International Journal of Machine Learning and Networked Collaborative Engineering http://mlnce.net/index.php/Home <p>International Journal of Machine Learning and Networked Collaborative Engineering (IJMLNCE) <strong>ISSN 2581-3242</strong> is a quarterly published, Open Access, peer-reviewed, international journal focuses on publishing authentic and unpublished quality research papers. This is a scientific journal which aims to promote quality and innovative research works, not limited to but focuses on the area of&nbsp; machine learning, collaborative engineering and allied areas. We publish original research articles, review articles and technical notes.</p> <p>The journal is registered with crossref&nbsp; <strong>10.30991/IJMLNCE</strong>. Each accepted manuscript shall be assigned a unique <strong>digital object identifier</strong>&nbsp; for identification. The abbreviated key title for our journal allocated by ISSN is &nbsp;<strong>Int. j. mach. learn. networked collab. eng.</strong> &nbsp;The journal appears&nbsp;in popular indexes like <strong>BASE (Bielefeld Academic Search Engine),&nbsp; CrossRef, CiteFactor, DRJI, Google Scholar, Index Copernicus, J-Gate, Portico, PKP-Index, ROAD, Scilit, Socolar. </strong>Our journals manuscript&nbsp; is also visible in ReserachGate &amp; Kudos.</p> <p>In this present era, the subjects like machine intelligence, machine learning and &nbsp;its associated domains are the first choice for the researchers and the industry peoples. In the past decade, the use of machine learning and its domain has drawn ample attention of the people which has generated a number of applications related to that area and hence it has become a very popular choice for the present day researchers. Machine intelligence or machine learning is also working towards improving the life style of the human beings nowadays. These are being used in various sectors like Healthcare, Space, Automation, Aviation industries and&nbsp;even in academia.&nbsp;</p> <p>With this insight, we are inviting you to consider <strong>IJMLNCE</strong> to publish your work. The Journal solicits latest research work carried out by researchers, academicians and industry practitioners in the domain of machine learning and collaborative engineering. It maintains a high standard in the term of similarity check and quality of paper. The originality of the work is highly appreciated. Each paper will be reviewed by the expert reviewers and in a multilayer approach. The journal editorial board believes in &nbsp;high ethical practices.</p> <p>The authors are invited to submit their unpublished manuscripts online only. The author will get final decision of manuscript <strong>within 06-12 weeks</strong> from the date of submission of manuscripts. Once the manuscript gets accepted, author will be asked to complete the copyright agreement. An e-mail communication is also sent to the author mail after verification of incorporation of all reviewers’ comments in term of their final camera-ready-paper; it will be published to the upcoming journal’s volumes. There are <strong>no publication fees; no article processing cost</strong> for publishing articles in this journal and the journal is open access<strong>.</strong>&nbsp;</p> CMR Institute of Technology (Autonomous), Hyderabad, Telangana, India en-US International Journal of Machine Learning and Networked Collaborative Engineering 2581-3242 <p>https://creativecommons.org/licenses/by/4.0/legalcode</p> IJMLNCE Editorial Note Volume No 02, Issue No 03 http://mlnce.net/index.php/Home/article/view/52 <p>The International Journal of Machine Learning and Networked Collaborative<br>Engineering (IJMLNCE) ISSN 2581-3242 continues to evolve and expand, receiving more<br>and more quality articles for evaluation and possible publication. We are happy to share<br>with you that apart from the existing indexing, we are able to place our journal manuscript<br>with two more indexing e.g., WorldCat-OCLC and Dimensions. We are now proud to<br>present the Volume No-02 Issue No-03, on this occasion, we have selected five interesting<br>papers that are framed in the scope of the journal, covering different aspects related to<br>machine learning and collaborative engineering.</p> <p><br>Küçük and Kiani [1] published a work entitled “Smart Advisor: An Intelligent<br>Inventory Prediction Based On Regression Model”. Authors focus on inventory<br>management of raw material and stock amounts in enterprises and present a model to<br>predict the demand of stock items by using a regression model. They analyze the outputs<br>of the model on a sample dataset to enable accurate estimation of the amount of stock to be<br>consumed in the future and to facilitate decision making.</p> <p>Küçük and Kiani [1] published a work entitled “Smart Advisor: An Intelligent<br>Inventory Prediction Based On Regression Model”. Authors focus on inventory<br>management of raw material and stock amounts in enterprises and present a model to<br>predict the demand of stock items by using a regression model. They analyze the outputs<br>of the model on a sample dataset to enable accurate estimation of the amount of stock to be<br>consumed in the future and to facilitate decision making.