A literature review of the positive displacement compressor : current challenges and future opportunities
- Lu, Kui, Sultan, Ibrahim, Phung, Truong
- Authors: Lu, Kui , Sultan, Ibrahim , Phung, Truong
- Date: 2023
- Type: Text , Journal article , Review
- Relation: Energies Vol. 16, no. 20 (2023), p.
- Full Text:
- Reviewed:
- Description: Positive displacement compressors are essential in many engineering systems, from domestic to industrial applications. Many studies have been devoted to providing more insights into the workings and proposing solutions for performance improvements of these machines. This study aims to present a systematic review of published research on positive displacement compressors of various geometrical structures. This paper discusses the literature on compressor topics, including leakage, heat transfer, friction and lubrication, valve dynamics, port characteristics, and capacity control strategies. Moreover, the current status of the application of machine learning methods in positive displacement compressors is also discussed. The challenges and opportunities for future work are presented at the end of the paper. © 2023 by the authors.
- Authors: Lu, Kui , Sultan, Ibrahim , Phung, Truong
- Date: 2023
- Type: Text , Journal article , Review
- Relation: Energies Vol. 16, no. 20 (2023), p.
- Full Text:
- Reviewed:
- Description: Positive displacement compressors are essential in many engineering systems, from domestic to industrial applications. Many studies have been devoted to providing more insights into the workings and proposing solutions for performance improvements of these machines. This study aims to present a systematic review of published research on positive displacement compressors of various geometrical structures. This paper discusses the literature on compressor topics, including leakage, heat transfer, friction and lubrication, valve dynamics, port characteristics, and capacity control strategies. Moreover, the current status of the application of machine learning methods in positive displacement compressors is also discussed. The challenges and opportunities for future work are presented at the end of the paper. © 2023 by the authors.
A smart healthcare framework for detection and monitoring of COVID-19 using IoT and cloud computing
- Nasser, Nidal, Emad-ul-Haq, Qazi, Imran, Muhammad, Ali, Asmaa, Razzak, Imran, Al-Helali, Abdulaziz
- Authors: Nasser, Nidal , Emad-ul-Haq, Qazi , Imran, Muhammad , Ali, Asmaa , Razzak, Imran , Al-Helali, Abdulaziz
- Date: 2023
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 35, no. 19 (2023), p. 13775-13789
- Full Text:
- Reviewed:
- Description: Coronavirus (COVID-19) is a very contagious infection that has drawn the world’s attention. Modeling such diseases can be extremely valuable in predicting their effects. Although classic statistical modeling may provide adequate models, it may also fail to understand the data’s intricacy. An automatic COVID-19 detection system based on computed tomography (CT) scan or X-ray images is effective, but a robust system design is challenging. In this study, we propose an intelligent healthcare system that integrates IoT-cloud technologies. This architecture uses smart connectivity sensors and deep learning (DL) for intelligent decision-making from the perspective of the smart city. The intelligent system tracks the status of patients in real time and delivers reliable, timely, and high-quality healthcare facilities at a low cost. COVID-19 detection experiments are performed using DL to test the viability of the proposed system. We use a sensor for recording, transferring, and tracking healthcare data. CT scan images from patients are sent to the cloud by IoT sensors, where the cognitive module is stored. The system decides the patient status by examining the images of the CT scan. The DL cognitive module makes the real-time decision on the possible course of action. When information is conveyed to a cognitive module, we use a state-of-the-art classification algorithm based on DL, i.e., ResNet50, to detect and classify whether the patients are normal or infected by COVID-19. We validate the proposed system’s robustness and effectiveness using two benchmark publicly available datasets (Covid-Chestxray dataset and Chex-Pert dataset). At first, a dataset of 6000 images is prepared from the above two datasets. The proposed system was trained on the collection of images from 80% of the datasets and tested with 20% of the data. Cross-validation is performed using a tenfold cross-validation technique for performance evaluation. The results indicate that the proposed system gives an accuracy of 98.6%, a sensitivity of 97.3%, a specificity of 98.2%, and an F1-score of 97.87%. Results clearly show that the accuracy, specificity, sensitivity, and F1-score of our proposed method are high. The comparison shows that the proposed system performs better than the existing state-of-the-art systems. The proposed system will be helpful in medical diagnosis research and healthcare systems. It will also support the medical experts for COVID-19 screening and lead to a precious second opinion. © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.
- Authors: Nasser, Nidal , Emad-ul-Haq, Qazi , Imran, Muhammad , Ali, Asmaa , Razzak, Imran , Al-Helali, Abdulaziz
- Date: 2023
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 35, no. 19 (2023), p. 13775-13789
- Full Text:
- Reviewed:
- Description: Coronavirus (COVID-19) is a very contagious infection that has drawn the world’s attention. Modeling such diseases can be extremely valuable in predicting their effects. Although classic statistical modeling may provide adequate models, it may also fail to understand the data’s intricacy. An automatic COVID-19 detection system based on computed tomography (CT) scan or X-ray images is effective, but a robust system design is challenging. In this study, we propose an intelligent healthcare system that integrates IoT-cloud technologies. This architecture uses smart connectivity sensors and deep learning (DL) for intelligent decision-making from the perspective of the smart city. The intelligent system tracks the status of patients in real time and delivers reliable, timely, and high-quality healthcare facilities at a low cost. COVID-19 detection experiments are performed using DL to test the viability of the proposed system. We use a sensor for recording, transferring, and tracking healthcare data. CT scan images from patients are sent to the cloud by IoT sensors, where the cognitive module is stored. The system decides the patient status by examining the images of the CT scan. The DL cognitive module makes the real-time decision on the possible course of action. When information is conveyed to a cognitive module, we use a state-of-the-art classification algorithm based on DL, i.e., ResNet50, to detect and classify whether the patients are normal or infected by COVID-19. We validate the proposed system’s robustness and effectiveness using two benchmark publicly available datasets (Covid-Chestxray dataset and Chex-Pert dataset). At first, a dataset of 6000 images is prepared from the above two datasets. The proposed system was trained on the collection of images from 80% of the datasets and tested with 20% of the data. Cross-validation is performed using a tenfold cross-validation technique for performance evaluation. The results indicate that the proposed system gives an accuracy of 98.6%, a sensitivity of 97.3%, a specificity of 98.2%, and an F1-score of 97.87%. Results clearly show that the accuracy, specificity, sensitivity, and F1-score of our proposed method are high. The comparison shows that the proposed system performs better than the existing state-of-the-art systems. The proposed system will be helpful in medical diagnosis research and healthcare systems. It will also support the medical experts for COVID-19 screening and lead to a precious second opinion. © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.
