درخت حوزه‌های تخصصی

  In the modern technological age, laptops are widely used for doing various day-to-day activities and getting updates all around us. The COVID-19 situation is playing a vital role in a dynamic shift in buyer behavior with multiple personal computing devices at home. Prioritizing and selecting appropriate laptop devices is difficult because there are several options of laptops that are available in the market, and these are equipped with the latest features to do gaming, designing, attending online classes, and performing office and other everyday tasks. There are multiple selection criteria that are complex in nature. MCDM (Multiple Criteria Decision Making) approaches can handle and analyze these complicated criteria. By using MCDM techniques, decision-making can be done to select the top-ranked alternative from among the available alternatives. This paper exhibits a group of two MCDM techniques; Best Worst Method (BWM) and Analytical Hierarchy Process (AHP), which have been used to evaluate relative weights of considered conflicting criteria such as brand, price, storage capacity, RAM, processor, weight, touch screen, Bluetooth, and screen size, and these weights are used in the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) for ranking and selecting the best product of laptops.

With the advent of user-generated text information on the Internet, text sentiment analysis plays an essential role in online business transactions. The expression of feelings and opinions depends on the domains, which have different distributions. In addition, each of these domains or so-called product groups has its vocabulary and peculiarities that make analysis difficult. Therefore, different methods and approaches have been developed in this area. However, most of the analysis involved a single-domain and few studies on cross-domain mood classification using deep neural networks have been performed. The aim of this study was therefore to examine the accuracy and transferability of deep learning frameworks for the cross-domain sentiment analysis of customer ratings for different product groups as well as the cross-domain sentiment classification in five categories “very positive”, “positive”, “neutral”, “negative” and “very negative”. Labels were extracted and weighted using the Long Short-Term Memory (LSTM) Recurrent Neural Network. In this study, the RNN LSTM network was used to implement a deep transfer learning framework because of its significant results in sentiment analysis. In addition, two different methods of text representation, BOW and CBOW were used. Based on the results, using deep learning models and transferring weights from the source domain to the target domain can be effective in cross-domain sentiment analysis.

Logistics has long been recognized as the main effective tool for generating competitive advantages in trading enterprises, and therefore there is an acute problem in finding strategic guidelines for improving logistics activities through the lens of organizational and economic support of logistic activity of a trading enterprise. The article compares the main reference models for the analysis of logistics activities and found the most appropriate for use - SCOR model, which identified the main indicators for evaluating the performance of logistics activities. An algorithm for determining the level of efficiency and performance of logistic activity have been constructed. According to the results of the study, the level of organizational and economic support, perormance and efficiency of logistic activity of trade enterprises of Ukraine of the sample population have been determined.

In recent privacy has emerged as one of the major concerns of deep learning, since it requires huge amount of personal data. Medical Image Analysis is one of the prominent areas where sensitive data are shared to a third party service provider. In this paper, a secure deep learning scheme called Metamorphosed Learning (MpLe) is proposed to protect the privacy of images in medical image analysis. An augmented convolutional layer and image morphing are two main components of MpLe scheme. Data providers morph the images without privacy information using image morphing component. The human unrecognizable image is then delivered to the service providers who then apply deep learning algorithms on morphed data using augmented convolution layer without any performance penalty. MpLe provides sturdy security and privacy with optimal computational overhead. The proposed scheme is experimented using VGG-16 network on CIFAR dataset. The performance of MpLe is compared with similar works such as GAZELLE and MiniONN and found that the MpLe attracts very less computational and data transmission overhead. MpLe is also analyzed for various adversarial attack and realized that the success rate is as low as . The efficiency of the proposed scheme is proved through experimental and performance analysis.

