scholarly journals Machine Learning Technique and Applications – An Classification Analysis

2021 ◽  
pp. 185-190
Author(s):  
J Xin Ge Ge ◽  
Yuan Xue
Keyword(s):  
Machine Learning ◽  
Cyber Security ◽  
Smart Cities ◽  
Real Life ◽  
Internet Technology ◽  
Future Research ◽  
Security Systems ◽  
Classification Analysis ◽  
Massive Scale ◽  
Media Data

The digitally-enhanced environment is susceptible to massive data, such as information security data, internet technology data, cellular internet, patient records, media data, corporate data, and so on, in the current era of Industry 4.0. Understanding of Machine Learning (ML) is essential for intelligently evaluating these sets of data and developing related "intelligent" and "automated" solutions. Different forms of ML algorithms e.g. reinforcement learning, semi-supervised, unsupervised and supervised learning exist in this segment. In addition, deep learning, which is a wider segment of ML techniques, can smartly evaluate datasets on a massive scale. In this research, a comprehensive analysis of ML techniques and classification analysis algorithms that are applicable to develop capabilities and intelligence of applications are analyzed. Therefore, this research’s contribution is illustrating the key principles of various ML techniques and their application in different real-life application realms e.g. e-commerce, healthcare, agriculture, smart cities, cyber-security systems etc. Lastly, this paper presents a discussion of the challenges and future research based on this research.

scholarly journals Security and Cryptographic Challenges for Authentication Based on Biometrics Data

Cryptography ◽  
2018 ◽  
Vol 2 (4) ◽  
pp. 39 ◽  
Author(s):  
Stefania Nita ◽  
Marius Mihailescu ◽  
Valentin Pau
Keyword(s):  
Machine Learning ◽  
Cloud Computing ◽  
Smart Cities ◽  
Clustering Algorithms ◽  
Security Analysis ◽  
Real Life ◽  
Analysis Tool ◽  
Biometric Analysis ◽  
Wide Range ◽  
Government Education

Authentication systems based on biometrics characteristics and data represents one of the most important trend in the evolution of the society, e.g., Smart City, Internet-of-Things (IoT), Cloud Computing, Big Data. In the near future, biometrics systems will be everywhere in the society, such as government, education, smart cities, banks etc. Due to its uniqueness, characteristic, biometrics systems will become more and more vulnerable, privacy being one of the most important challenges. The classic cryptographic primitives are not sufficient to assure a strong level of secureness for privacy. The current paper has several objectives. The main objective consists in creating a framework based on cryptographic modules which can be applied in systems with biometric authentication methods. The technologies used in creating the framework are: C#, Java, C++, Python, and Haskell. The wide range of technologies for developing the algorithms give the readers the possibility and not only, to choose the proper modules for their own research or business direction. The cryptographic modules contain algorithms based on machine learning and modern cryptographic algorithms: AES (Advanced Encryption System), SHA-256, RC4, RC5, RC6, MARS, BLOWFISH, TWOFISH, THREEFISH, RSA (Rivest-Shamir-Adleman), Elliptic Curve, and Diffie Hellman. As methods for implementing with success the cryptographic modules, we will propose a methodology which can be used as a how-to guide. The article will focus only on the first category, machine learning, and data clustering, algorithms with applicability in the cloud computing environment. For tests we have used a virtual machine (Virtual Box) with Apache Hadoop and a Biometric Analysis Tool. The weakness of the algorithms and methods implemented within the framework will be evaluated and presented in order for the reader to acknowledge the latest status of the security analysis and the vulnerabilities founded in the mentioned algorithms. Another important result of the authors consists in creating a scheme for biometric enrollment (in Results). The purpose of the scheme is to give a big overview on how to use it, step by step, in real life, and how to use the algorithms. In the end, as a conclusion, the current work paper gives a comprehensive background on the most important and challenging aspects on how to design and implement an authentication system based on biometrics characteristics.

scholarly journals Disruptive Technologies for Efficient and Sustainable Smart Cities

2021 ◽  
pp. 47-64
Author(s):  
Dipak S. Gade
Keyword(s):  
Data Analysis ◽  
Smart Cities ◽  
Rapid Development ◽  
Real Life ◽  
Research Area ◽  
Future Research ◽  
Research Papers ◽  
Digital Twins ◽  
New Findings ◽  
Operations And Maintenance

