4.5 Article

Fog Computing for 5G-Enabled Tactile Internet: Research Issues, Challenges, and Future Research Directions

Journal

MOBILE NETWORKS & APPLICATIONS
Volume -, Issue -, Pages -

Publisher

SPRINGER
DOI: 10.1007/s11036-019-01430-4

Keywords

Mobile communications; Tactile Internet; Fog computing; Fifth generation; Healthcare 4.0; Security and privacy

Funding

  1. TCS Innovation Lab, New Delhi

Ask authors/readers for more resources

From the last few years, we have witnessed an exponential increase in the usage of delay-sensitive applications by the end-users because of the paradigm shift and revolution in different technologies starting from 1G to 5G most of which are having focus on QoS and QoE to the end-users. The existing standards on 5G mainly concentrate on the following issues: 10 Gigabyte data rate, 1-millisecond latency, high bandwidth per unit area, 99.999% availability, 100% coverage and 90% reduction in network energy usage. Hence, 5G has the capability to support various types of communications from the low power Local Area Network (LAN) to Wide Area Networks (WAN) with low-latency and high-speed. It allows human-to-human (H2H), human-to-machine (H2M) interactions for exchanging of data and signals. So, for better data transmission between different entities (for example, smart objects located across different geographic locations), efficient communication between billions of smart devices is required and the associated technology is called as Internet of Things. However, issues such as- latency-tolerant, low-data rate, high complexity, privacy and security in existing solutions may deteriorate the performance of any implemented solution in this environment. To mitigate the above-mentioned problems, the literature suggests that fog computing can be one of the options as it provides ultra-low-latency for Tactile-based applications. Tactile Internet is an emerging technology used for H2M interactions to support high-reliability, ultra-responsive, and high fidelity. Keeping focus on all the aforementioned challenges and constraints, in this paper, we provide an analysis on the usage of the strong backbone infrastructure of fog computing for 5G-enabled Tactile Internet with a maximum bandwidth of 1 Gigabyte having the minimum latency of 1-millisecond. It supports low-latency and high-reliability in Tactile-based applications. Keeping focus on the issues such as- resource management, communication infrastructure, fog orchestration, fog networking, healthcare, security and privacy of fog system in Tactile-based applications, we have explored and compared the existing state-of-the-art proposals using various parameters such as- energy-efficient, QoS, scalability, mobility, and interoperability. In addition, a number of open research challenges of fog computing for 5G-enabled Tactile Internet are also explored to provide deep insights to the readers.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.5
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

Article Computer Science, Information Systems

Security enhancement in cellular networks employing D2D friendly jammer for V2V communication

J. Senthil Kumar, Akhil Gupta, Sudeep Tanwar, Neeraj Kumar, Sedat Akleylek

Summary: This paper thoroughly investigates the security aspects in vehicle-to-vehicle communication with the backbone cellular network, using a device-to-device communication link that shares spectral resources. The study derives the ergodic secrecy capacity and ergodic capacity for the wiretap channel and D2D link, and emphasizes the importance of optimizing power allocation and security through D2D communications for V2V applications.

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS (2023)

Article Computer Science, Software Engineering

Postal Automation System in Gurmukhi Script using Deep Learning

Sandhya Sharma, Sheifali Gupta, Neeraj Kumar, Tanvi Arora

Summary: The postal automation system is a major research area in the era of automation. Developing a postal automation system for India is challenging due to its multi-script and multi-lingual behavior. This study focuses on the postal automation of district names in Punjab, India, written in the Gurmukhi script. A segmentation-free technique using Convolutional Neural Network (CNN) and Deep learning (DL) is utilized for recognition. A database of 22000 handwritten images in Gurmukhi script for all 22 districts of Punjab is prepared, and two CNN models achieve validation accuracies of 90% and 98% respectively.

