IoT comprises sensors and other small devices interconnected locally and via the Internet. Typical IoT devices collect data from the environment through sensors, analyze it and act back on the physical world through actuators. We can find... more
IoT comprises sensors and other small devices interconnected locally and via the Internet. Typical IoT devices collect data from the environment through sensors, analyze it and act back on the physical world through actuators. We can find them integrated into home appliances, Healthcare, Control systems, and wearables. This chapter presents a variety of applications where IoT devices are used for anomaly detection and correction. We review recent advancements in Machine/Deep Learning Models and Techniques for Anomaly Detection in IoT networks. We describe significant in-depth applications in various domains, Anomaly Detection for IoT Time-Series Data, Cybersecurity, Healthcare, Smart city, and more. The number of connected devices is increasing daily; by 2025, there will be approximately 85 billion IoT devices, spreading everywhere in Manufacturing (40%), Medical (30%), Retail, and Security (20%). This significant shift toward the Internet of Things (IoT) has created opportunities f...
Research Interests:
Research Interests:
Free space wireless signal communication has the capacity and vast spread expansion to provide the right platform to support the growing demand for communication services. The propagation of electronic waves is the core of actual wireless... more
Free space wireless signal communication has the capacity and vast spread expansion to provide the right platform to support the growing demand for communication services. The propagation of electronic waves is the core of actual wireless communication links between ground stations and satellite ground communications. However, rain, dust, ground topography, urban surface, and other physical barriers weakened the transmitted signal strength and loss, reducing the quality and completion of the data transfer process. This work focuses on diffraction, weakening, and loss of signals when crossing urban areas surrounded by high buildings. We present a machine learning model for estimating the signal strength after crossing the urban areas. This assessment helps recommend the proper signal strength required when launching the signals towards the end station located in urban surroundings. We use a neural network system that derives patterns and rules from a given dataset containing simulate...
Research Interests:
Key distribution is a growing concern for symmetric cryptography and PKI certificate management. Most of the current key-distribution mechanisms assume the use of the Internet and LAN/WAN networks, which are exposed to security hazards... more
Key distribution is a growing concern for symmetric cryptography and PKI certificate management. Most of the current key-distribution mechanisms assume the use of the Internet and LAN/WAN networks, which are exposed to security hazards and other weaknesses. To overcome them, the use of comprehensive and robust cryptographic mechanisms, such as RSA are proposed. Another solution is the use of PKI/CA, which generates certificates and distributes them directly to the sender and receiver. This paper introduces a strict security approach covering the entire process, from key/certificate generation to the use of the received key by the other party. The approach is based on the following two elements: a. generation of a key/certificate in a highly secured environment provided by Intel-SGX technology. b. Key distribution using undetected high-speed optical camera communication (OCC), based on the rolling shutter effect of modern smart cameras. The Intel SGX processor enables the creation and protection of random keys and supports secure encryption and decoding of information. The key/certificate transfer is done by blinking LED lights in a specific sequence and frequency, following a coding system. The receiver decodes the received blinks to a bit string using a corresponding image processing application. This optical media ensures secure transfer without the ability to quote it. The experiment results show that this method is feasible, efficient, and implementable.
Research Interests:
IoT systems collect vast amounts of data which can be used in order to track and analyze the structure of future recorded data. However, due to limited computational power, bandwith, and storage capabilities, this data cannot be stored as... more
IoT systems collect vast amounts of data which can be used in order to track and analyze the structure of future recorded data. However, due to limited computational power, bandwith, and storage capabilities, this data cannot be stored as is, but rather must be reduced in such a way so that the abilities to analyze future data, based on past data, will not be compromised. We propose a parameterized method of sampling the data in an optimal way. Our method has three parameters — an averaging method for constructing an average data cycle from past observations, an envelope method for defining an interval around the average data cycle, and an entropy method for comparing new data cycles to the constructed envelope. These parameters can be adjusted according to the nature of the data, in order to find the optimal representation for classifying new cycles as well as for identifying anomalies and predicting future cycle behavior. In this work we concentrate on finding the optimal envelope, given an averaging method and an entropy method. We demonstrate with a case study of meteorological data regarding El Ninio years.
Research Interests:
Research Interests:
Research Interests:
The Internet of Things (IoT) is composed of a vast number of connected devices, interacting among them in real-time and high messaging volume. Such setting is in high probability to be targeted by malicious attackers. Therefore, robust... more
The Internet of Things (IoT) is composed of a vast number of connected devices, interacting among them in real-time and high messaging volume. Such setting is in high probability to be targeted by malicious attackers. Therefore, robust security measures are required. Encryption is one of the ways to prevent the exposure of the transmitted messages and authenticate it. The main challenge of implementing encryption, is the need to frequently and securely change the encryption keys, which require constant key construction and key distribution. IoT devices have poor memory, storage, and processing bandwidth. Most of the existing security solutions cannot be implemented on them, and so leading to lack of adequate security. Allowing safe interaction between any two IoT-devices, means having a unique encryption key per conversation. This requires frequent changes of the encryption keys. To increase the availability of keys at each IoT-device, we propose an ongoing key construction process that loads the network with a common key-pool. The protocol is scalable to ensure long term security sustainability and encryption availability. The proposed protocol is based on a probability analysis that ensures the existence of a common key between any pair of IoT devices in a predefine probability which is set by the system designer. The implementation proves the feasibility of our proposed security protocol for IoT networks.
