Voice denoising is the process of removing undesirable voices from the voice signal. Within the environmental noise and after the application of speech recognition system, the discriminative model finds it difficult to recognize the waveform of the voice signal. This is due to the fact that the environmental noise needs to use a suitable filter that does not affect the shaped waveform of the input microphone. This paper plans to build up a procedure for a discriminative model, using infinite impulse response filter (Butterworth filter) and local polynomial approximation (Savitzky-Golay) smoothing filter that is a polynomial regression on the signal values. Signal to noise ratio (SNR) was calculated after filtering to compare the results

     Sentiment Analysis is a research field that studies human opinion, sentiment, evaluation, and emotions towards entities such as products, services, organizations, events, topics, and their attributes. It is also a task of natural language processing. However, sentiment analysis research has mainly been carried out for the English language. Although the Arabic language is one of the most used languages on the Internet, only a few studies have focused on Arabic language sentiment analysis.

     In this paper, a review of the most important research works in the field of Arabic text sentiment analysis using deep learning algorithms is presented. This review illustrates the main steps used in these studies, which include

In this article, the numerical and approximate solutions for the nonlinear differential equation systems, represented by the epidemic SIR model, are determined. The effective iterative methods, namely the Daftardar-Jafari method (DJM), Temimi-Ansari method (TAM), and the Banach contraction method (BCM), are used to obtain the approximate solutions. The results showed many advantages over other iterative methods, such as Adomian decomposition method (ADM) and the variation iteration method (VIM) which were applied to the non-linear terms of the Adomian polynomial and the Lagrange multiplier, respectively. Furthermore, numerical solutions were obtained by using the fourth-orde Runge-Kutta (RK4), where the maximum remaining errors showed th

In recent years, the rapid development in the field of wireless technologies led to the appearance of a new topic, known as the Internet of things (IoT). The IoT applications can be found in various fields of our life, such as smart home, health care, smart building, and etc. In all these applications, the data collected from the real world are transmitted through the Internet; therefore, these data have become a target of many attacks and hackers. Hence, a secure communication must be provided to protect the transmitted data from unauthorized access. This paper focuses on designing a secure IoT system to protect the sensing data. In this system, the security is provided by the use of Lightweight AES encryption algorithm to encrypt the d

The study aims to build a water quality index that fits the Iraqi aquatic systems and reflects the environmental reality of Iraqi water. The developed Iraqi Water Quality Index (IQWQI) includes physical and chemical components. To build the IQWQI, Delphi method was used to communicate with local and global experts in water quality indices for their opinion regarding the best and most important parameter we can use in building the index and the established weight of each parameter. From the data obtained in this study, 70% were used for building the model and 30% for evaluating the model. Multiple scenarios were applied to the model inputs to study the effects of increasing parameters. The model was built 4 by 4 until it reached 17 parame

Botnet detection develops a challenging problem in numerous fields such as order, cybersecurity, law, finance, healthcare, and so on. The botnet signifies the group of co-operated Internet connected devices controlled by cyber criminals for starting co-ordinated attacks and applying various malicious events. While the botnet is seamlessly dynamic with developing counter-measures projected by both network and host-based detection techniques, the convention techniques are failed to attain sufficient safety to botnet threats. Thus, machine learning approaches are established for detecting and classifying botnets for cybersecurity. This article presents a novel dragonfly algorithm with multi-class support vector machines enabled botnet

Energy savings are very common in IoT sensor networks because IoT sensor nodes operate with their own limited battery. The data transmission in the IoT sensor nodes is very costly and consume much of the energy while the energy usage for data processing is considerably lower. There are several energy-saving strategies and principles, mainly dedicated to reducing the transmission of data. Therefore, with minimizing data transfers in IoT sensor networks, can conserve a considerable amount of energy. In this research, a Compression-Based Data Reduction (CBDR) technique was suggested which works in the level of IoT sensor nodes. The CBDR includes two stages of compression, a lossy SAX Quantization stage which reduces the dynamic range of the

Abstract: Word sense disambiguation (WSD) is a significant field in computational linguistics as it is indispensable for many language understanding applications. Automatic processing of documents is made difficult because of the fact that many of the terms it contain ambiguous. Word Sense Disambiguation (WSD) systems try to solve these ambiguities and find the correct meaning. Genetic algorithms can be active to resolve this problem since they have been effectively applied for many optimization problems. In this paper, genetic algorithms proposed to solve the word sense disambiguation problem that can automatically select the intended meaning of a word in context without any additional resource. The proposed algorithm is evaluated on a col

Imitation learning is an effective method for training an autonomous agent to accomplish a task by imitating expert behaviors in their demonstrations. However, traditional imitation learning methods require a large number of expert demonstrations in order to learn a complex behavior. Such a disadvantage has limited the potential of imitation learning in complex tasks where the expert demonstrations are not sufficient. In order to address the problem, we propose a Generative Adversarial Network-based model which is designed to learn optimal policies using only a single demonstration. The proposed model is evaluated on two simulated tasks in comparison with other methods. The results show that our proposed model is capable of completing co