and power consumption, the optimal current can be drawn.","PeriodicalId":6487,"journal":{"name":"2014 International Conference on Computational Intelligence and Communication Networks","volume":"24 1","pages":"116-121"},"PeriodicalIF":0.0,"publicationDate":"2014-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85051863","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}
Facial physical appearance normally have several variations which occurred due to changes in expression, illumination, occlusion, head pose, and aging. In actual, human eyes can able to justify the authenticity of a person by the use of single image per class. In this paper, a new framework is proposed for nonlinear classification of face images with only one training image per class. Histogram Equalization is used for contrast stretching, Gabor wavelets and Kernel 2D PCA is used to extract local and nonlinear features and those are invariant towards orientation & spatial locality. Those features are fused with PCA fusion and then Two Dimensional Dynamic Time Warping is used for the classification of those feature vectors. The constraints Continuity, Monotonicity and bounded properties of DTW will identify the non linear optimal path between two dimensions of feature vectors simultaneously. The proposed method has evaluated on standard bench mark face databases like ORL, Grimace & Yale and yielded better performance such as 91.35%, 98.5% and 97.16% respectively.
{"title":"Nonlinear Face Classification with Modified 2DDTW","authors":"S. Venkatramaphanikumar, V. Prasad","doi":"10.1109/CICN.2014.59","DOIUrl":"https://doi.org/10.1109/CICN.2014.59","url":null,"abstract":"Facial physical appearance normally have several variations which occurred due to changes in expression, illumination, occlusion, head pose, and aging. In actual, human eyes can able to justify the authenticity of a person by the use of single image per class. In this paper, a new framework is proposed for nonlinear classification of face images with only one training image per class. Histogram Equalization is used for contrast stretching, Gabor wavelets and Kernel 2D PCA is used to extract local and nonlinear features and those are invariant towards orientation & spatial locality. Those features are fused with PCA fusion and then Two Dimensional Dynamic Time Warping is used for the classification of those feature vectors. The constraints Continuity, Monotonicity and bounded properties of DTW will identify the non linear optimal path between two dimensions of feature vectors simultaneously. The proposed method has evaluated on standard bench mark face databases like ORL, Grimace & Yale and yielded better performance such as 91.35%, 98.5% and 97.16% respectively.","PeriodicalId":6487,"journal":{"name":"2014 International Conference on Computational Intelligence and Communication Networks","volume":"33 1","pages":"223-227"},"PeriodicalIF":0.0,"publicationDate":"2014-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87996314","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}
In order to improve the accuracy of Measuring Velocity from Doppler Radar, the method of extraction proposed is based on the cycle frequency spectrum of the center of gravity for the frequency spectrum. The collected doppler radar signal is used to make simulations for Period gram Method and the frequency spectrum of gravity method. The core of FFT in IPCore of FPGA is used to implement algorithm to complete the design combined with signal conditioning circuitry and A/D data acquisition. Experimental results show that the center of gravity of the frequency spectrum of the frequency extraction methods improve the accuracy for measuring velocity.
{"title":"Doppler Velocimetry System Design and FPGA Realization","authors":"Zhilong Deng, Liyan Liu, Ruijun Jing, Litao Jiao","doi":"10.1109/CICN.2014.210","DOIUrl":"https://doi.org/10.1109/CICN.2014.210","url":null,"abstract":"In order to improve the accuracy of Measuring Velocity from Doppler Radar, the method of extraction proposed is based on the cycle frequency spectrum of the center of gravity for the frequency spectrum. The collected doppler radar signal is used to make simulations for Period gram Method and the frequency spectrum of gravity method. The core of FFT in IPCore of FPGA is used to implement algorithm to complete the design combined with signal conditioning circuitry and A/D data acquisition. Experimental results show that the center of gravity of the frequency spectrum of the frequency extraction methods improve the accuracy for measuring velocity.","PeriodicalId":6487,"journal":{"name":"2014 International Conference on Computational Intelligence and Communication Networks","volume":"8 1","pages":"997-1000"},"PeriodicalIF":0.0,"publicationDate":"2014-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90435593","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}
A secure smart-card multi-server authentication scheme has been proposed using Diffie-Hellman, Hash-Function and XOR. The scheme made no use of verification table, or encryption techniques, or timestamps to generate a session key to provide secure communication between user and server and resists all possible security attacks, such as Man-in-the-Middle attack, Impersonation attack, Insider attack and many more. The scheme proved to be better when compared to Xie and Chen scheme in terms of security and performance.
