{"title":"Network Intrusion Detection and Monitoring in Cloud Based Systems","authors":"M. Nanda, M. Patra","doi":"10.1109/ICAML48257.2019.00045","DOIUrl":"https://doi.org/10.1109/ICAML48257.2019.00045","url":null,"abstract":"In recent times there has been a shift towards Cloud based systems for varieties of applications. But, security concerns have always been a challenge for its widespread acceptance. Some of the major challenges relate to data security, deployment of applications, and security of infrastructural elements. In this paper, we have dealt with one of the important security issues, namely, network intrusion detection, in order to protect cloud infrastructure from malicious users. Our work involves continuous tracking of communication among virtual machines and analyse the packets transmitted over the network for possible intrusive attempts. We have developed appropriate mechanism to monitor the network and measure the sensitivity of certain network ports used for data transmission.","PeriodicalId":369667,"journal":{"name":"2019 International Conference on Applied Machine Learning (ICAML)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114907072","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":"Blood Vessel Detection Using Modified Multiscale MF-FDOG Filters for Diabetic Retinopathy","authors":"Debojyoti Mallick, Kundan Kumar, Sumanshu Agarwal","doi":"10.1109/ICAML48257.2019.00024","DOIUrl":"https://doi.org/10.1109/ICAML48257.2019.00024","url":null,"abstract":"Blindness in diabetic patients caused by retinopathy (characterized by an increase in the diameter and new branches of the blood vessels inside the retina) is a grave concern. Many efforts have been made for the early detection of the disease using various image processing techniques on retinal images. However, most of the methods are plagued with the false detection of the blood vessel pixels. Given that, here, we propose a modified matched filter with the first derivative of Gaussian. The method uses the top-hat transform and contrast limited histogram equalization. Further, we segment the modified multiscale matched filter response by using a binary threshold obtained from the first derivative of Gaussian. The method was assessed on a publicly available database (DRIVE database). As anticipated, the proposed method provides a higher accuracy compared to the literature. Moreover, a lesser false detection from the existing matched filters and its variants have been observed.","PeriodicalId":369667,"journal":{"name":"2019 International Conference on Applied Machine Learning (ICAML)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127636785","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}
Saumendra Kumar Mohapatra, Geetika Srivastava, M. Mohanty
{"title":"Arrhythmia Classification Using Deep Neural Network","authors":"Saumendra Kumar Mohapatra, Geetika Srivastava, M. Mohanty","doi":"10.1109/ICAML48257.2019.00062","DOIUrl":"https://doi.org/10.1109/ICAML48257.2019.00062","url":null,"abstract":"Research on biomedical signal to support the physician is boom of current research. In this paper, the cardiac signal is considered for arrhythmia detection and classification. The data from MIT-BIH database is taken for experiment. In first phase the signals preprocessed using different types of filters as low pass filter and median filter. Further the efficient technique discrete wavelet transform (DWT) is utilized to extract the features. As the feature set is large, deep neural network (DNN) is considered for the classification model. In this case the model can be used for medical data mining and self optimization process. Due to such advantages the model is chosen. The accuracy is found 98.66 % which is better than the earlier methods. It is exhibited in result section","PeriodicalId":369667,"journal":{"name":"2019 International Conference on Applied Machine Learning (ICAML)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126420978","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":"Automatic Power Quality Disturbances Detection and Recognition Using Empirical Wavelet Transform and Random Forest Method","authors":"M. Sahani","doi":"10.1109/ICAML48257.2019.00051","DOIUrl":"https://doi.org/10.1109/ICAML48257.2019.00051","url":null,"abstract":"In this paper, empirical Wavelet transform (EWT), Hilbert transform (HT) and random forest (RF) are integrated to reorganized the signal as well as simulation of power quality disturbances (PQDs) in a real time. EWT is a method used to figure out series of amplitude modulated frequency modulated (AM-FM) signals for different given signal, known as detail and approximate coefficients. Hilbert transform (HT) is used to extract the productive features from