2008 International Conference on Signal Processing, Communications and Networking最新文献

Automated Detection of Transition Segments for Intensity and Time-Scale Modification for Speech Intelligibility Enhancement 自动检测过渡段的强度和时间尺度修改语音可理解性

2008 International Conference on Signal Processing, Communications and Networking Pub Date : 2008-02-07 DOI: 10.1109/ICSCN.2008.4447162

A. Jayan, P. C. Pandey, P. Lehana

{"title":"Automated Detection of Transition Segments for Intensity and Time-Scale Modification for Speech Intelligibility Enhancement","authors":"A. Jayan, P. C. Pandey, P. Lehana","doi":"10.1109/ICSCN.2008.4447162","DOIUrl":"https://doi.org/10.1109/ICSCN.2008.4447162","url":null,"abstract":"Spectral transition segments serve as landmarks for the perception of consonants. In \"clear speech\" mode adopted by speakers to improve intelligibility in difficult communication environments, transition segments are of increased duration and intensity. Modification of conversational speech to have acoustic properties of clear speech has been reported to improve its intelligibility. This paper presents an automated method for locating spectral transition segments in speech, and to produce natural quality resynthesized speech with intensity and time-scale modified spectral transition segments. The boundaries of spectral transition segments are located using an index derived from the rate of variation of energy and centroid frequency in five non-overlapping spectral bands. Time-scale modification is performed using harmonic plus noise model (HNM) based analysis-synthesis. The overall speech duration is kept unaltered by appropriately compressing the steady state segments. Transition segments are intensity scaled by 6 dB. The effectiveness of the method was evaluated by conducting listening tests on normal hearing subjects using VCV syllables as the test material.","PeriodicalId":158011,"journal":{"name":"2008 International Conference on Signal Processing, Communications and Networking","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114982106","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}

引用次数: 12

Algorithms for Placement of Wavelength Converters in Optical Networks 光网络中波长转换器的放置算法

2008 International Conference on Signal Processing, Communications and Networking Pub Date : 2008-02-07 DOI: 10.1109/ICSCN.2008.4447205

Sandra George, Vinod Chandra

引用次数: 1

Estimation of Compressive Strength of Femur Bones using Radiographic Imaging and Spectral Analysis 用放射成像和光谱分析估计股骨的抗压强度

2008 International Conference on Signal Processing, Communications and Networking Pub Date : 2008-02-07 DOI: 10.1109/ICSCN.2008.4447225

Asaithambi Mythili, Joseph Jesu Christopher, Swaminathan Ramakrishnan

引用次数: 1

A New Efficient Algorithm to Remove High Density Gaussian Noise with Edge Preservation 一种基于边缘保持的高密度高斯噪声去除新算法

2008 International Conference on Signal Processing, Communications and Networking Pub Date : 2008-02-07 DOI: 10.1109/ICSCN.2008.4447196

V. R. Vijaykumar, P. Vanathi, P. Kanagasabapathy, B. Senthilkumar

引用次数: 1

Optical Characterization of Abnormalities in Various Size and Shape in Tissue Equivalent Phantoms 组织等效幻影中不同大小和形状异常的光学表征

2008 International Conference on Signal Processing, Communications and Networking Pub Date : 2008-02-07 DOI: 10.1109/ICSCN.2008.4447171

P. S. Pandian, M. Singh

{"title":"Optical Characterization of Abnormalities in Various Size and Shape in Tissue Equivalent Phantoms","authors":"P. S. Pandian, M. Singh","doi":"10.1109/ICSCN.2008.4447171","DOIUrl":"https://doi.org/10.1109/ICSCN.2008.4447171","url":null,"abstract":"Tissue equivalent phantoms were made by mixing various combinations of wax colors with paraffin wax. Abnormalities of various size and shape were embedded into the tissue equivalent phantoms at different locations and depths to simulate real life abnormalities of tissues. The normalized back-scattered intensity (NBI) profiles at various locations on the tissue equivalent phantoms were obtained by multi-probe laser reflectometer. The laser radiations are guided by an optical fiber onto the phantoms and the backscattered radiations are collected by three optical fibers placed at a distance of 3 mm, 5 mm and 7 mm from the input fiber. The data after digitization, interpolation and filtering, are gray color-coded and displayed on the outline of the phantom. These NBI pattern vary depending on the optical characteristics of the phantom at various locations. For optical characterization the optical parameters, scattering (mu3) and absorption (mu2) coefficients and the anisotropy parameter (g) at each location on the phantom, by matching of reflectance profiles with that as simulated by a Monte Carlo simulation (MCS) procedure were determined. From the surface profile the size, location and depth of the abnormality were obtained.","PeriodicalId":158011,"journal":{"name":"2008 International Conference on Signal Processing, Communications and Networking","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114960086","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}

引用次数: 0

Implementation of Neural Networks Based ECG classifi'er on TMS320C6711 processor 基于神经网络的心电分类器在TMS320C6711处理器上的实现

2008 International Conference on Signal Processing, Communications and Networking Pub Date : 2008-02-07 DOI: 10.1109/ICSCN.2008.4447181

R. Thakare, N. Charniya

引用次数: 2

Intelligent Control Of Cellular Network Coverage Using Semi-Smart Antennas For Load Balancing 基于半智能天线负载均衡的蜂窝网络覆盖智能控制

2008 International Conference on Signal Processing, Communications and Networking Pub Date : 2008-02-07 DOI: 10.1109/ICSCN.2008.4447207

