Ahmad Almogren

A two-stage approach for task and resource management in multimedia cloud environment

In recent years, multimedia cloud computing is becoming a promising technology that can effectively process multimedia services and provide quality of service (QoS) provisioning for multimedia applications from anywhere, at any time and on any device at lower costs. However, there are two major challenges exist in this emerging computing paradigm: one is task management, which maps multimedia tasks to virtual machines, and the other is resource management, which maps virtual machines (VMs) to physical servers. In this study, we aim at providing an efficient solution that jointly addresses these challenges. In particular, a queuing based approach for task management and a heuristic algorithm for resource management are proposed. By adopting allocation deadline in each VM request, both task manager and VM allocator receive better chances to optimize the cost while satisfying the constraints on the quality of multimedia service. Various simulations were conducted to validate the efficiency of the proposed task and resource management approaches. The results showed that the proposed solutions provided better performance as compared to the existing state-of-the-art approaches.

Facial Expression Recognition Utilizing Local Direction-Based Robust Features and Deep Belief Network

Emotional health plays very vital role to improve people’s quality of lives, especially for the elderly. Negative emotional states can lead to social or mental health problems. To cope with emotional health problems caused by negative emotions in daily life, we propose efficient facial expression recognition system to contribute in emotional healthcare system. Thus, facial expressions play a key role in our daily communications, and recent years have witnessed a great amount of research works for reliable facial expressions recognition (FER) systems. Therefore, facial expression evaluation or analysis from video information is very challenging and its accuracy depends on the extraction of robust features. In this paper, a unique feature extraction method is presented to extract distinguished features from the human face. For person independent expression recognition, depth video data is used as input to the system where in each frame, pixel intensities are distributed based on the distances to the camera. A novel robust feature extraction process is applied in this work which is named as local directional position pattern (LDPP). In LDPP, after extracting local directional strengths for each pixel such as applied in typical local directional pattern (LDP), top directional strength positions are considered in binary along with their strength sign bits. Considering top directional strength positions with strength signs in LDPP can differentiate edge pixels with bright as well as dark regions on their opposite sides by generating different patterns whereas typical LDP only considers directions representing the top strengths irrespective of their signs as well as position orders (i.e., directions with top strengths represent 1 and rest of them 0), which can generate the same patterns in this regard sometimes. Hence, LDP fails to distinguish edge pixels with opposite bright and dark regions in some cases which can be overcome by LDPP. Moreover, the LDPP capabilities are extended through principal component analysis (PCA) and generalized discriminant analysis (GDA) for better face characteristic illustration in expression. The proposed features are finally applied with deep belief network (DBN) for expression training and recognition.

Energy-sustainable relay node deployment in wireless sensor networks

Emergence of diverse renewable energy harvesting technologies and their incorporation into tiny sensor devices have given birth to Energy Harvesting Wireless Sensor Networks (EH-WSNs), where the problem domain has shifted from energy conservation to energy sustainability of the network. Renewable energy harvesting and depletion of sensor devices are stochastic and thus, energy availability in the devices is sporadic rather than continuous. Therefore, the optimal deployment of data routing devices (i.e., relay nodes) and their activity scheduling to ensure that, the data from all source sensors could be routed to the sink while keeping the network functional perpetually, is a challenging research problem. In this paper, we develop a multi-constraint mixed integer linear program (MILP) to minimize the number of relay nodes to be deployed in the network, while considering connectivity, sustainability and unpredictable energy harvesting and depletion rates. We refer to this problem as SMRMC (sustainable minimum-relay maximum-connectivity deployment) which is proved to be NP-hard. A light weight k-connected greedy solution to the SMRMC problem has been developed first for k = 1 , and thereafter, a generalized solution has been presented for any k (k ź 2) by constructing convex-polytopes among the existing relay nodes. Extensive simulation experiments have been conducted to validate the performance of the proposed deployment strategies. Performance studies carried out in MATLAB, show that the proposed SMRMC algorithms can achieve up to twice the network lifetime compared to state-of-the-art approaches whilst deploying minimum number of relay nodes.

