Journal Article10.30574/wjarr.2023.20.3.2481
Security aspects in IoT based cloud computing
Ehsan Bazgir,Ehteshamul Haque,Numair Bin Sharif,Md. Faysal Ahmed +3 more
10
TL;DR: The study examines the latest advancements in cloud-based IoT attacks, analyzes significant security issues within each category, and presents the limitations from a broader perspective encompassing general, artificial intelligence, and deep learning aspects.
read more
Abstract: Cloud computing offers a flexible framework in which data and resources are spread across different locations and can be accessed from various industrial environments. This technology has revolutionized the way resources such as data, services, and applications are used, stored, and shared in industrial applications. Over the past decade, industries have rapidly embraced cloud computing due to its advantages of enhanced accessibility, cost reduction, and improved performance. Moreover, the integration of cloud computing has led to significant advancements in the field of the Internet of Things (IoT). However, this quick shift to the cloud has also introduced various security concerns and challenges. Traditional security solutions are not always suitable or effective for cloud-based systems. Despite the continuous use of complex cyber weapons, efforts have been made in recent years to address the security issues and concerns associated with cloud platforms. The rapid progress of deep learning (DL) in the field of artificial intelligence (AI) has provided opportunities to tackle these security challenges in the cloud. The research presented in this study encompasses a comprehensive survey of the enabling architecture, services, configurations, and security models for cloud-based IoT. It also categorizes the security concerns in IoT within four major categories (data, network and service, applications, and people-related security issues) and provides a detailed discussion on each category. Furthermore, the study examines the latest advancements in cloud-based IoT attacks, analyzes significant security issues within each category, and presents the limitations from a broader perspective encompassing general, artificial intelligence, and deep learning aspects.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Breast Cancer Classification using XGBoost
Rahmanul Hoque,Suman Das,Mahmudul Hoque +2 more
TL;DR: This study employs XGBoost to classify breast cancer with 94.74% accuracy and 95.24% recall on the Wisconsin breast cancer dataset, leveraging AI to detect and analyze breast cancer at an early stage for targeted prognosis.
18
Skin cancer classification using NASNet
Mohammad Atikur Rahman,Ehsan Bazgir,S. M. Saokat Hossain,Md. Maniruzzaman +3 more
TL;DR: The primary purpose of this study is to construct a DCNN-based model that is capable of automatically classifying different types of skin cancer as either melanoma or non-melanoma with a high level of accuracy.
15
Comparative analysis of MapReduce and Apache Tez Performance in Multinode clusters with data compression
Sifat Ibtisum,S M Atikur Rahman,S. M. Saokat Hossain +2 more
TL;DR: A thorough comparative analysis of Apache Tez and MapReduce in the context of big data processing, focusing on key performance metrics, scalability, and ease of use offers valuable insights for organizations and practitioners seeking suitable distributed computing frameworks.
10
Skin cancer classification using Inception Network
Ehsan Bazgir,Ehteshamul Haque,Md. Maniruzzaman,Rahmanul Hoque +3 more
TL;DR: This study proposes an optimized Inception architecture, in which the InceptionNet model is enhanced with data augmentation and basic layers, and enhances the model's capacity to deal with incomplete and inconsistent data.
9
Mechanical characterization of materials using advanced microscopy techniques
Suman Das,Joydeep Biswas,Iqtiar Md Siddique +2 more
TL;DR: Advanced microscopy techniques significantly impact materials science and mechanical engineering by elucidating microstructural dynamics, mechanical properties, and failure mechanisms. They contribute to optimizing material performance, bolstering structural integrity, and driving innovation in mechanical design.
8
References
Reducing the Dimensionality of Data with Neural Networks
TL;DR: In this article, an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data is described.
The NIST Definition of Cloud Computing
Peter Mell,Timothy Grance +1 more
- 28 Sep 2011
TL;DR: This cloud model promotes availability and is composed of five essential characteristics, three service models, and four deployment models.
17.6K
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
Geoffrey E. Hinton,Li Deng,Dong Yu,George E. Dahl,Abdelrahman Mohamed,Navdeep Jaitly,Andrew W. Senior,Vincent Vanhoucke,Patrick Nguyen,Tara N. Sainath,Brian Kingsbury +10 more
TL;DR: This article provides an overview of progress and represents the shared views of four research groups that have had recent successes in using DNNs for acoustic modeling in speech recognition.
11.4K
Speech recognition with deep recurrent neural networks
Alex Graves,Abdelrahman Mohamed,Geoffrey E. Hinton +2 more
- 26 May 2013
TL;DR: This paper investigates deep recurrent neural networks, which combine the multiple levels of representation that have proved so effective in deep networks with the flexible use of long range context that empowers RNNs.
10.4K
The risk concept—historical and recent development trends
TL;DR: Over the last 15–20 years the authors have seen a shift from rather narrow perspectives based on probabilities to ways of thinking which highlight events, consequences and uncertainties, however, some of the more narrow perspectives are still strongly influencing the risk field, although arguments can be provided against their use.
580