Applications of machine learning and deep learning in antenna design, optimization, and selection : a review
- Sarker, Nayan, Podder, Prajoy, Mondal, M., Shafin, Sakib, Kamruzzaman, Joarder
- Authors: Sarker, Nayan , Podder, Prajoy , Mondal, M. , Shafin, Sakib , Kamruzzaman, Joarder
- Date: 2023
- Type: Text , Journal article , Review
- Relation: IEEE Access Vol. 11, no. (2023), p. 103890-103915
- Full Text:
- Reviewed:
- Description: This review paper provides an overview of the latest developments in artificial intelligence (AI)-based antenna design and optimization for wireless communications. Machine learning (ML) and deep learning (DL) algorithms are applied to antenna engineering to improve the efficiency of the design and optimization processes. The review discusses the use of electromagnetic (EM) simulators such as computer simulation technology (CST) and high-frequency structure simulator (HFSS) for ML and DL-based antenna design, which also covers reinforcement learning (RL)-bases approaches. Various antenna optimization methods including parallel optimization, single and multi-objective optimization, variable fidelity optimization, multilayer ML-assisted optimization, and surrogate-based optimization are discussed. The review also covers the AI-based antenna selection approaches for wireless applications. To support the automation of antenna engineering, the data generation technique with computational electromagnetics software is described and some useful datasets are reported. The review concludes that ML/DL can enhance antenna behavior prediction, reduce the number of simulations, improve computer efficiency, and speed up the antenna design process. © 2013 IEEE.
- Authors: Sarker, Nayan , Podder, Prajoy , Mondal, M. , Shafin, Sakib , Kamruzzaman, Joarder
- Date: 2023
- Type: Text , Journal article , Review
- Relation: IEEE Access Vol. 11, no. (2023), p. 103890-103915
- Full Text:
- Reviewed:
- Description: This review paper provides an overview of the latest developments in artificial intelligence (AI)-based antenna design and optimization for wireless communications. Machine learning (ML) and deep learning (DL) algorithms are applied to antenna engineering to improve the efficiency of the design and optimization processes. The review discusses the use of electromagnetic (EM) simulators such as computer simulation technology (CST) and high-frequency structure simulator (HFSS) for ML and DL-based antenna design, which also covers reinforcement learning (RL)-bases approaches. Various antenna optimization methods including parallel optimization, single and multi-objective optimization, variable fidelity optimization, multilayer ML-assisted optimization, and surrogate-based optimization are discussed. The review also covers the AI-based antenna selection approaches for wireless applications. To support the automation of antenna engineering, the data generation technique with computational electromagnetics software is described and some useful datasets are reported. The review concludes that ML/DL can enhance antenna behavior prediction, reduce the number of simulations, improve computer efficiency, and speed up the antenna design process. © 2013 IEEE.
Cancer classification utilizing voting classifier with ensemble feature selection method and transcriptomic data
- Khatun, Rabea, Akter, Maksuda, Islam, Md Manowarul, Uddin, Md Ashraf, Talukder, Md Alamin, Kamruzzaman, Joarder, Azad, Akm, Paul, Bikash, Almoyad, Muhammad, Aryal, Sunil, Moni, Mohammad
- Authors: Khatun, Rabea , Akter, Maksuda , Islam, Md Manowarul , Uddin, Md Ashraf , Talukder, Md Alamin , Kamruzzaman, Joarder , Azad, Akm , Paul, Bikash , Almoyad, Muhammad , Aryal, Sunil , Moni, Mohammad
- Date: 2023
- Type: Text , Journal article
- Relation: Genes Vol. 14, no. 9 (2023), p.
- Full Text:
- Reviewed:
- Description: Biomarker-based cancer identification and classification tools are widely used in bioinformatics and machine learning fields. However, the high dimensionality of microarray gene expression data poses a challenge for identifying important genes in cancer diagnosis. Many feature selection algorithms optimize cancer diagnosis by selecting optimal features. This article proposes an ensemble rank-based feature selection method (EFSM) and an ensemble weighted average voting classifier (VT) to overcome this challenge. The EFSM uses a ranking method that aggregates features from individual selection methods to efficiently discover the most relevant and useful features. The VT combines support vector machine, k-nearest neighbor, and decision tree algorithms to create an ensemble model. The proposed method was tested on three benchmark datasets and compared to existing built-in ensemble models. The results show that our model achieved higher accuracy, with 100% for leukaemia, 94.74% for colon cancer, and 94.34% for the 11-tumor dataset. This study concludes by identifying a subset of the most important cancer-causing genes and demonstrating their significance compared to the original data. The proposed approach surpasses existing strategies in accuracy and stability, significantly impacting the development of ML-based gene analysis. It detects vital genes with higher precision and stability than other existing methods. © 2023 by the authors.
- Authors: Khatun, Rabea , Akter, Maksuda , Islam, Md Manowarul , Uddin, Md Ashraf , Talukder, Md Alamin , Kamruzzaman, Joarder , Azad, Akm , Paul, Bikash , Almoyad, Muhammad , Aryal, Sunil , Moni, Mohammad
- Date: 2023
- Type: Text , Journal article
- Relation: Genes Vol. 14, no. 9 (2023), p.
- Full Text:
- Reviewed:
- Description: Biomarker-based cancer identification and classification tools are widely used in bioinformatics and machine learning fields. However, the high dimensionality of microarray gene expression data poses a challenge for identifying important genes in cancer diagnosis. Many feature selection algorithms optimize cancer diagnosis by selecting optimal features. This article proposes an ensemble rank-based feature selection method (EFSM) and an ensemble weighted average voting classifier (VT) to overcome this challenge. The EFSM uses a ranking method that aggregates features from individual selection methods to efficiently discover the most relevant and useful features. The VT combines support vector machine, k-nearest neighbor, and decision tree algorithms to create an ensemble model. The proposed method was tested on three benchmark datasets and compared to existing built-in ensemble models. The results show that our model achieved higher accuracy, with 100% for leukaemia, 94.74% for colon cancer, and 94.34% for the 11-tumor dataset. This study concludes by identifying a subset of the most important cancer-causing genes and demonstrating their significance compared to the original data. The proposed approach surpasses existing strategies in accuracy and stability, significantly impacting the development of ML-based gene analysis. It detects vital genes with higher precision and stability than other existing methods. © 2023 by the authors.
