ijsab.com logo

Impact of Deep Learning on Transfer Learning : A Review Mohammed Jameel Barwary & Adnan Mohsin Abdulazeez

Impact of Deep Learning on Transfer Learning : A Review

Author (s)

Mohammed Jameel Barwary & Adnan Mohsin Abdulazeez

 

Abstract

­

Transfer learning and deep learning approaches have been utilised in several real-world applications and hierarchical systems for pattern recognition and classification tasks. However, in few of the real-world machine learning situations, this presumption does not sustain since there are instances where training data is costly or tough to gather and there is continually a necessity to produce high-performance learners competent with more easily attained data from diverse fields. The objective of this review is to determine more abstract qualities at the greater levels of the representation, by utilising deep learning to detach the variables in the outcomes, formally outline transfer learning, provide information on present solutions, and appraise applications employed in diverse facets of transfer learning and deep learning. This can be attained by rigorous literature exploration and discussion on all presently accessible techniques and prospective research studies on transfer learning solutions of independent as well as big data scale. The conclusions of this study could be an effectual platform directed at prospective directions for devising new deep learning patterns for different applications and dealing with the challenges concerned.

 Keywords: Machine Learning, Transfer Learning, Deep Learning, classifications, Supervised Learning techniques.

 

Download PDF

Title:Impact of Deep Learning on Transfer Learning : A Review
Author:Mohammed Jameel Barwary & Adnan Mohsin Abdulazeez
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4559668
Media:Online
Volume:5
Issue:3
Acceptance Date:6/02/2021
Date of Publication:24/02/2021
PDF URL:https://ijsab.com/wp-content/uploads/698.pdf
Free download:Available
Page:204-216
First Page:204
Last Page:216
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Barwary, M. J. & Abdulazeez, A. M. (2021). Impact of Deep Learning on Transfer Learning : A Review. International Journal of Science and Business, 5(3), 204-216. doi: https://doi.org/ 10.5281/zenodo.4559668

Retrieved from https://ijsab.com/wp-content/uploads/698.pdf

 

About Author (s)

Mohammed Jameel Barwary (corresponding author), Duhok Polytechnic University, Duhok, Kurdistan Region, Iraq. Email: mohammed.jameel@uod.ac

Professor Adnan Mohsin Abdulazeez, Duhok Polytechnic University, Duhok, Kurdistan Region, Iraq.

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4559668

ijsab.com logo

Feature selection technique applied in Medical application by Supervised algorithm: A Review Basna Mohammed Salih Hasan & Nawzat Sadiq Ahmed

Feature selection technique applied in Medical application by Supervised algorithm: A Review

Author (s)

Basna Mohammed Salih Hasan & Nawzat Sadiq Ahmed

Abstract

­Feature selection is a strategy for preprocessing that determines the main features of a specific problem. Traditionally, it has been employed across a variety of topics, including biological data analysis, finance, and intrusion detection systems. In addition to minimizing dimensionality, FS was successfully used in medical systems, which often enable one to consider the causes of the disease. In this paper, a review started to describe some basic concepts related to medical applications and provide some necessary background information on feature selection and reviewed more than ten articles of the FS in the medical field that have been introduced and published in the last years.

 Keywords: Supervised Algorithm, Dimensionality Reduction, Features Selection, Medical Imaging.

 

Download PDF

Title:Feature selection technique applied in Medical application by Supervised algorithm: A Review
Author:Basna Mohammed Salih Hasan & Nawzat Sadiq Ahmed
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4543647
Media:Online
Volume:5
Issue:3
Acceptance Date:5/02/2021
Date of Publication:16/02/2021
PDF URL:https://ijsab.com/wp-content/uploads/697.pdf
Free download:Available
Page:190-203
First Page:190
Last Page:203
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Hasan, B. M. S. & Ahmed, N. S. (2021). Feature selection technique applied in medical application by supervised algorithm: A Review. International Journal of Science and Business, 5(3), 190-203. doi: https://doi.org/10.5281/zenodo.4543647

Retrieved from https://ijsab.com/wp-content/uploads/697.pdf

 

About Author (s)

Basna Mohammed Salih Hasan (corresponding author), Technical College of Informatics Akre, Duhok Polytechnic University, IT Department, Duhok, Kurdistan Region, Iraq. Email: basna.mhmed@dpu.edu.krd

Dr. Nawzat Sadiq Ahmed, Department of Information Technology Management, Technical College of Administration, Duhok University, Kurdistan Region, Iraq.

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4543647

ijsab.com logo

Reinforcement Learning and Modeling Techniques: A Review Hindreen Rashid Abdulqadir & Adnan Mohsin Abdulazeez

Reinforcement Learning and Modeling Techniques: A Review

Author (s)

Hindreen Rashid Abdulqadir & Adnan Mohsin Abdulazeez

Abstract

­

The Reinforcement learning (RL) algorithms solve a wide range of problems we faced. The topic of RL has achieved a new, complete standard of public opinion. High difficulty in large-scale real-world implementations is the effective use of large data sets previously obtained in augmented learning algorithms. Q-learning (QL), by learning a conservative Q function that allows a policy to be below the predicted value of the Q function, is introduced by us, which aims to circumvent these restrictions. We revealed technical reinforcement learning in this study. In principle, we demonstrate that QL creates a lower relation to current policy importance and that this can be correlated with guarantees of political learning theoretical change. In reality, QL strengthens the benchmark objective with a simple, standardized Q value which, in addition to existing Q-learning and essential applications, is quickly applied. The findings indicate that all algorithms are needed to learn how to play successfully. In comparison, all dual Q-learning variables have a significantly higher score compared with Q-learning, and the incremental reward function shows no improved effects than the normal reward function. We present an attack mechanism that uses the portability of competing tests to execute policy incentives and to prove their usefulness and consequences by means of a pilot study of a play learning scenario.

