Localization is an important aspect in the field of wireless sensor networks (WSNs) that has developed significant research interest among academia and research community. Wireless sensor network is formed by a large number of tiny, low energy, limited processing capability and low-cost sensors that communicate with each other in ad-hoc fashion. The task of determining physical coordinates of sensor nodes in WSNs is known as localization or positioning and is a key factor in today’s communication systems to estimate the place of origin of events. As the requirement of the positioning accuracy for different applications varies, different localization methods are used in different applications and there are several challenges in some special scenarios such as forest fire detection. In this paper, we survey different measurement techniques and strategies for range based and range free localization with an emphasis on the latter. Further, we discuss different localization-based applications, where the estimation of the location information is crucial. Finally, a comprehensive discussion of the challenges such as accuracy, cost, complexity, and scalability are given.

Deep neural networks (DNNs), the integration of neural networks (NNs) and deep learning (DL), have proven highly efficient in executing numerous complex tasks, such as data and image classification. Because the multilayer in a nonlinearly separable data structure is not transparent, it is critical to develop a specific data classification model from a new and unexpected dataset. In this paper, we propose a novel approach using the concepts of DNN and decision tree (DT) for classifying nonlinear data. We first developed a decision tree-based neural network (DTBNN) model. Next, we extend our model to a decision tree-based deep neural network (DTBDNN), in which the multiple hidden layers in DNN are utilized. Using DNN, the DTBDNN model achieved higher accuracy compared to the related and relevant approaches. Our proposal achieves the optimal trainable weights and bias to build an efficient model for nonlinear data classification by combining the benefits of DT and NN. By conducting in-depth performance evaluations, we demonstrate the effectiveness and feasibility of the proposal by achieving good accuracy over different datasets.

With the advancement of the Long-Term Evolution (LTE) network and smart-phones, most of today’s internet content is delivered via cellular links. Due to the nature of wireless signal propagation, the capacity of the last hop link can vary within a short period of time. Unfortunately, Transmission Control Protocol (TCP) does not perform well in such scenarios, potentially leading to poor Quality of Service (QoS) (e.g., end-to-end throughput and delay) for the end user. In this work, we have studied the effect of Active Queue Management (AQM) based congestion control and intra LTE handover on the performance of different Medium Access Control (MAC) schedulers with TCP traffic by ns3 simulation. A proper AQM design in the Radio Link Control (RLC) buffer of eNB in the LTE network leads to the avoidance of forced drops and link under-utilization along with robustness to a variety of network traffic-loads. We first demonstrate that the original Random Early Detection (RED) linear dropping function cannot cope well with different traffic-load scenarios. Then, we establish a heuristic approach in which different non-linear functions are proposed with one parameter free to define. In our simulations, we demonstrate that the performance of different schedulers can be enhanced via proper dropping function.

Available bandwidth (ABW) estimation in wireless networks is a critical issue for quality-of-service (QoS) provisioning. Nowadays, a network path often contains at least one wireless link e.g., mobile users having wireless connection to the Internet through laptop PCs or smartphones. Most of the existing tools for measuring ABW have been developed and evaluated in wired networks. Since the characteristics of wired links and wireless links differ in many respects, such as fluctuations incapacity and stability due to the shared and unreliable nature of the wireless links, ABW estimation tools also need to be evaluated for network paths containing at least one wireless link. In this paper, we have extended our previous work, New Enhanced Available Bandwidth Estimation Technique (NEXT) by introducing a parameter-independent curve-fitting technique to detect the ABW from a one-way queuing delay signature and conducted a real test over a radio interface in a 4G/LTE mobile communication network. For the experiments, a commercial 4G/LTE mobile network of a Japanese mobile operator was used. Extensive simulations over an IEEE 802.11 network were also performed. Simulation results as well as real-world experimental results demonstrate that it is feasible to achieve reliable estimates under certain circumstances. Our extended approach, which we call NEXT -- FIT, has very good ABW estimation results under conditions of different packet sizes, dynamic wireless link rates, and channel noises.