Video pornography detection through deep learning techniques and motion information

Due to latest advancements in the field of remote sensing, it becomes easier to acquire high quality images by the use of various satellites along with the sensing components. But the massive quantity of data poses a challenging issue to store and effectively transmit the remote sensing images. Therefore, image compression techniques can be utilized to process remote sensing images. In this aspect, vector quantization (VQ) can be employed for image compression and the widely applied VQ approach is Linde–Buzo–Gray (LBG) which creates a local optimum codebook for image construction. The process of constructing the codebook can be treated as the optimization issue and the metaheuristic algorithms can be utilized for resolving it. With this motivation, this article presents an intelligent satin bowerbird optimizer based compression technique (ISBO-CT) for remote sensing images. The goal of the ISBO-CT technique is to proficiently compress the remote sensing images by the effective design of codebook. Besides, the ISBO-CT technique makes use of satin bowerbird optimizer (SBO) with LBG approach is employed. The design of SBO algorithm for remote sensing image compression depicts the novelty of the work. To showcase the enhanced efficiency of ISBO-CT approach, an extensive range of simulations were applied and the outcomes reported the optimum performance of ISBO-CT technique related to the recent state of art image compression approaches. 

/pdf/intelligent-satin-bowerbird-optimizer-based-compression-1gzhbe3m.pdf

Intelligent Satin Bowerbird Optimizer Based Compression Technique for Remote Sensing Images

Deep learning for Arabic subjective sentiment analysis: Challenges and research opportunities

Energy-efficient chain-cluster based intelligent routing technique for Wireless Sensor Networks

Due to its potential applications and the density of the deployed sensors, distributed wireless sensor networks are one of the highly anticipated key contributors of the big data in the future. Consequently, massive data collected by the sensors beside the limited battery power are the main limitations imposed by such networks. In this paper, we consider a periodic sensor networks (PSNs) where sensors transmit their data to the sink on a periodic basis. We propose an efficient adaptive model of data collection dedicated to PSN, in order to increase the network lifetime and to reduce the huge amount of the collected data. The main idea behind this approach is to allow each sensor node to adapt its sampling rate to the physical changing dynamics. In this way, the oversampling can be minimized and the power efficiency of the overall network system can be further improved. The proposed method is based on the dependence of measurements variance while taking into account the residual energy that varies over time. We study three well known statistical tests based on One-Way Anova model. Then, we propose a multiple levels activity model that uses behavior functions modeled by modified Bezier curves to define application classes and allow for sampling adaptive rate. Experiments on real sensors data show that our approach can be effectively used to minimize the amount of data retrieved by the network and conserve energy of the sensors, without loss of fidelity/accuracy.

Residual energy-based adaptive data collection approach for periodic sensor networks

Recently wireless sensor network (WSN) has become one of the most interesting networking technologies, since it can be deployed without communication infrastructures. A sensor network is composed of a large number of sensor nodes; these nodes are responsible for supervision of the physical phenomenon and transmission of the periodical results to the base station. Therefore, improving the energy efficiency and maximizing the networking lifetime are the major challenges in this kind of networks. To deal with this, a hierarchical clustering scheme, called Location-Energy Spectral Cluster Algorithm (LESCA), is proposed in this paper. LESCA determines automatically the number of clusters in a network. It is based on spectral classification and considers both the residual energy and some properties of nodes. In fact, our approach uses the K-ways algorithm and proposes new features of the network nodes such as average energy, distance to BS, and distance to clusters centers in order to determine the clusters and to elect the cluster's heads of a WSN. The simulation results show that if the clusters are not constructed in an optimal way and/or the number of the clusters is greater or less than the optimal number of clusters, the total consumed energy of the
sensor network per round is increased exponentially.

https://downloads.hindawi.com/journals/jcnc/2015/170138.pdf

An Energy-Efficient Clustering Routing Algorithm Based on Geographic Position and Residual Energy for Wireless Sensor Network

In the area of health care, fall is a dangerous problem for aged persons. Sometimes, they are a serious cause of death. In addition to that, the number of aged persons will increase in the future. Therefore, it is necessary to develop an accurate system to detect fall. In this paper, we present spatiotemporal method to detect fall form videos filmed by surveillance cameras. Firstly, we computed key points of human skeleton. We calculated distances and angles between key points of each two pair sequences frames. After that, we applied Principal Component Analysis (PCA) to unify the dimension of features. Finally, we utilized Support Vector Machine (SVM), Decision Tree, Random Forest and K Nearest Neighbors (KNN) to classify features. We found that SVM is the best classifier to our method. The results of our algorithm are as follow: accuracy is 98.5%, sensitivity is 97% and the specificity is 100%.

