Most recent issue published online in the International Journal of Intelligent Engineering Informatics.
International Journal of Intelligent Engineering Informatics
http://www.inderscience.com/browse/index.php?journalID=338&year=2023&vol=11&issue=4
Inderscience Publishers Ltd
en-uk
support@inderscience.com
International Journal of Intelligent Engineering Informatics
1758-8715
1758-8723
© 2024 Inderscience Enterprises Ltd.
© 2023 Inderscience Publishers Ltd
editor@inderscience.com
International Journal of Intelligent Engineering Informatics
https://www.inderscience.com/images/files/coverImgs/ijiei_scoverijiei.jpg
http://www.inderscience.com/browse/index.php?journalID=338&year=2023&vol=11&issue=4
-
Methods of anomaly detection for the prevention and detection of cyber attacks
http://www.inderscience.com/link.php?id=136097
The idea of the 'smart city' has developed in response to the issues brought on by the rapid growth in urbanisation and population. Smart cities are interconnected. IoT and big data analytics enable smart city efforts. IoT devices connected to the always-on IoT network for several functions make unauthorised entry easier. This issue involves the safety system's ability to identify prior unidentified attacks. System behavioural modelling and unattended or semi-supervised machine learning could solve this problem. Machine learning model training datasets affect security system efficacy. Cyber-physical objects' security restrictions make system data inaccessible. These datasets have been constructed several times, but their reliability and completeness are questionable. Cyber attacks affect data privacy and security in connected IoT contexts, including smart infrastructure, communication, e-governance, etc. Cybersecurity requires a machine learning-based intelligent detection system. IoT anomaly detection finds odd behaviour. Many researchers have studied anomaly detection methods to detect and thwart data exchange cyber attacks. Existing technologies detected some cyber attacks, but others required newer, more powerful approaches. This article discusses the pros and cons of different methods and highlights the obstacles and research gaps that prevent anomaly detection approaches from reaching their full potential.
Methods of anomaly detection for the prevention and detection of cyber attacks
N. Girubagari; T.N. Ravi
International Journal of Intelligent Engineering Informatics, Vol. 11, No. 4 (2023) pp. 299 - 316
The idea of the 'smart city' has developed in response to the issues brought on by the rapid growth in urbanisation and population. Smart cities are interconnected. IoT and big data analytics enable smart city efforts. IoT devices connected to the always-on IoT network for several functions make unauthorised entry easier. This issue involves the safety system's ability to identify prior unidentified attacks. System behavioural modelling and unattended or semi-supervised machine learning could solve this problem. Machine learning model training datasets affect security system efficacy. Cyber-physical objects' security restrictions make system data inaccessible. These datasets have been constructed several times, but their reliability and completeness are questionable. Cyber attacks affect data privacy and security in connected IoT contexts, including smart infrastructure, communication, e-governance, etc. Cybersecurity requires a machine learning-based intelligent detection system. IoT anomaly detection finds odd behaviour. Many researchers have studied anomaly detection methods to detect and thwart data exchange cyber attacks. Existing technologies detected some cyber attacks, but others required newer, more powerful approaches. This article discusses the pros and cons of different methods and highlights the obstacles and research gaps that prevent anomaly detection approaches from reaching their full potential.]]>
10.1504/IJIEI.2023.136097
International Journal of Intelligent Engineering Informatics, Vol. 11, No. 4 (2023) pp. 299 - 316
N. Girubagari
T.N. Ravi
Department of Computer Science, Thanthai Periyar Government Arts and Science College, Tiruchirappalli, Tamil Nadu, India; Affiliated to: Bharathidasan University, India ' Department of Computer Science, Thanthai Periyar Government Arts and Science College, Tiruchirappalli, Tamil Nadu, India; Affiliated to: Bharathidasan University, India
smart city
big data
internet of things
IoT
cyber attacks
attacks detection
anomaly detection
machine learning
2024-01-16T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
11
4
299
316
2024-01-16T23:20:50-05:00
-
Dual strategy based missing completely at random type missing data imputation on the internet of medical things
http://www.inderscience.com/link.php?id=136100
One problem that reduces performance in data analysis is missing data. Improper imputation of missing data may lead to an incorrect prediction. In the internet of medical things (IoMT) era, when a lot of data is created every second and data utilisation is a major issue for healthcare providers, missing values must be managed well. The literature proposes many missing data imputation methods. However, excessive missing value instances diminish the number of complete examples in the collection. Imputing missing data with few complete instances will not improve results. The number of complete instances could be raised by considering the imputed item as a complete object and utilising it alongside the existing complete instances for future imputations. So this work introduces a new dual strategy-based missing data imputation (DS-MDI) approach for IoMT missing completely at random (MCAR) data. The proposed DS-MDI technique uses cube-root-of-cubic-mean and enhanced Levenshtein distance-based clustering (ELDC) with cluster-directed closest neighbour selection (CSNN). This approach imputes more items using imputed objects. The Kaggle Machine Learning Repository's cStick IoMT dataset was processed using the suggested technique. The DS-MDI algorithm outperforms current missing data imputation algorithms in accuracy, precision, recall, and F-measure.