Comparative analysis of machine and deep learning models for soil properties prediction from hyperspectral visual band
- Datta, Dristi, Paul, Manoranjan, Murshed, Manzur, Teng, Shyh Wei, Schmidtke, Leigh
- Authors: Datta, Dristi , Paul, Manoranjan , Murshed, Manzur , Teng, Shyh Wei , Schmidtke, Leigh
- Date: 2023
- Type: Text , Journal article
- Relation: Environments Vol. 10, no. 5 (2023), p. 77
- Full Text:
- Reviewed:
- Description: Estimating various properties of soil, including moisture, carbon, and nitrogen, is crucial for studying their correlation with plant health and food production. However, conventional methods such as oven-drying and chemical analysis are laborious, expensive, and only feasible for a limited land area. With the advent of remote sensing technologies like multi/hyperspectral imaging, it is now possible to predict soil properties non-invasive and cost-effectively for a large expanse of bare land. Recent research shows the possibility of predicting those soil contents from a wide range of hyperspectral data using good prediction algorithms. However, these kinds of hyperspectral sensors are expensive and not widely available. Therefore, this paper investigates different machine and deep learning techniques to predict soil nutrient properties using only the red (R), green (G), and blue (B) bands data to propose a suitable machine/deep learning model that can be used as a rapid soil test. Another objective of this research is to observe and compare the prediction accuracy in three cases i. hyperspectral band ii. full spectrum of the visual band, and iii. three-channel of RGB band and provide a guideline to the user on which spectrum information they should use to predict those soil properties. The outcome of this research helps to develop a mobile application that is easy to use for a quick soil test. This research also explores learning-based algorithms with significant feature combinations and their performance comparisons in predicting soil properties from visual band data. For this, we also explore the impact of dimensional reduction (i.e., principal component analysis) and transformations (i.e., empirical mode decomposition) of features. The results show that the proposed model can comparably predict the soil contents from the three-channel RGB data.
- Authors: Datta, Dristi , Paul, Manoranjan , Murshed, Manzur , Teng, Shyh Wei , Schmidtke, Leigh
- Date: 2023
- Type: Text , Journal article
- Relation: Environments Vol. 10, no. 5 (2023), p. 77
- Full Text:
- Reviewed:
- Description: Estimating various properties of soil, including moisture, carbon, and nitrogen, is crucial for studying their correlation with plant health and food production. However, conventional methods such as oven-drying and chemical analysis are laborious, expensive, and only feasible for a limited land area. With the advent of remote sensing technologies like multi/hyperspectral imaging, it is now possible to predict soil properties non-invasive and cost-effectively for a large expanse of bare land. Recent research shows the possibility of predicting those soil contents from a wide range of hyperspectral data using good prediction algorithms. However, these kinds of hyperspectral sensors are expensive and not widely available. Therefore, this paper investigates different machine and deep learning techniques to predict soil nutrient properties using only the red (R), green (G), and blue (B) bands data to propose a suitable machine/deep learning model that can be used as a rapid soil test. Another objective of this research is to observe and compare the prediction accuracy in three cases i. hyperspectral band ii. full spectrum of the visual band, and iii. three-channel of RGB band and provide a guideline to the user on which spectrum information they should use to predict those soil properties. The outcome of this research helps to develop a mobile application that is easy to use for a quick soil test. This research also explores learning-based algorithms with significant feature combinations and their performance comparisons in predicting soil properties from visual band data. For this, we also explore the impact of dimensional reduction (i.e., principal component analysis) and transformations (i.e., empirical mode decomposition) of features. The results show that the proposed model can comparably predict the soil contents from the three-channel RGB data.
Detection and explanation of anomalies in healthcare data
- Samariya, Durgesh, Ma, Jiangang, Aryal, Sunil, Zhao, Xiaohui
- Authors: Samariya, Durgesh , Ma, Jiangang , Aryal, Sunil , Zhao, Xiaohui
- Date: 2023
- Type: Text , Journal article
- Relation: Health Information Science and Systems Vol. 11, no. 1 (2023), p. 20-20
- Full Text: false
- Reviewed:
- Description: The growth of databases in the healthcare domain opens multiple doors for machine learning and artificial intelligence technology. Many medical devices are available in the medical field however, medical errors remain a severe challenge. Different algorithms are developed to identify and solve medical errors, such as detecting anomalous readings, anomalous health conditions of a patient, etc. However, they fail to answer why those entries are considered an anomaly. This research gap leads to an outlying aspect mining problem. The problem of outlying aspect mining aims to discover the set of features (a.k.a subspace) in which the given data point is dramatically different than others. In this paper, we present a framework that detects anomalies in healthcare data and then provides an explanation of anomalies. This paper aims to effectively and efficiently detect anomalies and explain why they are considered anomalies by detecting outlying aspects. First, we re-introduced four anomaly detection techniques and outlying aspect mining algorithms. Then, we evaluate the performance of anomaly detection techniques and choose the best anomaly detection algorithm. Later, we detect the top k anomaly as a query and detect their outlying aspect. Lastly, we evaluate their performance on 16 real-world healthcare datasets. The experimental results show that the latest isolation-based outlying aspect mining measure, SiNNE, has outstanding performance on this task and has promising results.
Estimating the mean cutting force of conical picks using random forest with salp swarm algorithm
- Zhou, Jian, Dai, Yong, Tao, Ming, Khandelwal, Manoj, Zhao, Mingsheng, Li, Qiyue
- Authors: Zhou, Jian , Dai, Yong , Tao, Ming , Khandelwal, Manoj , Zhao, Mingsheng , Li, Qiyue
- Date: 2023
- Type: Text , Journal article
- Relation: Results in Engineering Vol. 17, no. (2023), p.
- Full Text:
- Reviewed:
- Description: Conical picks are widely used as cutting tools in shearers and roadheaders, and the mean cutting force (MCF) is one of the important parameters affecting conical pick performance. As MCF depends on a number of parameters and due to that the existing empirical and theoretical formulas and numerical modelling are not sufficient enough and reliable to predict MCF in a proficient manner. So, in this research, a novel intelligent model based on a random forest algorithm (RF) and a heuristic algorithm called the salp swarm algorithm (SSA) have been applied to determine the optimal hyper-parameters in RF, and root mean square error is used as a fitness function. A total of 188 data samples including 50 rock types and seven parameters (tensile strength of the rock
- Authors: Zhou, Jian , Dai, Yong , Tao, Ming , Khandelwal, Manoj , Zhao, Mingsheng , Li, Qiyue
- Date: 2023
- Type: Text , Journal article
- Relation: Results in Engineering Vol. 17, no. (2023), p.
