{"title":"Temporal classification for fault-prediction in a real-world telecommunications network","authors":"M. Jaudet, N. lqbal, A. Hussain, K. Sharif","doi":"10.1109/ICET.2005.1558882","DOIUrl":"https://doi.org/10.1109/ICET.2005.1558882","url":null,"abstract":"This paper presents a new temporal classification approach for fjldt-prediction in a Telecommutnications Network. The countrvwide data network of Pakistan Telecom (PTCL) has been selected as a basis for the investigation of classification algor-ithms to predict flults beJbre they stop a large numnber of users' circuits from normal operation. The main problenms addressed are the evalluation of alarms and clevelopment of newi, machine learning tools to help overcome the interoperabilitv issues. The motivation behind this work is to assist humian operators and nminimize the cost of the alarm evalulation","PeriodicalId":222828,"journal":{"name":"Proceedings of the IEEE Symposium on Emerging Technologies, 2005.","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124849070","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":"Kernel based robust object tracking using model updates and Gaussian pyramids","authors":"Z. Ali, S. Hussain, I. A. Taj","doi":"10.1109/ICET.2005.1558870","DOIUrl":"https://doi.org/10.1109/ICET.2005.1558870","url":null,"abstract":"Visionbasedtracking, being a challenging engineering problem isone ofthehotresearch areas in*nachine vision. Inrecentstuidies Kernel based tracking usinig Bhattacharya similaritv mea.sutre is showntobean eficient techniquie fornon-rigid object tracking through thesequienceofimnages. In this paper we presented a robutst and efficient tracking approach Jbrtargets having larger motions ascompared totheir sizes. Outr tracking approach is based on calculating theGaussian pyramids ofthe imagesandthenapplying mean shift algorithm at eachpyramid level fo6r tracking thetarget. Model based tracking often sq/fkm-s abruipt changes intarget model, which iscompensated bvthemodel updatesof target. Thisleads to a very efficient androbust nonparametric tracking algorithm Thenew method is easily abletotrack thefast moving targetsandis more robulst and environment independent as compared tooriginal kernel based object tracking.","PeriodicalId":222828,"journal":{"name":"Proceedings of the IEEE Symposium on Emerging Technologies, 2005.","volume":"556 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123142698","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":"PCA based image classification of single-layered cloud types","authors":"ImranSarwar Bajwa, S. Hyder","doi":"10.1109/ICET.2005.1558909","DOIUrl":"https://doi.org/10.1109/ICET.2005.1558909","url":null,"abstract":"The paper presents an automatic classification system, which discriminates the different types of single-layered clouds using principal component analysis (PCA) with enhanced accuracy as compared to other techniques. PCA is an image classification technique typically used for face recognition. Principal components are the distinctive or peculiar features of an image. The approach described in this paper uses this PCA capability for enhancing the accuracy of cloud image analysis. To demonstrate this enhancement, a software classifier system has been developed that incorporates PCA capability for better discrimination of cloud images. The system is first trained using cloud images. In training phase, system reads major principal features of the different cloud images to produce an image space. In testing phase, a new cloud image can be classified by comparing it with the specified image space using the PCA algorithm.","PeriodicalId":222828,"journal":{"name":"Proceedings of the IEEE Symposium on Emerging Technologies, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129936727","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}
I. Askari, S. A. Hassan, M.S. Faree, K. Munawar, M. Malik, T. Abbas
{"title":"Development of a 2 degrees of freedom tracking system. Part II: controller design and implementation","authors":"I. Askari, S. A. Hassan, M.S. Faree, K. Munawar, M. Malik, T. Abbas","doi":"10.1109/ICET.2005.1558928","DOIUrl":"https://doi.org/10.1109/ICET.2005.1558928","url":null,"abstract":"Platform stabilization and control problems are a major field of study in control systems. For a long period of time, analog control schemes using op-amps for gain, as differentiators and as integrators were used and are still used but they require complex circuitry even for simple PI controllers. With the advent of the digital era this approach has changed. Now even complex closed loop control schemes are easily achievable using programmable gains and adjustable parameters. Different