Secure and Energy-Efficient Computational Offloading Using LSTM in Mobile Edge Computing DOI Open Access
Muhammad Arif,

F. Ajesh,

Shermin Shamsudheen

et al.

Security and Communication Networks, Journal Year: 2022, Volume and Issue: 2022, P. 1 - 13

Published: Jan. 7, 2022

The use of application media, gamming, entertainment, and healthcare engineering has expanded as a result the rapid growth mobile technologies. This technology overcomes traditional computing methods in terms communication delay energy consumption, thereby providing high reliability bandwidth for devices. In today’s world, edge is improving various forms so to provide better output there no room simple architecture MEC. So, this paper proposed secure energy-efficient computational offloading scheme using LSTM. prediction tasks done LSTM algorithm, strategy computation devices based on tasks, migration cloud scheduling helps optimize model. Experiments show that our architecture, which consists an LSTM-based technique routing (LSTMOTR) can efficiently decrease total task with growing data subtasks, reduce bring much security due firewall nature

Language: Английский

Blockchain-Based Medical Certificate Generation and Verification for IoT-Based Healthcare Systems DOI
Suyel Namasudra, Pratima Sharma, Rubén González Crespo

et al.

IEEE Consumer Electronics Magazine, Journal Year: 2022, Volume and Issue: 12(2), P. 83 - 93

Published: Jan. 4, 2022

Nowadays, medical certificates are very important for many users as they want to avail health benefits like tax purposes, insurance claims, legal procedures, and more. Generating, issuing, maintaining remain a significant problem; before the invention of computer, were available hard copies. The digitization documents leads potential security issues, such forging risks privacy healthcare documents. Moreover, individuals still need be physically present wait at issuing centers get certificates. Currently, infrastructure any industry connects Internet Things (IoT) devices application software that communicates with information technology systems. Blockchain IoT can significantly affect by improving efficiency, security, transparency, provide more business opportunities. Therefore, privacy-preserving technique has been proposed in this article IoT-based systems using blockchain technology. architecture provides an interface between generate maintain Furthermore, scheme ensures specifying rules smart contract. Results discussion show is efficient than existing schemes.

Language: Английский

Citations

78
Blockchain-Based Privacy Preservation for IoT-Enabled Healthcare System DOI
Pratima Sharma, Suyel Namasudra, Naveen Chilamkurti

et al.

ACM Transactions on Sensor Networks, Journal Year: 2022, Volume and Issue: 19(3), P. 1 - 17

Published: Dec. 22, 2022

Blockchain technology provides a secure and reliable platform for managing data in various application areas, such as supply chain management, multimedia, financial sector, food Internet of Things (IoT) , healthcare, many more. The recent emergence blockchain with IoT significant growth the healthcare industry to improve security, privacy, efficiency, transparency more business opportunities. Nevertheless, conventional schemes suffer from security attacks like collusion, phishing, masquerade, etc. Therefore, privacy-preserving Distributed Application (DA) is proposed this paper using create maintain certificates. Here, distributed an interface between network system objects centers, verifiers, regular authorities generate issue medical documents. In addition, it also ensures by specifying rules smart contracts. To evaluate performance scheme, experimental tests are conducted Etherscan tool measuring operation cost, latency, processing time. efficiency compared existing systems terms throughput, response results comparative analysis show that work efficient than techniques.

Language: Английский

Citations

71
A robust drug recall supply chain management system using hyperledger blockchain ecosystem DOI
Divyansh Agrawal, Sachin Minocha, Suyel Namasudra

et al.

Computers in Biology and Medicine, Journal Year: 2021, Volume and Issue: 140, P. 105100 - 105100

Published: Dec. 2, 2021

Language: Английский

Citations

68
A Comprehensive Review of Bat Inspired Algorithm: Variants, Applications, and Hybridization DOI Open Access
Mohammad Shehab,

Muhannad A. Abu‐Hashem,

Mohd Khaled Yousef Shambour

et al.

Archives of Computational Methods in Engineering, Journal Year: 2022, Volume and Issue: 30(2), P. 765 - 797

Published: Sept. 21, 2022

Language: Английский

Citations

67
Blockchain‐based IoT architecture to secure healthcare system using identity‐based encryption DOI
Pratima Sharma, Nageswara Rao Moparthi, Suyel Namasudra

et al.

