Elnaz Bigdeli, B. Raahemi, M. Mohammadi, S. Matwin
{"title":"A fast noise resilient anomaly detection using GMM-based collective labelling","authors":"Elnaz Bigdeli, B. Raahemi, M. Mohammadi, S. Matwin","doi":"10.1109/SAI.2015.7237166","DOIUrl":"https://doi.org/10.1109/SAI.2015.7237166","url":null,"abstract":"Anomaly detection algorithms face several challenges including computational complexity and resiliency to noise in input data. In this paper, we propose a fast and noise-resilient cluster-based anomaly detection method using collective labelling approach. In the proposed Collective Probabilistic Anomaly Detection method, first instead of labelling each new sample (as normal or anomaly) individually, the new samples are clustered, then labelled. This collective labelling mitigates the negative impact of noise by relying on group behaviour rather than individual characteristics of incoming samples. Second, since grouping and labelling new samples may be time-consuming, we summarize clusters using Gaussian Mixture Model (GMM). Not only does GMM offer faster processing speed; it also facilitates summarizing clusters with arbitrary shape, and consequently, reducing the memory space requirement. Finally, a modified distance measure, based on Kullback-Liebner method, is proposed to calculate the similarity among clusters represented by GMMs. We evaluate the proposed method on various datasets by measuring its false alarm rate, detection rate and memory requirement. We also add different levels of noise to the input datasets to demonstrate the performance of the proposed collective anomaly detection method in the presence of noise. The experimental results confirm superior performance of the proposed method compared to individually-based labelling techniques in terms of memory usage, detection rate and false alarm rate.","PeriodicalId":210316,"journal":{"name":"2015 Science and Information Conference (SAI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123867851","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":"Load balancing enhancement in WMNs with new routing metric","authors":"Naima El Haoudar, A. Maach","doi":"10.1109/SAI.2015.7237279","DOIUrl":"https://doi.org/10.1109/SAI.2015.7237279","url":null,"abstract":"Wireless mesh networks is a smart technology with large connectivity and low cost. Load balancing in WMNs ameliorate the communication quality with least latency, jitter and error rate as amelioration of bandwidth. This paper gives survey the different routing metric, and a new routing metrics with load balancing. The literal of our metric is to balance the load between nodes and route the traffic across network. In our paper we realize the future works, in my last paper [15], and we demonstrate that our new routing metric provide more advantage for WMNs, such as load balancing, high throughput, and lower delay even if we implement our new metric in OLSR with manifold numbers of nodes. The characteristics of a better routing metric in WMNs are: High throughput, capacity of channel, load balancing....","PeriodicalId":210316,"journal":{"name":"2015 Science and Information Conference (SAI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125253274","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":"Using gradient model to compare between treatment samples and non-treatment samples","authors":"M. A. Ashabrawy","doi":"10.1109/SAI.2015.7237337","DOIUrl":"https://doi.org/10.1109/SAI.2015.7237337","url":null,"abstract":"Applications of digital image processing are mostly in the area of medical, plants laboratory, in the surgery images, Cameras, Video, Electro-photographic and Television images for improving the quality of images and code system. The scanning electron microscope (SEM) is the most acceptable tool being used for bio-measurements and in this paper we have designed the Gradient model to help us detecting and comparing between treatment samples and non-treatment samples in bacteria samples. The error probability of discussion becomes high due to poor information occurrence of some natural properties. We have addressed this issue in our paper by using different image processing technique in order to get more clarity and sufficiency of information. This analysis technique is called Gradient model (GD) and the model starts converting two dimensional images of the prepared samples to data file (*.dat). This 2D data is subsequently converted to 3D data file by using OpenGL under Visual C++ Language programming which after conversion, finally, can draw up time series charts like histogram; and traces management contours; and 3D surface to carry out image analysis. This analysis is of vital importance and can help in comparing between the treatment of bacterial samples and non-treatment samples. Instead of carryout full analysis again and again, this method facilitates partial analysis of any part of any randomly selected image and can accommodate different sizes of the images as well. This property and functionality of the model ensures more accuracy of the analysis and reduces the cost of hardware used.","PeriodicalId":210316,"journal":{"name":"2015 Science and Information Conference (SAI)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114450318","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":"Model based virtual engineering approach to remanufacturing design","authors":"O. Banjo, Atul K. Jain, Feng Chen","doi":"10.1109/SAI.2015.7237251","DOIUrl":"https://doi.org/10.1109/SAI.2015.7237251","url":null,"abstract":"Although remanufacturing can be both profitable and less harmful to the environment than traditional manufacturing, its uptake is still limited. Previous research shows that this limitation could be the consequence of poor definition of remanufacturing and confusion with terms like second-hand or refurbished products. Other research claims that this downturn is due to the fact that OEMs are not actively engaged in remanufacturing and therefore the products are not designed for remanufacture; inadvertently increasing the cost of remanufacturing. To make the remanufacturing oriented design, it is important to have effective flow of communication across the supply chain with the help of virtual engineering tools. This research investigates the model based virtual engineering approach in the search for a unique solution that would foster the growth of remanufacturing.","PeriodicalId":210316,"journal":{"name":"2015 Science and Information Conference (SAI)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127011594","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":"Towards real-time obstacle detection using stereo images","authors":"N. Baha, Mouslim Tolba","doi":"10.1109/SAI.2015.7237214","DOIUrl":"https://doi.org/10.1109/SAI.2015.7237214","url":null,"abstract":"This work aims at defining a new approach for real-time obstacle detection based on sparse disparity map. To achieve fast time execution, the image processing is performed on a subset of points. The proposed method begins by extracting the primitives of pixels of the two images. Then, a detection of the ground is made to limit obstacles area using color information. Subsequently, an extraction of subset of points is performed using the features extracted in the previous step. The use of the extracted features as well