- Full Text:
- Reviewed:
- Description: Conical picks are widely used as cutting tools in shearers and roadheaders, and the mean cutting force (MCF) is one of the important parameters affecting conical pick performance. As MCF depends on a number of parameters and due to that the existing empirical and theoretical formulas and numerical modelling are not sufficient enough and reliable to predict MCF in a proficient manner. So, in this research, a novel intelligent model based on a random forest algorithm (RF) and a heuristic algorithm called the salp swarm algorithm (SSA) have been applied to determine the optimal hyper-parameters in RF, and root mean square error is used as a fitness function. A total of 188 data samples including 50 rock types and seven parameters (tensile strength of the rock
Investigating the effectiveness of novel support vector neural network for anomaly detection in digital forensics data
- Islam, Umar, Alwageed, Hathal, Farooq, Malik, Khan, Inayat, Awwad, Fuad, Ali, Ijaz, Abonazel, Mohamed
- Authors: Islam, Umar , Alwageed, Hathal , Farooq, Malik , Khan, Inayat , Awwad, Fuad , Ali, Ijaz , Abonazel, Mohamed
- Date: 2023
- Type: Text , Journal article
- Relation: Sensors Vol. 23, no. 12 (2023), p.
- Full Text:
- Reviewed:
- Description: As criminal activity increasingly relies on digital devices, the field of digital forensics plays a vital role in identifying and investigating criminals. In this paper, we addressed the problem of anomaly detection in digital forensics data. Our objective was to propose an effective approach for identifying suspicious patterns and activities that could indicate criminal behavior. To achieve this, we introduce a novel method called the Novel Support Vector Neural Network (NSVNN). We evaluated the performance of the NSVNN by conducting experiments on a real-world dataset of digital forensics data. The dataset consisted of various features related to network activity, system logs, and file metadata. Through our experiments, we compared the NSVNN with several existing anomaly detection algorithms, including Support Vector Machines (SVM) and neural networks. We measured and analyzed the performance of each algorithm in terms of the accuracy, precision, recall, and F1-score. Furthermore, we provide insights into the specific features that contribute significantly to the detection of anomalies. Our results demonstrated that the NSVNN method outperformed the existing algorithms in terms of anomaly detection accuracy. We also highlight the interpretability of the NSVNN model by analyzing the feature importance and providing insights into the decision-making process. Overall, our research contributes to the field of digital forensics by proposing a novel approach, the NSVNN, for anomaly detection. We emphasize the importance of both performance evaluation and model interpretability in this context, providing practical insights for identifying criminal behavior in digital forensics investigations. © 2023 by the authors.
- Authors: Islam, Umar , Alwageed, Hathal , Farooq, Malik , Khan, Inayat , Awwad, Fuad , Ali, Ijaz , Abonazel, Mohamed
- Date: 2023
- Type: Text , Journal article
- Relation: Sensors Vol. 23, no. 12 (2023), p.
- Full Text:
- Reviewed:
- Description: As criminal activity increasingly relies on digital devices, the field of digital forensics plays a vital role in identifying and investigating criminals. In this paper, we addressed the problem of anomaly detection in digital forensics data. Our objective was to propose an effective approach for identifying suspicious patterns and activities that could indicate criminal behavior. To achieve this, we introduce a novel method called the Novel Support Vector Neural Network (NSVNN). We evaluated the performance of the NSVNN by conducting experiments on a real-world dataset of digital forensics data. The dataset consisted of various features related to network activity, system logs, and file metadata. Through our experiments, we compared the NSVNN with several existing anomaly detection algorithms, including Support Vector Machines (SVM) and neural networks. We measured and analyzed the performance of each algorithm in terms of the accuracy, precision, recall, and F1-score. Furthermore, we provide insights into the specific features that contribute significantly to the detection of anomalies. Our results demonstrated that the NSVNN method outperformed the existing algorithms in terms of anomaly detection accuracy. We also highlight the interpretability of the NSVNN model by analyzing the feature importance and providing insights into the decision-making process. Overall, our research contributes to the field of digital forensics by proposing a novel approach, the NSVNN, for anomaly detection. We emphasize the importance of both performance evaluation and model interpretability in this context, providing practical insights for identifying criminal behavior in digital forensics investigations. © 2023 by the authors.
- Siddiqui, Mustafa, Kahandawa, Gayan, Hewawasam, Hasitha, Rehman Siddiqi, Muftooh
- Authors: Siddiqui, Mustafa , Kahandawa, Gayan , Hewawasam, Hasitha , Rehman Siddiqi, Muftooh
- Date: 2023
- Type: Text , Conference paper
- Relation: 28th International Conference on Automation and Computing, ICAC 2023, Birmingham, UK, 30 August-1 September 2023, ICAC 2023 The 28th International Conference on Automation and Computing Digitalisation for Smart Manufacturing and Systems
- Full Text: false
- Reviewed:
- Description: Industrial control systems are excessively used in advanced manufacturing environments. The lack of information and data regarding the internal workings of certain systems makes virtual modelling for their Digital Twin challenging. As a result, these systems are often classified as 'black box' systems. There is minimal research found on DT models for industrial control black box systems. Therefore, a novel algorithm to model the Digital Twin of the industrial control black box system in the cyber domain has been presented in this paper. Machine Learning techniques were used to develop a high-fidelity Digital Twin model of a black box system. Real-time sensor data were recorded and used to validate the proposed novel algorithm. This paper presents the proposed algorithm's effectiveness in developing a robust Digital Twin model of industrial control back box system. © 2023 IEEE.
Machine learning-based agoraphilic navigation algorithm for use in dynamic environments with a moving goal
- Hewawasam, Hasitha, Kahandawa, Gayan, Ibrahim, Yousef
- Authors: Hewawasam, Hasitha , Kahandawa, Gayan , Ibrahim, Yousef
- Date: 2023
- Type: Text , Journal article
- Relation: Machines Vol. 11, no. 5 (2023), p. 513
- Full Text:
- Reviewed:
- Description: This paper presents a novel development of a new machine learning-based control system for the Agoraphilic (free-space attraction) concept of navigating robots in unknown dynamic environments with a moving goal. Furthermore, this paper presents a new methodology to generate training and testing datasets to develop a machine learning-based module to improve the performances of Agoraphilic algorithms. The new algorithm presented in this paper utilises the free-space attraction (Agoraphilic) concept to safely navigate a mobile robot in a dynamically cluttered environment with a moving goal. The algorithm uses tracking and prediction strategies to estimate the position and velocity vectors of detected moving obstacles and the goal. This predictive methodology enables the algorithm to identify and incorporate potential future growing free-space passages towards the moving goal. This is supported by the new machine learning-based controller designed specifically to efficiently account for the high uncertainties inherent in the robot’s operational environment with a moving goal at a reduced computational cost. This paper also includes comparative and experimental results to demonstrate the improvements of the algorithm after introducing the machine learning technique. The presented experiments demonstrated the success of the algorithm in navigating robots in dynamic environments with the challenge of a moving goal.