Defending unknown attacks on cyber-physical systems by semi-supervised approach and available unlabeled data

Abstract Cyber-physical systems (CPS) are used increasingly in modern industrial systems. These systems currently encounter a significant threat of malicious activities created by malicious software intent on exploiting the fact that the software of such industrial systems is integrated with hardware and network systems. Malicious codes dynamically and continuously change their internal structure and attack patterns using obfuscation techniques, such as polymorphism and metamorphism, in order to bypass and hide from conventional malware detection engines. This requires continuously updating the database of the malware detection engine, which requires periodic effort from manual experts. This could limit the real-time protection of CPS. In addition, this also makes preserving the availability and integrity of the services provided by CPS against malicious code challenging because there is a demand for the development of specialized malware detection techniques for CPS. In this paper, we propose a semi-supervised approach that automatically integrates the knowledge about unknown malware from already available and cheap unlabeled data into the detection system. The novelty of the proposed approach is that it does not require expert effort to update the database of the detection engine. Instead, the dynamic changes in malware attack patterns are extracted by unsupervised clustering from already available unlabeled data. Then the extracted geometric information about the intrinsic attack characteristics of the clusters is integrated into the classification systems of the detection engine, which updates the detection system automatically. The proposed approach uses global K-means clustering with term-frequency (TF), inverse document frequency (IDF), and cosine similarity as a distance measure for extracting the cluster information and adding it to a support vector machine (SVM) classification system. The proposed approach has been tested extensively on a real malware data set for both static and dynamic malware features. The experiment results show that the proposed semi-supervised approach achieves higher accuracy over the existing supervised approaches for all classifiers. We note that the static feature-based semi-supervised approach can improve detection accuracy significantly. While applying the proposed semi-supervised approach with the run-time characteristics of dynamic feature analysis, the combined effect of dynamic analysis and the proposed approach further increases the detection accuracy of all classifiers by up to a 100% for the SVM and the random forest classifiers, thus exceeding the existing supervised approaches with similar features.

Efficient Computation Offloading Decision in Mobile Cloud Computing over 5G Network

Due to the significant advancement of Smartphone technology, the applications targeted for these devices are getting more and more complex and demanding of high power and resources. Mobile cloud computing (MCC) allows the Smart phones to perform these highly demanding tasks with the help of powerful cloud servers. However, to decide whether a given part of an application is cost-effective to execute in local mobile device or in the cloud server is a difficult problem in MCC. It is due to the trade-off between saving energy consumption while maintaining the strict latency requirements of applications. Currently, 5th generation mobile network (5G) is getting much attention, which can support increased network capacity, high data rate and low latency and can pave the way for solving the computation offloading problem in MCC. In this paper, we design an intelligent computation offloading system that takes tradeoff decisions for code offloading from a mobile device to cloud server over the 5G network. We develop a metric for tradeoff decision making that can maximize energy saving while maintain strict latency requirements of user applications in the 5G system. We evaluate the performances of the proposed system in a test-bed implementation, and the results show that it outperforms the state-of-the-art methods in terms of accuracy, computation and energy saving.

Moving Target Tracking through Distributed Clustering in Directional Sensor Networks

The problem of moving target tracking in directional sensor networks (DSNs) introduces new research challenges, including optimal selection of sensing and communication sectors of the directional sensor nodes, determination of the precise location of the target and an energy-efficient data collection mechanism. Existing solutions allow individual sensor nodes to detect the targets location through collaboration among neighboring nodes, where most of the sensors are activated and communicate with the sink. Therefore, they incur much overhead, loss of energy and reduced target tracking accuracy. In this paper, we have proposed a clustering algorithm, where distributed cluster heads coordinate their member nodes in optimizing the active sensing and communication directions of the nodes, precisely determining the target location by aggregating reported sensing data from multiple nodes and transferring the resultant location information to the sink. Thus, the proposed target tracking mechanism minimizes the sensing redundancy and maximizes the number of sleeping nodes in the network. We have also investigated the dynamic approach of activating sleeping nodes on-demand so that the moving target tracking accuracy can be enhanced while maximizing the network lifetime. We have carried out our extensive simulations in ns-3, and the results show that the proposed mechanism achieves higher performance compared to the state-of-the-art works.