 Keywords: Machine learning, Reinforcement learning, Modelling – Technique, Q- learning.

Download PDF

Title:Reinforcement Learning and Modeling Techniques: A Review
Author:Hindreen Rashid Abdulqadir & Adnan Mohsin Abdulazeez
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4542638
Media:Online
Volume:5
Issue:3
Acceptance Date:11/02/2021
Date of Publication:16/02/2021
PDF URL:https://ijsab.com/wp-content/uploads/696.pdf
Free download:Available
Page:174-189
First Page:174
Last Page:189
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Abdulqadir, H. R. & Abdulazeez, A. M. (2021). Reinforcement Learning and Modeling Techniques: A Review. International Journal of Science and Business, 5(3), 174-189. doi: https://doi.org/10.5281/zenodo.4542638

Retrieved from https://ijsab.com/wp-content/uploads/696.pdf

 

About Author (s)

Hindreen Rashid Abdulqadir  (corresponding author),   Information Technology Department,  Akre Technical College of Informatics, Duhok Polytechnic University, Duhok Kurdistan Region, Iraq. Email: Hindreen.rashid@dpu.edu.krd

Professor Adnan Mohsin Abdulazeez, Duhok Polytechnic University, Duhok, Kurdistan Region, Iraq. E-mail: adnan.mohsin@dpu.edu.krd

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4542638

ijsab.com logo

A Review of most Recent Lung Cancer Detection Techniques using Machine Learning Dakhaz Mustafa Abdullah & Nawzat Sadiq Ahmed

A Review of most Recent Lung Cancer Detection Techniques using Machine Learning

Author (s)

Dakhaz Mustafa Abdullah & Nawzat Sadiq Ahmed

Abstract

­

Lung cancer is a sort of dangerous cancer and difficult to detect. It usually causes death for both gender men & women therefore, so it is more necessary for care to immediately & correctly examine nodules. Accordingly, several techniques have been implemented to detect lung cancer in the early stages. In this paper a comparative analysis of different techniques based on machine learning for detection lung cancer have been presented. There have been too many methods developed in recent years to diagnose lung cancer, most of them utilizing CT scan images and some of them using x-ray images. In addition, multiple classifier methods are paired with numerous segmentation algorithms to use image recognition to identify lung cancer nodules. From this study it has been found that CT scan images are more suitable to have the accurate results. Therefore, mostly CT scan images are used for detection of cancer. Also, marker-controlled watershed segmentation provides more accurate results than other segmentation techniques. In Addition, the results that obtained from the methods based deep learning techniques achieved higher accuracy than the methods that have been implemented using classical machine learning techniques.

 Keywords: Lung Cancer Detection, Machine Learning, Deep Learning, SCLC, and NSCLC.

Download PDF

Title:A Review of most Recent Lung Cancer Detection Techniques using Machine Learning
Author:Dakhaz Mustafa Abdullah & Nawzat Sadiq Ahmed
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4536818
Media:Online
Volume:5
Issue:3
Acceptance Date:06/02/2021
Date of Publication:12/02/2021
PDF URL:https://ijsab.com/wp-content/uploads/695.pdf
Free download:Available
Page:159-173
First Page:159
Last Page:173
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Abdullah, D. M. & Ahmed, N. S. (2021). A Review of most Recent Lung Cancer Detection Techniques using Machine Learning. International Journal of Science and Business, 5(3), 159-173. doi: https://doi.org/10.5281/zenodo.4536818

Retrieved from https://ijsab.com/wp-content/uploads/695.pdf

 

About Author (s)

Dakhaz Mustafa Abdullah (corresponding author), Information Technology, Technical College of Informatics, Akre Information Technology Management, Duhok Polytechnic University, Iraq. Email: dakhaz.abdullah@dpu.edu.kud

Nawzat Sadiq Ahmed, Information Technology Management, Technical College of Administration, DPU, Iraq.  Email: nawzat.ahmed@dpu.edu.krd 

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4536818

ijsab.com logo

Semantic Search Engine Optimisation (SSEO) for Dynamic Websites: A Review Mohammed J. Sadeeq & Subhi R. M. Zeebaree

Semantic Search Engine Optimisation (SSEO) for Dynamic Websites: A Review

Author (s)

Mohammed J. Sadeeq & Subhi R. M. Zeebaree

Abstract

­The billions of databases, worldwide, provide an increasing amount of information to the people. As a result, the researchers have to seek knowledge about the resources, which were generically known as the search engines. One such search technique that is popularly used is the semantic search technique which improves the search accuracy by determining the purpose of the search along with the contextual meaning of the terms which appeared in the data space or the web for generating accurate results. Many search engines exist today, which makes it difficult to collect useful data. In this paper, many types of research depended which prepared to describe the Semantic Search and Semantic Web techniques. Various types of semantic search engines are investigated and the differences between the Semantic Search and Semantic Search keywords are determined. Additionally, the benefits of using Semantic Search were highlighted. The literature review and the findings of the case study helped in understanding the new constructs. These researches also determined the relationship between the new and the previously existing constructs based on their perspective regarding the extension of Bedny’s activity theory with regards to the SEO promotion techniques. They added the functional consequences of extending Bedny’s activity theory faced by the promotion managers. The researchers have summarised the history of semantic search and its global position in search engine generation. The researchers also highlighted the role played by the search engines in the semantic search and smart web technologies.