- Authors: Hewawasam, Hasitha , Kahandawa, Gayan , Ibrahim, Yousef
- Date: 2023
- Type: Text , Journal article
- Relation: Machines Vol. 11, no. 5 (2023), p. 513
- Full Text:
- Reviewed:
- Description: This paper presents a novel development of a new machine learning-based control system for the Agoraphilic (free-space attraction) concept of navigating robots in unknown dynamic environments with a moving goal. Furthermore, this paper presents a new methodology to generate training and testing datasets to develop a machine learning-based module to improve the performances of Agoraphilic algorithms. The new algorithm presented in this paper utilises the free-space attraction (Agoraphilic) concept to safely navigate a mobile robot in a dynamically cluttered environment with a moving goal. The algorithm uses tracking and prediction strategies to estimate the position and velocity vectors of detected moving obstacles and the goal. This predictive methodology enables the algorithm to identify and incorporate potential future growing free-space passages towards the moving goal. This is supported by the new machine learning-based controller designed specifically to efficiently account for the high uncertainties inherent in the robot’s operational environment with a moving goal at a reduced computational cost. This paper also includes comparative and experimental results to demonstrate the improvements of the algorithm after introducing the machine learning technique. The presented experiments demonstrated the success of the algorithm in navigating robots in dynamic environments with the challenge of a moving goal.
- Pai, Raghuvir, Chattopadhyay, Gopinath, Karmakar, Gour
- Authors: Pai, Raghuvir , Chattopadhyay, Gopinath , Karmakar, Gour
- Date: 2023
- Type: Text , Journal article
- Relation: International Journal of Process Management and Benchmarking Vol. 13, no. 2 (2023), p. 233-256
- Full Text: false
- Reviewed:
- Description: There are a large number of rotating and sliding parts in industrial assets. Tribological behaviour plays a significant role in influencing friction and wear, and in turn, the life of these parts. There are issues and challenges in understanding the tribological aspects and behaviour of machine components by maintenance professionals so that informed decisions can taken to improve performance and productivity. An understanding of tribology helps in developing and applying the tools and techniques necessary for better maintenance. In recent years, remote performance monitoring (RPM), internet of things (IoT), machine learning, artificial intelligence and data analytics have made a significant contribution to maintenance and asset management. This paper reviews the tribological aspects related to maintenance, reliability and asset management. The findings of this study will be useful to engineers and managers to understand and appreciate the relationship between tribology, maintenance, reliability and availability for better asset management. Copyright © 2023 Inderscience Enterprises Ltd.
Malignant and non-malignant oral lesions classification and diagnosis with deep neural networks
- Liyanage, V.iduni, Tao, Mengqiu, Park, Joon, Wang, Kate, Azimi, Somayyeh
- Authors: Liyanage, V.iduni , Tao, Mengqiu , Park, Joon , Wang, Kate , Azimi, Somayyeh
- Date: 2023
- Type: Text , Journal article
- Relation: Journal of Dentistry Vol. 137, no. (2023), p.
- Full Text:
- Reviewed:
- Description: Objectives: Given the increasing incidence of oral cancer, it is essential to provide high-risk communities, especially in remote regions, with an affordable, user-friendly tool for visual lesion diagnosis. This proof-of-concept study explored the utility and feasibility of a smartphone application that can photograph and diagnose oral lesions. Methods: The images of oral lesions with confirmed diagnoses were sourced from oral and maxillofacial textbooks. In total, 342 images were extracted, encompassing lesions from various regions of the oral cavity such as the gingiva, palate, and labial mucosa. The lesions were segregated into three categories: Class 1 represented non-neoplastic lesions, Class 2 included benign neoplasms, and Class 3 contained premalignant/malignant lesions. The images were analysed using MobileNetV3 and EfficientNetV2 models, with the process producing an accuracy curve, confusion matrix, and receiver operating characteristic (ROC) curve. Results: The EfficientNetV2 model showed a steep increase in validation accuracy early in the iterations, plateauing at a score of 0.71. According to the confusion matrix, this model's testing accuracy for diagnosing non-neoplastic and premalignant/malignant lesions was 64% and 80% respectively. Conversely, the MobileNetV3 model exhibited a more gradual increase, reaching a plateau at a validation accuracy of 0.70. The MobileNetV3 model's testing accuracy for diagnosing non-neoplastic and premalignant/malignant lesions, according to the confusion matrix, was 64% and 82% respectively. Conclusions: Our proof-of-concept study effectively demonstrated the potential accuracy of AI software in distinguishing malignant lesions. This could play a vital role in remote screenings for populations with limited access to dental practitioners. However, the discrepancies between the classification of images and the results of "non-malignant lesions" calls for further refinement of the models and the classification system used. Clinical significance: The findings of this study indicate that AI software has the potential to aid in the identification or screening of malignant oral lesions. Further improvements are required to enhance accuracy in classifying non-malignant lesions. © 2023 The Author(s)
- Authors: Liyanage, V.iduni , Tao, Mengqiu , Park, Joon , Wang, Kate , Azimi, Somayyeh
- Date: 2023
- Type: Text , Journal article
- Relation: Journal of Dentistry Vol. 137, no. (2023), p.