Purpose: The most active and rapid development in today's world is happening in Smart cities. Smart Cities are changing very fast in every aspect, be it development, operations, and or maintenance points of view. Today's Smart Cities are aiming to be at an advanced stage of urbanization and fully exploiting digital infrastructure for rapid urban development. In order to make the cities better places to live and to offer more comfortable and enjoyable living for their residents, Smart Cities are using and employing various tools and technologies to make themselves smarter and more connected with their stakeholders using technology means. Industry 4.0, Digital Transformation, and various latest technologies such as 5G, Data Analytics, IoT, AI, and Machine Learning, Digital Twins, etc. are transforming and shaping up Smart Cities in never before style. In this paper, various such key technologies that are positively affecting Smart Cities are discussed at length. It is also highlighted in detail how these technologies are impacting Smart Cities development and operations. Finally, future research directions are also discussed in brief. Design/Methodology/Approach: Extensive exploration of available literature with research papers, conference papers, white papers, online blogs, dedicated websites, etc. on the research area and interactions with field researchers, subject matter experts, industry professionals is carried out to collect, analyse and process the collected data to find out the facts. The resulted facts and findings about the latest technologies used in Smart Cities is presented in this research paper. Findings/Result: After analysis of available literature and based on interactions with relevant stakeholders and based on own data analysis, it is identified that Smart City services are making use of various latest tools and technologies to solve their real-life challenges. Among vast list of technologies specifically IoT, Blockchain, Digital Twins, 5G, Contactless Technology, AI and ML are found the most significant and widely used technologies in Smart Cities development, operations, and maintenance activities. Originality/Value: It is found that not many research papers are available on analysis of future technologies used in Smart Cities. The data presented in this paper is genuine and original and completely based on systematic literature review, interactions with SME, Researchers and Industry experts and based on own data analysis which produced new findings. Paper Type: Technology oriented Research

scholarly journals Deep Learning for Cyber Security Applications: A Comprehensive Survey

2021 ◽  
Author(s):  
vinayakumar R ◽  
Mamoun Alazab ◽  
Soman KP ◽  
Sriram Srinivasan ◽  
Sitalakshmi Venkatraman ◽  
...  
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Cyber Security ◽  
Smart Cities ◽  
Critical Discussion ◽  
Future Research ◽  
Next Generation ◽  
Security Applications ◽  
The Past ◽  
Comprehensive Survey

Deep Learning (DL), a novel form of machine learning (ML) is gaining much research interest due to its successful application in many classical artificial intelligence (AI) tasks as compared to classical ML algorithms (CMLAs). Recently, DL architectures are being innovatively modelled for diverse applications in the area of cyber security. The literature is now growing with DL architectures and their variations for exploring different innovative DL models and prototypes that can be tailored to suit specific cyber security applications. However, there is a gap in literature for a comprehensive survey reporting on such research studies. Many of the survey-based research have a focus on specific DL architectures and certain types of malicious attacks within a limited cyber security problem scenario of the past and lack futuristic review. This paper aims at providing a well-rounded and thorough survey of the past, present, and future DL architectures including next-generation cyber security scenarios related to intelligent automation, Internet of Things (IoT), Big Data (BD), Blockchain, cloud and edge technologies. <br>This paper presents a tutorial-style comprehensive review of the state-of-the-art DL architectures for diverse applications in cyber security by comparing and analysing the contributions and challenges from various recent research papers. Firstly, the uniqueness of the survey is in reporting the use of DL architectures for an extensive set of cybercrime detection approaches such as intrusion detection, malware and botnet detection, spam and phishing detection, network traffic analysis, binary analysis, insider threat detection, CAPTCHA analysis, and steganography. Secondly, the survey covers key DL architectures in cyber security application domains such as cryptography, cloud security, biometric security, IoT and edge computing. Thirdly, the need for DL based research is discussed for the next generation cyber security applications in cyber physical systems (CPS) that leverage on BD analytics, natural language processing (NLP), signal and image processing and blockchain technology for smart cities and Industry 4.0 of the future. Finally, a critical discussion on open challenges and new proposed DL architecture contributes towards future research directions.

scholarly journals Deep Learning for Cyber Security Applications: A Comprehensive Survey

2021 ◽  
Author(s):  
vinayakumar R ◽  
Mamoun Alazab ◽  
Soman KP ◽  
Sriram Srinivasan ◽  
Sitalakshmi Venkatraman ◽  
...  
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Cyber Security ◽  
Smart Cities ◽  
Critical Discussion ◽  
Future Research ◽  
Next Generation ◽  
Security Applications ◽  
The Past ◽  
Comprehensive Survey

