A. Gokhan Yavuz

On coverage issues in directional sensor networks: A survey

The coverage optimization problem has been examined thoroughly for omni-directional sensor networks in the past decades. However, the coverage problem in directional sensor networks (DSN) has newly taken attraction, especially with the increasing number of wireless multimedia sensor network (WMSN) applications. Directional sensor nodes equipped with ultrasound, infrared, and video sensors differ from traditional omni-directional sensor nodes with their unique characteristics, such as angle of view, working direction, and line of sight (LoS) properties. Therefore, DSN applications require specific solutions and techniques for coverage enhancement. In this survey article, we mainly aim at categorizing available coverage optimization solutions and survey their problem definitions, assumptions, contributions, complexities and performance results. We categorize available studies about coverage enhancement into four categories. Target-based coverage enhancement, area-based coverage enhancement, coverage enhancement with guaranteed connectivity, and network lifetime prolonging. We define sensing models, design issues and challenges for directional sensor networks and describe their (dis)similarities to omni-directional sensor networks. We also give some information on the physical capabilities of directional sensors available on the market. Moreover, we specify the (dis)advantages of motility and mobility in terms of the coverage and network lifetime of DSNs.

Hybrid movement strategy in self-orienting directional sensor networks

The coverage problem in directional sensor networks (DSNs) introduces new challenges especially for randomly deployed networks. As many overlapped regions and coverage holes might occur after the initial deployment, self-orientation of the nodes is a necessity for randomly deployed DSNs. There exist two main approaches for the self-orientation of directional sensor nodes in DSNs 1], motility and mobility. Motility refers to the adjustment of the working direction of the nodes, whereas mobility describes the physical movement of the nodes. Most existing studies propose solutions based on the motility capability of the directional sensor nodes. On the other hand, mobility is a powerful feature offering great flexibility. Nevertheless, the high energy consumption of mobility discourages researchers to utilize this approach in their solutions. In this study, we propose a novel approach, a hybrid movement strategy (HMS), where we exploit motility/mobility in a cascaded manner for the coverage improvement in DSNs. The HMS improves the initial coverage up to 47% and achieves up to 7% more coverage than the motility only solution. Besides, it has provided at least 40% energy-saving compared to the mobility only solution in our scenarios.

Network Anomaly Detection with Stochastically Improved Autoencoder Based Models

Intrusion detection systems do not perform well when it comes to detecting zero-day attacks, therefore improving their performance in that regard is an active research topic. In this study, to detect zero-day attacks with high accuracy, we proposed two deep learning based anomaly detection models using autoencoder and denoising autoencoder respectively. The key factor that directly affects the accuracy of the proposed models is the threshold value which was determined using a stochastic approach rather than the approaches available in the current literature. The proposed models were tested using the KDDTest+ dataset contained in NSL-KDD, and we achieved an accuracy of 88.28% and 88.65% respectively. The obtained results show that, as a singular model, our proposed anomaly detection models outperform any other singular anomaly detection methods and they perform almost the same as the newly suggested hybrid anomaly detection models.

A new coverage improvement algorithm based on motility capability of directional sensor nodes

In directional sensor networks (DSNs), motility capability of a directional sensor node has a considerable impact on the coverage enhancement after the initial deployment. Since random deployment may result in overlapped field of views (FoVs) and occluded regions, directional sensor nodes with rotatable mechanisms may reorganize their working directions to improve the coverage. Our proposed algorithm, Attraction Forces of Uncovered Points (AFUP), aims at both minimizing the overlapped areas and facing the working directions towards the area of interest. AFUP is a distributed iterative algorithm and exploits the repel forces exerted by the uncovered points around the sensor nodes. The proposed algorithm improves the coverage by 18%-25% after the initial deployment. Moreover, AFUP outperforms three well-known area coverage enhancement methods [15] [19] [16] in terms of coverage improvement and overlap minimization. Our simulation results show that AFUP converges in five iterations in most of the scenarios.

Application identification via network traffic classification

Recent developments in Internet technology have led to an increased importance of network traffic classification. In this study, we used machine-learning methods for the identification of applications using network traffic classification. Contrary to existing studies, which classify applications into categories like FTP, Instant Messaging, etc., we tried to identify popular end-user applications such as Facebook, Twitter, Skype and many more individually. We are motivated by the fact that individual identification of applications is of high importance for network security, QoS enforcement, and trend analysis. For our tests, we used UNB ISCX Network Traffic dataset and our internal dataset, consisting of 14 and 13 well-known applications respectively. In our experiments, we evaluated four classification algorithms, namely J48, Random Forest, k-NN, and Bayes Net. With the complete set of 111 features, k-NN gave the best result for the ISCX Dataset as 93.94% of accuracy using the value of k as 1, and Random Forest gave the best result for the internal dataset as 90.87% of accuracy. During the course of this study, the initial numbers of features were successfully reduced to two sets of 12 features specific to each dataset without a compromise to the success. Moreover, we observed a 2% increase in the success rate for the internal dataset. We believe that individual application identification by applying machine-learning methods is a viable solution and currently we are investigating a two-tier approach to make it more resilient to in category confusion.

