درخت حوزه‌های تخصصی

The widespread use of E-commerce websites has drastically increased the need for automatic recommendation systems with machine learning. In recent years, many ML-based recommenders and analysers have been built; however, their scope is limited to using a single filtering technique and processing with clustering-based predictions. This paper aims to provide a systematic year-wise survey and evolution of these existing recommenders and analysers in specific deep learning-based hybrid filtering categories using movie datasets. They are compared to others based on their problem analysis, learning factors, data sets, performance, and limitations. Most contributions are found with collaborative filtering using user or item similarity and deep learning for the IMDB datasets. In this direction, this paper introduces a new and efficient Hybrid Filtering based Recommendation System using Deep Learning (HFRS-DL), which includes multiple layers and stages to provide a better solution for generating recommendations.

The paper considers the possibilities of optimizing the search for agricultural information based on Shannon information entropy criterion. A comparison of the degree of uncertainty of information search through the Internet – search systems with similar indicators of Ukrainian agricultural websites. According to the number of hit count in Ukraine in July 2020 to the search engine, which consists of 10 sources, and to agricultural websites (43 sources) by estimating entropy, a conclusion was made about the significant degree of dispersion of agricultural information sources. It should be emphasized that the artificial division into 4 categories (AgroMedia, Agrotrade web resources, Information and advisory resources, Specialized web resources) did not improve the situation according to the degree of uncertainty compared to the search engine system. As for the entropy index, for almost all 4 categories of entropy indices (heterogeneity or diversity) is close to the case of uniform distribution, i.e., the same hit count of all possible resources (their number for all categories is approximately the same 10-11). As a result of the analysis of the potential client base of electronic consulting, it can be quantified as 4,700,000 of agricultural households and about 50,000 small and medium-sized farms. The transition to the land market is likely to lead to a substantial increase in the number of the latter. It was demonstrated that the current educational level of household owners indicates both the need to increase this indicator and the presence of a close relationship with the existing system of professional advisory in Ukraine, which operates in recent years through self-sufficiency and uncertain financial support from central and regional authorities. The existing official database of advisors should be restructured in line with the call of the times to reduce the degree of uncertainty in finding a specialist of the desired profile.

  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.

Purpose: The current research aims to develop a model for digital transformation within the virtual space of the Broadcasting Organization in accordance with increasing the functionality of the virtual space among the audiences. Due to the lack of a model in this field in order to benefit from it, this research aims to extract the components of the model using the thematic qualitative method or theme analysis.Method: The statistical population includes 15 experts in media management and virtual space. To measure reliability, intra-subject agreement method (reliability between two coders/evaluators) was used to determine the reliability of the texts, and the reliability coefficient obtained for all three interviews and the total reliability coefficient was (0.87), surpassing the minimum acceptable threshold of 0.7, confirming the reliability of the codings and the interviews.Findings: The findings indicate that the model requirements consist of 6 main categories, 9 sub-categories, and 38 sub-categories essential for creating digital transformation and enhancing the interaction of the Islamic Republic of Iran's radio and television with the virtual space. The main categories of the model encompass content production, comprising six main components: content production (with six indicators), opportunities and threats (with 11 indicators), strengths and weaknesses (with 13 indicators), digital transformation components (with five indicators), platforms of introduction (with seven indicators), and consequences of digital transformation (with four indicators), totaling 46 indicators.Conclusion: The results show that establishing a favorable interaction in the virtual space and new media by creating a digital transformation in the national media is effective in attracting the audience and improving the performance of the national media and ensuring the satisfaction of the stakeholders.

Diabetes is a type of metabolic disorder with a high level of blood glucose. Due to the high blood sugar, the risk of heart-related diseases like heart attack and stroke got increased. The number of diabetic patients worldwide has increased significantly, and it is considered to be a major life-threatening disease worldwide. The diabetic disease cannot be cured but it can be controlled and managed by timely detection. Artificial Intelligence (AI) with Machine Learning (ML) empowers automatic early diabetes detection which is found to be much better than a manual method of diagnosis. At present, there are many research papers available on diabetes detection using ML techniques. This article aims to outline most of the literature related to ML techniques applied for diabetes prediction and summarize the related challenges. It also talks about the conclusions of the existing model and the benefits of the AI model. After a thorough screening method, 74 articles from the Scopus and Web of Science databases are selected for this study. This review article presents a clear outlook of diabetes detection which helps the researchers work in the area of automated diabetes prediction.

In the Industry 4.0 era, many pioneering industries are leveraging emerging technologies such as the Internet of Things (IoT) as solutions in the digital age. One of the largest and most active industries in Iran is the food industry, which stands to benefit significantly from these advancements. Achieving a sustainable competitive advantage is often possible at the level of the supply chain, where companies use information and communication technologies, such as IoT, to coordinate information, finances, and materials among supply chain actors. This research aimed to identify the key success factors (KSFs) for implementing IoT in the food supply chain. Firstly, through a systematic literature review, the KSFs for IoT implementation in the food supply chain were identified. To develop a measurement model, confirmatory factor analysis using structural equation modeling was employed, making the research applied-descriptive. A questionnaire was designed and completed by 142 members of the "Amadeh Laziz" supply chain (a case study), who were selected using a stratified random sampling method. Confirmatory factor analysis and LISREL 8.83 were then used to validate the proposed model. Finally, the cause-and-effect relationship between KSFs in IoT implementation in the food supply chain was analyzed using Grey DEMATEL. Based on the confirmatory factor analysis findings, the KSFs in implementing IoT in the food supply chain were identified as technical, economic, legal, cultural and social, security, applicability of IoT throughout the supply chain, and implementation of IoT applications. Thus, the measurement model included eight factors and 27 measures. According to the cause-and-effect relationship findings, "Implementation of IoT applications" and "Economic" factors were found to be mostly influenced, while "Applicability of IoT throughout the supply chain" and "Technical" factors were recognized as the most influential. The results of this research can guide food producers and technology policymakers in their supply chains and help avoid trial and error in IoT implementation by leveraging global and national experiences.

