Dharm Singh Jat

Bio: Dharm Singh Jat is an academic researcher from Polytechnic of Namibia. The author has contributed to research in topics: The Internet & Big data. The author has an hindex of 6, co-authored 22 publications receiving 65 citations.

Artificial Intelligence-Enabled Robotic Drones for COVID-19 Outbreak

Abstract: Artificial intelligence (AI) can help to address coronavirus if applied creatively. Artificial intelligence training models to deal with COVID-19 are having challenges as historical data is still not available. Drones and robots equipped with IoT devices provide raw data that needs computing analysis to make that data meaningful and actionable without human involvement. The power of AI and edge computing lies in its ability to process a massive amount of data at breakneck speed and improving efficiency. It enables big data analytics and deployment of algorithm and transmission of data across edge and cloud. This chapter presents how current artificial intelligence enables robotic drone applications and network connectivity is used to improve their performance and increase efficiency in various situations to fight COVID-19. Further, it provides an in-depth review and analysis of literature on related work on COVID-19 outbreak. It also gives the necessary background for future research in edge intelligence, AI-enabled robotic drone and intelligent networks.

An Intelligent Wireless QoS Technology for Big Data Video Delivery in WLAN

Abstract: With the development of internet technologies and applications, video becomes the main source of online generated data. Real-time generated big data video on the internet have many challenges, which include broadcast, evaluation, storage, analysis, and transmission. For multimedia applications, processing and communication are important areas to realizing ambient intelligence and Quality of Service (QoS) is a major challenge for designing and implementation of processing and communication of multimedia traffic. In this study, simulation results have verified the possibility and effectiveness of the developed intelligent wireless QoS technology in terms of big data video communication over a Wireless Local Area Network (WLAN). Structural Similarity Index (SSIM) and Video Quality Metric (VQM) video quality matrixes are used for measurement of received video at receiver. The results show that dynamics frame aggregation mechanism improve the big data video delivery for SSIM and VQM in comparison to frame aggregation mechanism defined by the draft of IEEE802.11n WLAN.

Three-dimensional object recognition based intelligence system for identification

Abstract: If we compare the object recognition abilities of human and computer-based system, it is much complex task for a machine. Human brain can recognize an object quickly but for a computer system accuracy depends on the level of algorithms, software and tools used for recognition. Image processing, pattern recognition and compute vision are being challenging but becomes a crucial component for developing such a computer system in the modern digital world. Last four decades many researchers offered many algorithms to recognize objects from an image. If knowledge is acquired, how objects are appearing and an image to be identified from those objects. The intelligent system must be able to recognize different objects from the scenes or images. In this paper, we present a three-dimensional object recognition system based intelligence system to identify individuals.

A quick cybersecurity wellness evaluation framework for critical organizations

Abstract: The dynamics of cyber threats globally exposes many critical organizations to information security risks on a daily basis or even shorter. As a result, some of the critical organizations lose focus and becomes blinded of changing risks level. Thus, there is an urgent need to have a quick evaluation framework based on well-established security criteria that would enable critical organizations to detect security weaknesses as fast as the threats that come, and rectify those vulnerabilities before attackers taking advantage. This paper proposes a simplified and quick framework of measuring cyber security risks profile for critical organizations. This simplified framework can also be built into a real time cybersecurity dashboard system for critical organizations to use for quick monitoring.

Applications of statistical techniques and artificial neural networks: A review

Abstract: Big data is everywhere, and storage is affordable. The existing hardware and software are unable to analysis the vast amount of various types of data. Big data has become too complex and too dynami...

Analytical Study of Hybrid Techniques for Image Encryption and Decryption.

Abstract: The majority of imaging techniques use symmetric and asymmetric cryptography algorithms to encrypt digital media. Most of the research works contributed in the literature focus primarily on the Advanced Encryption Standard (AES) algorithm for encryption and decryption. This paper propose an analysis for performing image encryption and decryption by hybridization of Elliptic Curve Cryptography (ECC) with Hill Cipher (HC), ECC with Advanced Encryption Standard (AES) and ElGamal with Double Playfair Cipher (DPC). This analysis is based on the following parameters: (i) Encryption and decryption time, (ii) entropy of encrypted image, (iii) loss in intensity of the decrypted image, (iv) Peak Signal to Noise Ratio (PSNR), (v) Number of Pixels Change Rate (NPCR), and (vi) Unified Average Changing Intensity (UACI). The hybrid process involves the speed and ease of implementation from symmetric algorithms, as well as improved security from asymmetric algorithms. ECC and ElGamal cryptosystems provide asymmetric key cryptography, while HC, AES, and DPC are symmetric key algorithms. ECC with AES are perfect for remote or private communications with smaller image sizes based on the amount of time needed for encryption and decryption. The metric measurement with test cases finds that ECC and HC have a good overall solution for image encryption.

Smart Contract-Based Blockchain-Envisioned Authentication Scheme for Smart Farming

Abstract: A blockchain-based smart farming technology provides the agricultural data to the farmers and other users associated with smart farming on a single integrated platform. Moreover, persistence and auditability of stored data in blocks into the blockchain provide the confidence of using the correct data when needed later and adds transparency, anonymity, and traceability at the same time. To fulfill such a goal, in this article, we design a new smart contract-based blockchain-envisioned authenticated key agreement mechanism in a smart farming environment. The device-to-device (D2D) authentication phase and device-to-gateway (D2G) authentication phase support mutual authentication and key agreement between two Internet-of-Things (IoT)-enabled devices and between an IoT device and the gateway node (GWN) in the network, respectively. The blocks are created by the edge servers on the authenticated data of IoT devices received from the GWNs and then sent to the cloud server (CS). The smart contract-based consensus mechanism allows verification and addition of the formed blocks by a peer-to-peer (P2P) CSs network. The security of the proposed scheme is done through formal and informal security analysis, and also using the formal security verification tool. A detailed comparative study reveals that the proposed scheme offers superior security and more functionality features as compared to existing competing authentication protocols. Finally, the blockchain-based simulation has been conducted to measure computational time for a varied number of mined blocks and also a varied number of transactions per block.