Journal of Information Technology Management (مدیریت فناوری اطلاعات)

This article discusses a device focused on images that enables users to recognise and detect many face-related features using the webcam. In this article, we are performing comprehensive and systemic studies to check the efficacy of these classic representation learning structures on class-imbalanced outcomes. We also show that deeper discrimination can be learned by creating a deep network that retains inter-cluster differences both and within groups. MobileNet, which provides both offline and real-time precision and speed to provide fast and consistent stable results, is the recently suggested Convolutional Neural network (CNN) model. The recently proposed Convolutional Neural Network (CNN) model is MobileNet, which has both offline and real-time accuracy and speed to provide fast and predictable real-time results. This also solved a problem related to the face that occurs in the identification and recognition of the face. This paper presents the different methods and models used by numerous researchers in literature to solve the issue of faces. They get a better result in using the highest number of layers. It is also noted that the combination of a machine learning approach with multiple image-based dataset increases the efficiency of the classifier to predict knowledge related to face detection and recognition

Now a day's software is the baseline for the success of any organization. There is a huge demand of quality software in the customer-oriented market. Regression testing makes it possible but it’s a costly affair. Regression test suite minimization is way to reduce this cost but it is NP hard problem. This paper proposes an effective approach for regression test suite minimization using Artificial Ecosystem Optimization algorithm. To improve its performance a modified Artificial Ecosystem Optimization algorithm is proposed for Test case minimization. To evaluate the performance of proposed approach experiment is conducted in controlled parameter setting on open-source subject program from SIR repository. The results are collected and analyzed in comparison to existing approaches using statistical test. The test results reflect the superiority of proposed approach.

The steadily growing dependency over network environment introduces risk over information flow. The continuous use of various applications makes it necessary to sustain a level of security to establish safe and secure communication amongst the organizations and other networks that is under the threat of intrusions. The detection of Intrusion is the major research problem faced in the area of information security, the objective is to scrutinize threats or intrusions to secure information in the network Intrusion detection system (IDS) is one of the key to conquer against unfamiliar intrusions where intruders continuously modify their pattern and methodologies. In this paper authors introduces Intrusion detection system (IDS) framework that is deployed over KDD Cup99 dataset by using machine learning algorithms as Support Vector Machine (SVM), Naïve Bayes and Random Forest for the purpose of improving the precision, accuracy and recall value to compute the best suited algorithm.

Object Detection has been one of the areas of interest of research community for over years and has made significant advances in its journey so far. There is a tremendous scope in the applications that would benefit with more innovations in the domain of object detection. Rapid growth in the field of machine learning has complemented the efforts in this area and in the recent times, research community has contributed a lot in real time object detection. In the current work, authors have implemented real time object detection and have made efforts to improve the accuracy of the detection mechanism. In the current research, we have used ssd_v2_inception_coco model as Single Shot Detection models deliver significantly better results. A dataset of more than 100 raw images is used for training and then xml files are generated using labellimg. Tensor flow records generated are passed through training pipelines using the proposed model. OpenCV captures real-time images and CNN performs convolution operations on images. The real time object detection delivers an accuracy of 92.7%, which is an improvement over some of the existing models already proposed earlier. Model detects hundreds of objects simultaneously. In the proposed model, accuracy of object detection significantly improvises over existing methodologies in practice. There is a substantial dataset to evaluate the accuracy of proposed model. The model may be readily useful for object detection applications including parking lots, human identification, and inventory management.

The data stored in data warehouse is used for making strategic decisions by integrating heterogeneous data from multiple sources at a single storage place, where data is used for querying and analysis purposes. With the advancement in the technology, Business Analytics and Business intelligence are being increasingly used in the financial sector for forecasting business decisions. Many On-Line Analytical Processing (OLAP) tools are being largely explored that can contribute to business decision making. Banking operation handles a lot of data as they operate daily. Subsequently, preparing of this tremendous volume of information requires instant and quick tools that can process the information at high processing speeds. Through this research paper, we represent the OLAP cube as one of the tools which can be used for business analysis. A case study of a bank and loan approval process is considered as one of the areas for implementation and analysis of business decisions using business intelligence which can serve as a key factor for increasing intelligence in the banking sector to make reliable business decisions. Higher management can forecast and predict various outcomes from the bank data warehouse using On-Line Analytical Processing technology which provided a multidimensional view of the data. Analysts can make business decisions by analyzing the reports and pattern trends in the graphs. Management can modify existing policies and procedures to increase the growth of the bank and can have a healthy competition with their competitors.

Smart applications with interconnected intelligent devices for sharing services arise serious security problems to the stability of this IoT complex and heterogeneous environment. Unless security considerations are analyzed and implemented properly in real time then IoT cannot be perceived as a pervasive network for the possible stakeholders. Current state of the art has analyzed trust-based security solutions as additional feature to application layer of the system which can identify and filter out the malicious nodes. In this paper we are proposing holistic trust management with edge computing mechanism to create trustworthy zones comprising different clusters, where Gateway on behalf of clusters will initiate migration of their nodes if falls below the defined Zone trust threshold level. The created zones are self-resilient against any malicious attacks and saves lots processing usage time and energy to address the security issues. By analyzing our proposed algorithm with other contemporary approaches to handle IoT security issues using trust mechanism, this approach is more precise in terms of protecting system against incurring malicious behavior, and also prolong the application operation duration by reducing communication and processing overhead.

World of technology provides everyone with a great outlet to give their opinion, using social media like Twitter and other platforms. This paper employs machine learning methods for text analysis to obtain sentiments of reviews by the people on twitter. Sentiment analysis of the text uses Natural language processing, a machine learning technique to tell the orientation of opinion of a piece of text. This system extracts attributes from the piece of writing such as a) The polarity of text, whether the speaker is criticizing or appreciating, b) The topic of discussion, subject of the text. A comparison of the work done so far on sentiment analysis on tweets has been shown. A detailed discussion on feature extraction and feature representation is provided. Comparison of six classifiers: Naïve Bayes, Decision Tree, Logistic Regression, Support Vector Machine, XGBoost and Random Forest, based on their accuracy depending upon type of feature, is shown. Moreover, this paper also provides sentiment analysis of political views and public opinion on lockdown in India. Tweets with ‘#lockdown’ are analysed for their sentiment categorically and a schematic analysis is shown.

In today’s era when a substitute for almost every product is readily available, acceptance and adoption of a new product in a market requires substantial amount of promotion. Here we formulate and analyze policies for promoting sales of a product in a market through optimal control theory problems. The market is partitioned into various segments depending upon multifarious demands of customers and promotion of the product is done segment-wise. The aim is to maximize the profits keeping in mind the demand requirements and the available budget for promotion. In order to provide a realistic model, the total available budget is taken to be imprecise. The optimal control model with fuzzy parameter is converted into crisp form using necessity and possibility constraints, and thereafter solved by using Pontryagin Maximum principle. To illustrate this technique, a numerical example is also considered by discretizing the model. The analysis also gives a deep insight of how the promotional effort should be planned by the decision makers keeping in mind the financial constrains without hindering the promotional effort at the end of the planning period. This paper mirrors the real time situation that could be faced by any industry, including that of software development, where budgets may have variable components and promotion of products may vary according to different regions and markets. The experimental data reveals that profitability can still be maximized if real-life constraints are applied in promotional planning by any industry.