Kinan Ghanem, Francisco J. Aparicio-Navarro, K. Kyriakopoulos, S. Lambotharan, J. Chambers
{"title":"Support Vector Machine for Network Intrusion and Cyber-Attack Detection","authors":"Kinan Ghanem, Francisco J. Aparicio-Navarro, K. Kyriakopoulos, S. Lambotharan, J. Chambers","doi":"10.1109/SSPD.2017.8233268","DOIUrl":"https://doi.org/10.1109/SSPD.2017.8233268","url":null,"abstract":"Cyber-security threats are a growing concern in networked environments. The development of Intrusion Detection Systems (IDSs) is fundamental in order to provide extra level of security. We have developed an unsupervised anomaly-based IDS that uses statistical techniques to conduct the detection process. Despite providing many advantages, anomaly-based IDSs tend to generate a high number of false alarms. Machine Learning (ML) techniques have gained wide interest in tasks of intrusion detection. In this work, Support Vector Machine (SVM) is deemed as an ML technique that could complement the performance of our IDS, providing a second line of detection to reduce the number of false alarms, or as an alternative detection technique. We assess the performance of our IDS against one-class and two-class SVMs, using linear and non- linear forms. The results that we present show that linear two-class SVM generates highly accurate results, and the accuracy of the linear one-class SVM is very comparable, and it does not need training datasets associated with malicious data. Similarly, the results evidence that our IDS could benefit from the use of ML techniques to increase its accuracy when analysing datasets comprising of non- homogeneous features.","PeriodicalId":404200,"journal":{"name":"2017 Sensor Signal Processing for Defence Conference (SSPD)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115338039","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":"Polynomial Root-MUSIC Algorithm for Efficient Broadband Direction of Arrival Estimation","authors":"William Coventry, C. Clemente, J. Soraghan","doi":"10.1109/SSPD.2017.8233256","DOIUrl":"https://doi.org/10.1109/SSPD.2017.8233256","url":null,"abstract":"The popular MUSIC algorithm has been recently extended to broadband scenarios through the use of polynomial matrix methods and polynomial eigenvalue decomposition algorithms, producing impressive results, at the cost of a high computational complexity. This is due to the heuristic angular search stage of the algorithm. Through the extension of the popular narrowband variant of the MUSIC algorithm, Root-MUSIC, we aim to significantly reduce the computational cost of spatio-spectral polynomial MUSIC algorithm by eliminating this searching requirement. The performance of both algorithms are analysed and compared, demonstrating a similar performance with a significant reduction in computation time.","PeriodicalId":404200,"journal":{"name":"2017 Sensor Signal Processing for Defence Conference (SSPD)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124808417","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":"Optimality Criteria for Adaptive Waveform Design in MIMO Radar Systems","authors":"Steven Herbert, J. Hopgood, B. Mulgrew","doi":"10.1109/SSPD.2017.8233254","DOIUrl":"https://doi.org/10.1109/SSPD.2017.8233254","url":null,"abstract":"Adaptive waveform design in MIMO radar can improve the estimation of target parameters. Comparing the relative benefits of known optimality criteria, namely the A-optimal, D-optimal and E-optimal criteria, is important to inform the best implementation of actual MIMO radar adaptive waveform design systems. In this paper we provide such a comparison, both theoretically and by assessing simulated numerical results. Whilst all three criteria are complementary, and thus all potentially could have a role in adaptive waveform design for MIMO radar, our results indicate that a system which generally uses A-optimal design, but switches to E-optimal design in some circumstances may be suitable for practical application.","PeriodicalId":404200,"journal":{"name":"2017 Sensor Signal Processing for Defence Conference (SSPD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128745340","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":"Novel Approach for Ballistic Targets Classification from HRRP Frame","authors":"A. Persico, C. Ilioudis, C. Clemente, J. Soraghan","doi":"10.1109/SSPD.2017.8233248","DOIUrl":"https://doi.org/10.1109/SSPD.2017.8233248","url":null,"abstract":"Nowadays the challenge of the identification of Ballistic Missile (BM) warheads in a cloud of decoys and debris is essential for the defence system in order to optimize the use of ammunition resources avoiding to run out of all the available interceptors in vain. In this paper a novel approach for the classification of ballistic threats from the High Resolution Range Profile (HRRP) frame