{"title":"Spectral Analysis of Speech Quality in VoIP for G.729A and AMR-WB Speech Coders","authors":"Sarabjeet Singh, H. Singh, Jasvir Singh","doi":"10.1109/CICSyN.2010.70","DOIUrl":"https://doi.org/10.1109/CICSyN.2010.70","url":null,"abstract":"The transmission of Voice over Internet protocol requires signal processing for reliable & efficient performance over the computer and the communication platform. Speech quality, as perceived by the users of VoIP telephony, is critically important to the update of the service. Signal quality is degraded by network layer problems including delay, jitter and packet loss. The work presented in this paper presents the spectral analysis of speech quality for narrowband and wideband VoIP. The simulation model of VoIP network under impairments is presented. The VoIP simulations are conducted for G.729A and AMR-WB speech coders at different packet loss rates. The comparison results of various speech analysis algorithms such as power density spectrum FFT etc. for both narrowband and wideband VoIP signals are presented in this paper. The results are also measured using PESQ for narrowband speech signal and WB-PESQ for wideband speech signal","PeriodicalId":358023,"journal":{"name":"2010 2nd International Conference on Computational Intelligence, Communication Systems and Networks","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122456994","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}
{"title":"Woods Recognition System Based on Local Binary Pattern","authors":"M. Nasirzadeh, A. A. Khazael, M. Khalid","doi":"10.1109/CICSyN.2010.27","DOIUrl":"https://doi.org/10.1109/CICSyN.2010.27","url":null,"abstract":"Malaysia is the largest exporter of tropical woods in the world, accounting for 70 percent of the world's supply of raw-logs. Sabah and Sarawak, the two Malaysian states on the island of Borneo, occupies some of the oldest and the most diverse rain forest in the world. Malaysia has a rich variety of tree species, and the wood produced from each of these has unique structure, physical and mechanical properties. The differences in woods structure and properties allow for the manufacture of woods based products with many different appearances and uses. In order to use this precious material efficiently, proper species must be used in the appropriate places. Intelligent Woods species recognition is a new application studied in the Computer Vision field to help prevent misclassifying of woods species in woods industries. Woods recognition is an implementation on identifying the different species of woods provided with the images captured for the woods samples or the characteristics observed. In this study, the features from the enhanced woods images are extracted using the LBP histogram, which determines the classification between the various woods species. The recognition is performed using a nearest neighbor classifier in the computed feature space with Chi square as a dissimilarity measure. The intelligent woods recognition system is designed to explore the possibility of developing a system which is able to perform automated woods recognition based on woods anatomy. The result thus obtained shows a high rate of recognition accuracy proving that the techniques due to its rotation invariance and robustness to gray-scale variations are very promising for practical applications.","PeriodicalId":358023,"journal":{"name":"2010 2nd International Conference on Computational Intelligence, Communication Systems and Networks","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128174052","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}
{"title":"Simulation Model of the Scanner Servocontrols for the Orientation of a Fighter Aircraft by Using the Bond Graph Technique","authors":"M. L. Martínez, G. Romero, J. Maroto, J. Félez","doi":"10.1109/CICSyN.2010.67","DOIUrl":"https://doi.org/10.1109/CICSyN.2010.67","url":null,"abstract":"Nowadays the use of complex models has increasedthe requirements of the simulation tools and techniques forworking and analyzing with different domains at the sametime. This work focuses on the study of the Scannerservocontrols of a fighter aircraft. The model has the feature ofintegrating various physical domains into the same system(electrical, mechanical and system control environments) withdifferent dimensions in each domain. The technique used is theBond Graph (BG), which is typically used in fields wheredifferent physical domains coexist, just as in the case we aredealing with, where such domains are fundamental. At thebeginning of the study, the different coordinate references areintroduced and the physical subsystems are also described.After this the different subsystems are presented in the form ofBG submodels one by one and the global Multibond Graph(MBG) model is displayed. Lastly, an example of simulation is shown and some important conclusions are reached.","PeriodicalId":358023,"journal":{"name":"2010 2nd International Conference on Computational Intelligence, Communication Systems and Networks","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131618495","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}
Pooia Lalbakhsh, Bahram Zaeri, A. Lalbakhsh, M. Fesharaki
{"title":"AntNet with Reward-Penalty Reinforcement Learning","authors":"Pooia Lalbakhsh, Bahram Zaeri, A. Lalbakhsh, M. Fesharaki","doi":"10.1109/CICSyN.2010.11","DOIUrl":"https://doi.org/10.1109/CICSyN.2010.11","url":null,"abstract":"The paper deals with a modification in the learning phase of AntNet routing algorithm, which improves the system adaptability in the presence of undesirable events. Unlike most of the ACO algorithms which consider reward-inaction reinforcement learning, the proposed strategy considers both reward and penalty onto the action probabilities. As simulation results show, considering penalty in AntNet routing algorithm increases the exploration towards other possible and sometimes much optimal selections, which leads to a more adaptive strategy. The proposed algorithm also uses a self-monitoring solution called Occurrence-Detection, to sense traffic fluctuations and make decision about the level of undesirability of the current status. The proposed algorithm makes use of the two mentioned strategies to prepare a self-healing version of AntNet routing algorithm to face undesirable and unpredictable traffic conditions.","PeriodicalId":358023,"journal":{"name":"2010 2nd International Conference on Computational Intelligence, Communication Systems and Networks","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134285070","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}