Expert Systems, Journal Year: 2021, Volume and Issue: 39(10)

Published: Dec. 13, 2021

Abstract Nowadays, blockchain and Internet of Things (IoT) are two emerging areas the Information Technology (IT) sector. These used in various fields, such as supply chain, logistics automotive industry. Due to low processing power storage space IoT devices, users' medical information is usually saved a centralized third party like clinical repository or cloud computing environment. Thus, many cases, users lose control their information, which can result security disclosure single‐point impediment. So, an advanced solution required improve data sharing process, while restricting it terms security. Blockchain technology with significantly affect healthcare industry by improving its efficiency, transparency, well provide more business opportunities. The efficient Electronic Health Record (EHR) treatment diagnosis accuracy, privacy. This article proposes blockchain‐based architecture enhanced using Identity‐Based Encryption (IBE) algorithm. Here, smart contract defines all basic operations system, be beneficial stakeholders. Many experiments executed evaluate efficiency proposed scheme. results show that scheme better than existing renowned schemes.

Language: Английский

Citations

66
A Novel Technique for Accelerating Live Migration in Cloud Computing DOI

Ambika Gupta,

Suyel Namasudra

Automated Software Engineering, Journal Year: 2022, Volume and Issue: 29(1)

Published: March 23, 2022

Language: Английский

Citations

43
Experience Replay-based Deep Reinforcement Learning for Dialogue Management Optimisation DOI Open Access
Shrikant Malviya, Piyush Kumar, Suyel Namasudra

et al.

ACM Transactions on Asian and Low-Resource Language Information Processing, Journal Year: 2022, Volume and Issue: unknown

Published: May 25, 2022

Dialogue policy is a crucial component in task-oriented Spoken Systems (SDSs). As decision function, it takes the current dialogue state as input and generates appropriate system’s response. In this paper, we explore reinforcement learning approaches to solve problem an Indic language scenario. Recently, Deep Reinforcement Learning (DRL) has been used optimise policy. However, many DRL are not sample-efficient. Hence, particular attention given actor-critic methods based on off-policy that utilise Experience Replay (ER) technique for reducing bias variance achieve high sample efficiency. ER methods, such Advantage Actor-Critic (A2CER) proven deliver competitive results gaming environments fully observable have very small action-set. While, SDSs, states often deal with large action space. Describing limitations of traditional i.e., value-based policy-based variance, low sample-efficiency, converging local optima, firstly use A2CER learning. It shown beat state-of-the-art deep SDS. Secondly, handle issues early-stage performance, demonstration corpus pre-train models prior on-line We thus experiment larger space find significantly faster than state-of-the-art. Combining both approaches, present novel optimisation method, its effectiveness SDS language.

Language: Английский

Citations

35
Collaboration of features optimization techniques for the effective diagnosis of glaucoma in retinal fundus images DOI
Law Kumar Singh, Munish Khanna, Shankar Thawkar

et al.

Advances in Engineering Software, Journal Year: 2022, Volume and Issue: 173, P. 103283 - 103283

Published: Sept. 12, 2022

Language: Английский

Citations

30
LSTM algorithm optimization for COVID-19 prediction model DOI Creative Commons
Irwan Sembiring, Sri Ngudi Wahyuni, Eko Sediyono

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(4), P. e26158 - e26158

Published: Feb. 1, 2024

The development of predictive models for infectious diseases, specifically COVID-19, is an important step in early control efforts to reduce the mortality rate. However, traditional time series prediction used analyze disease spread trends often encounter challenges related accuracy, necessitating need develop with enhanced accuracy. Therefore, this research aimed a model based on Long Short-Term Memory (LSTM) networks better predict number confirmed COVID-19 cases. proposed optimized LSTM (popLSTM) was compared Basic and improved MinMaxScaler developed earlier using dataset taken from previous research. collected four countries high daily increase cases, including Hong Kong, South Korea, Italy, Indonesia. results showed significantly accuracy methods. contributions popLSTM included 1) Incorporating output gate effectively filter more detailed information model, 2) Reducing error value by considering hidden state improve experiment exhibited significant 4%

Language: Английский

Citations

8
Abnormal Respiratory Sounds Classification Using Deep CNN Through Artificial Noise Addition DOI Creative Commons

Rizwana Zulfiqar,

Fiaz Majeed,

Rizwana Irfan

et al.

Frontiers in Medicine, Journal Year: 2021, Volume and Issue: 8

Published: Nov. 17, 2021

Respiratory sound (RS) attributes and their analyses structure a fundamental piece of pneumonic pathology, it gives symptomatic data regarding patient's lung. A couple decades back, doctors depended on hearing to distinguish signs in lung audios by utilizing the typical stethoscope, which is usually considered cheap secure method for examining patients. Lung disease third most ordinary cause death worldwide, so; essential classify RS abnormality accurately overcome rate. In this research, we have applied Fourier analysis visual inspection abnormal respiratory sounds. Spectrum was done through Artificial Noise Addition (ANA) conjunction with different deep convolutional neural networks (CNN) seven sounds-both continuous (CAS) discontinuous (DAS). The proposed framework contains an adaptive mechanism adding similar type noise unhealthy ANA makes features enough reach be identified more than sounds without ANA. obtained results using are superior previous techniques since simultaneously classes.

Language: Английский

Citations

37