{"title":"Diffie-Hellman Based Smart-Card Multi-server Authentication Scheme","authors":"H. Mittal","doi":"10.1109/CICN.2014.173","DOIUrl":"https://doi.org/10.1109/CICN.2014.173","url":null,"abstract":"A secure smart-card multi-server authentication scheme has been proposed using Diffie-Hellman, Hash-Function and XOR. The scheme made no use of verification table, or encryption techniques, or timestamps to generate a session key to provide secure communication between user and server and resists all possible security attacks, such as Man-in-the-Middle attack, Impersonation attack, Insider attack and many more. The scheme proved to be better when compared to Xie and Chen scheme in terms of security and performance.","PeriodicalId":6487,"journal":{"name":"2014 International Conference on Computational Intelligence and Communication Networks","volume":"422 1","pages":"808-812"},"PeriodicalIF":0.0,"publicationDate":"2014-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84932619","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}
Santanu Halder, R. Mandal, D. Bhattacharjee, M. Nasipuri
In this paper, a novel Automatic Cartoon Movie Builder (ACMB) system has been proposed to generate a cartoon movie based on a given story collected from the user and this concept is new in the literature. It has useful applications in cinematography and especially in the world of animation. The system has two types of databases: (a) Movie Database (DB-M) consisting of cartoon movies (animations) collected from different sources (b) Frame Database (DB-FR) consisting of shots (or sequence of frames depicting a continuous action) extracted from the movies of DB-M along with their textual characterization. The proposed system automatically generates a new cartoon movie from a given story with the help of DB-FR. In this paper, we focus on the generation of new cartoon movie with the retrieved shots from DB-FR as per the textual descriptions of a shot given by the user in the form of a story. The proposed method has been tested on 1000 shots which are extracted from 10 movies stored in DB-M.
本文提出了一种新颖的自动动画电影生成器(Automatic Cartoon Movie Builder, ACMB)系统，该系统可以根据用户提供的给定故事生成动画电影，这在文献中是一个新的概念。它在电影摄影，特别是在动画世界中有很好的应用。该系统有两种类型的数据库:(a)电影数据库(DB-M)由从不同来源收集的卡通电影(动画)组成;(b)帧数据库(DB-FR)由从DB-M的电影中提取的镜头(或描绘连续动作的帧序列)及其文本特征组成。该系统在DB-FR的帮助下，根据给定的故事自动生成新的卡通电影。在本文中，我们的重点是根据用户以故事的形式给出的镜头的文本描述，从DB-FR中检索到的镜头生成新的卡通电影。本文对DB-M存储的10部电影中提取的1000个镜头进行了测试。
{"title":"Design of an Automatic Cartoon Movie Builder (ACMB) System for Generation of a Cartoon Movie from a Given Story","authors":"Santanu Halder, R. Mandal, D. Bhattacharjee, M. Nasipuri","doi":"10.1109/CICN.2014.153","DOIUrl":"https://doi.org/10.1109/CICN.2014.153","url":null,"abstract":"In this paper, a novel Automatic Cartoon Movie Builder (ACMB) system has been proposed to generate a cartoon movie based on a given story collected from the user and this concept is new in the literature. It has useful applications in cinematography and especially in the world of animation. The system has two types of databases: (a) Movie Database (DB-M) consisting of cartoon movies (animations) collected from different sources (b) Frame Database (DB-FR) consisting of shots (or sequence of frames depicting a continuous action) extracted from the movies of DB-M along with their textual characterization. The proposed system automatically generates a new cartoon movie from a given story with the help of DB-FR. In this paper, we focus on the generation of new cartoon movie with the retrieved shots from DB-FR as per the textual descriptions of a shot given by the user in the form of a story. The proposed method has been tested on 1000 shots which are extracted from 10 movies stored in DB-M.","PeriodicalId":6487,"journal":{"name":"2014 International Conference on Computational Intelligence and Communication Networks","volume":"7 1","pages":"697-702"},"PeriodicalIF":0.0,"publicationDate":"2014-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88132293","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}
This paper proposes an enhanced pilot-aided channel estimation algorithm for the second generation of the digital video broadcast for terrestrial (DVB-T2) standard. Two channel estimation techniques are discussed, the first is based on the 3-points averaging technique, while the second is based on studying the frequency domain pattern of the channel response. The second technique leads to a 0.5 dB reduction in the SNR needed to guarantee a specific bit error rate (BER) requirement when compared to the conventional estimation technique recommended by the DVB-T2 implementation guide lines.
{"title":"Modified MIMO-OFDM Channel Estimation Technique for DVB-T2 Systems","authors":"Mona Z. Saleh, M. Sadek, S. E. El Ramly","doi":"10.1109/CICN.2014.57","DOIUrl":"https://doi.org/10.1109/CICN.2014.57","url":null,"abstract":"This paper proposes an enhanced pilot-aided channel estimation algorithm for the second generation of the digital video broadcast for terrestrial (DVB-T2) standard. Two channel estimation techniques are discussed, the first is based on the 3-points averaging technique, while the second is based on studying the frequency domain pattern of the channel response. The second technique leads to a 0.5 dB reduction in the SNR needed to guarantee a specific bit error rate (BER) requirement when compared to the conventional estimation technique recommended by the DVB-T2 implementation guide lines.","PeriodicalId":6487,"journal":{"name":"2014 International Conference on Computational Intelligence and Communication Networks","volume":"35 1","pages":"212-218"},"PeriodicalIF":0.0,"publicationDate":"2014-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90683852","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：