{"title":"A Multi-objective Gravitational Search Algorithm","authors":"H. Hassanzadeh, M. Rouhani","doi":"10.1109/CICSYN.2010.32","DOIUrl":"https://doi.org/10.1109/CICSYN.2010.32","url":null,"abstract":"Recently there has been a great research conducted on diverse variations of multi-objective swarm optimization algorithms each of which might have its own strengths and weaknesses. Due to the high complexity of multi-objective problems the efficiency of these methods has become a matter of concern. In this paper a new multi-objective meta-heuristic algorithm based on gravitational forces is proposed and applied to different test benches. The acquired results proved the superiority of the algorithm comparing with other pioneering techniques such as the MOPSO","PeriodicalId":358023,"journal":{"name":"2010 2nd International Conference on Computational Intelligence, Communication Systems and Networks","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116354740","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}
{"title":"Risk Identification, Mitigation and Avoidance Model for Handling Software Risk","authors":"B. Shahzad, A. Al-Mudimigh","doi":"10.1109/CICSyN.2010.82","DOIUrl":"https://doi.org/10.1109/CICSyN.2010.82","url":null,"abstract":"Risks in software development have emerged over time and so is the risk management. Quiet a few efforts have been done by the individuals and institutions to contribute in this area to help ensuring that the software development can be done without intervention of risks. This paper focuses on proposing a model that takes care of the most frequently occurring risks and provides a way for handling all of them. The sequence of activities for mitigating all risk factors: proposed in this paper are combined in the model. This paper is expected to unleash all the handling and avoidance mechanisms for software risks.","PeriodicalId":358023,"journal":{"name":"2010 2nd International Conference on Computational Intelligence, Communication Systems and Networks","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116277116","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}
{"title":"Enhancements of H.264 Encoder Performance Using Platform Specific Optimizations in Low Cost Dsp Platforms","authors":"T. Chattopadhyay","doi":"10.1109/CICSyN.2010.65","DOIUrl":"https://doi.org/10.1109/CICSyN.2010.65","url":null,"abstract":"In this age of multimedia convergence, video based applications for conferencing and streaming are seeing big market traction. The main challenge of implementing these systems is a tradeoff between several factors like bandwidth, image quality, implementation cost and speed (in terms of Mega Cycles per second). Moreover to implement this Encoder-Decoder system (CODECs) in a real time system based on any Digital Signal Processor (DSP) is more difficult because of their restricted resources like memory and CPU speed. In this paper author has presented the platform specific optimization techniques for realization of a QCIF H.264 baseline encoder in a TMS320C55x DSP, which has only 256 KB RAM and 150 MHz clock speed. We achieve almost 60% MCPS reduction with respect to optimized reference encoder by applying these platform specific optimizations.","PeriodicalId":358023,"journal":{"name":"2010 2nd International Conference on Computational Intelligence, Communication Systems and Networks","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114837734","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}
{"title":"Non-linear Image Enhancement Using Opportunity Costs","authors":"Lung-Jen Wang, Ya-Chun Huang","doi":"10.1109/CICSyN.2010.72","DOIUrl":"https://doi.org/10.1109/CICSyN.2010.72","url":null,"abstract":"Image enhancement is a commonly used method for the improvement of the quality of blurred image. Among many image enhancement approaches, the nonlinear image enhancement method has a simple structure and can obtain a good processing effect. For various target images, it is difficult to decide the best combination of clipping and scaling parameters within the nonlinear image enhancement method. In this paper, we propose a new method involving the concept of opportunity cost to simulate the image enhancement, and identify the most suitable enhancement parameters of clipping and scaling. Furthermore, a smoothing cubic B-spline filter is proposed for the conventional nonlinear image enhancement. Experimental results show that the proposed method improves the quality of blurred image and obtains a better subjective quality and objective PSNR performance than other nonlinear image enhancement methods.","PeriodicalId":358023,"journal":{"name":"2010 2nd International Conference on Computational Intelligence, Communication Systems and Networks","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123096354","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}
{"title":"A Novel Approach to Noise Reduction and Real-Time Enhancement of Speech Synthesis","authors":"M. Saadeq, Rafieee, A. Khazaei","doi":"10.1109/CICSyN.2010.41","DOIUrl":"https://doi.org/10.1109/CICSyN.2010.41","url":null,"abstract":"This paper is proposed for an explicit synthetic speech on LPC speech synthesis by discovering a novel parameter for speech enhancement. We present the NSSA(Natural Synthetic Speech Approach) to converge the same input utterances by different speakers to a new common parameter. The analysis of phonemes is beingused in order to make a much more natural and clear synthesize with minimum noise. In this paper, we enhanced the real time speech synthesis with a novel approachfor advance noise reduction and high fidelity of the synthesizer system. According to this approach, many conventional applications such as text-to-speech synthesiscan be used more efficiently. Therefore we implement the Linear Predictive Coding with Levinson-Durbin algorithm for synthesizer via TMS320C6713 DSK with RTDXmodule for testing and optimizing the results to create the best enjoyable synthetic voice.","PeriodicalId":358023,"journal":{"name":"2010 2nd International Conference on Computational Intelligence, Communication Systems and Networks","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133879809","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}
{"title":"SaLAM: Scalable @ Location Advertisement Management in MANET","authors":"Amjad Osmani, A. Haghighat","doi":"10.1109/CICSyN.2010.25","DOIUrl":"https://doi.org/10.1109/CICSyN.2010.25","url":null,"abstract":"Heretofore several position-based routing protocols have been developed for mobile ad hoc networks. Many of these protocols assume that a location service is available which provides location information on the nodes in the network. Our solutions decrease location update without loss of query success probability and even increase that. We use a new composed method to update mobile nodes location when cross a grid boundary. Our solutions work on HGRID and SLALoM and SLURP and simulation results show that our methods are effective. The algorithms are distributed and can keep scalability in scenarios of increasing nodes density and mobility. Our methods on mobility management can be used as an independent component in different hierarchical location services.","PeriodicalId":358023,"journal":{"name":"2010 2nd International Conference on Computational Intelligence, Communication Systems and Networks","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132736610","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}