is presented. The algorithm is based on the computation of the inverse Radon Transform (IRT) of the HRRP frame as target signature, and on the evaluation of pseudo-Zernike moments, as final feature vector. Firstly, the algorithm is presented emphasizing the characteristics of the HRRP frame due to target micro-motions. Then, the classification results on simulated data are shown for various operational conditions.","PeriodicalId":404200,"journal":{"name":"2017 Sensor Signal Processing for Defence Conference (SSPD)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129826633","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":"Correlation Based Classification of Complex PRI Modulation Types","authors":"Fotios Katsilieris, Sabine Apfeld, A. Charlish","doi":"10.1109/SSPD.2017.8233227","DOIUrl":"https://doi.org/10.1109/SSPD.2017.8233227","url":null,"abstract":"Classification of pulse repetition interval (PRI) modulation type is an important task of electronic warfare systems. Correct classification of the PRI modulation of an emitter can lead to significant knowledge about the observed emitter and can facilitate an electronic warfare system with applying its functions. Several methods have been proposed in the literature for identifying standard PRI modulation types (random, stable, jittered, dwell & switch, sliding, wobulated). The last two types, i.e. sliding and wobulated, are also called complex and the classification of their subtypes, i.e. sawtooth, triangle, sine, and saturated sine, remains unaddressed. This paper addresses the classification of complex PRI modulation subtypes. The proposed algorithm evaluates the correlation between a received signal and several ideal complex PRI modulated signals in order to detect such complex modulations. The performance of the proposed classification algorithm is demonstrated using simulated signals.","PeriodicalId":404200,"journal":{"name":"2017 Sensor Signal Processing for Defence Conference (SSPD)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116643211","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}
H. Shoukry, Satyanarayana Vuppala, P. Chambers, M. Sellathurai, J. Thompson
{"title":"Non-Cooperative Target Localisation Using Rank Based EDM Approach","authors":"H. Shoukry, Satyanarayana Vuppala, P. Chambers, M. Sellathurai, J. Thompson","doi":"10.1109/SSPD.2017.8233247","DOIUrl":"https://doi.org/10.1109/SSPD.2017.8233247","url":null,"abstract":"An analysis of the effect of the number of sensors on the non-cooperative target node localisation is presented. This work examines the target localisation using a centralised range based approach. In doing this, the work leverages an algorithm based on a class of matrix structure called Euclidean distance matrices (EDMs) for the specific purpose of improving localisation performance when the fusion centre (FC) cannot receive certain sensors' information due to fading or shadowing, etc. While this interesting approach to the problem of localisation has been found to be successful, it is also shown at high delay values the proposed alternating rank-based EDM algorithm outperforms the conventional linear least squares (LLS) based algorithm for the minimum number of sensors. The localisation error decreases when the conditioning of EDM is better, i.e., when the sensors are further apart from each other and closer to the target.","PeriodicalId":404200,"journal":{"name":"2017 Sensor Signal Processing for Defence Conference (SSPD)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125004829","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}
Christian Siebert, M. Leng, S. G. Razul, C. See, Guohua Wang
{"title":"Human Motion Detection and Classification Using Ambient WiFi Signals","authors":"Christian Siebert, M. Leng, S. G. Razul, C. See, Guohua Wang","doi":"10.1109/SSPD.2017.8233236","DOIUrl":"https://doi.org/10.1109/SSPD.2017.8233236","url":null,"abstract":"We investigate the detection and classification of human motions using ambient 802.11 wifi signals. Extensive experiments are conducted and show that different human motions introduce unique patterns in the received signal waveforms. As a starting point of the research, the Received Signal Strength (RSS) is explored as a reliable measurement due to its easy implementation and robustness against frequency nonsynchronization. A two stage algorithm was proposed by first detecting human motion and then classifying different motion types using the random forest algorithm. We studied statistical features not only for the raw RSS values but also for its dominant frequency component and time differencing variant. These features allows us to accurately characterize different human motions and provide sufficient yet concise information for the detection and classification. Experiment results shows that our