Research Interests:
Access control systems using face recognition, are widely implemented. This technic lacks the ability to bypass it. To avoid it, an authentication process is required. In this paper we propose a new security image-signature, which... more
Access control systems using face recognition, are widely implemented. This technic lacks the ability to bypass it. To avoid it, an authentication process is required. In this paper we propose a new security image-signature, which authenticates the given image. The proposed signature is generated from the corresponding hyperspectral image layers. The process extracts unique patterns from the hyperspectral layers, these are collected to build a unique biometric signature for the related person. Experiments show the potential of enhancing image authentication using the proposed signature.
Research Interests:
Research Interests:
Research Interests: Computer Science, Internet of Things, Standardization, Interoperability, Smart Cities, and 11 morePhysical sciences, Engineering and Technology, Internet of Things (IoT), Computer Networks and Communications, Tk, Reference Architecture, Technology Standardization, Security Protocol, Sensing Technology, Computer and Information Science, and arXiv
Research Interests:
E-commerce sector has been the most promising one since its inception in the 1970's. E-commerce ecosystem is a complex arrangement of different tools and systems making the entire system full of complexities. The higher the rate of a... more
E-commerce sector has been the most promising one since its inception in the 1970's. E-commerce ecosystem is a complex arrangement of different tools and systems making the entire system full of complexities. The higher the rate of a complex system in any business operations, the higher are the stakes of risk. The E-Commerce sector is no exception and is constantly barraged by risks due to strategic, operational, and financial hiccups. The Internet has not only accelerated the E-Commerce ecosystem but has also given a new set of threats which requires dynamic detection and Fixes. The major challenge faced by this sector is related to a risk of revenue loss due to revenue leakages in the area of network /system security and cyber frauds. Hence the objective of this paper is to explore sources of revenue leakages happening because of cyber frauds and technical failures and proposes probable solutions to mitigate the revenue loss.
Research Interests:
Optical Communication (OC) for data transmission was introduced more than 30 years ago. It employs two main technologies, fiber optics using a physical wire and Free Space Optical (FSO) wireless transmission. Fiber optics has been well... more
Optical Communication (OC) for data transmission was introduced more than 30 years ago. It employs two main technologies, fiber optics using a physical wire and Free Space Optical (FSO) wireless transmission. Fiber optics has been well developed over the years in terms of distance, bandwidth, speed, reliability, and other enhancements that contribute to its use. Recent developments in FSO transmission has made it the mainstream and a better alternative compared to RF wireless transmission, concerning all parameters. In this chapter, we focus on advancements in OC that represent innovative ideas of how to enable new methods of secured optical data transmission in different ways and not simply as an extension to current methods and technologies.
Research Interests:
Free-space communication is a leading component in global communications. Its advantages relate to a broader signal spread, no wiring, and ease of engagement. Satellite communication services became recently attractive to mega-companies... more
Free-space communication is a leading component in global communications. Its advantages relate to a broader signal spread, no wiring, and ease of engagement. Satellite communication services became recently attractive to mega-companies that foresee an excellent opportunity to connect disconnected remote regions, serve emerging machine-to-machine communication, Internet-of-things connectivity, and more. Satellite communication links suffer from arbitrary weather phenomena such as clouds, rain, snow, fog, and dust. In addition, when signals approach the ground station, it has to overcome buildings blocking the direct access to the ground station. Therefore, satellites commonly use redundant signal strength to ensure constant and continuous signal transmission, resulting in excess energy consumption, challenging the limited power capacity generated by solar energy or the fixed amount of fuel. This research proposes LTSM, an artificial recurrent neural network technology that provides ...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Device-to-Device (D2D) communications enable a wider set of applications and use cases in the Internet of Things (IoT) paradigm. Without the presence of Access Points (APs), Wi- Fi Direct, also known as Wi-Fi Peer-to-Peer (P2P), becomes... more
Device-to-Device (D2D) communications enable a wider set of applications and use cases in the Internet of Things (IoT) paradigm. Without the presence of Access Points (APs), Wi- Fi Direct, also known as Wi-Fi Peer-to-Peer (P2P), becomes an intrinsic facilitator for IoT applications due to its popularity. In particular, the P2P group owner (GO) plays the role of the AP and is responsible for making connections with P2P group client (GC). In IoT paradigm, power control should be carefully examined to prevent significant power drop on both Wi-Fi P2P GO and GC. By leveraging the information of connections such as received signal strength and retry count, this paper proposes two novel power control mechanisms for Wi-Fi P2P connections in IoT paradigm. We first design a threshold-based mechanism, which limits the maximum number of connection retries to eliminate unnecessary power consumption. However, considering the dynamic change of wireless condition, an adaptive power control mechanism is proposed to further reduce the waste of energy. We establish an intensive experiment by practically implementing both mechanisms in Wi-Fi P2P devices. The experiment results show that the proposed mechanisms can significantly reduce the power consumption and thus makes Wi-Fi P2P connection more efficient for IoT applications.
