Maryam Vahabi

Bio: Maryam Vahabi is an academic researcher from Mälardalen University College. The author has contributed to research in topics: Wireless sensor network & Key distribution in wireless sensor networks. The author has an hindex of 8, co-authored 33 publications receiving 166 citations. Previous affiliations of Maryam Vahabi include Universiti Putra Malaysia & Aster.

A Comparative Analysis of Hybrid Deep Learning Models for Human Activity Recognition.

Abstract: Recent advances in artificial intelligence and machine learning (ML) led to effective methods and tools for analyzing the human behavior. Human Activity Recognition (HAR) is one of the fields that has seen an explosive research interest among the ML community due to its wide range of applications. HAR is one of the most helpful technology tools to support the elderly’s daily life and to help people suffering from cognitive disorders, Parkinson’s disease, dementia, etc. It is also very useful in areas such as transportation, robotics and sports. Deep learning (DL) is a branch of ML based on complex Artificial Neural Networks (ANNs) that has demonstrated a high level of accuracy and performance in HAR. Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are two types of DL models widely used in the recent years to address the HAR problem. The purpose of this paper is to investigate the effectiveness of their integration in recognizing daily activities, e.g., walking. We analyze four hybrid models that integrate CNNs with four powerful RNNs, i.e., LSTMs, BiLSTMs, GRUs and BiGRUs. The outcomes of our experiments on the PAMAP2 dataset indicate that our proposed hybrid models achieve an outstanding level of performance with respect to several indicative measures, e.g., F-score, accuracy, sensitivity, and specificity.

An efficient placement of sinks and SDN controller nodes for optimizing the design cost of industrial IoT systems

Abstract: Recently, a growing trend has emerged toward using Internet of Things (IoT) in the context of industrial systems, which is referred to as industrial IoT. To deal with the time-critical requirements ...

A Heterogeneous IoT-Based Architecture for Remote Monitoring of Physiological and Environmental Parameters

Abstract: A heterogeneous Internet of Things (IoT) architecture for remote health monitoring (RHM) is proposed, that employs Bluetooth and IEEE 802.15.4 wireless connectivity. The RHM system encompasses Shimmer physiological sensors with Bluetooth radio, and OpenMote environmental sensors with IEEE 802.15.4 radio. This system architecture collects measurements in a relational database in a local server to implement a Fog node for fast data analysis as well as in a remote server in the Cloud.

SDN-TAP: An SDN-based traffic aware protocol for wireless sensor networks

Abstract: Congestion control is a challenging issue in wireless sensor networks with limited channel bandwidth. Thus, many protocols have been designed to provide a distributed traffic control during packet forwarding. However, all these approaches are applied to single-hop communication networks, ignoring the multi-hop restrictions. In this work, we take advantage of software defined networking paradigm by devising a controller node in such a way that it collects all the necessary information from wireless sensor network nodes. Thus, based on hop count and local traffic information, controller decides for possible flow path changes to evenly distribute the traffic. The evaluations revealed that the SDN-TAP outperforms conventional routing protocols by reducing packet loss rate up to 46%.

Low Energy Consumption MAC Protocol for Wireless Sensor Networks

Abstract: Recent technological advances in sensors, low power integrated circuits, and wireless communications have enabled the design of low-cost, lightweight, and intelligent physiological sensor nodes. The IEEE 802.15.4 is a new wireless personal area network standard designed for wireless monitoring and control applications. The fast progress of research on energy efficiency in wireless sensor networks, and the need to compare with the solutions adopted in the standards motivates the need for this work. In the analysis presented, the star network configuration of 802.15.4 standard at 868 MHz is considered for a Zigbee network. In this paper, a new MAC protocol, EMAC, has been proposed. We analyzed the active duration of the superframe and entered the sleep mode status inside this active period. By this mechanism, the idle listening will be decreased and leads to more energy efficiency.