Deep Learning (DL), a novel form of machine learning (ML) is gaining much research interest due to its successful application in many classical artificial intelligence (AI) tasks as compared to classical ML algorithms (CMLAs). Recently, DL architectures are being innovatively modelled for diverse applications in the area of cyber security. The literature is now growing with DL architectures and their variations for exploring different innovative DL models and prototypes that can be tailored to suit specific cyber security applications. However, there is a gap in literature for a comprehensive survey reporting on such research studies. Many of the survey-based research have a focus on specific DL architectures and certain types of malicious attacks within a limited cyber security problem scenario of the past and lack futuristic review. This paper aims at providing a well-rounded and thorough survey of the past, present, and future DL architectures including next-generation cyber security scenarios related to intelligent automation, Internet of Things (IoT), Big Data (BD), Blockchain, cloud and edge technologies. <br>This paper presents a tutorial-style comprehensive review of the state-of-the-art DL architectures for diverse applications in cyber security by comparing and analysing the contributions and challenges from various recent research papers. Firstly, the uniqueness of the survey is in reporting the use of DL architectures for an extensive set of cybercrime detection approaches such as intrusion detection, malware and botnet detection, spam and phishing detection, network traffic analysis, binary analysis, insider threat detection, CAPTCHA analysis, and steganography. Secondly, the survey covers key DL architectures in cyber security application domains such as cryptography, cloud security, biometric security, IoT and edge computing. Thirdly, the need for DL based research is discussed for the next generation cyber security applications in cyber physical systems (CPS) that leverage on BD analytics, natural language processing (NLP), signal and image processing and blockchain technology for smart cities and Industry 4.0 of the future. Finally, a critical discussion on open challenges and new proposed DL architecture contributes towards future research directions.

scholarly journals Managing cyber risk in supply chains: a review and research agenda

2019 ◽  
Vol 25 (2) ◽  
pp. 223-240 ◽  
Author(s):  
Abhijeet Ghadge ◽  
Maximilian Weiß ◽  
Nigel D. Caldwell ◽  
Richard Wilding
Keyword(s):  
Supply Chain ◽  
Literature Review ◽  
Supply Chains ◽  
Conceptual Model ◽  
Systematic Literature Review ◽  
Cyber Security ◽  
Future Research ◽  
Security Systems ◽  
Content Type ◽  
Cyber Risk

Purpose In spite of growing research interest in cyber security, inter-firm based cyber risk studies are rare. Therefore, this study aims to investigate cyber risk management in supply chain contexts. Design/methodology/approach Adapting a systematic literature review process, papers from interdisciplinary areas published between 1990 and 2017 were selected. Different typologies, developed for conducting descriptive and thematic analysis, were established using data mining techniques to conduct a comprehensive, replicable and transparent review. Findings The review identifies multiple future research directions for cyber security/resilience in supply chains. A conceptual model is developed, which indicates a strong link between information technology, organisational and supply chain security systems. The human/behavioural elements within cyber security risk are found to be critical; however, behavioural risks have attracted less attention because of a perceived bias towards technical (data, application and network) risks. There is a need for raising risk awareness, standardised policies, collaborative strategies and empirical models for creating supply chain cyber-resilience. Research limitations/implications Different types of cyber risks and their points of penetration, propagation levels, consequences and mitigation measures are identified. The conceptual model developed in this study drives an agenda for future research on supply chain cyber security/resilience. Practical implications A multi-perspective, systematic study provides a holistic guide for practitioners in understanding cyber-physical systems. The cyber risk challenges and the mitigation strategies identified support supply chain managers in making informed decisions. Originality/value To the best of the authors’ knowledge, this is the first systematic literature review on managing cyber risks in supply chains. The review defines supply chain cyber risk and develops a conceptual model for supply chain cyber security systems and an agenda for future studies.

scholarly journals Machine Learning Approaches to Bike-Sharing Systems: A Systematic Literature Review

2021 ◽  
Vol 10 (2) ◽  
pp. 62
Author(s):  
Vitória Albuquerque ◽  
Miguel Sales Dias ◽  
Fernando Bacao
Keyword(s):  
Machine Learning ◽  
Literature Review ◽  
Systematic Literature Review ◽  
Smart Cities ◽  
Research Question ◽  
Machine Learning Algorithms ◽  
Urban Transport ◽  
Machine Learning Techniques ◽  
Future Research ◽  
Bike Sharing