Research Interests:
Free-space communication is a leading component in global communications. Its advantages relate to a broader signal spread, no wiring, and ease of engagement. However, satellite communication links suffer from arbitrary weather phenomena... more
Free-space communication is a leading component in global communications. Its advantages relate to a broader signal spread, no wiring, and ease of engagement. However, satellite communication links suffer from arbitrary weather phenomena such as clouds, rain, snow, fog, and dust. Therefore, satellites commonly use redundant signal strength to ensure constant and continuous signal transmission, resulting in excess energy consumption, challenging the limited power capacity generated by solar energy or the fixed amount of fuel. This research proposes a Machine Learning [ML]-based model that provides a time-dependent prediction of the expected attenuation level due to rain and fog. Based on the predicted attenuation level, we calibrate the communication signal strength to save energy. We used collected data from the Genesis LEO satellite and corresponding simulated data in the range of 2.4GHz to 72GHz. We then executed the ML system, and after several adjustments for the frequencies up to 48GHz, we reached a very narrow gap between the predicted and actual attenuation levels. However, in the 72GHz frequency, we got a partial correlation.
Research Interests:
Key distribution is a growing concern for symmetric cryptography. Most of the current key-distribution mechanisms assume the use of the Internet and WAN networks, which are exposed to security hazards. To overcome them, the use of... more
Key distribution is a growing concern for symmetric cryptography. Most of the current key-distribution mechanisms assume the use of the Internet and WAN networks, which are exposed to security hazards. To overcome them, the use of comprehensive and robust cryptographic mechanisms such as Diffie–Hellman (DH) and RSA (Rivest–Shamir–Adleman) algorithms are proposed. These solutions are limited. DH and RSA have been under threat since the introduction of quantum computing. Hence, new ideas are required. This paper introduces a new security approach for a safe key transmission using undetected high-speed optical camera communication (OCC), which is based on the rolling shutter effect of modern smart cameras. The key transfer is done by blinking light-emitting diode (LED) lights in a specific sequence and frequency, following an encoding pattern. The receiver decodes the received blinks to a bit string using a corresponding image processing application. This optical media ensures secure t...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Sustainable smart cities (SSC) are becoming a reality as many develop their unique model of smart cities based on vast communication infrastructure. New technologies led to innovative ecosystems where transportation, logistics,... more
Sustainable smart cities (SSC) are becoming a reality as many develop their unique model of smart cities based on vast communication infrastructure. New technologies led to innovative ecosystems where transportation, logistics, maintenance, etc., are automated and accessed remotely. Information and communication coordinate their overall activities. Sensors embedded in these devices sense the environment to provide the required input. Together with artificial intelligence, machine learning, and deep learning, it enables them to facilitate effective decision-making. This chapter discusses the role of integrating technologies in smart cities, focusing on the information and communication aspects, challenges, limitations, and mitigation strategies related to the infrastructure, implementations, and best practices for attaining SSC. We propose a four-layered model covering the main aspects of incorporating communication technology within sustainable smart cities. It covers the basic phys...
Research Interests:
E-commerce is one of the rapidly booming sectors in India today, thanks to the rising internet user base and faster mobile penetration. The E-commerce industry is a complex ecosystem as it involves huge transaction volumes, complex... more
E-commerce is one of the rapidly booming sectors in India today, thanks to the rising internet user base and faster mobile penetration. The E-commerce industry is a complex ecosystem as it involves huge transaction volumes, complex procurement and logistics systems and reliance on new technologies for customer access and payment transactions. This complexity has given rise to frauds and revenue leakages, which is impacting the revenue for the ecommerce companies. Hence the major concern facing the Ecommerce sector today is how to mitigate the revenue loss. Very few studies have been done in academic literature in this area hence the objective of this study is to understand the sources of revenue leakage in the ecommerce sector and propose solutions for mitigating these revenue leakages. The study focusses on [2] major areas of revenue leakage viz. Customer side, Vendor side. The proposed revenue assurance model will be helpful to Ecommerce companies for detecting the sources of reve...