 Keywords: Semantic Search Engines, Semantic Web, Intelligent Search, Dynamic Websites.

Download PDF

Title:Semantic Search Engine Optimisation (SSEO) for Dynamic Websites: A Review
Author:Mohammed J. Sadeeq & Subhi R. M. Zeebaree
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4536804
Media:Online
Volume:5
Issue:3
Acceptance Date:09/02/2021
Date of Publication:12/02/2021
PDF URL:https://ijsab.com/wp-content/uploads/694.pdf
Free download:Available
Page:148-158
First Page:148
Last Page:158
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Sadeeq, M. J. & Zeebare, S. R. M. (2021). Semantic Search Engine Optimisation (SSEO) for Dynamic Websites: A Review.  International Journal of Science and Business, 5(3), 148-158. doi: https://doi.org/10.5281/zenodo.4536804

Retrieved from https://ijsab.com/wp-content/uploads/694.pdf

 

About Author (s)

Mohammed J. Sadeeq, Information Technology Department, Duhok Polytechnic University,  Duhok – Kurdistan Region, Iraq. Email: mohammed.jameel@uod.ac.

Subhi R. M. Zeebaree, (Corresponding author) Information Technology Department, Duhok Polytechnic University, Duhok – Kurdistan Region, Iraq. Emailil: subhi.rafeeq@dpu.edu.krd.

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4536804

ijsab.com logo

Fog Computing Analysis Based on Internet of Thing: A Review Hindreen Rashid Abdulqadir & Nawzat Sadiq Ahmed

Fog Computing Analysis Based on Internet of Thing: A Review

Author (s)

Hindreen Rashid Abdulqadir & Nawzat Sadiq Ahmed

Abstract

­Cloud machine architectures face many drawbacks due to the improved autonomous and distributed IoT configuration. The IoT is closer to the cloud infrastructure. The fog offers IoT data care and storage locally on IoT devices rather than in the cloud. The fog provides quicker responses and better performance in relation to the cloud. The best alternative for IoT to provide powerful and effective resources for many IoT customers may therefore be called Fog Computing. This paper aims at fog computing’s state-of-the-art and alignment with IoT in detailing the advantages and challenges of implementation. This study will concentrate also on the conception of cloud and fog technology and the application of the cloud and fog paradigm to improve modern IoT technologies. Finally, open issues and alternative research directions are discussed on fog estimation and IoT.

 Keywords: Internet of Things (IoT) , Big data ,  Analyses, Fog Computing , Cloud computing.

Download PDF

Title:Fog Computing Analysis Based on Internet of Thing: A Review
Author:Hindreen Rashid Abdulqadir & Nawzat Sadiq Ahmed
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4534437
Media:Online
Volume:5
Issue:3
Acceptance Date:06/02/2021
Date of Publication:11/02/2021
PDF URL:https://ijsab.com/wp-content/uploads/693.pdf
Free download:Available
Page:137-147
First Page:137
Last Page:147
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Abdulqadir, H. R. & Ahmed, N. S. (2021). Fog computing Analysis Based on Internet of Thing: A Review. International Journal of Science and Business, 5(3), 137-147. doi: https://doi.org/10.5281/zenodo.4534437

 

About Author (s)

Hindreen Rashid Abdulqadir  (corresponding author),   Information Technology Department,  Akre Technical College of Informatics, Duhok Polytechnic University, Duhok Kurdistan Region, Iraq. Email: Hindreen.rashid@dpu.edu.krd

Nawzat Sadiq Ahmed, Information Technology Management Department, Technical College of Administration, Duhok Polytechnic University,Duhok, Kurdistan Region, Iraq. Email: nawzat.ahmed@dpu.edu.krd

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4534437

ijsab.com logo

State of Art for Distributed Databases: Faster Data Access, processing, Growth Facilitation and Improved Communications Ibrahim Shamal Abdulkhaleq, Subhi R. M. Zeebaree

State of Art for Distributed Databases: Faster Data Access, processing, Growth Facilitation and Improved Communications

Author (s)

Ibrahim Shamal Abdulkhaleq, Subhi R. M. Zeebaree

Abstract

­

The technological development has been experiencing rapid growth in the recent years. Individuals need access to required data and information more readily than ever before. To consider this need, the resource development and management are prioritized by the digital world entrepreneurs. In order to provide quick access to the individuals and provide necessary support are fundamentally important for the users. In the present aspects of the digital world, the concept of distributed database, grid system, and cloud systems have completely replaced the need for independent databases. Because of the increasing need and requirements of the computer power and capacity, digital world has been adopting different strategic concerns in order to promote and interconnect dispersedly reserved databases. The concept of distributed database provides the solution for the growing need for addressing the vital aspects of the data management and provision of the access to the required data. This article analyses the concept of database management system, considering relevant review of literature, systematic analysis, investigating the rules for distributed database management system DDBMS, finding appropriate architecture for the DDBMS solutions and providing justified recommendations based on the users’ need and perception.

 Keywords: Distributed Database, Homogeneous Database, Database Securit, DDBMS,  System architecture for DBBMS.

