درخت حوزه‌های تخصصی

K nearest neighbor algorithm is one of the most frequently used techniques in data mining for its integrity and performance. Though the KNN algorithm is highly effective in many cases, it has some essential deficiencies, which affects the classification accuracy of the algorithm. First, the effectiveness of the algorithm is affected by redundant and irrelevant features. Furthermore, this algorithm does not consider the differences between samples, which led the algorithm to have inaccurate predictions. In this paper, we proposed a novel scheme for improving the accuracy of the KNN classification algorithm based on the new weighting technique and stepwise feature selection. First, we used a stepwise feature selection method to eliminate irrelevant features and select highly correlated features with the class category. Then a new weighting method was proposed to give authority value to each sample in train dataset based on neighbor categories and Euclidean distances. This weighting approach gives a higher preference to samples that have neighbors with close Euclidean distance while they are in the same category, which can effectively increase the classification accuracy of the algorithm. We evaluated the accuracy rate of the proposed method and analyzed it with the traditional KNN algorithm and some similar works with the use of five real-world UCI datasets. The experiment results determined that the proposed scheme (denoted by WAD-KNN) performed better than the traditional KNN algorithm and considered approaches with the improvement of approximately 10% accuracy.

The quest for improving the software quality has given rise to various studies which focus on the enhancement of the quality of software through various processes. Code smells, which are indicators of the software quality have not been put to an extensive study for as to determine their role in the prediction of defects in the software. This study aims to investigate the role of code smells in prediction of non-faulty classes. We examine the Eclipse software with four versions (3.2, 3.3, 3.6, and 3.7) for metrics and smells. Further, different code smells, derived subjectively through iPlasma, are taken into conjugation and three efficient, but subjective models are developed to detect code smells on each of Random Forest, J48 and SVM machine learning algorithms. This model is then used to detect the absence of defects in the four Eclipse versions. The effect of balanced and unbalanced datasets is also examined for these four versions. The results suggest that the code smells can be a valuable feature in discriminating absence of defects in a software.

The Analytic visualization suggests representing knowledge during a visual type that may be charts, graphs, lists, or maps. The COVID 19 detection and analysis of spreading is very important for countries. Database management with respect to virus deep analysis is a critical task to the researcher through conventional algorithms. The RNA, DNA, and biological data are helping to the bio-inspired algorithm but its implementation can be complex by software tools. Therefore, an effective technique is required to cross over the above limitations. So that covid 19 pandemic data analysis is performed through FCNN (Fully conventional Neural Network) pre-training network. The dataset is collected from social media, Kaggle, and GitHub databases. At 1st stage, the auto stack encoding process is applied later same data is processed with FCNN deep learning classifier. In this research work, covid-pandemic affects parameters like infected persons, deaths, active cases, and recovering cases. The FCNN is take care of feature extraction, training, testing, and classification. Finally using a confusion matrix accuracy of 98.34%, sensitivity 97.63%, Recall 98.26%, and F measure 98.83% had been estimated.

It has been proved that in the era of globalization and the development of information technologies, the need to optimize the supply chain of services increases, since the integration of participants in this chain is performed without the use of modern management information systems. In the paper, with the help of logic-cognitive, structural-functional methods, structural-logical and imitation modelling, a management approach to simulation of business interaction in the integration of enterprises with elements of ERP-system and CBIP is developed and proposed, which allows you to create a flexible, adaptive and secure IT infrastructure , which increases the efficiency of the enterprise and allows you to optimize the management of relations with other participants in the service supply chain. As a result of this application of modern supply chain management systems, a synergistic effect is achieved that allows you to minimize the number of technological operations, shorten the production cycle and reduce the cost of services both for each individual enterprise and in the service supply chain as a whole.

Detecting occluded faces is a non-trivial problem for face detection in computer vision. This challenge becomes more difficult when the occlusion covers majority of the face. Despite the high performance of current state-of-the-art face detection algorithms, the detection of occluded and covered faces is an unsolved problem and is still worthy of study. In this paper, a deep-learning-face-detection model Niqab-Face-Detector is proposed along with context-based labeling technique for detecting unconstrained veiled faces such as faces covered with niqab. An experimental test was conducted to evaluate the performances of the proposed model using the Niqab-Face dataset. The experiment showed encouraging results and improved accuracy compared with state-of-the-art face detection algorithms