</p> <p>Kalaskar et al. [2] published a work entitled “Forecasting Ventricular Deviation in<br>Monitoring of Live ECG Signal”. This work shows the problem of the increasing number<br>of coronary artery diseases and ventricular arrhythmias cases. Authors propose a novel<br>platform for real time diagnosis of Ventricular Tachyarrhythmia with the help of a portable<br>electrocardiography device. In addition, it includes a solution for signal analysis and<br>cloud-based processing for the diagnosis.<br>International Journal of Machine Learning and Networked Collaborative Engineering, ISSN: 2581-3242, Vol.2 No. 3<br>iii</p> <p>Hoang et al. [3] published a work entitled “Cow Behavior Monitoring Using a<br>Multidimensional Acceleration Sensor and Multiclass SVM”. In this work, authors talk<br>about the health of cows based on their daily behavior. Thus, they propose an automated<br>monitoring system for suitable management. Cow’s activities are monitored by using a<br>multidimensional acceleration sensor and data is processed in a server through an<br>algorithm based on multiclass support vector machine.</p> <p>Kumar and Sairam [4] published a work entitled “Machine Learning Approach for<br>User Accounts Identification with Unwanted Information and data”. Authors focus on<br>identifying fake and suspicious accounts in Facebook in an effective way through a novel<br>architecture and a process flow. They also apply machine learning supervised models for<br>text classification and machine learning unsupervised models for image classification<br>respectively.</p> <p>Puri et al [5] published a work entitled “Internet of Things and Healthcare<br>Technologies: A Valuable Synergy from Design to Implementation”. In this work, authors<br>introduce a review on various enabling Internet of Medical Things technologies based on<br>the latest research work and technology available in the marketplace. The work also<br>analyzes different software platforms available in the field and the current challenges that<br>the industry is addressing.</p> Vijender Kumar Solanki Vicente Garcia Diaz ##submission.copyrightStatement## http://creativecommons.org/licenses/by-nc-nd/4.0 2018-10-11 2018-10-11 2 03 Smart Advisor: An Intelligent Inventory Prediction Based On Regression Model http://mlnce.net/index.php/Home/article/view/41 <p><em>Today one of the biggest expense items of the enterprises is raw material and stock amounts. Therefore, proper inventory management is very important for the profitability of the enterprises. Products that are not purchased on time cause interruptions in production and products left over because the expiration date has passed will also cause losses for businesses. Therefore, proper inventory management is critical for profit / loss situations of businesses. In this paper we presented a model to predict the demand of certain stock items by using a regression model. Our model can analysis and computer the prediction results on a given dataset. We evaluate our model on sample dataset and provide the analysis as well calculations over the existing inventory. Accurate analysis of stock consumption enables accurate estimation of the amount of stock to be consumed in the future. Accurate forecasting of stock consumption helps to take corrective steps in decision making. That is, it only allows you to buy in sufficient quantity when necessary. These stages are critical for economic stock management. For this reason, robust and adaptable approaches that can provide models ensure that stock consumption can be managed properly. It is difficult to find previously written sources on estimating the direction of stock movements. One of the most important reasons for this is the lack of incentive to make such studies in the academic literature. As a result, articles written about the subject and the work done have been limited, the results have not reached the reproducible level.</em></p> Ömer Küçük Farzad Kiani ##submission.copyrightStatement## http://creativecommons.org/licenses/by-nc-nd/4.0 2018-09-30 2018-09-30 2 03 86 94 Forecasting Ventricular Deviation in Monitoring of Live ECG Signal http://mlnce.net/index.php/Home/article/view/40 <p>Number of coronary artery disease cases and ventricular arrhythmias has been increasing in India. One of the common forms of cardiac disorder is Ventricular Tachycardia(VT). Due to improper&nbsp;electrical activities&nbsp;in the&nbsp;ventricles,&nbsp;consistent and&nbsp;rapid heart rate&nbsp;occurs, which produces Ventricular Tachycardia disorder. Short time period may not lead to severe heart problem, but the longer duration increases it may be a severe heart issue. In this disorder,for short durations it is possible that there may not be any symptoms or few symptoms with palpitations(increase / decrease in heart beats), dizziness or&nbsp;pain in chest. This disorder may result in&nbsp;cardiac arrest. This may also results into&nbsp;ventricular fibrillation.&nbsp;initially it was found that near about 7% of people in cardiac arrest are caused by Ventricular Tachycardia.