/pdf/fall-detection-for-elderly-people-using-the-variation-of-key-cf1mxvggkp.pdf

Fall Detection for Elderly People Using the Variation of Key Points of Human Skeleton

Wireless sensor network has recently become an area of attractive research interest. It consists of low-cost, low power, and energy-constrained sensors responsible for monitoring a physical phenomenon and reporting to sink node where the end-user can access the data. Saving energy and therefore extending the wireless sensor network lifetime, involves great challenges. For these purposes, clustering techniques are largely used. Using many empirical successes of spectral clustering methods, we propose a new algorithm that we called Spectral Classification for Robust Clustering in Wireless Sensor Networks (SCRC-WSN). This protocol is a spectral partitioning method using graph theory technics with the aim to separate the network in a fixed optimal number of clusters. The cluster's nodes communicate with an elected node called cluster head, and then the cluster heads communicate the information to the base station. Defining the optimal number of clusters and changing dynamically the cluster head election probability are the SCRC-WSN strongest characteristics. In addition our proposed protocol is a centralized one witch take into account the node's residual energy to define the cluster heads. We studied the impact of node density on the robustness of the SCRC-WSN algorithm as well as its energy and its lifetime gains. Simulation results show that the proposed algorithm increases the lifetime of a whole network and presents more energy efficiency distribution compared to the Low-Energy Adaptive Clustering Hierarchy (LEACH) approach and the Centralized LEACH (LEACH-C)one.

A new spectral classification for robust clustering in wireless sensor networks

In this paper, we present a novel technique to estimate vehicle speed on highway using stereo images. First, traffic images are captured using calibrated and synchronized stereo cameras, then we detect moving vehicles on the left image by subtracting the background image. On each detected vehicle, we extract and match Speed Up Robust Features (SURF) in order to compute sparse depth maps. Finally, we get vehicle speed from vehicle depth variation using some geometric derivations. The experiments shows that the proposed algorithm has a satisfactory estimation of vehicle speed comparing to GPS ground truth with a speed error of 2 Km/h in the Moroccan environment.

Vehicle speed estimation using extracted SURF features from stereo images

Wireless Sensor Networks (WSNs) are composed of large number of sensor nodes that are randomly distributed in a region of interest. The nodes are responsible of the supervision of a physical phenomenon and periodic transmission of results to the sink. Energy saving results in extending the life of the network, which presents a great challenge of WSNs. To deal with this, a hierarchical clustering scheme, called K-Way Spectral Clustering Algorithm in Wireless Sensor Network (KSCA-WSN), is proposed in this paper. This algorithm is based on spectral classification; it also considers the residual energy, as well as some properties of the network nodes. Thus, our approach aims to seek for an ideal distribution of sensor nodes (clusters) and proposes new feautures to elect the appropriate cluster-heads. In term of extending the network lifetime and minimizing the energy consumption, the simulation results show an important improvement of the network performances with KSCA-WSN compared to other existing clustering methods. Keywords-Clustering; Graph theory; Spectral classification; Energy consumption.

/pdf/a-new-clustering-algorithm-in-wsn-based-on-spectral-3u0kea5hfa.pdf

Sanaa El Fkihi

Papers

An Energy-Efficient Clustering Routing Algorithm Based on Geographic Position and Residual Energy for Wireless Sensor Network

Fall Detection for Elderly People Using the Variation of Key Points of Human Skeleton

A new spectral classification for robust clustering in wireless sensor networks

Vehicle speed estimation using extracted SURF features from stereo images

A New Clustering Algorithm in WSN Based on Spectral Clustering and Residual Energy