درخت حوزه‌های تخصصی

Dimensionality reduction is among the data mining process that is used to reduce the noise and complexity of features in various datasets. Feature selection (FS) is one of the most commonly used dimensionalities that reduces the unwanted features from the datasets. FS can be either wrapper or filter. Wrappers select subsets of the feature with better classification performance but are computationally expensive. On the other hand, filters are computationally fast but lack feature interaction among selected subsets of features which in turn affect the classification performance of the chosen subsets of features. This study proposes two concepts of information theory mutual information (MI). As well as entropy (E). Both were used together with binary cuckoo optimization algorithm BCOA (BCOA-MI and BCOA-EI). The target is to improve classification performance (reduce the error rate and computational complexity) on eight datasets with varying degrees of complexity. A support vector machine classifier was used to measure and computes the error rates of each of the datasets for both BCOA-MI and BCOA-E. The analysis of the results showed that BCOA-E selects a fewer number of features and performed better in terms of error rate. In contrast, BCOA-MI is computationally faster but chooses a larger number of features. Comparison with other methods found in the literature shows that the proposed BCOA-MI and BCOA-E performed better in terms of accuracy, the number of selected features, and execution time in most of the datasets.

The core capital of many businesses is their brand. Today companies not only use the brand to differentiate themselves from competitors in the market, but also use the brand to reach the minds and hearts of customers and create a special emotional relationship with them. In this study, due to the great differences between consumer markets and industrial markets, the factors affecting in industrial brand equity have been investigated. The statistical population includes all companies producing composite products and unsaturated polyester resins and vinyl esters in Iran. Due to the limitations of competitive industrial markets, the Convenience sampling method has been used and to test the research hypotheses, structural equation modeling based on the partial least squares method has been used. Research findings have shown that Consumers’ understanding of brand characteristics, Consumers’ brand evaluation, Consumers’ affective towards the brand and customer behavior towards the brand have a positive and significant effect on the brand equity. Also, brand awareness and brand association have a positive and significant effect on Consumers’ understanding of brand characteristics. Reputation, leadership, quality and distinction or uniqueness of the brand has a positive and significant effect on customers' evaluation of the brand. Brand satisfaction, brand commitment, brand trust and brand identity have a positive and significant effect on consumers’ affective towards the brand. Finally, willing to pay a price premium, Word – of – mouth (WOM) recommendation, brand usage and Acceptance of brand extensions has a positive and significant effect on customer behavior towards the brand.

As a vital practice in human resources management, workforce planning determines that the organization is needed how many workforces, when, and which position. Workforce planning is not formed in a vacuity, and job variables such as skill, ability, and knowledge affect the planning. This study examines workforce planning in the health sector concerning the workforce's flows such as recruitment, promotion, degradation, fired, retention, and termination of the contract according to the skill audit and the role of performance appraisal results in this program. For this purpose, a dynamic model has been applied that can provide optimal answers to the number of workforces required and the workforce's flows at any time during the planning periods. This model has been implemented in a hospital ward with two levels of hierarchy: nurses, supervisors, and nursing directors. The results show that the designed system can converge the existing values to the optimal values by noting delays by the optimal control model.

Trust establishment (TE) among sensor nodes has become a vital requirement to improve security, reliability, and successful cooperation. Existing trust management approaches for large scale WSN are failed due to their low cooperation (i.e., dependability), higher communication and memory overheads (i.e., resource inefficient). This paper provides a new and comprehensive hybrid trust estimation approach for large scale WSN employing clustering to improve cooperation, trustworthiness, and security by detecting selfish sensor nodes with reduced resource (memory, power) consumption. The proposed scheme consists of unique features like authentication based data trust, scheduler based node trust, and attack resistant by giving the high penalty and minimum reward during node misbehavior. A task scheduling mechanism is employed for scheduling the significant task to reduce computation overhead. The proposed trust model would be capable to provide security against blackhole attack, grey hole attack, and badmouthing attack. Moreover, the proposed trust model feasibility has been tested with MATLAB. Simulation results exhibit the great performance of our proposed approach in terms of trust evaluation cost, prevention, and detection of malicious nodes with the help of analyzing consistency in trust values and communication overhead.

In recent times amount of data is increasing rapidly and analysis of data is a must to come up with business decisions, predictions etc. It’s not just text are numbers which has to be stored properly. Data Types these days varies from images, video, social media data, surveys to blogs etc. When this is the case its mandatory to deal with Bigdata and to safeguard those Bigdata. Technologies available in Bigdata and Bitcoin helps us in achieving this. Bigdata technologies helps in storing the unstructured data effectively and processing of such voluminous data is taken care of. Hashing algorithms are used in Blockchain to keep the data safe. Hashing algorithms like SHA 256 are used to make it more secure. Its almost not possible to break the data available in Blockchain. Let’s try to secure the data even more using encryption algorithms to make sure that proper data is used for analysis etc.

Heart disease is stated as the world's biggest killer. The risk factors of this deadly disease are due to some bad habits such as being overweight, bad eating diet, smoking, assumption of alcohol, etc. Nevertheless, patients can live a healthy lifestyle if they have the proper guidance of persuasive-emotional featured technologies. In line with this, this study focuses on developing an emotional-persuasive habit-change support mobile application called BeHabit to improve heart disease patients’ lifestyles. Persuasive-emotional features are two different features that are integrated with BeHabit to distinguish this application from the existing ones. The proposed system is designed, implemented, tested, and evaluated by 10 users. In conclusion, the users are satisfied to used BeHabit to change their bad habits. Emotional and persuasive features that are integrated into BeHabit are the key to help patients to change their bad habits. BeHabit and the integrated feature can be used as a guideline for healthcare developers and providers for the improvement of mHealth services.

The improved model of the Agile Kanban (i-KAM) is developed to enhance the software project monitoring task when employing Agile project management (APM) approach. The i-KAM have been initially verified by 11 knowledge and domain experts. In consequence, it has been reconstructed and enhanced based on the remarks and recommendations provided by the experts. This paper aims to present the final evaluation results of i-KAM achieved from seven software practitioners participated in a focus group. The focus group method was selected because it is an empirical approach used in the evaluation studies conducted in the software engineering (SE) domain. Therefore, this method was employed to obtain the practitioners’ feedback on the proposed model. Results confirm the effectiveness of i-KAM, in which it can assist the project managers and team members in monitoring their projects’ progress effectively. In addition, it is indicated that i-KAM is an applicable model with easy and practical implementation. This study contributes to improve the task of monitoring software development projects within the APM environment. Accordingly, this would systematically facilitate the top managements’ work, and assist in making meaningful decisions regarding to the management of projects’ workflow. Practically, case studies will be carried out in different software development organizations (SDOs) to implement i-KAM in actual projects within real environments