&nbsp; In this work, a novel platform for real time diagnosis of Ventricular Tachyarrhythmia with the help of a portable Single lead ECG device is proposed. The gateway for signal analysis and combined edge and cloud based processing for the diagnosis is used. The biosignal captured by the device in LEAD II configuration is pushed to a cloud based diagnosis API through a mobile gateway. An algorithm in the cloud analyses this signal and finds out P, Q, R, S, T, their amplitude positions, onset and offset. From the onset and offset ST segment slope, elevation, depression, S morphology and ST segment variation statistics is captured and classified using rule based classifier. The work evaluates the performance of the classifier with Physionet dataset.&nbsp; The accuracy of the system was found to be 90% with accuracy of detecting normal ECG being 100% where as the accuracy of detection of VT being 80%. Results shows that the system is extremely efficient in detecting Ventricular Tachyarrhythmia and many related cardio vascular diseases.</p> Radha Bheemsen Rao Kalaskar DR. Bharati Harsoor Rupam Das ##submission.copyrightStatement## http://creativecommons.org/licenses/by-nc-nd/4.0 2018-09-30 2018-09-30 2 03 95 109 Cow Behavior Monitoring Using a Multidimensional Acceleration Sensor and Multiclass SVM http://mlnce.net/index.php/Home/article/view/46 <p>The daily behavior of dairy cows reflects the health and well being status.&nbsp; An&nbsp; automated monitoring system is needed for suitable management. It helps farmers to have a comprehensive view of the cattle healthy and manage large of cows. Acceleration sensors can be found in various kinds of applications. In this paper, we detect the cow’s activities by using a multidimensional acceleration sensor and multiclass support vector machine (SVM). The acceleration sensor is attached to the cow’s neck-collar in order to sense the movements in X, Y, and Z axes. The data is brought to a microprocessor for pre-processing, and join in a wireless sensor network (WSN) through a Zigbee module. After that, the data are transferred to the server. At the server, a suitable SVM algorithm is chosen and applied to classify four main behaviors: standing, lying, feeding and walking. A well know kernels, Radius Basic Function (RBF), is chosen. After that, a cross validation (k-fold) is used to measure the error and select the best fit model. The sensor is used to acquire experimental data from Vietnam Yellow cows in the cattle farm. The promising results with the average sensitivity of 87.51%, and the average precision of 90.24% confirm the reliability of our solution. The classification results can be automatically uploaded to the&nbsp; cloud internet and the farmer can easily access to check the status of his cows</p> Quang-Trung Hoang Phung Cong Phi Khanh Bui Trung Ninh Chu Thi Phuong Dung Tan Duc Tran ##submission.copyrightStatement## http://creativecommons.org/licenses/by-nc-nd/4.0 2018-09-24 2018-09-24 2 03 110 118 Machine Learning Approach for User Accounts Identification with Unwanted Information and data http://mlnce.net/index.php/Home/article/view/47 <p>Machine Learning used for many real time issues in many organizations and for the purpose of social media analytics machine learning models is used most prominently and to identify the genuine accounts and the information in the social media we are her with a new pattern of identification. In this pattern of model we are proposing some words which are hidden to identify the accounts with fake data and the some of the steps we are proposing will be help to identify the fake and unwanted accounts in Facebook in an efficient manner. Clustering in machine learning will be used and in prior to that we are proposing an efficient architecture and the process flow which can identify the fake and suspicious accounts in the social media. This article will be on machine learning implementations and will be working on OSN (online social networks). Our work will be more on Facebook which is maintaining more amount of accounts and identifying which are over ruling the rules of privacy and protection of the user content. Machine learning supervised models will be used for text classification and the image classification is performed by CNN of unsupervised learning and the explanation will be given in the implementation phase</p> Abhishek Kumar TVM SAIRAM ##submission.copyrightStatement## http://creativecommons.org/licenses/by-nc-nd/4.0 2018-09-24 2018-09-24 2 03 119 127 Internet of Things and Healthcare Technologies: A Valuable Synergy from Design to Implementation http://mlnce.net/index.php/Home/article/view/49 <p><em>Internet of Things (IoT) promises to be a reliable technology for the future. Healthcare is one of the fields which are rapidly developing new solutions. The synergy between IoT and healthcare promises to be very beneficial for human healthcare and evolved into a new field of research and development: the Internet of Medical Things (IoMT). This paper presents a review on various enabling IoMT technologies based on the latest publications and technology available in the marketplace. This article also analyzes the various software platforms available in the field of IoMT and the current challenges faced by the industry</em></p> Kalpna Gautam Vikram Puri Jolanda G Tromp Chung Van Le Nhu Gia Nguyen ##submission.copyrightStatement## http://creativecommons.org/licenses/by-nc-nd/4.0 2018-09-24 2018-09-24 2 03 128 142