- Full Text:
- Reviewed:
- Description: Objectives: Given the increasing incidence of oral cancer, it is essential to provide high-risk communities, especially in remote regions, with an affordable, user-friendly tool for visual lesion diagnosis. This proof-of-concept study explored the utility and feasibility of a smartphone application that can photograph and diagnose oral lesions. Methods: The images of oral lesions with confirmed diagnoses were sourced from oral and maxillofacial textbooks. In total, 342 images were extracted, encompassing lesions from various regions of the oral cavity such as the gingiva, palate, and labial mucosa. The lesions were segregated into three categories: Class 1 represented non-neoplastic lesions, Class 2 included benign neoplasms, and Class 3 contained premalignant/malignant lesions. The images were analysed using MobileNetV3 and EfficientNetV2 models, with the process producing an accuracy curve, confusion matrix, and receiver operating characteristic (ROC) curve. Results: The EfficientNetV2 model showed a steep increase in validation accuracy early in the iterations, plateauing at a score of 0.71. According to the confusion matrix, this model's testing accuracy for diagnosing non-neoplastic and premalignant/malignant lesions was 64% and 80% respectively. Conversely, the MobileNetV3 model exhibited a more gradual increase, reaching a plateau at a validation accuracy of 0.70. The MobileNetV3 model's testing accuracy for diagnosing non-neoplastic and premalignant/malignant lesions, according to the confusion matrix, was 64% and 82% respectively. Conclusions: Our proof-of-concept study effectively demonstrated the potential accuracy of AI software in distinguishing malignant lesions. This could play a vital role in remote screenings for populations with limited access to dental practitioners. However, the discrepancies between the classification of images and the results of "non-malignant lesions" calls for further refinement of the models and the classification system used. Clinical significance: The findings of this study indicate that AI software has the potential to aid in the identification or screening of malignant oral lesions. Further improvements are required to enhance accuracy in classifying non-malignant lesions. © 2023 The Author(s)
Nonsmooth optimization-based hyperparameter-free neural networks for large-scale regression
- Karmitsa, Napsu, Taheri, Sona, Joki, Kaisa, Paasivirta, Pauliina, Defterdarovic, J., Bagirov, Adil, Mäkelä, Marko
- Authors: Karmitsa, Napsu , Taheri, Sona , Joki, Kaisa , Paasivirta, Pauliina , Defterdarovic, J. , Bagirov, Adil , Mäkelä, Marko
- Date: 2023
- Type: Text , Journal article
- Relation: Algorithms Vol. 16, no. 9 (2023), p.
- Relation: http://purl.org/au-research/grants/arc/DP190100580
- Full Text:
- Reviewed:
- Description: In this paper, a new nonsmooth optimization-based algorithm for solving large-scale regression problems is introduced. The regression problem is modeled as fully-connected feedforward neural networks with one hidden layer, piecewise linear activation, and the (Formula presented.) -loss functions. A modified version of the limited memory bundle method is applied to minimize this nonsmooth objective. In addition, a novel constructive approach for automated determination of the proper number of hidden nodes is developed. Finally, large real-world data sets are used to evaluate the proposed algorithm and to compare it with some state-of-the-art neural network algorithms for regression. The results demonstrate the superiority of the proposed algorithm as a predictive tool in most data sets used in numerical experiments. © 2023 by the authors.
- Authors: Karmitsa, Napsu , Taheri, Sona , Joki, Kaisa , Paasivirta, Pauliina , Defterdarovic, J. , Bagirov, Adil , Mäkelä, Marko
- Date: 2023
- Type: Text , Journal article
- Relation: Algorithms Vol. 16, no. 9 (2023), p.
- Relation: http://purl.org/au-research/grants/arc/DP190100580
- Full Text:
- Reviewed:
- Description: In this paper, a new nonsmooth optimization-based algorithm for solving large-scale regression problems is introduced. The regression problem is modeled as fully-connected feedforward neural networks with one hidden layer, piecewise linear activation, and the (Formula presented.) -loss functions. A modified version of the limited memory bundle method is applied to minimize this nonsmooth objective. In addition, a novel constructive approach for automated determination of the proper number of hidden nodes is developed. Finally, large real-world data sets are used to evaluate the proposed algorithm and to compare it with some state-of-the-art neural network algorithms for regression. The results demonstrate the superiority of the proposed algorithm as a predictive tool in most data sets used in numerical experiments. © 2023 by the authors.
Proposed machine learning techniques for bridge structural health monitoring : a laboratory study
- Noori Hoshyar, Azadeh, Rashidi, Maria, Yu, Yang, Samali, Bijan
- Authors: Noori Hoshyar, Azadeh , Rashidi, Maria , Yu, Yang , Samali, Bijan
- Date: 2023
- Type: Text , Journal article
- Relation: Remote Sensing Vol. 15, no. 8 (2023), p.
- Full Text:
- Reviewed:
- Description: Structural health monitoring for bridges is a crucial concern in engineering due to the degradation risks caused by defects, which can become worse over time. In this respect, enhancement of various models that can discriminate between healthy and non-healthy states of structures have received extensive attention. These models are concerned with implementation algorithms, which operate on the feature sets to quantify the bridge’s structural health. The functional correlation between the feature set and the health state of the bridge structure is usually difficult to define. Therefore, the models are derived from machine learning techniques. The use of machine learning approaches provides the possibility of automating the SHM procedure and intelligent damage detection. In this study, we propose four classification algorithms to SHM, which uses the concepts of support vector machine (SVM) algorithm. The laboratory experiment, which intended to validate the results, was performed at Western Sydney University (WSU). The results were compared with the basic SVM to evaluate the performance of proposed algorithms. © 2023 by the authors.
- Authors: Noori Hoshyar, Azadeh , Rashidi, Maria , Yu, Yang , Samali, Bijan
- Date: 2023
- Type: Text , Journal article
- Relation: Remote Sensing Vol. 15, no. 8 (2023), p.
- Full Text:
- Reviewed:
- Description: Structural health monitoring for bridges is a crucial concern in engineering due to the degradation risks caused by defects, which can become worse over time. In this respect, enhancement of various models that can discriminate between healthy and non-healthy states of structures have received extensive attention. These models are concerned with implementation algorithms, which operate on the feature sets to quantify the bridge’s structural health. The functional correlation between the feature set and the health state of the bridge structure is usually difficult to define. Therefore, the models are derived from machine learning techniques. The use of machine learning approaches provides the possibility of automating the SHM procedure and intelligent damage detection. In this study, we propose four classification algorithms to SHM, which uses the concepts of support vector machine (SVM) algorithm. The laboratory experiment, which intended to validate the results, was performed at Western Sydney University (WSU). The results were compared with the basic SVM to evaluate the performance of proposed algorithms. © 2023 by the authors.