Download PDF

Title:State of Art for Distributed Databases: Faster Data Access, processing, Growth Facilitation and Improved Communications
Author:Ibrahim Shamal Abdulkhaleq, Subhi R. M. Zeebaree
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4518872
Media:Online
Volume:5
Issue:3
Acceptance Date:06/02/2021
Date of Publication:08/02/2021
PDF URL:https://ijsab.com/wp-content/uploads/692.pdf
Free download:Available
Page:126-136
First Page:126
Last Page:136
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Abdulkhaleq, I. S. and Zeebaree, S. R. M. (2021). State of Art for Distributed Databases: Faster Data Access, processing, Growth Facilitation and Improved Communications. International Journal of Science and Business, 5(3), 126-136. doi: https://doi.org/10.5281/zenodo.4518872

Retrieved from https://ijsab.com/wp-content/uploads/692.pdf

 

About Author (s)

Ibrahim Shamal Abdulkhaleq (corresponding author), Information System Engineering Dept.,  Erbil polytechnic University, KRG-Iraq. ibrahim.abdulkhalik@gmail.com

Subhi R. M. Zeebaree Duhok Polytechnic University, KRG-Iraq. subhi.rafeeq@dpu.edu.krd

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4518872

ijsab.com logo

Resistant Blockchain Cryptography to Quantum Computing Attacks Zhwan Mohammed Khalid & Shavan Askar

Resistant Blockchain Cryptography to Quantum Computing Attacks

Author (s)

Zhwan Mohammed Khalid & Shavan Askar

Abstract

­

Due to the need to maintain confidentiality, redundancy, and openness, the usage of Blockchain and other DLTs has dramatically advanced in recent years, and is being recommended for various applications. In blockchain, these capabilities are supplied by means of hash functions and public-key encryption. However, the rapid development of quantum computation in the near future has opened the door to the Grover and Shor algorithms. These algorithms challenge both public and hash encryption, causing blockchains to redesign and use quantum attack-tolerant cryptosystems; this produces cryptosystems which are considered post-quantum cryptosystems, which are quantum-resistant. This paper reviews current scientists on quantum blockchain for such purposes. In addition, the major challenges are studied with the most important post-quantum blockchain systems. In addition, the most promising post quantum signature encryption and digital blockchain signature schemes are detailed in terms of the functionality and durability of the most promising public signatures. In this article, researchers and developers in blockchain have an extensive perspective and practical advice on post-quantum blockchain protection.

 Keywords: Blockchain, cryptography, post-quantum, quantum-resistant, quantum computing, blockchain security.

Download PDF

Title:Resistant Blockchain Cryptography to Quantum Computing Attacks
Author:Zhwan Mohammed Khalid & Shavan Askar
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4497732
Media:Online
Volume:5
Issue:3
Acceptance Date:01/02/2021
Date of Publication:03/02/2021
PDF URL:https://ijsab.com/wp-content/uploads/691.pdf
Free download:Available
Page:116-125
First Page:116
Last Page:125
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Zhwan Mohammed Khalid & Shavan Askar (2021). Resistant Blockchain Cryptography to Quantum Computing Attacks. International Journal of Science and Business, 5(3), 116-125. doi: https://doi.org/10.5281/zenodo.4497732

Retrieved from https://ijsab.com/wp-content/uploads/691.pdf

 

About Author (s)

Zhwan Mohammed Khalid,  Raparin University, Sulaimany, Iraq. Email:eng.zhwan90@uor.edu.krd.

Shavan Askar (Corresponding Author), Assistant Professor, Erbil Polytechnic University, Erbil, Iraq. Email shavan.askar@epu.edu.iq.

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4497732

ijsab.com logo

Security Issues and Vulnerability of IoT Devices Kurdistan Ali & Shavan Askar

Security Issues and Vulnerability of IoT Devices

Author (s)

Kurdistan Ali & Shavan Askar

Abstract

­

The principle of linking intelligent device to the internet is taken out in the internet of things. This model facilitates the relation across the Cloud between the intellectual real items and the separate contact parties, such as the servers, the cellular devices. Internet of things is entering in all aspects of life including home, industries, medical care, cars, sensors, but the main and very important open challenges in this area is security issues. IoT security is very weak this is due to heterogeneous devices used in this field. Therefore, the expansion of security weak points will bring serious dangers to users’ security, and property. This paper discuss the security aspects in the IoT communication protocols and Security threats of multiple layers dependent on the security concepts of data confidently, data integrity and privacy, it also discusses and investigates the main IoT protocols that used to communicate between IoT based nodes and sensors. Furthermore, vulnerability in different protocols are reviewed and compared.

 Keywords: Internet of Things, Security, Privacy, Vulnerabilities, ZigBee, LoRaWaN, 6LoWPAN.

Download PDF

Title:Security Issues and Vulnerability of IoT Devices
Author:Kurdistan Ali & Shavan Askar
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4497707
Media:Online
Volume:5
Issue:3
Acceptance Date:01/02/2021
Date of Publication:03/02/2021
PDF URL:https://ijsab.com/wp-content/uploads/690.pdf
Free download:Available
Page:101-115
First Page:101
Last Page:115
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Kurdistan Ali & Shavan Askar (2021). Security Issues and Vulnerabilities of IoT Devices. International Journal of Science and Business, 5(3), 101-115. doi: https://doi.org/ 10.5281/zenodo.4497707

Retrieved from https://ijsab.com/wp-content/uploads/690.pdf

 

About Author (s)

Kurdistan Ali, Information System Engineering, Erbil Polytechnic University, Erbil, Iraq. Email: Kurdistan.hamaali@epu.edu.iq.

