Allaa R. Hilal

A Service-Oriented Architecture Suite for Sensor Management in Distributed Surveillance Systems

The increased popularity of the proactive security paradigm aggravated the need for distributed surveillance systems. These systems are built using smart sensor networks which cover large areas of civilian concentration. Such networks need intelligent management systems to control the large number of sensor nodes and the large volume of data. Sensor Management Frameworks (SMF) aim to coordinate the sensor nodes in a manner that improves the process of system control and situation awareness. Most SMFs proposed in literature are point solutions that do not use generic development architectures to allow reusability and extendability of different research projects. This work introduces an organizational development suite based on the service-oriented architecture to address the requirements of SMF from a stacked layer perspective. Furthermore, this paper discusses the important functional properties of such systems, and categorizes these functional properties according to their processing level. A case study was proposed that shows the extendability and reusability of the proposed organizational suite.

Fault Tolerant Wireless Sensor Networks using Adaptive Partitioning

Abstract Wireless Sensor Networks (WSNs) communicate over error-prone wireless links that make reliable data transmis–sion a challenging task. Retransmission functions are typically employed as a mechanism to provide data integrity and correctness, however, it has been proven that such mechanism is extremely inefficient, especially in environments characterized with high error rates. This paper proposes an adaptive partitioning technique that adds error correction at the Link Layer to minimize retransmission. This method involves partitioning frames such that errors can be isolated and corrected. The paper compares the proposed method with current retransmission protocols and justifies how the proposed model outperforms in certain scenarios.

A Scalable Sensor Management Architecture Using BDI Model for Pervasive Surveillance

Recent world events have amplified the need for improved safety and security to contend with natural and man-made threats. The universality and unpredictability of such threats have stimulated intense interest in smart pervasive surveillance systems. They are built by adopting smart sensor networks that cover large areas and can perform self-contained assessments of situations in the environment. However, such systems rely on a massive number of sensors with diverse capabilities but limited resources, e.g., power, processing, and storage. Thus, successful management of tasks hinges on the systems architecture. Sensor management architectures (SMAs) coordinate the sensor nodes and their resources in a manner that improves system control and situation awareness. This paper introduces a scalable and flexible SMA for many sensor management (SM) applications, particularly, pervasive surveillance. This novel SMA is called the extended hybrid architecture for SM (E-HASM), an architecture that combines the advantages of the holonic, federated, and market-based paradigms. The E-HASM models each node as an intelligent sensor by using the beliefs, desires, and intentions model and defines the interaction and cooperation among the nodes. The simulation results illustrate the performance of the E-HASM over a variety of security threats, background targets, and network sizes. The results prove that the proposed architecture is significantly more scalable and flexible than centralized architectures.

HASM: A hybrid architecture for sensor management in a distributed surveillance context

The increased popularity of the proactive security paradigm aggravated the need for pervasive surveillance systems. These systems are built using smart sensor networks which cover large areas of civilian concentration. Such networks need intelligent management systems to control the large number of sensor nodes and the large amount of data. Sensor Management Frameworks (SMF) aim to coordinate the sensor nodes in a manner that improves the process of system control and situation awareness. Large number of non-functional merits, i.e., autonomy, scalability, inter-operability, and others, can characterize SMFs. This paper provides a scalable and adaptable control architecture that is applicable in a variety of sensor management applications with a focus on tactical surveillance. The proposed Hybrid Architecture for Sensor Management (HASM) mixes the advantages of the holonic and federated paradigms. Experimental results illustrate the performance of the proposed architecture and show that the proposed paradigm is highly scalable compared to the centralized one.

A Holonic Federated Sensor Management Framework for pervasive surveillance systems

The increased popularity of the proactive security paradigm aggravated the need for pervasive surveillance systems. These systems are built using smart sensor networks which cover large areas of civilian concentration. Such networks need intelligent management systems to control the large number of sensor nodes and the large amount of data. Sensor Management Frameworks (SMF) aim to coordinate the sensor nodes in a manner that improves the process of system control and situation awareness. Large number of non-functional merits, i.e., autonomy, scalability, inter-operability, and others, can characterize SMFs. This paper proposes a taxonomy for these non-functional merits based on the design concepts. Furthermore, this paper discusses the important functional properties of such systems, and categorizes these functional properties according to their processing level. In addition, a scalable and adaptable control architecture that is applicable in a variety of sensor management applications with a focus on tactical surveillance is introduced. The proposed Holonic-Federated Sensor Management Framework (HF-SMF) mixes the advantages of the holonic and federated paradigms. Experimental results illustrate the performance of the proposed architecture and show that the proposed paradigm is highly scalable compared to the centralized one.

A Low-Cost Lane-Determination System Using GNSS/IMU Fusion and HMM-Based Multistage Map Matching

This paper presents a low-cost real-time lane-determination system that fuses micro-electromechanical systems inertial sensors (accelerometers and gyroscopes), global navigation satellite system (GNSS), and commercially available road network maps. The system can be used for intelligent transportation systems, telematics applications, and autonomous driving. The system does not depend on visual markings or highly precise GNSS technology, such as DGPS or RTK, and it does not need explicit lane-level resolution maps. High-resolution estimation of the vehicle’s position, velocity, and orientation is implemented by fusing inertial sensors with GNSS in a loosely coupled mode using extended Kalman filter. A curve-to-curve road-level map-matching is implemented using a hidden Markov model followed by a least-square regression step that estimates the vehicle’s lane. The system includes a lane-change detector based on inertial sensors and the filtered vehicle’s state. The system has been realized in real time and tested extensively on real-road data. Experiments showed robust map-matching in challenging road intersections and a 97.14% lane-determination success rate.

