Omar Abdulkareem Mahmood

This study introduces the concept of the combined software-defined networking (SDN) and clustering approach for wireless sensor networks (WSNs), which merges an SDN with adaptive clustering methodologies to advocate energy efficiency along with the management of the network. The proposed architecture utilizes a central SDN controller located at the base station (BS), which enables the creation of a flexible cluster based on the remaining energy and location of the sensor nodes (SNs). It happens through proper data and result transmission using an adaptive routing protocol; hence, it provides energy-efficient data aggregation at the CH. The performance evaluation shows that the combined SDN-based clustering approach for WSNs (CSCA-WSN) architecture lowers the average node energy use of nodes consumption by about 30%. Additionaly, it delays the first dead node (FDN) by 40%, which extends the network's lifespan and increases throughput by 25% compared to other traditional clustering protocols, such as LEACH. In sensor networks, the new architecture also reduces average delays (latency) by 20%, making it very suitable for real-time applications. The effectiveness of the integration of the SDN principle into WSNs in improving energy consumption and overall performance is presented.

Considering today's variety of technologies and devices connected to the network, a huge number of manufacturers, there are many problems of their interaction and the need to create and adopt specialized communication standards and protocols. This article is devoted to the description of various protocols proposed by the IEEE, IETF and ITU for use in the framework of the concept of the Internet of Things. The article includes a description of the protocols of the application, transport, network and data link layers of the TCP / IP model. It also discusses protocols designed specifically to meet IoT requirements. A brief description of the protocols and the principle of operation of each of them are given. This review article contributes to a more correct choice of protocols when building a network, detecting and managing devices, and establishing interaction between objects of the Internet of Things.

Сardiovascular diseases, also known as CVDs, currently rank as the primary incidence of mortality. The present approach for identifying illnesses involves the analysis of the Electrocardiogram (ECG), an electronic diagnostic device utilized to capture the rhythm of the heart. Regrettably, the process of seeking out specialists to conduct analysis on a substantial volume of electrocardiogram (ECG) data results in a significant depletion of medical capabilities. Hence, the utilization of deep learning algorithms for the identification of ECG characteristics has progressively gained prominence. Nevertheless, there exist certain limitations associated with these conventional approaches, which necessitate the need for manual characteristic identification, intricate models, and extensive training duration. This study presents a novel and effective approach for categorizing the five different types of heartbeats in the MIT-BIH Arrhythmia database. The proposed method involves the utilization of a 16-layer deep one-dimensional convolutional neural network, which exhibits both robustness and efficiency in its classification performance. Thus, the designed model is consisting of five-groups, first to fourth groups are the main feature extraction and mapping blocks, while the fifth group is fully connected and classification layers. The findings indicate that the model presented in this study has superior performance in terms of accuracy, precision, and F1-score. The proper classification of medical cases has a significant impact on the conservation of medical resources, hence positively influencing clinical practice. Additionally, the model training phase is characterized by its efficiency, since it does not significantly deplete resources.

Deep learning (DL), a relatively recent AI technique, has been successfully applied to the problem of automated modulation categorization (AMC), with promising results. An essential part of developing the spectrum-sensing capabilities needed by software-defined radio is carrying out radio signal classification jobs, which we did in this research by introducing a better deep neural architecture. Different detection techniques were utilized in the literature; however, DL neural networks are recently utilized in this field. Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) which is one variation of the RNN network, and other techniques are some of the employed DL architectures in the field of AMC. In this paper, Convolutional Neural Network (CNN) model has been built to automatically classify ten-modulation formats correctly. The suggested CNN network is constructed mainly of six-Convolutional layers. The overall number of trainable parameters in the proposed network is 1,757,962. Thus, the network accuracy, which was achieved during the training reached more than 90%. Python programming packages have been used to implement the suggested approach using Kaggle.com platform, which provides wide-range of facilities.

Congestion in the world’s traffic systems is a major issue that has far-reaching repercussions, including wasted time and money due to longer commutes and more frequent stops for gas. Modern scholarly challenges arise alongside chances to greatly enhance traffic prediction made possible by the integration of modern technologies into transportation systems. Various techniques have been utilized for the purpose of traffic flow prediction, including statistical, machine learning, and deep neural networks. In this paper, deep neural network architecture based on long short term memory (LSTM), bi-directional version, and gated recurrent units (GRUs) layers have been structured to build the deep neural network, in order to predict the performance of the traffic flow in four distinct junctions which has a great impact on the Internet of vehicles’ applications. The structure comprised of sixteen-layers, five of them are GRU-layers and one bi-directional LSTM-layer. The dataset employed in this work involved four congested junctions. The dataset extended from the first of November 2016 to 30th of June 2017. Cleaning and preprocessing operations were achieved on the dataset before feeding it to the designed deep neural network of this paper. Results show that the suggested method produced a comparable performance with respect to state-of-the art approaches.

Telecommunication networks are growing exponentially due to their significant role in civilization and industry. As a result of this very significant role, diverse applications have been appeared, which require secured links for data transmission. However, Internet-of-Things (IoT) devices are a substantial field that utilizes the wireless communication infrastructure. However, the IoT, besides the diversity of communications, are more vulnerable to attacks due to the physical distribution in real world. Attackers may prevent the services from running or even forward all of the critical data across the network. That is, an Intrusion Detection System (IDS) has to be integrated into the communication networks. In the literature, there are numerous methodologies to implement the IDSs. In this paper, two distinct models are proposed. In the first model, a custom Convolutional Neural Network (CNN) was constructed and combined with Long Short Term Memory (LSTM) deep network layers. The second model was built about the all fully connected layers (dense layers) to construct an Artificial Neural Network (ANN). Thus, the second model, which is a custom of an ANN layers with various dimensions, is proposed. Results were outstanding a compared to the Logistic Regression algorithm (LR), where an accuracy of 97.01% was obtained in the second model and 96.08% in the first model, compared to the LR algorithm, which showed an accuracy of 92.8%.

Computers and various imaging technologies effectively enhanced the diagnostic procedures of medical imaging, where various medical images enhance the early diagnosis, characterizing and discriminating of different health problems, which lead to efficient healthcare services and treatments. Digital image processing and medical images analysis can significantly support medical diagnosis by providing the necessary tools for automatic detection, extracting significant information and accurate measurement of visible abnormalities. However, there are many challenges related to medical images as well as challenges that arise during the various stages of image processing. This paper provides an overview of different challenges related to medical images and medical image processing. The most prominent and significant challenges are identified and introduced not to discourage the interested researchers in this field of image processing, but to fill the gap of missing a comprehensive overview on these challenges.