Shavan Askar (Corresponding Author), Assistant Professor, Erbil Polytechnic University, Erbil, Iraq. Email: shavan.askar@epu.edu.iq.

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4497707

ijsab.com logo

Machine Learning Powered IoT for Smart Applications Zhala Jameel Hamad & Shavan Askar

Machine Learning Powered IoT for Smart Applications  

Author (s)

Zhala Jameel Hamad & Shavan Askar

Abstract

­

With the coming of fast advancements, with the assistance of IoT, a great percentage of heterogeneous devices can be connected with each other. The technology with the relationship of different devices through the internet is named the internet of things (IoT), makes a wide number of different characteristics and qualities of data. IoT and Machine learning (ML) guarantees the widespread advancement to grow the insights of the IoT devices and applications. Over the final few years, artificial intelligence and machine learning have advanced very significantly. It allows a machine or system to learn more effectively than people learn on their own. When we learn some kind of system about the concept of our trial or the knowledge obtained after evaluating it. Combining IoT with rapidly advancing ML technologies can make ‘smart machines’ that mimic smart action to do well-informed resolve with little or no human involvement. There are at least two fundamental reasons, why machine learning is a suitable solution for the IoT world? The primary has got to do with the volume of data and the automation openings. The second is related to the prescient investigation. Therefore, this paper focuses on ML in different techniques and different domains that motivate and support IoT applications. Many previous works related to this subject and examples have been addressed, explained in detail. The results showed that ML plays a vital role in monitoring, processing, systematic investigation, and smart use of the expansive measure of data in several fields. It was also beneficial for helping users’ process massive data.

 Keywords: Machine Learning, Internet of things, SDN, Smart Applications.

Download PDF

Title:Machine Learning Powered IoT for Smart Applications  
Author:Zhala Jameel Hamad & Shavan Askar
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4497664
Media:Online
Volume:5
Issue:3
Acceptance Date:01/02/2021
Date of Publication:03/02/2021
PDF URL:https://ijsab.com/wp-content/uploads/689.pdf
Free download:Available
Page:92-100
First Page:92
Last Page:100
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Zhala Jameel Hamad & Shavan Askar (2021). Machine Learning Powered IoT for Smart Applications. International Journal of Science and Business, 5(3), 92-100. doi: https://doi.org/10.5281/zenodo.4497664

Retrieved from https://ijsab.com/wp-content/uploads/689.pdf

 

About Author (s)

Zhala Jameel Hamad  Information System Engineering, Erbil Polytechnic University, Erbil, Iraq. Email: zhalla.mei20@epu.edu.iq.

Shavan Askar (Corresponding Author), Assistant Professor, Erbil Polytechnic University, Erbil, Iraq. Email: shavan.askar@epu.edu.iq.

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4497664

ijsab.com logo

Software Defined Network Based VANET Glena Aziz & Shavan Askar

Software Defined Network Based VANET

Author (s)

Glena Aziz & Shavan Askar

Abstract

­

As the number of cars is growing, there is also a rapid growth in the number of road side accident. Much of these incidents have occurred by an error made by a driver. New protocols and architecture are rapidly being created for intelligent transport networks by researchers all over the world. To guarantee passengers’ safety, several companies are now encouraging an ad hoc vehicular network (VANET). In another side, before practically adopting VANET technology, there are many concerns related to this field that need to be discussed. A number of attacks can occur in the event of no or weak protection, which can be affected by the performance and reliability of the process. In order to make VANET networks more successful, it implements software defined networking (SDN) technology. This technique was briefly called SDN-VANET. The SDN in VANET framework enables us to prevent from the limitations and complexities of basic VANET structures. Through handling the whole network from a single remote controller, it allows them to reduce the overall burden on the network. In this article we describe SDN-based VANET, its working, benefits, challenges and services, applications, and security attacks.

 Keywords: Network Security, transport networks, VANET, software defined networking (SDN).

Download PDF

Title:Software Defined Network Based VANET
Author:Glena Aziz & Shavan Askar
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4497640
Media:Online
Volume:5
Issue:3
Acceptance Date:01/02/2021
Date of Publication:03/02/2021
PDF URL:https://ijsab.com/wp-content/uploads/688.pdf
Free download:Available
Page:83-91
First Page:83
Last Page:91
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Ibrahim Shamal Abdulkhaleq & Shavan Askar (2021). Evaluating the Impact of Network Latency on the Safety of Blockchain Transactions. International Journal of Science and Business, 5(3), 71-82. doi: https://doi.org/10.5281/zenodo.4497512

Retrieved from https://ijsab.com/wp-content/uploads/687.pdf

 

About Author (s)

Glena Aziz Qadir,  Information System Engineering, Erbil Polytechnic University, Erbil, Iraq. Email: glena.mei20@epu.edu.iq.

Shavan Askar (Corresponding Author), Assistant Professor, Erbil Polytechnic University, Erbil, Iraq. Email: shavan.askar@epu.edu.iq.

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4497640

ijsab.com logo

Evaluating the Impact of Network Latency on the Safety of Blockchain Transactions Ibrahim Shamal Abdulkhaleq & Shavan Askar

Evaluating the Impact of Network Latency on the Safety of Blockchain Transactions

Author (s)

Ibrahim Shamal Abdulkhaleq & Shavan Askar

Abstract

­

Blockchain technology has lately become widely regarded, partially because of the surge in cryptocurrencies such as Bitcoin and their ability to be a force for economic and financial shift. While tokenomics also helped push blockchain in mainstream, this technology’s strengths are far more than crypt-monetary. Often known as distributed leader technologies, it is hypothesized that blockchain would serve like a catalyst for global disruptions and that blockchain-based applications in many industries such as the supply chain; the medical and legal fields are now being developed and implemented. By simultaneous research, we prove that the six confirms convention is vulnerable to peer-to-peer latency in the network and show just how readily PoW mining is broken. The divergences between these latest blocks open the transactions in question to the possibility that the blockchain fork will not be used. We concentrate on evaluating block detection accuracy and the breach of the six confirmed blockchain agreement.

