Feature selection is the process of identifying relevant features and removing irrelevant and repetitive features with the aim of observing a subset of features that describe the problem well and with minimal loss of efficiency. One of the feature selection approaches is using optimization algorithms. This work provides a summary of some meta-heuristic feature selection methods proposed from 2018 to 2021 that were designed and implemented on a wide range of different data. The results of the study showed that some meta-heuristic algorithms alone cannot perfectly solve the feature selection problem on all types of datasets with an acceptable speed. In other words, depending on dataset, a special meta-heuristic algorithm should be used. تفاصيل المقالة

The smart city is one of the Internet of Thing-based applications that its use is increasing today. One of the requirements of this system is privacy which protects citizens from disclosure. This paper proposes to protect citizens' privacy by combining chaotic functions and a new method of steganography and image blocking. In this paper, two methods are proposed. In the first proposed method, randomly selected secret data bits are hidden in the pixels of image blocks that have also been randomly selected by the least significant bit method. In the second proposed method, the secret data and image are first converted to the DNA sequence, then the secret data genomes are replaced with the least significant genomes of the pixels of the image blocks that have also been randomly selected. Simulation results show that DNA use increases the quality of hidden images compared to without DNA methods and existing methods. تفاصيل المقالة

In recent years, the emergence of various social networks has led to the growth of social network users. However, activity in such networks depends on the level of trust that users have in each other. Therefore, trust is essential and important issue in these networks, especially when users interact with each other. In this article, we examine this issue and provide a method to evaluate it. It is not easy to measure the accuracy of trust for users who interact with social networks. Here, interactions are virtual. In this article, we have used the adaptive neuro-fuzzy inference system to evaluate trustworthiness by considering different personality attributes of users such as reliability, availability, interest, patience and adaptability. Using these features as input and based on the adaptive neuro-fuzzy inference system, we evaluated the trustworthiness of users in social network. The proposed adaptive neuro-fuzzy inference system is expandable because in this system, trust can be defined as a set of one or more personality attributes. Epinions social network dataset is also used to simulate and validate the proposed method. In the proposed method, the absolute mean value of error is less than 0.0095 and the value of F-score is more than 0.9884. Based on the obtained results and compared to the previous methods, the proposed adaptive neuro-fuzzy inference system shows an acceptable accuracy for evaluating the trustworthiness of users. تفاصيل المقالة

Provision of high-quality services to end users in a cost-effective way with minimum energy consumption is one of the main challenges facing cloud service providers. Accordingly, this paper presents an energy-efficient scheduling strategy in a QOS-Aware and cost-effective manner for real-time workflow programs in cloud environment. The proposed approach utilizes dynamic voltage and frequency scaling technique on multi-core nonhomogeneous processors to fill the gaps within time schedule. The aim is to develop an energy-aware strategy which, besides yielding accurate results, maintains the high quality of the delivered services in a standard and financially-rational manner. The proposed scheduling algorithm is compared with other basic strategies in terms of different service quality requirements. The performed experiments demonstrate that the proposed approach outperforms existing methods and can be vowed as a promising scheduling strategy. تفاصيل المقالة

توسعه کاربر نهایی (EUD) یک حوزه تحقیقاتی پویا در علوم کامپیوتر است که بر توانمندسازی کاربران نهایی برای ایجاد و اصلاح نرم‌افزار از طریق رویکردهای مختلف تمرکز دارد و دائماً با روش‌ها و ابزارهای جدید در حال تکامل است. برای افزایش مشارکت کاربر نهایی، پژوهشها، توسعه ابزارهای کاربر پسند برای کاربران نهایی به منظور طراحی رابط کاربری، به علاوۀ کد منبع نهایی که از تجزیه و تحلیل و تبدیل خودکار این رابط کاربری به دست می‌آید، را پیشنهاد می‌کنند. برنامه نویسی زبان طبیعی کنترل شده از ویرایش محدود شده ای از یک زبان طبیعی برای کدنویسی استفاده می کند. این رویکرد دسترسی به برنامه نویسی را از طریق فراهم کردن امکان کدنویسی به زبانی آشنا توسط کاربران نهایی و درعین حال حفظ دقت و وضوح لازم، افزایش می دهد. این پژوهش توسعه زبان CNUIML و تولید یک ویرایشگر برای آن را با استفاده از Xtext بررسی کرده و به خطاهای نحوی و تولید کد مقصد با استفاده از Xtext و Xtend می پردازد. زبان CNUIML برای توصیف رابط های برنامه کاربردی تحت وب، با تمرکز بر نیازهای سیستم و نگرانی های کاربر نهایی مورد بهره بردای قرار می گیرد. برنامه های کاربردی وب از صفحات و فرم های به هم پیوسته تشکیل شده اند که درختی از اشیاء را شکل می دهند. متا مدل یک برنامه وب شامل فرم، فرم فرعی، آیتم داده و محدوده دامنه و نوع مقادیر است. هر برنامه مجموعه ای از فرم ها با انواع مقادیر و دامنه های خاص هر یک است. تفاصيل المقالة