Persian language is one of the most widely used languages in the Web environment. Hence, the Persian Web includes invaluable information that is required to be retrieved effectively. Similar to other languages, ranking algorithms for the Persian Web content, deal with different challenges, such as applicability issues in real-world situations as well as the lack of user modeling. CF-Rank, as a recently proposed learning to rank data, aims to deal with such issues by the classifier fusion idea. CF-Rank generates a few click-through features, which provide a compact representation of a given primitive dataset. By constructing the primitive classifiers on each category of click-through features and aggregating their decisions by the use of information fusion techniques, CF-Rank has become a successful ranking algorithm in English datasets. In this paper, CF-Rank is customized for the Persian Web content. Evaluation results of this algorithm on the dotIR dataset indicate that the customized CF-Rank outperforms baseline rankings. Especially, the improvement is more noticeable at the top of ranked lists, which are observed most of the time by the Web users. According to the NDCG@1 and MAP evaluation criteria, comparing the CF-Rank with the preeminent baseline algorithm on the dotIR dataset indicates an improvement of 30 percent and 16.5 percent, respectively.

Wireless sensor networks (WSNs) are the sensor nodes that are generally interconnected and these nodes communicate wirelessly to collect the data from the environment around them. Sensor nodes are low-powered and distributed in a decentralized ADHOC manner. WSNs setup comes with some limitations such as energy constraints and the cooperative demands essential to perform multi-hop geographic routing for Internet of things (IoT) applications. Quality of Service (QoS) depends to a great extent on offering participating nodes an incentive for collaborating. The real-time applications of WSNs have potential design limitations such as energy and other QoS constraints in the context of IoT. This work formulates two different re-transmission strategies for optimized cross-layer design and also integrates the framework with a swarm intelligence technique assisted Bacteria Foraging Optimization (BFO) for efficient Cluster Head (CH) selection. The proposed work designs analytical modelling to realize the formulated concept and also simulates the computational design in a numerical computing tool. Finally, an extensive simulation is carried out using the MATLAB simulation tool. The obtained results show the effectiveness of the proposed system in terms of delay is reduced by 12%, throughput is increased to 10%, remaining energy of the network is increased to 11%, and packet delivery ratio of the proposed work in increased to 7-9% in comparison with the existing system.

The focus of this study is on lecturer’s use of online technology in the higher education context. Precisely, this study aims to understand the effect of personal innovativeness in IT (PI) in determining technology adoption behavior of lecturers in the higher education institutes in Sri Lanka. In this study, the variable of personal innovativeness in IT is integrated with the UTAUT framework and thereby the causal paths which effects VLE adoption intention of individuals is examined. Literature suggests that domain-specific innovativeness is a crucial factor in determining an individual’s adoption of technological innovations. Therefore, understanding the multifaceted effects of this factor along with other significant factors can help higher education institutes to effectively endorse online technology among lectures, generating productive payoffs in the long run. The quantitative method was used for data collection, which yielded # 1253 responses through the Question Pro online survey tool. The targeted respondents were the registered lecturers in higher education institutes of Sri Lanka, selected based on simple random sampling method. Structural equation modelling (SEM) procedure was employed for data analysis using IBM SPSS (ver.21) and AMOS (Ver.26). The structural path analysis resulted in partial mediation, confirming that “lecturer’s innovativeness in IT” exerts its influence on VLE adoption intention by altering the mediators set in the study. Further, the study validated a unique set of factors that determine lecturer’s acceptance of VLE in a higher education setting.

The purpose of this study is to develop proposals for the introduction of ecological, digital, professional, innovation and social public procurements in the national strategy on E-Public Procurement Reform and the strategy of procurements on the company-customer level. The relevance of this study is due to the need to ensure the development of “smart”, sustainable, inclusive economy, which will help reduce unemployment, poverty, facilitate access for people with disabilities to work, create opportunities for the education of young people and adults, stimulate innovations, meet expectations of citizens, solve environmental problems, carry out digital transformations taking into consideration the best world practices. The share of public procurements in expenditures of the state budget and gross domestic product of Ukraine, the dynamics of the procurement’s participants in the B2G segment is evaluated. In Ukraine, the largest share of expenditures falls on security and social protection, however, the prosperity index in these categories is critical (“red” zone). In order to form The E-Public Procurement Strategy, the best world practices of introducing innovative, environmental and social procurement criteria should be considered. Strategic directions of public procurement, namely – ecological, digital, professional, innovation and social, which provide sustainable and inclusive development of economy, are proposed.