 Keywords: Blockchain, network latency, PoW, cryptocurrency, IoT.

Download PDF

Title:Evaluating the Impact of Network Latency on the Safety of Blockchain Transactions
Author:Ibrahim Shamal Abdulkhaleq & Shavan Askar
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4497512
Media:Online
Volume:5
Issue:3
Acceptance Date:01/02/2021
Date of Publication:03/02/2021
PDF URL:https://ijsab.com/wp-content/uploads/687.pdf
Free download:Available
Page:71-82
First Page:71
Last Page:82
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Ibrahim Shamal Abdulkhaleq & Shavan Askar (2021). Evaluating the Impact of Network Latency on the Safety of Blockchain Transactions. International Journal of Science and Business, 5(3), 71-82. doi: https://doi.org/10.5281/zenodo.4497512

Retrieved from https://ijsab.com/wp-content/uploads/687.pdf

 

About Author (s)

Ibrahim Shamal Abdulkhaleq, Information System Engineering, Erbil Polytechnic University, Erbil, Iraq.

Shavan Askar (Corresponding Author), Assistant Professor, Erbil Polytechnic University, Erbil, Iraq. Email: shavan.askar@epu.edu.iq.

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4497512

ijsab.com logo

Deep Learning Models for Cyber Security in IoT Networks: A Review Kosrat Dlshad Ahmed & Shavan Askar

Deep Learning Models for Cyber Security in IoT Networks: A Review

Author (s)

Kosrat Dlshad Ahmed & Shavan Askar

Abstract

­

The IoT systems and connectivity provide improved experience and improve the quality of service for the users in different perspectives. Recent development of the technological prospects and management of the sufficient aspects for the delivery of performance need to be ensured in this regard. The concept of IoT is related with the widely connected features, systems, data storage facilities, management processes, applications, devices, users, gateways, services and thousands of other elements. As the importance of IoT applications has been growing in recent times, the prospects for development and management are immense for the development opportunities. In recent times, cybersecurity and ensuring privacy for the users have attracted attention of the users. With growing popularity of the social media platforms, more and more people are becoming connected. With growing opportunity of connectivity, people need more secured space to connect. In this article, different aspects of the cybersecurity based on the deep learning models and analyzing the concepts of machine learning, understanding the concept of security and privacy, contributing to the development and management of cybersecurity etc. To demonstrate the understanding of cybersecurity in the IoT networks, effective deep learning models such as MLP, CNN, LSTP and a hybrid model of CNN and LSTP have been analyzed. To contribute to the learning process, future research opportunities have also been identified.

 Keywords: Deep Leaning, Machine Learning, Cyber Security, Internet of Things, Privacy, Cyber Security.

Download PDF

Title:Deep Learning Models for Cyber Security in IoT Networks: A Review
Author:Kosrat Dlshad Ahmed & Shavan Askar
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4497017
Media:Online
Volume:5
Issue:3
Acceptance Date:01/02/2021
Date of Publication:03/02/2021
PDF URL:https://ijsab.com/wp-content/uploads/686.pdf
Free download:Available
Page:61-70
First Page:61
Last Page:70
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Kosrat Dlshad Ahmed, Shavan Askar (2021). Deep Learning Models for Cyber Security in IoT Networks: A Review. International Journal of Science and Business, 5(3), 61-70. doi: https://doi.org/10.5281/zenodo.4497017

Retrieved from https://ijsab.com/wp-content/uploads/686.pdf

 

About Author (s)

Kosrat Dlshad Ahmed, Information System Engineering, Erbil Polytechnic University, Erbil, Iraq. Email: kosrat.ahmed@epu.edu.iq.

Shavan Askar (Corresponding Author), Assistant Professor, Erbil Polytechnic University, Erbil, Iraq.  Email: shavan.askar@epu.edu.iq.

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4497017

ijsab.com logo

Survey on Edge Computing Security Baydaa Hassan Husain & Shavan Askar

Survey on Edge Computing Security

Author (s)

Baydaa Hassan Husain & Shavan Askar

Abstract

­

It’s possible to explain Edge computing (EC) as a distributed system of IT that decentralized the power of processing in which the mobile Internet of Things (IoT) computing would be allowed. In EC, data processed by local tools, computers, or servers, instead of being process and transmitted from the data center. However, with the wider capabilities of EC by increasing the network performance and reducing the latency, security challenges, and the risks will increase with data being stored and used on these devices on the edge or end of the network. This paper first provides a definition of EC and explain the reasons that led to the rapid spread of this type of computing with an explanation of the most important differences between EC and CC, in terms of the resources available for each type, processing, storage, as well as the privacy and security factor. Later, explaining the uses and benefits of this type of computing. However, the challenges are also taken into consideration, foremost among which is security. Through reviewing a number of previous researches, security challenges have been identified in four main sectors, including data privacy and security, access control, attack mitigation, and detection for anomalies Finally, choosing a set of solutions that were drawn from previous studies and contributed in reducing and limiting these challenges. Hopping this paper sheds light on Edge Computing security and paves the way for more future research.