scenarios require different control schemes that optimize different parameters of the systems closed loop response. Object tracking requires a highly stable platform capable of tracking high speed moving targets. This paper is the continuation of our previous paper in which we discussed the design and construction of a real time target tracker, a 2 DOF platform with emphasis on its stability and balanced weight distribution. In this paper we discuss the digital control scheme for the closed loop control of the designed platform.","PeriodicalId":222828,"journal":{"name":"Proceedings of the IEEE Symposium on Emerging Technologies, 2005.","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129666975","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}
M. Ahmed, Mohib-ur-Rehman, Imran Ihsan, M. Qadir, N. Iftikhar
{"title":"Semantic integration of learning objects for UREKA navigation & integration toolkit - UNIT","authors":"M. Ahmed, Mohib-ur-Rehman, Imran Ihsan, M. Qadir, N. Iftikhar","doi":"10.1109/ICET.2005.1558936","DOIUrl":"https://doi.org/10.1109/ICET.2005.1558936","url":null,"abstract":"Now a day, education is getting more expensive, relative to other fields. The reason for such increasingly expensive field is due to less investment and efforts to involve information technology. There is a need to develop new and effective models for learning through information technology. The key component for such learning models is learning object, which includes different types of media i.e. audio, video, image. text etc. A lecture is a combination of one or more learning objects. Thus efficient and effective integration of learning objects becomes the key part of this activity. UNIT (UREKA navigation and integration toolkit) is emerging model for such type of integration. It defines CMF (common media framework) that has a predefined schema for integration of learning objects, and also the capability of handling spatial und temporal behavior for learning activity separately. Furthermore, it allows users to modify these behaviors and to attach presentational templates of their own comfort that provide reusability of both the integrated information and templates. The integration information in CMF file will be combined with loosely hounded presentational templates, dynamically to generate presentation for learning activity (A Lecture).","PeriodicalId":222828,"journal":{"name":"Proceedings of the IEEE Symposium on Emerging Technologies, 2005.","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131590554","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 framework for fault tolerance in distributed real time systems","authors":"S. Malik, M. Rehman","doi":"10.1109/ICET.2005.1558933","DOIUrl":"https://doi.org/10.1109/ICET.2005.1558933","url":null,"abstract":"Real time systems have a characteristic that they should be fault tolerant. In this paper, a fault tolerance mechanism for real time systems is proposed. First a model is discussed which is a modification of distributed recovery block and is based on distributed computing. Then a model is proposed which is based on distributed computing along with feed forward artificial neural network methodology. The proposed technique is based on execution of design diverse variants on replicated hardware, and assigning weights to the results produced by variants. Thus the proposed method encompasses both the forward and backward recovery mechanism, but main focus is on forward recovery.","PeriodicalId":222828,"journal":{"name":"Proceedings of the IEEE Symposium on Emerging Technologies, 2005.","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126976231","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":"SIP-based QoS control over satellite networks","authors":"R. Qureshi, O. Alphand","doi":"10.1109/ICET.2005.1558888","DOIUrl":"https://doi.org/10.1109/ICET.2005.1558888","url":null,"abstract":"Satellite access networks (SAN) are expected to play a decisive role in bridging the digital divide through providing broadband access to multimedia services in geographical area where terrestrial access networks like cable or ADSL cannot be deployed. SANs currently lack a clear QoS architecture in order to fit seamlessly into the end-to-end NGN framework. Several architectures mixing [P QoS layer mechanisms with specific satellite MAC dynamic allocation schemes are already designed. However, very few multimedia applications can actually benefit from these architectures since most of them are not QoS aware. This work presents a SIP based multimedia signaling architecture where existing SIP applications can beneficiate from a QoS enabled IP network without undergoing any adjustments or