the detail and approximation coefficients. The terms standard deviation of magnitude, Hilbert energy array, Shannon entropy and crest factor are extracted from the Hilbert array and train to classifier random forest. RF is a quintet learning technique used for classification and regression purposes. The algorithm commences with the selection of many bootstrap samples from the data. Furthermore, the proposed less computational complex and superior classification accuracy based EWTHT-RF method is implemented in the digital signal processor (DSP) based platform to validate the feasibility of the proposed method.","PeriodicalId":369667,"journal":{"name":"2019 International Conference on Applied Machine Learning (ICAML)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121884764","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 Bi-Level Approach for Hyper-Parameter Tuning of an Evolutionary Extreme Learning Machine","authors":"Krishanu Maity, Satyabrata Maity, Nimisha Ghosh","doi":"10.1109/ICAML48257.2019.00032","DOIUrl":"https://doi.org/10.1109/ICAML48257.2019.00032","url":null,"abstract":"One of the critical challenges in the implementation of machine learning algorithm is hyperparameter optimization as performance of any machine learning model is sensitive to the setting of their hyperparametersr. Evolutionary Algorithms (EA) is widely used for hyperparameter optimization due to its efficient intellectual tuning strategies. The time complexity is appreciably changed with respect to the size of dataset used for training. On the other hand, large dataset is required for pursuing the better prediction. In this paper, we have proposed a methodology namely Bi-Level Evolutionary Extreme Learning Machine(bL-EELM) based on bi-level programming approach for tuning hyperparameter of an Evolutionary Extreme Learning Machine(EELM). we divided our problem into two levels. We consider an E-ELM module as a lower level optimization problem. In our upper level we placed a evolutionary module whose task is to create a population of hyperparameters and feed to lower Level as an input of EELM. We have chosen ten benchmark classification problems for the experiment and analysis of our proposed approach. Experimental results proofs that our proposed approach has better prediction accuracy as well as generalization performances compare to Extreme learning machine(ELM) and EELM.","PeriodicalId":369667,"journal":{"name":"2019 International Conference on Applied Machine Learning (ICAML)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122570979","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":"Role of Social Media Marketing on Consumer Purchase Behaviour: A Critical Analysis","authors":"Smita Satpathy, S. Patnaik","doi":"10.1109/ICAML48257.2019.00026","DOIUrl":"https://doi.org/10.1109/ICAML48257.2019.00026","url":null,"abstract":"For sharing and expressing opinions, an individual can use the virtual space in the web and Social media is a platform for such things; where discuss on certain issues, comments on different facts and comparing things with others. On the other hand, consumer marketing and brand management are connected with it and create much more complexity in this global, quickly growing technology-world. Also it influences consumer purchasing behavior and purchasing attitude. Currently, social media like facebook, youtube, etc., has gained remarkable attention in the last decade. Social media has become so important in affecting purchasing behavior of prospective customers that the companies have their own social site to handle to provide customers information they require and found it easily. The major focus on this paper is to describe the potential benefits associated with the application of machine learning techniques. Adopting a Neuro-Fuzzy system that, under uncertainty, has the capacity to process information towards better choices linked to virtual retail system parameter. Focus is on the particular field like business, education, society and youth how it affects society in a broad way.","PeriodicalId":369667,"journal":{"name":"2019 International Conference on Applied Machine Learning (ICAML)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126339877","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":"Importance of Cloud Deployment Model and Security Issues of Software as a Service (SaaS) for Cloud Computing","authors":"I. Nowrin, Fahima Khanam","doi":"10.1109/ICAML48257.2019.00042","DOIUrl":"https://doi.org/10.1109/ICAML48257.2019.00042","url":null,"abstract":"Cloud computing, now-a-days has become the jargon in the industry of IT. It is a model that gives worldwide access to shared pools of configurable resources over the internet. That means it run several