 Keywords: Edge Computing (EC), Internet of Things (IoT), Cloud Computing, Security, distributed system of IT.

Download PDF

Title:Survey on Edge Computing Security
Author:Baydaa Hassan Husain & Shavan Askar
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4496939
Media:Online
Volume:5
Issue:3
Acceptance Date:01/02/2021
Date of Publication:03/02/2021
PDF URL:https://ijsab.com/wp-content/uploads/685.pdf
Free download:Available
Page:52-60
First Page:52
Last Page:60
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Baydaa Hassan Husain & Shavan Askar (2021). Survey on Edge Computing Security. International Journal of Science and Business, 5(3), 52-60. doi: https://doi.org/ 10.5281/zenodo.4496939

Retrieved from https://ijsab.com/wp-content/uploads/685.pdf

 

About Author (s)

Baydaa Hassan Husain,  Information System Engineering, Erbil Polytechnic University, Erbil, Iraq. Email: baydaa.mei20@epu.edu.iq.

Shavan Askar (Corresponding Author), Assistant Professor, Erbil Polytechnic University, Erbil, Iraq. Email: shavan.askar@epu.edu.iq.

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4496939

ijsab.com logo

Machine Learning for IoT HealthCare Applications: A Review Chnar Mustafa Mohammed & Shavan Askar

Machine Learning for IoT HealthCare Applications: A Review

Author (s)

Chnar Mustafa Mohammed & Shavan Askar

Abstract

­

Internet of Things and Machine Learning (ML) have wide applicability in many aspects of life, health care is one of them. With the rapid development and improvement of the internet, the conventional strategies for patient services diminished and supplanted with electronic healthcare systems. The use of IoT technology offers medical professionals and patients the most modern medical device environment. IoT things and Machine-Learning are valuable in various classifications from far off observing of the modern climate to mechanical mechanization. Moreover, medical care applications are principally indicating interest in IoT things in view of cost decrease, easy to understand and improve the personal satisfaction of patients. The latest applications for IoT medical treatment, investigated and still facing problems in the clinical environment, are needed for intellectual, creativity-based answers. In specific, portable, and implantable IoT model devices, investigated for calculating the data transmission. Implantable technologies lead to the natural substitution of the injured part of the human body. The creation of a wearable and implantable healthcare body area network faced several challenges that are illustrated in this study. In this paper, an overview of IoT and Machine Learning based on healthcare care demonstrated in detail, the applications that use in health care by incorporating Machine Learning (ML) for the Internet of Things (IoT) listed with all issues and challenges while using this application or devices for health care and their important usage. Also, algorithms used by Machine Learning in IoT for developing devices are indicated by showing previous work and classified each of them according to the used method.

 Keywords: Internet of Things, Machine Learning, Wearable devices, personalized health care, and implantable devices.

Download PDF

Title:Machine Learning for IoT HealthCare Applications: A Review
Author:Chnar Mustafa Mohammed & Shavan Askar
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4496904
Media:Online
Volume:5
Issue:3
Acceptance Date:31/01/2021
Date of Publication:03/02/2021
PDF URL:https://ijsab.com/wp-content/uploads/684.pdf
Free download:Available
Page:42-51
First Page:42
Last Page:51
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Chnar Mustafa Mohammed & Shavan Askar (2021). Machine Learning for IoT HealthCare Applications: A Review. International Journal of Science and Business, 5(3), 42-51. doi: https://doi.org/10.5281/zenodo.4496904

Retrieved from https://ijsab.com/wp-content/uploads/684.pdf

 

About Author (s)

Chnar Mustaf Mohammed,  Information System Engineering, Erbil Polytechnic University, Erbil, Iraq.

Shavan Askar (Corresponding Author), Assistant Professor, Erbil Polytechnic University, Erbil, Iraq. Email: shavan.askar@epu.edu.iq

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4496904

ijsab.com logo

Medical Text Classification Based on Convolutional Neural Network: A Review Hazha Saeed Yahia & Adnan Mohsin Abdulazeez

Medical Text Classification Based on Convolutional Neural Network: A Review

Author (s)

Hazha Saeed Yahia & Adnan Mohsin Abdulazeez

Abstract

­

Medical text classification has a significant impact on disease diagnosis, medical research, and the automatic development of disease ontology, acquiring knowledge of clinical results recorded in the medical literature. Hence, medical text classification is challenging because it contains terminologies that describe medical concepts and terminologies. Furthermore, the medical data mostly does not follow natural language grammar; it has inadequate grammatical sentences. The techniques used for text classification give different results comparing to medical text classifications, as extracting text and training sets are different. One of the most significant text classification models in general and medical text classification specifically is CNN-based models. In this paper, many papers on medical text classification have been reviewed, and the details of each article, such as algorithms, or approaches used, databases, classification techniques, and outcomes obtained, are evaluated and outlined thoroughly. Besides, discussions were carried out on all the studied papers, which profoundly influenced medical documents classification.

 Keywords: Text classification, Medical text classification, Neural networks, Convolutional neural networks, CNN architecture.