INTERNATIONAL JOURNAL OF IMAGE AND GRAPHICS (2023)

Review Computer Science, Theory & Methods

EEG Based Emotion Recognition: A Tutorial and Review

Xiang Li, Yazhou Zhang, Prayag Tiwari, Dawei Song, Bin Hu, Meihong Yang, Zhigang Zhao, Neeraj Kumar, Pekka Marttinen

Summary: Emotion recognition technology using EEG signals is crucial in Artificial Intelligence, with applications in emotional health care, human-computer interaction, and multimedia content recommendation. This paper reviews recent representative works in EEG-based emotion recognition research from the perspective of researchers taking the first step in this field. It introduces the scientific basis of EEG-based emotion recognition and categorizes reviewed works into different technical routes, providing readers with a better understanding of the motivation behind these studies. The paper also discusses existing challenges and future research directions.

ACM COMPUTING SURVEYS (2023)

Article Computer Science, Software Engineering

Robotic Process Automation use cases in academia and early implementation experiences

Ankur Gupta, Purnendu Prabhat, Sahil Sawhney, Rajesh Gupta, Sudeep Tanwar, Neeraj Kumar, Mohammad Shabaz

Summary: Robotic Process Automation (RPA) is a new sub-domain of software-based automation that aims to alleviate tedious manual and repetitive tasks. It finds wide adoption across industries and domains, including academia and document processing. While RPA offers potential benefits in terms of efficient data collation and analysis, as well as operational efficiency, its long-term seamless operation requires significant software engineering effort.

IET SOFTWARE (2023)

Article Computer Science, Hardware & Architecture

Blockchain and artificial intelligence-empowered smart agriculture framework for maximizing human life expectancy

Nilesh Kumar Jadav, Tejal Rathod, Rajesh Gupta, Sudeep Tanwar, Neeraj Kumar, Ahmed Alkhayyat

Summary: →Massive population growth and rising environmental issues pose challenges in agriculture, such as land scarcity, pesticide overuse, and global food demand. To tackle this, we proposed a blockchain and AI-powered smart agriculture framework to predict pesticide levels in crops. The blockchain ensures data integrity, storing records securely. Evaluation metrics show that our framework outperforms baseline approaches in accuracy, scalability, and latency.

COMPUTERS & ELECTRICAL ENGINEERING (2023)

Article Computer Science, Theory & Methods

Adaptive federated learning scheme for recognition of malicious attacks in an IoT network

Prateek Chhikara, Rajkumar Tekchandani, Neeraj Kumar

Summary: The Internet of Things (IoT) is crucial for deploying a novel Artificial Intelligence (AI) model for both network and application management. However, using classical centralized learning algorithms in the IoT environment is challenging, given massively distributed private datasets. The paper proposes two adaptive approaches for making model training differentially private in a vertical federated environment.

COMPUTING (2023)

Review Computer Science, Theory & Methods

Fusion of blockchain and IoT in scientific publishing: Taxonomy, tools, and future directions

Sudeep Tanwar, Dakshita Ribadiya, Pronaya Bhattacharya, Anuja R. Nair, Neeraj Kumar, Minho Jo

Summary: Scientific publishing systems (SPS) provide a platform for authors, reviewers, and editors to share their research, leading to the advancement of the academic community. However, traditional SPS face challenges in managing large databases, complex queries and retrievals, lengthy publishing processes, and lack of rewarding methods for peer review and storage of unsuccessful articles. In this paper, a fusion of blockchain and IoT technologies is proposed to address these limitations and provide a secure, transparent, and efficient publishing platform.

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE (2023)

Article Computer Science, Theory & Methods

An adaptive DNN inference acceleration framework with end-edge-cloud collaborative computing

Guozhi Liu, Fei Dai, Xiaolong Xu, Xiaodong Fu, Wanchun Dou, Neeraj Kumar, Muhammad Bilal

Summary: This paper proposes an adaptive DNN inference acceleration framework that utilizes end-edge-cloud collaborative computing to accelerate inference latency. The framework includes a latency prediction model and a computation partitioning algorithm, and experimental results show significant improvements in prediction accuracy and inference latency reduction.

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE (2023)

Article Computer Science, Artificial Intelligence

Physiotherapy-based human activity recognition using deep learning

Disha Deotale, Madhushi Verma, P. Suresh, Neeraj Kumar

Summary: This study focuses on physiotherapy video dataset and proposes a deep learning-based neural network framework to address the issues in continuous human activity recognition.