Enterprise Social Media (ESM) has been normally embraced by companies to boost team performance and agility for workers. The goal of this study is to investigate the mediating effect of workplace isolation on the relationships among usage ESM, employee agility and Team Performance along with exploration of the moderating influence of workplace Integrational study model. This research adds to corporate awareness in illustrating the impact of ESM use on team performance and employee agility based on theory of social exchange, theory of information processing and the theory of transactive memory. Cross-sectional survey was employed to collect data from telecommunication firms (public & private). 400 respondents were selected through purposive sampling technique and given close ended questionnaires, 348 questionnaires were selected for further analysis; through a number of statistical tools, after screening out the filled responses. It resulted in Suggesting ESM has a favorable effect on Employee Agility and Team Performance, but the negative relationships were observed among workplace isolation and employee agility and team performance. Further, Workplace Isolation mediated the relationship among ESM, Employee Agility and Team performance. Additionally, Workplace Integration strongly moderated the relationship between ESM and Workplace Isolation.  Experts and/or administrators should pay consideration to the impact of using ESM on agility and team performance of the workers. In addition, when implementing ESM to increase team performance they should concentrate on the extent of team diversity. By presenting the relationship between use of ESM, isolation in the workplace, workplace integration, agility of workers and performance of teams; it enriches the ESM use works by exploring the moderating functions of workplace integration while describing the beneficial consequences of workplace integration.

The positive effect of social networking, particularly social networking sites (SNSs), on improving the process of learning has been acknowledged by many recent types of research. The relationship between features and characteristics of SNSs and the development of students' social networking was of interest to past researchers. As social networking is primarily perceived as intelligent thought and action in both real and virtual environments, there seems to be a need for a qualitative exploration of the influential factors of students' social networking. The study has been conducted using the case study method to look at the identified factors retrieved from previous research. A semi-structured in-depth interview was used to investigate the viewpoints and experiences of socially proactive and successful students at Iranian universities. Findings explain students' social networking due to three factors categorized as central, causal, and contextual. The personal learning system has a critical position among the various factors affecting students' social networking. Therefore, despite the facilitating role of social networking in promoting the learning process, students' social networking would be useless without utilizing a personal learning system. We can see a dynamic and interactive cycle of learning and social networking in the university context. The research has been founded on critical consideration of previously studied factors affecting social networking that were mainly limited to online technologies according to qualitative exploration. As a result of this research, different learning and social networking levels regarding diverse meaning, function, and complexity were identified.

Agriculture is one of the essential sources of occupation and revenue in India. Conferring to existing statistics, most agriculturalists are facing severe losses due to poor farming yield. Farming activities are challenged by various environmental factors that affect agricultural productivity to a greater extent. The present farming situation is above the average of the process involves more biochemical bases for managing the diseases and other destructing facts. The foremost problems they are facing in day-to-day farming tasks are crop or plant diseases affecting productivity. Also, the growth of weeds along with field crops has been another challenge.  The technology has developed to rectify the problems using some machine learning algorithms like Random Forest algorithms, Decision trees, Naïve Bayes, KNN, K-Means clustering, Support vector machines. The result has been evaluated and observed through the performance evaluation metrics using confusion matrix, accuracy, precision, Sensitivity, specificity with the observations, research, and studies. The statistics have expressed the overall accuracy of 98% by achieving the detection of diseases in plants and by removing the weeds that ruin the growth of plants.

Learning effective segment depictions and resemblance measures are fundamental to the recuperation execution of a substance based picture recuperation (CBIR) structure. Regardless of wide research tries for a significant long time, it stays one of the most testing open gives that broadly impedes the achievements of real-world CBIR structures. The key test has been credited to the extraordinary "semantic hole" subject that happens between low-level photo pixels got by technologies and raised close semantic thoughts saw by a human. Among various techniques, AI has been successfully analyzed as a possible course to interface the semantic gap in the whole deal. Impelled by late triumphs of significant learning techniques for PC vision and various applications, in this paper, we try to address an open issue: if significant learning is a longing for spreading over the semantic gap in CBIR and how much updates in CBIR endeavors can be cultivated by exploring the front line significant learning methodology for learning feature depictions and likeness measures. Specifically, we explore a structure of significant learning with application to CBIR assignments with a wide game plan of definite examinations by investigating front line significant learning methodologies for CBIR endeavors under moved settings. From our exploratory examinations, we find some encouraging results and compress some huge bits of information for upcoming research.