Download PDF

Title:Medical Text Classification Based on Convolutional Neural Network: A Review
Author:Hazha Saeed Yahia & Adnan Mohsin Abdulazeez
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4483635
Media:Online
Volume:5
Issue:3
Acceptance Date:30/01/2021
Date of Publication:31/01/2021
PDF URL:https://ijsab.com/wp-content/uploads/683.pdf
Free download:Available
Page:27-41
First Page:27
Last Page:41
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Hazha Saeed Yahia & Adnan Mohsin Abdulazeez (2021). Medical Text Classification Based on Convolutional Neural Network: A Review. International Journal of Science and Business, 5(3), 27-41. doi: https://doi.org/10.5281/zenodo.4483635

Retrieved from https://ijsab.com/wp-content/uploads/683.pdf

 

About Author (s)

Hazha Saeed Yahia (corresponding author), Poly Techniques University, Duhok, Kurdistan Region, Iraq. E-mail: Hazha.yahia@gmail.com

Professor Adnan Mohsin Abdulazeez, Duhok Polytechnic University, Duhok, Kurdistan Region, Iraq.

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4483635

ijsab.com logo

Identifying Speakers Using Deep Learning: A review Lawchak Fadhil Khalid & Adnan Mohsin Abdulazeez

Identifying Speakers Using Deep Learning: A review

Author (s)

Lawchak Fadhil Khalid & Adnan Mohsin Abdulazeez

Abstract

­With the advancement of technology and the increasing demand on smart systems and smart applications that provide a quality-of-life improvement, there has been a surge in the demand of more conscious applications, Machine Learning (ML) is considered one of the driving forces behind implementing these types of applications, and one of its implementations is Speaker Identification (SID). Deep Neural Networks (DNNs) and also Recurrent Neural Networks (RNNs) are two main types of Deep Learning that are being used in the implementation of such applications. Speaker Identification is being utilized more and more on daily basis and is being focused on by the research community as a result of this demand. In this paper, a review will be conducted to some of the most recent researches that were conducted in this area and compare their results while discussing their outcomes.

 Keywords: Machine Learning, Speaker Identification, Deep Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks.

Download PDF

Title:Identifying Speakers Using Deep Learning: A review
Author:Lawchak Fadhil Khalid & Adnan Mohsin Abdulazeez
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4481596
Media:Online
Volume:5
Issue:3
Acceptance Date:28/01/2021
Date of Publication:30/01/2021
PDF URL:https://ijsab.com/wp-content/uploads/682.pdf
Free download:Available
Page:15-26
First Page:15
Last Page:26
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Lawchak Fadhil Khalid & Adnan Mohsin Abdulazeez (2021). Identifying Speakers Using Deep Learning: A review. International Journal of Science and Business, 5(3), 15-26. doi: https://doi.org/10.5281/zenodo.4481596

Retrieved from https://ijsab.com/wp-content/uploads/682.pdf

 

About Author (s)

Lawchak Fadhil Khalid (corresponding author), Technical College of Informatics – Akre, Duhok Polytechnic University (DPU), Kurdistan Region, Iraq. Email: lawchak.fadhil@gmail.com

Adnan Mohsin Abdulazeez, Duhok Polytechnic University (DPU), Kurdistan Region, Iraq.

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4481596

ijsab.com logo

Deep Learning Convolutional Neural Network for Speech Recognition: A Review Kazheen Ismael Taher & Adnan Mohsin Abdulazeez

Deep Learning Convolutional Neural Network for Speech Recognition: A Review

Author (s)

Kazheen Ismael Taher & Adnan Mohsin Abdulazeez

Abstract

­In the last few decades, there has been considerable amount of research on the use of Machine Learning (ML) for speech recognition based on Convolutional Neural Network (CNN). These studies are generally focused on using CNN for applications related to speech recognition. Additionally, various works are discussed that are based on deep learning since its emergence in the speech recognition applications. Comparing to other approaches, the approaches based on deep learning are showing rather interesting outcomes in several applications including speech recognition, and therefore, it attracts a lot of researches and studies. In this paper, a review is presented on the developments that occurred in this field while also discussing the current researches that are being based on the topic currently.

 Keywords: Machine Learning, Speech Recognition, Convolutional Neural Networks, Deep Learning, Word Error Rate (WER).

Download PDF

Title:Deep Learning Convolutional Neural Network for Speech Recognition: A Review
Author:Kazheen Ismael Taher & Adnan Mohsin Abdulazeez
Journal Name:International Journal of Science and Business
Website:ijsab.com
ISSN:ISSN 2520-4750 (Online), ISSN 2521-3040 (Print)
DOI:https://doi.org/10.5281/zenodo.4475361
Media:Online
Volume:5
Issue:3
Acceptance Date:24/01/2021
Date of Publication:28/01/2021
PDF URL:https://ijsab.com/wp-content/uploads/681.pdf
Free download:Available
Page:1-14
First Page:1
Last Page:14
Paper Type:Literature Review
Current Status:Published

 

Cite This Article:

Kazheen Ismael Taher & Adnan Mohsin Abdulazeez (2021). Deep Learning Convolutional Neural Network for Speech Recognition: A Review. International Journal of Science and Business, 5(3), 1-14. doi: https://doi.org/10.5281/zenodo.4475361

Retrieved from https://ijsab.com/wp-content/uploads/681.pdf

 

About Author (s)

Kazheen Ismael Taher (corresponding author), Information Technology Department, Akre Technical College of Informatics, Duhok Polytechnic University, Duhok, Kurdistan Region, Iraq. E-mail: kajeen.ismael@gmail.com

Professor Adnan Mohsin Abdulazeez, Duhok Polytechnic University, Duhok, Kurdistan Region, Iraq. E-mail: adnan.mohsin@dpu.edu.krd

 

 Download PDF

DOI: https://doi.org/10.5281/zenodo.4475361