Article
Automation & Control Systems
Xiaoding Wang, Mengyao Peng, Hui Lin, Yulei Wu, Xinmin Fan
Summary: The continuous development of Healthcare 4.0 has brought great convenience to people by enabling doctors to analyze patients' health data and make timely diagnoses through IoT technology. However, the mobile crowdsensing technology used for data transmission still poses risks of privacy leakage. In response to this issue, this article proposes a privacy-enhanced multi-area task assignment strategy called PMTA. By incorporating deep differential privacy, a noise is added to patient data and fed into a deep Q-network for training, combined with spectral clustering for optimal classification. Federated learning is employed to jointly train classification models across different hospitals, allowing for data sharing and addressing data silos. The optimal patient classification is deployed on the blockchain using smart contract technology, ensuring task privacy. Experimental results demonstrate that this strategy effectively protects task and patient privacy while improving system performance.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Theory & Methods
Kinza Sarwar, Sira Yongchareon, Jian Yu, Saeed Ur Rehman
Summary: Despite the challenges in adopting IoT due to data privacy concerns, the introduction of fog computing can address some of the issues and provide improvements for preserving data privacy in IoT applications. Future research directions in this area are also discussed.
ACM COMPUTING SURVEYS
(2023)
Article
Computer Science, Artificial Intelligence
Vu Khanh Quy, Nguyen Van Hau, Dang Van Anh, Le Anh Ngoc
Summary: This article discusses the importance of healthcare applications in driving technological development, and explores the use of cloud, edge, and fog computing technologies in healthcare. Research findings indicate significant potential for Fog-based Healthcare IoT applications, presenting important implications for future development.
COMPLEX & INTELLIGENT SYSTEMS
(2022)
Article
Engineering, Civil
Ke Gu, Keming Wang, Xiong Li, Weijia Jia
Summary: The paper proposes a decentralized traceable privacy-preserving scheme for vehicular identity in fog computing-based Internet of Vehicles (IoV), which uses multiple fog servers to trace the identity and trajectory of a vehicle under certain conditions. By utilizing a secret sharing scheme, the true identity of a vehicle is hidden and traced, ensuring security requirements are met and data collection procedure is secure under the real-or-random model. Experimental results show the efficiency of the proposed scheme in IoV.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Information Systems
Jasleen Kaur, Alka Agrawal, Raees Ahmad Khan
Summary: With the growth of the digital population, managing users' private data flowing across the web has become challenging. Fog computing has addressed certain issues but also raised concerns about privacy. The authors propose an encryfuscation model that employs obfuscation and encryption techniques, selecting suitable privacy preservation techniques based on offloading decisions. They also propose obfuscation techniques for data and location.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Sabrina Sicari, Alessandra Rizzardi, Alberto Coen-Porisini
Summary: This paper analyzes the evolution of fog computing and IoT methodologies, discussing the advantages and challenges of moving security and privacy tasks to the network edge. It provides an overview of the requirements for secure and privacy-aware IoT-based fog computing infrastructures.
COMPUTERS & SECURITY
(2022)
Article
Telecommunications
Amit Kishor, Chinmay Chakraborty
Summary: AI is widely used in healthcare 4.0 for early and accurate disease predictions, aided by IoT technology. This study proposes a machine learning model to predict different diseases, involving seven classification algorithms. The Random Forest classifier achieved high accuracy, sensitivity, specificity, and AUC for various diseases.
WIRELESS PERSONAL COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
Tariq Ahamed Ahanger, Munish Bhatia, Abdullah Aljumah
Summary: This article analyzes the quality of healthcare services provided by hospitals and healthcare centers using Internet of Things (IoT) technology. It quantifies healthcare service using the Probability of Health Grade (PoHG) and performs numerical analysis of healthcare service quality using the health quality index (HQI). It also uses a 2-player game theory-inspired decision modeling to analyze healthcare quality in a time-sensitive manner. The evaluation of the proposed framework in a simulated environment shows enhanced performance measures in terms of classification efficacy, decision-making efficiency, temporal delay, and reliability.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Hardware & Architecture
Shubhani Aggarwal, Neeraj Kumar, Musaed Alhussein, Ghulam Muhammad
Summary: The healthcare industry has evolved from Healthcare 1.0 to Healthcare 4.0 in the IoT era, with advancements such as UAVs and blockchain addressing privacy concerns and providing cost-effective solutions for medical data sharing and security. The proposed blockchain-based UAV path planning architecture offers a secure and efficient platform for real-time medical data collection and transmission.
Review
Chemistry, Analytical
Van Anh Dang, Quy Vu Khanh, Van-Hau Nguyen, Tien Nguyen, Dinh C. C. Nguyen
Summary: Health is invaluable and crucial for human survival, and the healthcare industry has made significant progress with the advancement of science and technology. The development of IoT-based technologies in medicine, including remote medical examination, pandemic prediction, and remote patient health monitoring, has brought about breakthroughs. The upcoming 6G communication networks will revolutionize the IoT era and bring new possibilities for smart healthcare.
Article
Computer Science, Information Systems
Syed Umar Amin, M. Shamim Hossain
Summary: This study focuses on analyzing, understanding, and improving the architecture and technology of edge computing in smart healthcare to address the challenges of meeting individual health needs of patients, and explores the areas involving health data classification and artificial intelligence applications.
Review
Computer Science, Information Systems
Dalius Navakauskas, Mantas Kazlauskas
Summary: Healthcare has seen advancements in sensor technology, and with improvements in networks and the Internet of Things, fog computing has emerged as a promising solution. However, fog computing is still facing challenges and requires further research and development.
Article
Telecommunications
Syed Atif Moqurrab, Noshina Tariq, Adeel Anjum, Alia Asheralieva, Saif U. R. Malik, Hassan Malik, Haris Pervaiz, Sukhpal Singh Gill
Summary: With the emergence of COVID-19, smart healthcare, the Internet of Medical Things, and big data-driven medical applications have become even more important. However, conventional health systems cannot support the vast amount of biomedical data and hence it needs to be stored and shared through the cloud. Unfortunately, this data is prone to security threats and attacks.
WIRELESS PERSONAL COMMUNICATIONS
(2022)
Article
Computer Science, Hardware & Architecture
Prabh Deep Singh, Gaurav Dhiman, Rohit Sharma
Summary: The thyroid is a critical endocrine gland in regulating various bodily processes. Research on the disease's origins and spread is urgently needed. The integration of fog computing and artificial intelligence aims to provide early detection of thyroid infections, with proposed frameworks and classifiers showing better performance than traditional methods.
SUSTAINABLE COMPUTING-INFORMATICS & SYSTEMS
(2022)
Article
Computer Science, Hardware & Architecture
Mohammad Aazam, Sherali Zeadally, Eduardo Feo Flushing
Summary: Advancements in networking and mobile technologies have enabled the development of intelligent services, however, tasks like machine learning on edge devices may lead to higher energy consumption.
Article
Computer Science, Information Systems
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
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
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
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.
Article
Computer Science, Hardware & Architecture
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
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.
Review
Computer Science, Theory & Methods
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
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
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
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
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
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
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
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
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)