Multicasting is an important operation in software-defined wireless sensor networks (SDWSNs). In this operation, a group of nodes specified by their unique node identification numbers is supposed to receive the same multicast message at the approximately same time, if possible. These nodes are termed as multicast members or multicast destinations. They need not be physically close to one another to form a group. The present article proposes an energy-efficient scheduler exclusively for multicast operation in the SDWSN environment. Based on the advantages provided by underlying network architecture, a router can efficiently schedule multicast packets belonging to various multicast sessions. This promotes greenery in the network and significantly increases the packet delivery ratio. These claims are supported and justified by the experimental results presented in this paper. As far as the authors know, there is no multicast packet scheduler in the literature of wireless sensor networks or WSN. SDWSN is a more advanced version, and no multicast protocol has yet been proposed for these kinds of networks. Therefore, while designing the present fuzzy scheduler, we kept in mind all standard multicast protocols in the WSN environment.

Co-Saliency object detection is the process of identifying common and repetitive objects from the group of images. Earlier studies have looked over several state-of-art deep neural network methodologies for co-saliency detection approach. The Deep CNN approaches rely heavily on co-saliency detection due to their potent feature extraction capabilities both deep and wide. This article assess the performance of several state-of-art deep learning model (VGG19, Inceptionv3, modifiedResNet, MobileNetV2 and PoolNet) for the purpose of co-saliency detection among images from benchmark datasets. All the models were trained on   70% part of the dataset and remaining were used for testing purpose. Experimental results show that modified ResNetmodel outperforms getting 96.53% accuracy as compared to other state-of-the-art deep neural network models.

The article proposes a methodical approach to assessing the competitiveness of enterprises in the logistics infrastructure of the Black Sea region in the context of the strategy of the development of the Black Sea. The article is presented is the author's interpretation of the steel development of the territory and injected into the logistic infrastructure. It was proposed of the methodical approach to assessing the competitiveness of enterprises-moving enterprises in the development of the territory, as one of the stages of the methodology for assessing the development of the territory in the region. It have been identified Indicators for assessing sustainable development in assessing the competitiveness of key enterprises in the region and in terms of using the TOPSIS model. The application of the TOPSIS model allows to assess the value of the aggregate indicator of sustainable development of a region or territory, taking into account the impact of the level of competitiveness of its key enterprises. In the context of this approach, it is studied and evaluated the level of competitiveness of powerful enterprises of the Black Sea region, which form the logistics infrastructure of the region. It was  determined their influence on the strategy of sustainable development of the territory. This approach allowed to expand the methodology for assessing the assessment of sustainable development of the territory through the methodology of assessing the competitiveness of enterprises-engines of development of the territory, as one of the stages of the overall methodology.

After the Coronavirus diseases (COVID-19) outbreak, the Whole world witnessed the strangest buying behavior within the customers. Suddenly masks, hand sanitizers, and toilet papers became the priority list of the customers. High demand and lesser availability of essentials products like masks, toilet papers, and hand sanitizers create a chaotic situation inside the retail outlet's stores.  The buyer’s behavior and the chaotic scenario inside a retail outlet drew the attention of several consumer psychologists, academicians, and researchers. A panic buying situation is the most common behavior that exists in a time of crisis. This paper discusses the panic buying situation briefly during COVID-19. However, a few types of research and studies were captured in the panic buying behavior. The current study examined the factors that influenced the customers buying decisions during the COVID-19 outbreak and secondly, it examined to what extent the buying decision of a customer creates a panic situation. Furthermore, the study looked at the emotional and cognitive responses of the individuals which play a pivotal role in influencing customer decision making the journey. Qualitative content analysis and thematic methodology were considered for data analysis. The results indicated that fear and uncertainties were the key emotional responses; whereas rumors, fallacious thinking, and survivalist psychological were the key cognitive responses that influenced the customer decision journey.

Getting highly accurate output in biomedical data processing concerning biomedical signals and images is impossible because biomedical data are generated from various electronic and electrical resources that can deliver the data with noise. Filtering is widely used for signal and image processing applications in medical, multimedia, communications, biomedical electronics, and computer vision. The biggest problem in biomedical signal and image processing is developing a perfect filter for the system. Digital filters are more advanced in precision and stability than analog filters. Digital filters are getting more attention due to the increasing advancements in digital technologies. Hence, most medical image and signal processing techniques use digital filters for preprocessing tasks. This paper briefly explains various filters used in medical image and signal processing. Matlab is a famous mathematical, analytical software with a platform and built-in tools to design filters and experiment with different inputs. Even though this paper implements filters like, Mean, Median, Weighted Average, Guassian, and Bilateral in Python to verify their performance, a suitable filter can be selected for biomedical applications by comparing their performance.