Jiayi Wu, J. Bigham, P. Jiang, Yapeng Wang

引用次数: 9

Design of Adaptive Channel Equaliser on Neural Framework Using Fuzzy Logic Based Multilevel Sigmoid Slope Adaptation 基于模糊逻辑的多电平s型斜率自适应神经网络信道均衡器设计

2008 International Conference on Signal Processing, Communications and Networking Pub Date : 2008-02-07 DOI: 10.1109/ICSCN.2008.4447203

Susmita Das

{"title":"Design of Adaptive Channel Equaliser on Neural Framework Using Fuzzy Logic Based Multilevel Sigmoid Slope Adaptation","authors":"Susmita Das","doi":"10.1109/ICSCN.2008.4447203","DOIUrl":"https://doi.org/10.1109/ICSCN.2008.4447203","url":null,"abstract":"Adaptive equalisation in digital communication systems is a process of compensating the disruptive effects caused mainly by inter symbol interference in a band-limited channel and plays a vital role for enabling higher data rate in modern digital communication system. Designing efficient equalisers having low structural complexity and faster learning algorithms is also an area of much research interest in the present scenario. This research work proposes adaptive channel equalisation techniques on Recurrent Neural Network framework. Exhaustive simulation studies carried out prove that by replacing the conventional sigmoid activation functions in each of the processing nodes of recurrent neural network with multilevel sigmoid activation functions, the bit error rate performance have significantly improved. Further slopes of different levels of the multi-level sigmoid have been adapted using fuzzy logic control concept Simulation results cosidering standard channel models show faster learning with less number of training samples and performance level comparable to the their conventional counterparts. Also there is scope for parallel implementation of slope adaptation technique in real-time implementation.","PeriodicalId":158011,"journal":{"name":"2008 International Conference on Signal Processing, Communications and Networking","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129399216","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}

引用次数: 2

Consolidate and Advance: An Efficient QoS Management Technique in Heterogeneous Wireless Sensor Networks 巩固与发展:异构无线传感器网络中一种高效的QoS管理技术

2008 International Conference on Signal Processing, Communications and Networking Pub Date : 2008-02-07 DOI: 10.1109/ICSCN.2008.4447165

S. Tarannum, Divya Prakash, S. George, B V Tara, S. Ushe, L. Nalini, K. Venugopal, L. M. Patnaik

{"title":"Consolidate and Advance: An Efficient QoS Management Technique in Heterogeneous Wireless Sensor Networks","authors":"S. Tarannum, Divya Prakash, S. George, B V Tara, S. Ushe, L. Nalini, K. Venugopal, L. M. Patnaik","doi":"10.1109/ICSCN.2008.4447165","DOIUrl":"https://doi.org/10.1109/ICSCN.2008.4447165","url":null,"abstract":"Research in wireless sensor networks has become an extensive explorative area during the last few years. In this paper we emphasize the need for repositioning of the consolidating and advancing node, (CAN : Principal Node) to improve network lifetime in terms of energy and other QoS parameters such as latency and throughput. We also address issues related to its repositioning such as the time and position of relocation and the control of its movement without causing negative impact on the performance of the WSN. Mobility factor is exploited to support QoS requirements. We present a scheme called energy conserving relocation (ECR) to pursue relocation of CAN to a safe location on demand. ECR performs relocation based on the minimum energy concept of sensor nodes. The concept of repositioning adds a new dimension to the existing heterogeneous wireless sensor network. It is observed through simulation that lifetime of the network, average energy consumption and QoS parameters are much better when compared to earlier algorithms.","PeriodicalId":158011,"journal":{"name":"2008 International Conference on Signal Processing, Communications and Networking","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130852410","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}

引用次数: 2

An Intrusion Detection System Based on Multiple Level Hybrid Classifier using Enhanced C4.5 基于增强C4.5的多级混合分类器入侵检测系统

2008 International Conference on Signal Processing, Communications and Networking Pub Date : 2008-02-07 DOI: 10.1109/ICSCN.2008.4447164

L. Rajeswari, A. Kannan

{"title":"An Intrusion Detection System Based on Multiple Level Hybrid Classifier using Enhanced C4.5","authors":"L. Rajeswari, A. Kannan","doi":"10.1109/ICSCN.2008.4447164","DOIUrl":"https://doi.org/10.1109/ICSCN.2008.4447164","url":null,"abstract":"Intrusion Detection System (IDS) has recently emerged as an important component for enhancing information system security. However, constructing and maintaining a misuse intrusion detection system for a network is labor ¿ intensive, since attack scenarios and patterns need to be analyzed and categorized. Moreover, the rules corresponding to the scenarios and patterns need to be carefully hand-coded. In such situations, data mining can be used to ease this inconvenience. This paper proposes a multiple level hybrid classifier for an intrusion detection system that uses a combination of tree classifiers which uses Enhanced C4.5 which rely on labeled training data and an Enhanced Fast Heuristic Clustering Algorithm for mixed data (EFHCAM). The main advantage of this approach is that the system can be trained with unlabelled data and is capable of detecting previously \"unseen\" attacks. Verification tests have been carried out by using the 1999 KDD Cup data set. From this work, it is observed that significant improvement has been achieved from the viewpoint of both high intrusion detection rate and reasonably low false alarm rate.","PeriodicalId":158011,"journal":{"name":"2008 International Conference on Signal Processing, Communications and Networking","volume":"193 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114359291","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}

引用次数: 20