A tree-based stacking ensemble technique with feature selection for network intrusion detection
- Rashid, Mamanur, Kamruzzaman, Joarder, Imam, Tasadduq, Wibowo, Santoso, Gordon, Steven
- Authors: Rashid, Mamanur , Kamruzzaman, Joarder , Imam, Tasadduq , Wibowo, Santoso , Gordon, Steven
- Date: 2022
- Type: Text , Journal article
- Relation: Applied Intelligence Vol. 52, no. 9 (2022), p. 9768-9781
- Full Text: false
- Reviewed:
- Description: Several studies have used machine learning algorithms to develop intrusion systems (IDS), which differentiate anomalous behaviours from the normal activities of network systems. Due to the ease of automated data collection and subsequently an increased size of collected data on network traffic and activities, the complexity of intrusion analysis is increasing exponentially. A particular issue, due to statistical and computation limitations, a single classifier may not perform well for large scale data as existent in modern IDS contexts. Ensemble methods have been explored in literature in such big data contexts. Although more complicated and requiring additional computation, literature has a note that ensemble methods can result in better accuracy than single classifiers in different large scale data classification contexts, and it is interesting to explore how ensemble approaches can perform in IDS. In this research, we introduce a tree-based stacking ensemble technique (SET) and test the effectiveness of the proposed model on two intrusion datasets (NSL-KDD and UNSW-NB15). We further enhance incorporate feature selection techniques to select the best relevant features with the proposed SET. A comprehensive performance analysis shows that our proposed model can better identify the normal and anomaly traffic in network than other existing IDS models. This implies the potentials of our proposed system for cybersecurity in Internet of Things (IoT) and large scale networks. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
Adaptation of a real-time deep learning approach with an analog fault detection technique for reliability forecasting of capacitor banks used in mobile vehicles
- Rezaei, Mohammad, Fathollahi, Arman, Rezaei, Sajad, Hu, Jiefeng, Gheisarnejad, Meysam, Teimouri, Ali, Rituraj, Rituraj, Mosavi, Amir, Khooban, Mohammad-Hassan
- Authors: Rezaei, Mohammad , Fathollahi, Arman , Rezaei, Sajad , Hu, Jiefeng , Gheisarnejad, Meysam , Teimouri, Ali , Rituraj, Rituraj , Mosavi, Amir , Khooban, Mohammad-Hassan
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Access Vol. 10, no. (2022), p. 132271-132287
- Full Text:
- Reviewed:
- Description: The DC-Link capacitor is defined as the essential electronics element which sources or sinks the respective currents. The reliability of DC-link capacitor-banks (CBs) encounters many challenges due to their usage in electric vehicles. Heavy shocks may damage the internal capacitors without shutting down the CB. The fundamental development obstacles of CBs are: lack of considering capacitor degradation in reliability assessment, the impact of unforeseen sudden internal capacitor faults in forecasting CB lifetime, and the faults consequence on CB degradation. The sudden faults change the CB capacitance, which leads to reliability change. To more accurately estimate the reliability, the type of the fault needs to be detected for predicting the correct post-fault capacitance. To address these practical problems, a new CB model and reliability assessment formula covering all fault types are first presented, then, a new analog fault-detection method is presented, and a combination of online-learning long short-term memory (LSTM) and fault-detection method is subsequently performed, which adapt the sudden internal CB faults with the LSTM to correctly predict the CB degradation. To confirm the correct LSTM operation, four capacitors degradation is practically recorded for 2000-hours, and the off-line faultless degradation values predicted by the LSTM are compared with the actual data. The experimental findings validate the applicability of the proposed method. The codes and data are provided. © 2013 IEEE.
- Authors: Rezaei, Mohammad , Fathollahi, Arman , Rezaei, Sajad , Hu, Jiefeng , Gheisarnejad, Meysam , Teimouri, Ali , Rituraj, Rituraj , Mosavi, Amir , Khooban, Mohammad-Hassan
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Access Vol. 10, no. (2022), p. 132271-132287
- Full Text:
- Reviewed:
- Description: The DC-Link capacitor is defined as the essential electronics element which sources or sinks the respective currents. The reliability of DC-link capacitor-banks (CBs) encounters many challenges due to their usage in electric vehicles. Heavy shocks may damage the internal capacitors without shutting down the CB. The fundamental development obstacles of CBs are: lack of considering capacitor degradation in reliability assessment, the impact of unforeseen sudden internal capacitor faults in forecasting CB lifetime, and the faults consequence on CB degradation. The sudden faults change the CB capacitance, which leads to reliability change. To more accurately estimate the reliability, the type of the fault needs to be detected for predicting the correct post-fault capacitance. To address these practical problems, a new CB model and reliability assessment formula covering all fault types are first presented, then, a new analog fault-detection method is presented, and a combination of online-learning long short-term memory (LSTM) and fault-detection method is subsequently performed, which adapt the sudden internal CB faults with the LSTM to correctly predict the CB degradation. To confirm the correct LSTM operation, four capacitors degradation is practically recorded for 2000-hours, and the off-line faultless degradation values predicted by the LSTM are compared with the actual data. The experimental findings validate the applicability of the proposed method. The codes and data are provided. © 2013 IEEE.
- Rashid, Md Mamunur, Kamruzzaman, Joarder, Mehedi Hassan, Mohammad, Imam, Tasadduq, Wibowo, Santoso, Gordon, Steven, Fortino, Giancarlo
- Authors: Rashid, Md Mamunur , Kamruzzaman, Joarder , Mehedi Hassan, Mohammad , Imam, Tasadduq , Wibowo, Santoso , Gordon, Steven , Fortino, Giancarlo
- Date: 2022
- Type: Text , Journal article
- Relation: Computers and Security Vol. 120, no. (2022), p.