Dual strategy based missing completely at random type missing data imputation on the internet of medical things
P. Iris Punitha; J.G.R. Sathiaseelan
International Journal of Intelligent Engineering Informatics, Vol. 11, No. 4 (2023) pp. 317 - 336
One problem that reduces performance in data analysis is missing data. Improper imputation of missing data may lead to an incorrect prediction. In the internet of medical things (IoMT) era, when a lot of data is created every second and data utilisation is a major issue for healthcare providers, missing values must be managed well. The literature proposes many missing data imputation methods. However, excessive missing value instances diminish the number of complete examples in the collection. Imputing missing data with few complete instances will not improve results. The number of complete instances could be raised by considering the imputed item as a complete object and utilising it alongside the existing complete instances for future imputations. So this work introduces a new dual strategy-based missing data imputation (DS-MDI) approach for IoMT missing completely at random (MCAR) data. The proposed DS-MDI technique uses cube-root-of-cubic-mean and enhanced Levenshtein distance-based clustering (ELDC) with cluster-directed closest neighbour selection (CSNN). This approach imputes more items using imputed objects. The Kaggle Machine Learning Repository's cStick IoMT dataset was processed using the suggested technique. The DS-MDI algorithm outperforms current missing data imputation algorithms in accuracy, precision, recall, and F-measure.]]>
10.1504/IJIEI.2023.136100
International Journal of Intelligent Engineering Informatics, Vol. 11, No. 4 (2023) pp. 317 - 336
P. Iris Punitha
J.G.R. Sathiaseelan
Department of Computer Applications, Bishop Heber College (Autonomous), Tiruchirappalli, Tamil Nadu, 620 017, India; Affiliated to: Bharathidasan University, India ' Department of Computer Applications, Bishop Heber College (Autonomous), Tiruchirappalli, Tamil Nadu, 620 017, India; Affiliated to: Bharathidasan University, India
missing data imputation
internet of medical things
IoMT
mean imputation and clustering
cluster-directed closest neighbour selection
CSNN
enhanced Levenshtein distance-based clustering
ELDC
2024-01-16T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
11
4
317
336
2024-01-16T23:20:50-05:00
-
A hybrid optimal solution for the combinatorial problem of vehicle routing
http://www.inderscience.com/link.php?id=136104
Vehicle routing problem (VRP) is a classic combinatorial optimisation problem. It is a type of problem in which the solution is made up of a set of fundamental discrete decisions or assumptions. For solving a class of this issue, we devised a hybrid approach that integrates certain characteristics of firefly optimisation and particle swarm optimisation algorithms. The objective is to derive the best possible solutions for capacitated VRP using this hybrid optimisation model. The unexplored solution space is searched in the proposed work through FA, whereas PSO provided the essential structure for our suggested approach. Dynamic adaptation for some parameters is applied to some particles which gradually increases its values during the search process for the velocity values. It is worth noting that the particles utilise the dynamic values at each generation will be different. The best possible solutions are from a run of 20 experiments are evaluated and compared with the other approaches.
A hybrid optimal solution for the combinatorial problem of vehicle routing
Kirti Pandey; Chandra Kumar Jha
International Journal of Intelligent Engineering Informatics, Vol. 11, No. 4 (2023) pp. 337 - 352
Vehicle routing problem (VRP) is a classic combinatorial optimisation problem. It is a type of problem in which the solution is made up of a set of fundamental discrete decisions or assumptions. For solving a class of this issue, we devised a hybrid approach that integrates certain characteristics of firefly optimisation and particle swarm optimisation algorithms. The objective is to derive the best possible solutions for capacitated VRP using this hybrid optimisation model. The unexplored solution space is searched in the proposed work through FA, whereas PSO provided the essential structure for our suggested approach. Dynamic adaptation for some parameters is applied to some particles which gradually increases its values during the search process for the velocity values. It is worth noting that the particles utilise the dynamic values at each generation will be different. The best possible solutions are from a run of 20 experiments are evaluated and compared with the other approaches.]]>
10.1504/IJIEI.2023.136104
International Journal of Intelligent Engineering Informatics, Vol. 11, No. 4 (2023) pp. 337 - 352
Kirti Pandey
Chandra Kumar Jha
Computer Science Department, Banasthali Vidyapith, Rajasthan, India ' Computer Science Department, Banasthali Vidyapith, Rajasthan, India
combinatorial problem
firefly algorithm
particle swarm optimisation
PSO
vehicle routing problem
VRP
dynamic adaptation mechanism
2024-01-16T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
11
4
337
352
2024-01-16T23:20:50-05:00
-
Type-n fuzzy logic - the next level of type-1 and type-2 fuzzy logic
http://www.inderscience.com/link.php?id=136106
The level of uncertainty in a system can be reduced by using type-2 fuzzy logic, which has a superior ability to handle linguistic uncertainties by modelling ambiguity and unreliability of information. Unfortunately, type-2 fuzzy sets are harder to use and understand than type-1 fuzzy sets. This article provides a comprehensive idea on non-stationary fuzzy inference system (FIS) as well as a generalised approach to the extended type-2 fuzzy approach. A new proposed breakdown of T2FS along with stationary and non-stationary fuzzy sets (FIS) is also described using the fuzzy inference system in this article. Besides that, it describes a new generalised FIS technique and ends with a generalised computation of the centroid of a type-2 fuzzy system. A new proposed breakdown of T2FS along with stationary and non-stationary fuzzy sets (FIS) is also described using the fuzzy inference system in this article.