Semantic Interoperability in Heterogeneous IoT Infrastructure for Healthcare

Abstract: Interoperability remains a significant burden to the developers of Internet of Things’ Systems. This is due to the fact that the IoT devices are highly heterogeneous in terms of underlying communication protocols, data formats, and technologies. Secondly due to lack of worldwide acceptable standards, interoperability tools remain limited. In this paper, we proposed an IoT based Semantic Interoperability Model (IoT-SIM) to provide Semantic Interoperability among heterogeneous IoT devices in healthcare domain. Physicians communicate their patients with heterogeneous IoT devices to monitor their current health status. Information between physician and patient is semantically annotated and communicated in a meaningful way. A lightweight model for semantic annotation of data using heterogeneous devices in IoT is proposed to provide annotations for data. Resource Description Framework (RDF) is a semantic web framework that is used to relate things using triples to make it semantically meaningful. RDF annotated patients’ data has made it semantically interoperable. SPARQL query is used to extract records from RDF graph. For simulation of system, we used Tableau, Gruff-6.2.0, and Mysql tools.

A federated learning system with enhanced feature extraction for human activity recognition

Abstract: With the rapid growth of mobile devices, wearable sensor-based human activity recognition (HAR) has become one of the hottest topics in the Internet of Things. However, it is challenging for traditional approaches to achieving high recognition accuracy while protecting users’ privacy and sensitive information. To this end, we design a federated learning system for HAR (HARFLS). Based on the FederatedAveraging method, HARFLS enables each user to handle its activity recognition task safely and collectively. However, the recognition accuracy largely depends on the system’s feature extraction ability. To capture sufficient features from HAR data, we design a perceptive extraction network (PEN) as the feature extractor for each user. PEN is mainly composed of a feature network and a relation network. The feature network, based on a convolutional block, is responsible for discovering local features from the HAR data while the relation network, a combination of long short-term memory (LSTM) and attention mechanism, focuses on mining global relationships hidden in the data. Four widely used datasets, i.e., WISDM, UCI_HAR 2012, OPPORTUNITY, and PAMAP2, are used for performance evaluation. Experimental results demonstrate that PEN outperforms 14 existing HAR algorithms on these datasets in terms of the F1-score; HARFLS with PEN obtains better recognition results on the WISDM and PAMAP2 datasets, compared with 11 existing federated learning systems with various feature extraction structures.

A Flexible and Pervasive IoT-Based Healthcare Platform for Physiological and Environmental Parameters Monitoring

Abstract: The concentration in the new era of healthcare is the medical Internet of Things (IoT) according to preventive and prediction ( $p^{2}~Health$ ). In large scale and general perspective, the effective parameters from behavioral, ambient, and physiological domains as the most influencing fields of interest in healthcare must be monitored. In personalized healthcare monitoring, wearables are playing an important role in terms of data measurement and collection. We aim at creating a configurable and adaptable platform for comprehensive parameters monitoring, according to the convenient mode of wearability. Hence, we develop an innovative wrist-worn prototype for ambient monitoring and a flexible IoT gateway. The prototype measures the most critical parameters from an ambient domain. In this platform, via IoT gateway as an intermediate hub between the wearables and the IoT server, bidirectional communication between the end user and medics is established in real time. In addition, the physician as the real-time observer of patients are given the possibility to set up the required parameters for measurement through the IoT gateway and activate/deactivate the sensors on the wearables. Therefore, depending on the target investigation, status of patients, requirements, and demands, medics can determine the setup parameters for measurement. Thus, the application of this platform is not limited to specific groups, but widely may be applied whether in daily routine or medical research investigation. Under the flexible IoT gateway, the new wearables can readily be integrated and synchronized into the platform. The users are not restricted to select only one specific product but there are alternatives as well. To support the solution, experimental results are provided.

Security in IoMT Communications: A Survey

Abstract: The Internet of Medical Things (IoMT) couples IoT technologies with healthcare services in order to support real-time, remote patient monitoring and treatment. However, the interconnectivity of critical medical devices with other systems in various network layers creates new opportunities for remote adversaries. Since most of the communication protocols have not been specifically designed for the needs of connected medical devices, there is a need to classify the available IoT communication technologies in terms of security. In this paper we classify IoT communication protocols, with respect to their application in IoMT. Then we describe the main characteristics of IoT communication protocols used at the perception, network and application layer of medical devices. We examine the inherent security characteristics and limitations of IoMT-specific communication protocols. Based on realistic attacks we identify available mitigation controls that may be applied to secure IoMT communications, as well as existing research and implementation gaps.