proposed algorithm gives a high detection rate and a satisfactory classification accuracy in various environments.","PeriodicalId":404200,"journal":{"name":"2017 Sensor Signal Processing for Defence Conference (SSPD)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121490926","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":"Robust Raman Spectral Decomposition with Wavenumber Shifts Parametric Modelling","authors":"Mehrdad Yaghoobi","doi":"10.1109/SSPD.2017.8233261","DOIUrl":"https://doi.org/10.1109/SSPD.2017.8233261","url":null,"abstract":"Nonlinearity in Raman spectral mixtures caused by wavenumber shifts, has been investigated in this paper. The spectral shifts are mainly caused by the existence of multiple chemicals in the mixtures, with complex molecular interactions, which can change the spectral features of each constituent. While such non-linear behaviour may be negligible in some mixtures, it may lead to incorrect identification of chemicals in some instances. We investigate some real spectra and demonstrate the nature of such nonlinearity in Raman spectra. We then mathematically formulate such spectral behaviour and present an approach to compensate the nonlinearity artifacts. The nonlinearity has been modelled as a smooth transition in a parametric space, which can be locally modelled using first order approximation. Such a first order approximation can be translated to some augmented spectral libraries to be used with a linear generative model. A convex sparse approximation program, with nonlinearity considerations, has finally been introduced to decompose the spectral mixtures. Such decomposition has been used for chemical fingerprinting and quantification. The effect of new approach has been demonstrated with some real and synthetic spectra.","PeriodicalId":404200,"journal":{"name":"2017 Sensor Signal Processing for Defence Conference (SSPD)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124304432","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":"Node Sampling by Partitioning on Graphs via Convex Optimization","authors":"Cristian Rusu, John Thompson","doi":"10.1109/SSPD.2017.8233246","DOIUrl":"https://doi.org/10.1109/SSPD.2017.8233246","url":null,"abstract":"In this paper we deal with the problem of efficiently and accurately reconstructing a complete graph signal from partially observed noisy measurements. Given a graph structure, we propose a solution based on convex optimization techniques to partition the nodes of the graph into subsets such that sampling a graph signal from any of these subsets provides an accurate, low mean squared error for example, reconstruction of the original complete graph signal. We show how the proposed sampling set construction approach relates to optimal experimental design, sensor management, positioning and selection problems and provide numerical simulation results on synthetic and real-world graphs.","PeriodicalId":404200,"journal":{"name":"2017 Sensor Signal Processing for Defence Conference (SSPD)","volume":"204 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122210321","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":"Co-Prime Arrays with Reduced Sensors (CARS) for Direction-Of-Arrival Estimation","authors":"Mingyang Chen, Lu Gan, Wenwu Wang","doi":"10.1109/SSPD.2017.8233226","DOIUrl":"https://doi.org/10.1109/SSPD.2017.8233226","url":null,"abstract":"In traditional direction-of-arrival (DoA) estimation, the number of sources to be detected is widely assumed to be smaller than the number of physical sensors. In practice, however, the number of sources encountered may be greater than that of the sensors. To address this problem, nested array structure can be considered, however, the effects of mutual coupling between sensors may become significant when the sensors are located closely. Recently, the co-prime array structure has been developed to further enhance the uniform degrees-of- freedom (DoF) with less mutual coupling, by utilizing a co-prime pair of uniform linear subarrays. This paper proposes a pair of co-prime arrays with reduced sensors (CARS) structure, where the first array is shifted until symmetrical to the center (reference sensor) and the number of sensors in the second array can be reduced as compared to existing optimized co-prime array configurations, according to the odd and even of the co-prime number pair. Furthermore, with the CARS structure, much more uniform DoF can be detected. The feasibility of the proposed CARS structure is demonstrated by numerical results of DoA estimations for multiple stationary sources with noise.","PeriodicalId":404200,"journal":{"name":"2017 Sensor Signal Processing for Defence Conference (SSPD)","volume":"332 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115978033","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}