Type-n fuzzy logic - the next level of type-1 and type-2 fuzzy logic
Saikat Maity; Sanjay Chakraborty; Saroj Kumar Pandey; Indrajit De; Sourasish Nath
International Journal of Intelligent Engineering Informatics, Vol. 11, No. 4 (2023) pp. 353 - 389
The level of uncertainty in a system can be reduced by using type-2 fuzzy logic, which has a superior ability to handle linguistic uncertainties by modelling ambiguity and unreliability of information. Unfortunately, type-2 fuzzy sets are harder to use and understand than type-1 fuzzy sets. This article provides a comprehensive idea on non-stationary fuzzy inference system (FIS) as well as a generalised approach to the extended type-2 fuzzy approach. A new proposed breakdown of T2FS along with stationary and non-stationary fuzzy sets (FIS) is also described using the fuzzy inference system in this article. Besides that, it describes a new generalised FIS technique and ends with a generalised computation of the centroid of a type-2 fuzzy system. A new proposed breakdown of T2FS along with stationary and non-stationary fuzzy sets (FIS) is also described using the fuzzy inference system in this article.]]>
10.1504/IJIEI.2023.136106
International Journal of Intelligent Engineering Informatics, Vol. 11, No. 4 (2023) pp. 353 - 389
Saikat Maity
Sanjay Chakraborty
Saroj Kumar Pandey
Indrajit De
Sourasish Nath
Department of Computer Science and Engineering, Sister Nivedita University, Kolkata, India ' Department of Computer Science and Engineering, Techno International New Town, Kolkata, India ' Department of Computer Engineering and Applications, GLA University, Mathura, India ' Department of Computer Science and Engineering, Institute of Engineering and Management, Kolkata, India ' Department of Computer Science and Engineering, JIS University, Kolkata, India
fuzzy sets
type-2
decomposition
non-stationary fuzzy sets
fuzzy logic
2024-01-16T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
11
4
353
389
2024-01-16T23:20:50-05:00
-
Sentiment analysis using various machine learning algorithms for disaster related tweets classification
http://www.inderscience.com/link.php?id=136101
Once a crisis arises, people use social media platforms (such as Twitter) to communicate real-time updates. This data is incredibly helpful to disaster relief and response organisations and may offer rapid notifications for prioritising requests. Text mining and machine learning algorithms can scan enormous amounts of unstructured data created by social media outlets like Twitter to recognise disaster-related content based on keywords and phrases. One of the difficulties that algorithms may confront is determining whether the tweet content discusses actual disasters or uses these keywords as metaphors. As a result, this research aims to apply natural language processing (NLP) and classification models to discriminate between authentic and bogus disaster tweets. This dataset from the Kaggle website includes tweets about genuine disasters and fictional disasters. Four machine learning classifier methods were used: KNN, SVM, XGBoostand, and Naive Bayes. KNN offers the highest accuracy.
Sentiment analysis using various machine learning algorithms for disaster related tweets classification
S. Baby Sudha; S. Dhanalakshmi
International Journal of Intelligent Engineering Informatics, Vol. 11, No. 4 (2023) pp. 390 - 417
Once a crisis arises, people use social media platforms (such as Twitter) to communicate real-time updates. This data is incredibly helpful to disaster relief and response organisations and may offer rapid notifications for prioritising requests. Text mining and machine learning algorithms can scan enormous amounts of unstructured data created by social media outlets like Twitter to recognise disaster-related content based on keywords and phrases. One of the difficulties that algorithms may confront is determining whether the tweet content discusses actual disasters or uses these keywords as metaphors. As a result, this research aims to apply natural language processing (NLP) and classification models to discriminate between authentic and bogus disaster tweets. This dataset from the Kaggle website includes tweets about genuine disasters and fictional disasters. Four machine learning classifier methods were used: KNN, SVM, XGBoostand, and Naive Bayes. KNN offers the highest accuracy.]]>
10.1504/IJIEI.2023.136101
International Journal of Intelligent Engineering Informatics, Vol. 11, No. 4 (2023) pp. 390 - 417
S. Baby Sudha
S. Dhanalakshmi
Department of Computer Science, Sri Krishna Arts and Science College, Coimbatore, Tamil Nadu, India ' Department of Software Systems, Sri Krishna Arts and Science College, Coimbatore, Tamil Nadu, India
disaster tweets
SVM
XGBoost
naïve Bayes
KNN
tweets classification
various machine learning algorithms
fakes and metaphors
disaster prediction task
2024-01-16T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
11
4
390
417
2024-01-16T23:20:50-05:00