A robust human activity recognition system using smartphone sensors and deep learning

Abstract In last few decades, human activity recognition grabbed considerable research attentions from a wide range of pattern recognition and human–computer interaction researchers due to its prominent applications such as smart home health care. For instance, activity recognition systems can be adopted in a smart home health care system to improve their rehabilitation processes of patients. There are various ways of using different sensors for human activity recognition in a smartly controlled environment. Among which, physical human activity recognition through wearable sensors provides valuable information about an individual’s degree of functional ability and lifestyle. In this paper, we present a smartphone inertial sensors-based approach for human activity recognition. Efficient features are first extracted from raw data. The features include mean, median, autoregressive coefficients, etc. The features are further processed by a kernel principal component analysis (KPCA) and linear discriminant analysis (LDA) to make them more robust. Finally, the features are trained with a Deep Belief Network (DBN) for successful activity recognition. The proposed approach was compared with traditional expression recognition approaches such as typical multiclass Support Vector Machine (SVM) and Artificial Neural Network (ANN) where it outperformed them.

Enhanced Living by Assessing Voice Pathology Using a Co-Occurrence Matrix

A large number of the population around the world suffers from various disabilities. Disabilities affect not only children but also adults of different professions. Smart technology can assist the disabled population and lead to a comfortable life in an enhanced living environment (ELE). In this paper, we propose an effective voice pathology assessment system that works in a smart home framework. The proposed system takes input from various sensors, and processes the acquired voice signals and electroglottography (EGG) signals. Co-occurrence matrices in different directions and neighborhoods from the spectrograms of these signals were obtained. Several features such as energy, entropy, contrast, and homogeneity from these matrices were calculated and fed into a Gaussian mixture model-based classifier. Experiments were performed with a publicly available database, namely, the Saarbrucken voice database. The results demonstrate the feasibility of the proposed system in light of its high accuracy and speed. The proposed system can be extended to assess other disabilities in an ELE.

Balanced Load Distribution With Energy Hole Avoidance in Underwater WSNs

Due to limited energy resources, energy balancing becomes an appealing requirement/challenge in Underwater Wireless Sensor Networks (UWSNs). In this paper, we present a Balanced Load Distribution (BLOAD) scheme to avoid energy holes created due to unbalanced energy consumption in UWSNs. Our proposed scheme prolongs the stability period and lifetime of the UWSNs. In BLOAD scheme, data (generated plus received) of underwater sensor nodes is divided into fractions. The transmission range of each sensor node is logically adjusted for evenly distributing the data fractions among the next hop neighbor nodes. Another distinct feature of BLOAD scheme is that each sensor node in the network sends a fraction of data directly to the sink by adjusting its transmission range and continuously reports data to the sink till its death even if an energy hole is created in its next hop region. We implement the BLOAD scheme, by varying the fractions of data using adjustable transmission ranges in homogeneous and heterogeneous simulation environments. Simulation results show that the BLOAD scheme outperforms the selected existing schemes in terms of stability period and network lifetime.

A Framework for a Context-Aware Elderly Entertainment Support System

Elderly people constitute a major portion of worlds population. Many of them are physically and mentally vulnerable and need continuous support for their health and well-being. There is a growing trend that these elderly people are placed in an ambient assisted living environment (AAL) with an aim to receive better care and support. In such settings, a lot of attention has been given to continuous health monitoring for maintaining physical health status. However, much less attention has been given toward understanding the entertainment needs of the elderly people, which is an important factor relevant to their mental health and joyful living. This paper thus addresses the entertainment needs of the elderly and proposes a framework of an elderly entertainment support system. The proposed framework enables different categories of residents (e.g., elderly people and caregivers) to access various media services in both implicit and explicit manner in order to enhance the quality of their living experience in different contexts. Our experimental results demonstrate the viability of the proposed framework. We believe that the proposed approach will establish the need to develop entertainment systems and services for the elderly people and allow us to sensibly address the problems associated with their independent, happy and active living.