modifications. In addition to that, the realization of the proposed solution is also described along with its performance evaluation tests and their results on an emulated satellite platform, providing DiffServ services, which was implemented during the European IST SATIP6 project.","PeriodicalId":222828,"journal":{"name":"Proceedings of the IEEE Symposium on Emerging Technologies, 2005.","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126431795","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":"Two layered behaviour based navigation of a mobile robot in an unstructured environment using fuzzy logic","authors":"N. Rahman, A. R. Jafri","doi":"10.1109/ICET.2005.1558886","DOIUrl":"https://doi.org/10.1109/ICET.2005.1558886","url":null,"abstract":"This paper proposes a fuzzy behaviour based controls for the navigation of a differential drive mobile robot in an unstructured environment. Behaviours are implemented by incorporating the information of the current location of mobile robot, location of target and distance of the obstacles from the ultrasonic range finders. This behaviour based controls architecture is composed of two layers, the first layer selects a group of behaviours and second implements controller actions for the selected group. The layered architecture reduces the rule base as well as allows further decomposition of behaviours. The behaviour conflict management is done by using inhibition at first layer and suppression at second layer. Simulation results verify the effectiveness of proposed method by implementing obstacle avoidance, wall following, corridor following, target steering and emergency behaviours successfully","PeriodicalId":222828,"journal":{"name":"Proceedings of the IEEE Symposium on Emerging Technologies, 2005.","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129038540","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":"Evaluation of VoIP quality over the pakistan internet exchange (PIE) backbone","authors":"M. Mehmood, T.M. Jadoon, N. Sheikh","doi":"10.1109/ICET.2005.1558891","DOIUrl":"https://doi.org/10.1109/ICET.2005.1558891","url":null,"abstract":"This paper assesses VoIP quality over the Pakistan Internet Exchange (PIE) backbone between major cities of Pakistan. Passive measurements for voice calls in the presence of background Internet data traffic for different speech codecs such as the ITU-T G.711, G.723.1 and G.729 were carried out. Interpacket delay and jitter were measured over the PIE IP/ATM backbone and the corresponding inter-packet delay densities were calculated for evaluating the perceptual quality of computer telephony calls using the ITU-T G.107 E-model. The transmission quality (R-factor) and resultant Mean Opinion Scores (MOS) were calculated for both backbone and access links of ISPs. The study highlights the growth of VoIP as a significant component of the PIE backbone traffic in Pakistan as well as reconfirms the presence of congestion hot spots in the access links.","PeriodicalId":222828,"journal":{"name":"Proceedings of the IEEE Symposium on Emerging Technologies, 2005.","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114940939","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":"Power optimized logic circuit design with a novel synthesis technique","authors":"P. Balasubramanian, M. Narayana, R. Chinnadurai","doi":"10.1109/ICET.2005.1558899","DOIUrl":"https://doi.org/10.1109/ICET.2005.1558899","url":null,"abstract":"The purpose of this paper is to propose a systematic methodology for non-regenerative logic circuit design at the gate level. The tr-aditional logic synthesis methods [5f, [6] become inetfective in ccase of Non-Adjacent Jfnctions. In this paper, we address the redutction problem for this case by evolving a set of minimization lemmas based on the Hamming distance between the terms. Though our main emphasis has been on the satisfiabilitv of the circuiit functionality with minimum number of active gates, the approach presented here takes a viewpoint, in which all critical design metrics are investigated with the primary goal of reducing the dynamic power consunmption of the circuit. The SPICE simulation results obtained on the basis of 3.3V, 0.5,um CMOS technology are very encouraging, as they report minimization in average power consumption by about 36 %for the examples cited, along with a substantial improvement in the Figure oj Merit (FoM) of the circuit, in comparison with that obtainable using conventional approaches.","PeriodicalId":222828,"journal":{"name":"Proceedings of the IEEE Symposium on Emerging Technologies, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130325422","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}