applications or programs at the same time on more than one computer. The nature and usage of the cloud computing are developing rapidly both virtually and in reality. It is making things easier for the user of internet by many of its attractive features but these features, have not just only challenged the existing security system, but have also revealed new security issues. In this paper the deployment of cloud models are discussed . The cloud models are deployed as public cloud, private cloud and hybrid cloud. Each of these models have their own advantages and disadvantages. Cloud also provides some services like software as a service (SaaS), Platform as a service (PaaS), Infrastructure as a service (IaaS) . This paper is an insightful analysis of the features as well as the securities challenges of Software as a Service (SaaS) for cloud computing.","PeriodicalId":369667,"journal":{"name":"2019 International Conference on Applied Machine Learning (ICAML)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132789553","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":"Design of Bend-Limited Large-Mode Area Dispersion Shifted Few-Mode Fiber for Fast Communication","authors":"B. Behera, M. Mohanty","doi":"10.1109/ICAML48257.2019.00058","DOIUrl":"https://doi.org/10.1109/ICAML48257.2019.00058","url":null,"abstract":"We propose the novel design of ring core dispersion-shifted fiber (RC-DSF) for a few-mode operation. The design claims to support four linearly-polarized (LP) modes such as LP01, Lp11, LP02, and LP31over C+L-band with large-mode-area and low bending-loss. We numerically exhibit the design principles of RC-DSF and compare the results with the triangular profile DSF that supports only the fundamental LP01 mode with the lesser effective area. The modal properties of the proposed fiber have been investigated by using a finite difference method based solver. The proposed RC-DSF attains an effective area 250 µm2and bending-loss 0.002dB/km for LP01 mode witha bending radius of 20 mm at 1550 nm. The dispersion parameter is nearly zero at 1550 nm and the differential-mode group-delay(DMGD) between the guided modes is less than 0.04 ps/m. With this modal properties, the proposed few-mode fiber (FMF) can be chosen as a suitable agent for mode-division multiplexing (MDM).","PeriodicalId":369667,"journal":{"name":"2019 International Conference on Applied Machine Learning (ICAML)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131813416","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":"DOA Estimation on Sub-Array Geometry Using Model Based Approach","authors":"P. Raiguru, Rabindra Kishore Mishore","doi":"10.1109/ICAML48257.2019.00018","DOIUrl":"https://doi.org/10.1109/ICAML48257.2019.00018","url":null,"abstract":"The paper presents a model-based method to estimate the DOAs of multiple targets using various adaptive algorithms. The model the parameters of the LTI system are considered as the weight associating the adaptive filter. Further to improve the performance, the geometry of the Antenna array is altered which can reduce the computation complexity and the cost of the array system for practical consideration.","PeriodicalId":369667,"journal":{"name":"2019 International Conference on Applied Machine Learning (ICAML)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133582931","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":"Emulation of Virtual Inertia with the Dynamic Virtual Damping in Microgrids","authors":"Pritam Bhowmik, P. Rout","doi":"10.1109/ICAML48257.2019.00033","DOIUrl":"https://doi.org/10.1109/ICAML48257.2019.00033","url":null,"abstract":"Following the modern trend of the energy policies, renewable energy sources are being integrated in the power network in a distributed environment through the power electronic mediums. In regards to electrical power, these interfacing mediums can efficiently couple micro sources and electrical loads, sacrificing the available inertia. As a result, the transient stability of the distribution network is continually decaying. As a solution to this threat of the very near future, the study proposes a virtual spinning reserve, having the ability to emulate the inertia and the damping characteristics of a physical synchronous generator. A fuzzy tuned derivative control loop (FTDCL) is proposed to realise the virtual spinning reserve in the study. The proposed control scheme is comparatively evaluated against the conventional virtual synchronous generator (VSG), and found to be superior in performance.","PeriodicalId":369667,"journal":{"name":"2019 International Conference on Applied Machine Learning (ICAML)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125973700","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}