Cities are moving towards new mobility strategies to tackle smart cities’ challenges such as carbon emission reduction, urban transport multimodality and mitigation of pandemic hazards, emphasising on the implementation of shared modes, such as bike-sharing systems. This paper poses a research question and introduces a corresponding systematic literature review, focusing on machine learning techniques’ contributions applied to bike-sharing systems to improve cities’ mobility. The preferred reporting items for systematic reviews and meta-analyses (PRISMA) method was adopted to identify specific factors that influence bike-sharing systems, resulting in an analysis of 35 papers published between 2015 and 2019, creating an outline for future research. By means of systematic literature review and bibliometric analysis, machine learning algorithms were identified in two groups: classification and prediction.

scholarly journals Technologies to Overcome Spoofing Attack in Facial Recognition

2019 ◽  
Vol 8 (2S4) ◽  
pp. 36-41
Keyword(s):  
Facial Recognition ◽  
Real Life ◽  
Future Research ◽  
Biometric System ◽  
Security Systems ◽  
Research Directions ◽  
Biometric Systems ◽  
Future Research Directions ◽  
Behavioral Attributes ◽  
Compare And Contrast

The identification technologies used nowadays consists of biometrics as an essential component. The basic use of a conventional biometric system is to identify the authenticity of an individual through its physical as well as behavioral attributes, which is considered as one of the most suitable method to secure confidentiality of data. Though the security of these systems is stringent to breach, still it does consists of vulnerabilities due to various reasons. One of the major threats the current biometric system possess are the spoofing attacks. Spoofing attacks are difficult to conquer due to the fact that a person tries to masquerade as others in order to gain unauthorized access to the security systems. This is one of the biggest problem concerning the integrity of the biometric system. The study of spoofing attacks has gained interest of various researchers in the field of computer science, still there are aspects which needs greater attention in order to achieve a plausible solution. The study is based on the current biometric systems in order to compare and contrast the existing technology used in facial recognition. A detailed review of the existing anti – spoofing methods will be taken into account to discuss the future research directions. Thus, the work will focus on threats to the current security systems, with an aim to analyse the possible countermeasures, and its applications in real life scenarios.

Smart Cities and Internet Technology Research for Sustainable and Inclusive Development

2019 ◽  
pp. 318-342
Author(s):  
Christina Marouli ◽  
Miltiadis D. Lytras
Keyword(s):  
Citizen Participation ◽  
Information Technologies ◽  
Smart Cities ◽  
Internet Technology ◽  
Inclusive Development ◽  
Future Research ◽  
Public And Private ◽  
Special Character ◽  
Efficient Resource ◽  
Strategic Policy

The concept of smart cities has recently emerged to highlight the significance of innovation and information technologies in urban planning. In this chapter, after a discussion of different conceptions and important dimensions of smart cities, a wealth of information technologies that have been used in cities for a variety of services is presented. The authors advocate that smart urban solutions should be designed within a smart cities vision and strategic plan, defined by people's needs. They propose an integrated strategic policy making model for smart, sustainable and inclusive cities and they make recommendations for policies and education for smart cities. The special character of public and private spaces, the significance of everyday life, the pivotal role of open governance and meaningful citizen participation, as well as the balance between the desired surveillance for efficient resource management and freedom and creativity have been highlighted as challenges that should inform the design of smart urban solutions and future research on smart cities.

Smart Cities and Internet Technology Research for Sustainable and Inclusive Development

2018 ◽  
pp. 434-458
Author(s):  
Christina Marouli ◽  
Miltiadis D. Lytras
Keyword(s):  
Citizen Participation ◽  
Information Technologies ◽  
Smart Cities ◽  
Internet Technology ◽  
Inclusive Development ◽  
Future Research ◽  
Public And Private ◽  
Special Character ◽  
Efficient Resource ◽  
Strategic Policy

The concept of smart cities has recently emerged to highlight the significance of innovation and information technologies in urban planning. In this chapter, after a discussion of different conceptions and important dimensions of smart cities, a wealth of information technologies that have been used in cities for a variety of services is presented. The authors advocate that smart urban solutions should be designed within a smart cities vision and strategic plan, defined by people's needs. They propose an integrated strategic policy making model for smart, sustainable and inclusive cities and they make recommendations for policies and education for smart cities. The special character of public and private spaces, the significance of everyday life, the pivotal role of open governance and meaningful citizen participation, as well as the balance between the desired surveillance for efficient resource management and freedom and creativity have been highlighted as challenges that should inform the design of smart urban solutions and future research on smart cities.

Sign in / Sign up

Export Citation Format

Share Document