NEURAL COMPUTING & APPLICATIONS (2023)

Article Computer Science, Artificial Intelligence

A systematic analysis of deep learning methods and potential attacks in internet-of-things surfaces

Ahmed Barnawi, Shivani Gaba, Anna Alphy, Abdoh Jabbari, Ishan Budhiraja, Vimal Kumar, Neeraj Kumar

Summary: This paper aims to enhance the security of IoT systems by exploring deep learning algorithms. It identifies and evaluates potential security threats and attack surfaces for IoT, and provides a systematic survey of deep learning methods for IoT security. This research opens the door for future studies by highlighting the advantages, disadvantages, and opportunities in this field.

NEURAL COMPUTING & APPLICATIONS (2023)

Article Computer Science, Information Systems

Dynamic SFC Embedding Algorithm Assisted by Federated Learning in Space-Air-Ground-Integrated Network Resource Allocation Scenario

Peiying Zhang, Yi Zhang, Neeraj Kumar, Mohsen Guizani

Summary: This study proposes a service provision method based on service function chaining (SFC) to address the resource allocation challenge in the space-air-ground-integrated network (SAGIN). By using network function virtualization (NFV) and a federated learning (FL)-based algorithm, efficient resource allocation and reduced service blocking rate can be achieved.

IEEE INTERNET OF THINGS JOURNAL (2023)

Article Computer Science, Information Systems

Deep AI-Powered Cyber Threat Analysis in IIoT

Iram Bibi, Adnan Akhunzada, Neeraj Kumar

Summary: Distributed Industrial Internet of Things (IIoT) has revolutionized the industrial sector, but threat hunting and intelligence in distributed IIoT is complex due to lack of standard architectures. The authors propose a self-learning multivector threat intelligence and detection mechanism to defend IIoT systems. They introduce a novel ConvLSTM2D mechanism that can efficiently tackle dynamic variants of emerging IIoT threats. The proposed mechanism outperforms benchmark algorithms in detection accuracy with minimal tradeoff in speed efficiency.

IEEE INTERNET OF THINGS JOURNAL (2023)

Article Computer Science, Information Systems

Blockchain-Enabled Secure Big Data Analytics for Internet of Things Smart Applications

Prakash Tekchandani, Indranil Pradhan, Ashok Kumar Das, Neeraj Kumar, Youngho Park

Summary: Smart devices in IoT generate big data through sensors, which is used for intelligent applications through machine learning. This requires data collection from devices to central servers for model training, but privacy and bandwidth limitations hinder the efficiency of centralized training. To address this, we propose a hybrid secure federated learning approach with blockchain for local device training and blockchain storage for traceability and immutability. A detailed analysis shows the approach's effectiveness in terms of security, resilience against attacks, and cost efficiency.

IEEE INTERNET OF THINGS JOURNAL (2023)

Article Engineering, Electrical & Electronic

Secrecy Rate Maximization in THz-Aided Heterogeneous Networks: A Deep Reinforcement Learning Approach

Himanshu Sharma, Neeraj Kumar, Ishan Budhiraja, Ahmed Barnawi

Summary: This article proposes a scheme to optimize the secrecy rate of terahertz-enabled femtocells. By utilizing deep reinforcement learning techniques, the optimization problem is successfully addressed, and two schemes are presented to maximize the secrecy rate of the femtocells. Simulation results demonstrate significant improvements in secrecy rate, SINR, and energy-efficiency for the proposed schemes.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2023)

Article Engineering, Electrical & Electronic

A Deep Reinforcement Learning Scheme for Sum Rate and Fairness Maximization Among D2D Pairs Underlaying Cellular Network With NOMA

Vineet Vishnoi, Ishan Budhiraja, Suneet Gupta, Neeraj Kumar

Summary: Device-to-device (D2D) communication is an emerging technology in 5G and upcoming 6G networks that enhances the overall transmission rate. However, interference and connectivity issues pose challenges. To mitigate these issues, researchers integrated power domain non-orthogonal multiple access techniques (PD-NOMA) on base stations (BS). By reducing interference and optimizing power allocation, the proposed solution improves sum rate and fairness among users.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2023)

No Data Available