as the subset of points will enable us to calculate a sparse disparity map which is used to calculate the v-disparity image. The use of v-disparity image allows us to extract the obstacle profile in order to eliminate disparities of the ground. To eliminate the obstacles belonging to the background, we use the ground limits to remove all object points outside these limits. Finally, a segmentation based on disparity value of the remaining points is applied to extract obstacles. To end, validation step is used to remove false positives. The experimental results obtained are interesting with real time execution. This allows early detection to prevent collisions.","PeriodicalId":210316,"journal":{"name":"2015 Science and Information Conference (SAI)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124276062","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":"Re-appraising instance seeking in Public Clouds","authors":"J. O’Loughlin, Lee Gillam","doi":"10.1109/SAI.2015.7237237","DOIUrl":"https://doi.org/10.1109/SAI.2015.7237237","url":null,"abstract":"Variable compute performance has been widely reported on for virtual machine instances of the same type, and price, on Public Infrastructure Clouds. This has led to the proposal of a number of so called `instance seeking' or `placement gaming' strategies, with the aim of obtaining better performing instances for the same price for a given workload. However, a number of assumptions made in models presented in the literature fail to hold for real large-scale Public Infrastructure Clouds. We demonstrate, using data from our experiments on EC2, the problems of such assumptions, discuss how these models are likely to underestimate the costs involved, and demonstrate why such literature requires a better Cloud Compute Model.","PeriodicalId":210316,"journal":{"name":"2015 Science and Information Conference (SAI)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121104814","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":"Consumer centric dynamic business process customization of web service using ontology","authors":"R. Prasad, K. Kumar, S. Paul, U. S. Surya Prabha","doi":"10.1109/SAI.2015.7237141","DOIUrl":"https://doi.org/10.1109/SAI.2015.7237141","url":null,"abstract":"Semantics plays a major role in modern world of ecommerce. Web contents are systematized by adding semantics to current web resources. Business process customization constitutes knowledge based semantic web that provides a shift from producer centric to consumer centric methodology. Business processes contents need customization in order to eliminate the repugnancies and make business process in web more promiscuous for customers. Ontology based dynamic customization of web services divides up with the customization of web services, which are capable of machinating contents of business processes and solves discrepancies on the runtime context of business process execution. The mapped producer centric process is accessed by the consumer centric after the business process is instantiated by grouping and also maps the contents of various web services relevant to business process services in relation to the consumer centric process.","PeriodicalId":210316,"journal":{"name":"2015 Science and Information Conference (SAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123281936","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":"Android malware detection: An eigenspace analysis approach","authors":"S. Yerima, S. Sezer, Igor Muttik","doi":"10.1109/SAI.2015.7237302","DOIUrl":"https://doi.org/10.1109/SAI.2015.7237302","url":null,"abstract":"The battle to mitigate Android malware has become more critical with the emergence of new strains incorporating increasingly sophisticated evasion techniques, in turn necessitating more advanced detection capabilities. Hence, in this paper we propose and evaluate a machine learning based approach based on eigenspace analysis for Android malware detection using features derived from static analysis characterization of Android applications. Empirical evaluation with a dataset of real malware and benign samples show that detection rate of over 96% with a very low false positive rate is achievable using the proposed method.","PeriodicalId":210316,"journal":{"name":"2015 Science and Information Conference (SAI)","volume":"325 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116440666","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":"An advanced wireless medium access backoff algorithm for MANETs","authors":"Y. Neeraja, V. Sumalatha","doi":"10.1109/SAI.2015.7237269","DOIUrl":"https://doi.org/10.1109/SAI.2015.7237269","url":null,"abstract":"Wireless networks have experienced sudden improvements from the past decade, and most rapidly developing areas are MANETs. In this paper, we propose an improved backoff scheme for IEEE 802.11 MAC based on Padovan Sequence. A MAC protocol used to address how to resolve the contention and collisions in the communication medium, we performed study and analysis on the existing PBA and BEB algorithms and proposed advanced backoff algorithm (ABA) implemented in IEEE 802.11 in distributed coordinated function mode for better improvement. The ABA reduces the number of collisions, when more than one node shared the medium and leads to the improved network performance. Existing binary exponential backoff algorithm has been proven not to be the optimal algorithm in MANETs due to the exponential increase of the contention window size and degrades the network performance by waiting time. The proposed ABA minimizes the size of contention window and improves the network performance.","PeriodicalId":210316,"journal":{"name":"2015 Science and Information Conference (SAI)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122774098","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":"Safe haven in the cloud: Secure access controlled file encryption (SAFE) system","authors":"F. Shahzad","doi":"10.1109/SAI.2015.7237315","DOIUrl":"https://doi.org/10.1109/SAI.2015.7237315","url":null,"abstract":"The evolution of cloud computing has revolutionized how the computing is abstracted and utilized on remote third party infrastructure. It is now feasible to try out novel ideas over the cloud with no or very low initial cost. There are challenges in adopting cloud computing; but with obstacles, we have opportunities for research in several aspects of cloud computing. One of the main issue is the data security and privacy of information stored and processed at cloud provider's systems. In this work, a practical system (called SAFE) is designed and implemented to securely store/retrieve user's files on the third party cloud storage systems using well established cryptographic techniques. It utilizes the client-side, multilevel, symmetric/asymmetric encryption and decryption operations to provide policy-based access control and assured deletion of remotely hosted client's files. The SAFE is a generic application which can be extended to support any cloud storage provider as long as there is an API which support basic file upload and download operations.","PeriodicalId":210316,"journal":{"name":"2015 Science and Information Conference (SAI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122074736","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}