In situ image processing capabilities of ARM-based micro-controllers

Dealing with visual data is the key for environmental monitoring tasks in Wireless Multimedia Sensor Networks (WMSNs). Tasks such as object detection, recognition, and/or tracking do require extracting and using the right information from the inherently large amount of visual data. The widely accepted solution of legacy WSNs, transmitting the acquired data to a central base station for further processing, would render a WMSN totally useless because of the unacceptable use of bandwidth and energy. Therefore, we consider the in situ processing as a viable solution for WMSNs. However, processing power and memory capacity restrictions of existing multimedia sensor nodes along with their power consumption are the limiting factors for wide-spread use of in situ processing. Nevertheless, recent technological improvements and introduction of the new ARM cores encourage us to evaluate the image processing capabilities of ARM7/ARM9/ARM11 based micro-controllers for in situ processing in WMSNs. In this work, we first discussed the architectural design differences among the various ARM cores. Then we classified image processing algorithms into three categories. Then, we evaluated the performance of each microcontroller by running a set of basic image processing algorithms necessary for object detection, recognition, and/or tracking. The test results show that ARM11 runs up to 6–30 times faster than ARM9 and ARM7, respectively. Besides, ARM11 consumes up to 5–7 times less energy than ARM9 and ARM7 for the same type of operations.

Motility-based coverage enhancement in directional sensor networks

Random deployment may cause to the overlapped areas in directional sensor networks. The proposed algorithm Weighted Attraction Forces of Uncovered Points (W-AFUP), aims at both minimizing the overlapped areas and facing the working directions towards the area of interest. W-AFUP is a distributed iterative algorithm which exploits motility capability of the nodes. The proposed algorithm finds the appropriate working direction for each sensor node by using the repel forces exerted by the uncovered points around the sensor nodes. W-AFUP improves the coverage by %19-%37 after the initial deployment.

Image processing capabilities of new generation arm cores for WMSNs

Last decade witnessed the rapid development of Wireless Sensor Networks (WSNs). More recently, the availability of inexpensive hardware such as CMOS cameras and microphones that are able to ubiquitously capture multimedia content from the environment has fostered the development of Wireless Multimedia Sensor Networks (WMSNs). Nodes in such networks require significant amount of processing power to interpret the collected sensor data. Most of the currently available wireless multimedia sensor nodes are equipped with ARM7 core microcontrollers. On the other hand, ARM9 and ARM11 cores are viable alternatives, which deliver deterministic high performance and flexibility for demanding and cost-sensitive embedded applications. Thus, we evaluated the performance of the ARM9 and the ARM11 cores in terms of processing power and energy consumption. Our test results showed that the ARM11 core performed 3 to 4 times faster than the ARM9 core.

ETSI compliant GeoNetworking protocol layer implementation for IVC simulations

Inter-Vehicle Communication (IVC) is a promising technology for the next generation of automotive vehicles. Recent advancements in IVC enabled the use of a wide range of safety and infotainment applications. Due to the fact that practical experiments are often not feasible, simulation of network protocol behavior in VANET scenarios is strongly demanded to evaluate the applicability of developed applications. In this paper, we propose a ETSI complaint Geonetworking protocol layer on well known NCTUns simulation framework. We also discuss the implementation details of the Geonetworking protocol layer and evaluate the performance of our implementation. We tested our implementation for different simulation scenarios. A detailed discussion about the performance of our implementation is also given.

Image Processing Capabilities of ARM-based Micro-controllers for Visual Sensor Networks

Last decade witnessed the rapid development of Wireless Sensor Networks (WSNs). More recently, the availability of inexpensive hardware such as CMOS cameras and microphones that are able to ubiquitously capture multimedia content from the environment has fostered the development of Wireless Multimedia Sensor Networks (WMSNs) [1]. Nodes in such networks require significant amount of processing power to interpret the collected sensor data. Most of the currently available wireless multimedia sensor nodes are equipped with ARM7 core micro-controllers [2]. On the other hand, ARM9 core is a viable alternative, which delivers deterministic high performance and flexibility for demanding and cost-sensitive embedded applications. Thus, we evaluated the performance of the ARM7 core against the ARM9 core in terms of processing power and energy consumption. Our test results showed that architectural improvements of the ARM9 core alone resulted in a 30% speed-up in execution time, where the ARM9 core in general performed 9 to 11 times faster than the ARM7 core.