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%.

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.

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.

Fiber to the home (FTTH) passive optical network is one of the cost effective and effortlessly planning systems in the current era of communication systems. However, one of the substantial limitations of this optical communication network is the monitoring operation. It is essential to locate the fault branch in the network in order to take the required action to overcome the problem. Unfortunately, since the network is all passive, it is necessary to introduce a technique that should be passive and has the capacity to locate the fault location inside the network. In this paper, a methodology to localize the fault line was introduced, where a combination of Fiber Bragg Gratings was suggested, using this approach, the fault location can be easily determined among 36-branch, distributed in eight groups. Simulation results show that the broken line can be determined through monitoring the reflected signals from all the branches in the Central Office without paying any power to locate the leakage. In other words, it is easy to recognize the fault location by monitoring the power of the reflected signals, where after comprehensive simulations and power calculations, it was possible to put a threshold for that reflected power, hence, the fault branch, for any reason, may reflect power of less than that threshold, otherwise, the branch is not considered as broken.

The Intrusion Detection System (IDS) is an important feature that should be integrated in high density sensor networks, particularly in wireless sensor networks (WSNs). Dynamic routing information communication and an unprotected public media make them easy targets for a wide variety of security threats. IDSs are helpful tools that can detect and prevent system vulnerabilities in a network. Unfortunately, there is no possibility to construct advanced protective measures within the basic infrastructure of the WSN. There seem to be a variety of machine learning (ML) approaches that are used to combat the infiltration issues plaguing WSNs. The Slime Mould Algorithm (SMA) is a recently suggested ML approach for optimization problems. Therefore, in this paper, SMA will be integrated into an IDS for WSN for anomaly detection. The SMA’s role is to reduce the number of features in the dataset from 41 to five features. The classification was accomplished by two methods, Support Vector Machine with polynomial core and decision tree. The SMA showed comparable results based on the NSL-KDD dataset, where 99.39%, 0.61%, 99.36%, 99.42%, 99.33%, 0.58%, and 99.34%, corresponding to accuracy, error rate, sensitivity, specificity, precision, false positive rate, and F-measure, respectively, are obtained, which are significantly improved values when compared to other works.