A Collaborative Energy-Aware Sensor Management System Using Team Theory

With limited battery supply, power is a scarce commodity in wireless sensor networks. Thus, to prolong the lifetime of the network, it is imperative that the sensor resources are managed effectively. This task is particularly challenging in heterogeneous sensor networks for which decisions and compromises regarding sensing strategies are to be made under time and resource constraints. In such networks, a sensor has to reason about its current state to take actions that are deemed appropriate with respect to its mission, its energy reserve, and the survivability of the overall network. Sensor Management controls and coordinates the use of the sensory suites in a manner that maximizes the success rate of the system in achieving its missions. This article focuses on formulating and developing an autonomous energy-aware sensor management system that strives to achieve network objectives while maximizing its lifetime. A team-theoretic formulation based on the Belief-Desire-Intention (BDI) model and the Joint Intention theory is proposed as a mechanism for effective and energy-aware collaborative decision-making. The proposed system models the collective behavior of the sensor nodes using the Joint Intention theory to enhance sensors’ collaboration and success rate. Moreover, the BDI modeling of the sensor operation and reasoning allows a sensor node to adapt to the environment dynamics, situation-criticality level, and availability of its own resources. The simulation scenario selected in this work is the surveillance of the Waterloo International Airport. Various experiments are conducted to investigate the effect of varying the network size, number of threats, threat agility, environment dynamism, as well as tracking quality and energy consumption, on the performance of the proposed system. The experimental results demonstrate the merits of the proposed approach compared to the state-of-the-art centralized approach adapted from Atia et al. [2011] and the localized approach in Hilal and Basir [2015] in terms of energy consumption, adaptability, and network lifetime. The results show that the proposed approach has 12 × less energy consumption than that of the popular centralized approach.

Multi-hop Interference-Aware Routing Protocol for Wireless Sensor Networks

Abstract Wireless Sensor Networks (WSN) have gained much attention in recent years, however, these networks suffer from limited energy supply and noisy wireless links. Thus, efficient energy management and noise handling are key requirements in designing WSNs. This paper proposes an interference-aware and energy-aware routing algorithm such that power dissipation is uniform among all sensors. The proposed algorithm utilizes time synchronization and traffic scheduling to avoid interference. This work mathematically models the problem as node clustering optimization. Simulation results show the optimized proportions of packets sent by nodes to ensure uniform energy dissipation, as well as, reduced interference within clusters.

A distributed sensor management for large-scale IoT indoor acoustic surveillance

Abstract The recent world events have underscored the need for large area surveillance systems. Such systems require effective sensing and collaborative decision-making to operate in highly dynamic environments with demanding time constraints. The Pervasive Internet of Things (IoT) is a novel paradigm that enables detailed characterization of the real physical applications. To this end, a pervasive IoT surveillance applications can offer an effective framework to collect situation-aware knowledge that is vital for planning effective security measures. Nevertheless, most state-of-the-art focus only on visual abnormal event recognition using centralized systems, thus, ignoring the need for distributed operation to enable large-scale IoT surveillance systems. This paper presents a novel Sensor Management (SM) framework for pervasive IoT acoustic surveillance, IntelliSurv, that automatically detects and localizes abnormal acoustic events in a distributed collaborative manner. The proposed framework coordinates the sensing resources using a novel team-theoretic SM, based on the Belief–Desire–Intention (BDI) model, for autonomous decision-making and resource allocation. The proposed abnormal event recognition module, using Support Vector Machines (SVM) and Linear Discriminate Analysis (LDA) classifiers, relies on audio information to recognize human screams or high-stress speech signals. The simulation scenario in this work is the surveillance of the Waterloo International Airport implemented using Jadex platform and Speech Under Simulated and Actual Stress (SUSAS) database. The simulation results show the merits of the proposed IntelliSurv framework, compared to the popular centralized systems, over varying network size, number of threats, Signal-to-Noise Ratios (SNR), tracking quality, and energy consumption.

Uniform illumination constraint enhancement and utility weighted voting fusion for ultrasonic breast lesion segmentation

The risk of breast cancer in women increases notably with age; one of every eight women is prone to get breast cancer in her lifetime. Ultrasonography is a noninvasive and painless medical imaging technique which achieves high lesion detection accuracy. However, ultrasound images are characterized by their specular nature, attenuation, speckle, shadows, and low contrast. This work proposes a six step algorithm to identify and segment lesions in ultrasound images. The proposed methodology uses radial intensity analysis followed by a uniform illumination constraint function to highlight the region of interest. The results of four segmentation techniques are fused to yield a consensus fused map. The final lesion boundary is the one that maximizes the utility function. The results show that the proposed algorithm outperforms the four tested segmentation algorithms, resulting in an average overlap of 71.3% and deviation of 2.2%with an average modification over each of the tested algorithms of 28%.