- Full Text: false
- Reviewed:
- Description: Intrusion Detection Systems (IDS) based on deep learning models can identify and mitigate cyberattacks in IoT applications in a resilient and systematic manner. These models, which support the IDS's decision, could be vulnerable to a cyberattack known as adversarial attack. In this type of attack, attackers create adversarial samples by introducing small perturbations to attack samples to trick a trained model into misclassifying them as benign applications. These attacks can cause substantial damage to IoT-based smart city models in terms of device malfunction, data leakage, operational outage and financial loss. To our knowledge, the impact of and defence against adversarial attacks on IDS models in relation to smart city applications have not been investigated yet. To address this research gap, in this work, we explore the effect of adversarial attacks on the deep learning and shallow machine learning models by using a recent IoT dataset and propose a method using adversarial retraining that can significantly improve IDS performance when confronting adversarial attacks. Simulation results demonstrate that the presence of adversarial samples deteriorates the detection accuracy significantly by above 70% while our proposed model can deliver detection accuracy above 99% against all types of attacks including adversarial attacks. This makes an IDS robust in protecting IoT-based smart city services. © 2022 Elsevier Ltd
An automatic detection of breast cancer diagnosis and prognosis based on machine learning using ensemble of classifiers
- Naseem, Usman, Rashid, Junaid, Ali, Liaqat, Kim, Jungeun, Haq, Qazi, Awan, Mazhar, Imran, Muhammad
- Authors: Naseem, Usman , Rashid, Junaid , Ali, Liaqat , Kim, Jungeun , Haq, Qazi , Awan, Mazhar , Imran, Muhammad
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Access Vol. 10, no. (2022), p. 78242-78252
- Full Text:
- Reviewed:
- Description: Breast cancer (BC) is the second most prevalent type of cancer among women leading to death, and its rate of mortality is very high. Its effects will be reduced if diagnosed early. BC's early detection will greatly boost the prognosis and likelihood of recovery, as it may encourage prompt surgical care for patients. It is therefore vital to have a system enabling the healthcare industry to detect breast cancer quickly and accurately. Machine learning (ML) is widely used in breast cancer (BC) pattern classification due to its advantages in modelling a critical feature detection from complex BC datasets. In this paper, we propose a system for automatic detection of BC diagnosis and prognosis using ensemble of classifiers. First, we review various machine learning (ML) algorithms and ensemble of different ML algorithms. We present an overview of ML algorithms including ANN, and ensemble of different classifiers for automatic BC diagnosis and prognosis detection. We also present and compare various ensemble models and other variants of tested ML based models with and without up-sampling technique on two benchmark datasets. We also studied the effects of using balanced class weight on prognosis dataset and compared its performance with others. The results showed that the ensemble method outperformed other state-of-the-art methods and achieved 98.83% accuracy. Because of high performance, the proposed system is of great importance to the medical industry and relevant research community. The comparison shows that the proposed method outperformed other state-of-the-art methods. © 2013 IEEE.
- Authors: Naseem, Usman , Rashid, Junaid , Ali, Liaqat , Kim, Jungeun , Haq, Qazi , Awan, Mazhar , Imran, Muhammad
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Access Vol. 10, no. (2022), p. 78242-78252
- Full Text:
- Reviewed:
- Description: Breast cancer (BC) is the second most prevalent type of cancer among women leading to death, and its rate of mortality is very high. Its effects will be reduced if diagnosed early. BC's early detection will greatly boost the prognosis and likelihood of recovery, as it may encourage prompt surgical care for patients. It is therefore vital to have a system enabling the healthcare industry to detect breast cancer quickly and accurately. Machine learning (ML) is widely used in breast cancer (BC) pattern classification due to its advantages in modelling a critical feature detection from complex BC datasets. In this paper, we propose a system for automatic detection of BC diagnosis and prognosis using ensemble of classifiers. First, we review various machine learning (ML) algorithms and ensemble of different ML algorithms. We present an overview of ML algorithms including ANN, and ensemble of different classifiers for automatic BC diagnosis and prognosis detection. We also present and compare various ensemble models and other variants of tested ML based models with and without up-sampling technique on two benchmark datasets. We also studied the effects of using balanced class weight on prognosis dataset and compared its performance with others. The results showed that the ensemble method outperformed other state-of-the-art methods and achieved 98.83% accuracy. Because of high performance, the proposed system is of great importance to the medical industry and relevant research community. The comparison shows that the proposed method outperformed other state-of-the-art methods. © 2013 IEEE.
An ensemble of machine learning and clinician set thresholds for vital signs alarms
- Mai, Shenhan, Balasubramanian, Venki, Arora, Teena
- Authors: Mai, Shenhan , Balasubramanian, Venki , Arora, Teena
- Date: 2022
- Type: Text , Conference paper
- Relation: 2022 Australasian Computer Science Week, ACSW 2022, Virtual, Online, 14-17 February 2022, ACM International Conference Proceeding Series p. 232-234
- Full Text:
- Reviewed:
- Description: High false alarm rates is a common issue in patient vital sign monitoring systems and may result in alarm fatigue for medical workers and even cause alarm-related patient deaths. In this study, the research toward the use of ensemble learning that combines a feed forward back propagation neural network, a random forest and manually set threshold based alarms is used. A method for estimating the false alarm rate using the machine learning, to help clinicians set thresholds is also proposed. Experimental results to date on a small dataset are promising. © 2022 ACM.
- Authors: Mai, Shenhan , Balasubramanian, Venki , Arora, Teena
- Date: 2022
- Type: Text , Conference paper
- Relation: 2022 Australasian Computer Science Week, ACSW 2022, Virtual, Online, 14-17 February 2022, ACM International Conference Proceeding Series p. 232-234
- Full Text:
- Reviewed:
- Description: High false alarm rates is a common issue in patient vital sign monitoring systems and may result in alarm fatigue for medical workers and even cause alarm-related patient deaths. In this study, the research toward the use of ensemble learning that combines a feed forward back propagation neural network, a random forest and manually set threshold based alarms is used. A method for estimating the false alarm rate using the machine learning, to help clinicians set thresholds is also proposed. Experimental results to date on a small dataset are promising. © 2022 ACM.
An exploratory application of machine learning methods to optimize prediction of responsiveness to digital interventions for eating disorder symptoms
- Linardon, Jake, Fuller-Tyszkiewicz, Matthew, Shatte, Adrian, Greenwood, Christopher
- Authors: Linardon, Jake , Fuller-Tyszkiewicz, Matthew , Shatte, Adrian , Greenwood, Christopher
- Date: 2022
- Type: Text , Journal article
- Relation: International Journal of Eating Disorders Vol. 55, no. 6 (2022), p. 845-850
- Full Text:
- Reviewed:
- Description: Objective: Digital interventions show promise to address eating disorder (ED) symptoms. However, response rates are variable, and the ability to predict responsiveness to digital interventions has been poor. We tested whether machine learning (ML) techniques can enhance outcome predictions from digital interventions for ED symptoms. Method: Data were aggregated from three RCTs (n = 826) of self-guided digital interventions for EDs. Predictive models were developed for four key outcomes: uptake, adherence, drop-out, and symptom-level change. Seven ML techniques for classification were tested and compared against the generalized linear model (GLM). Results: The seven ML methods used to predict outcomes from 36 baseline variables were poor for the three engagement outcomes (AUCs = 0.48–0.52), but adequate for symptom-level change (R2 =.15–.40). ML did not offer an added benefit to the GLM. Incorporating intervention usage pattern data improved ML prediction accuracy for drop-out (AUC = 0.75–0.93) and adherence (AUC = 0.92–0.99). Age, motivation, symptom severity, and anxiety emerged as influential outcome predictors. Conclusion: A limited set of routinely measured baseline variables was not sufficient to detect a performance benefit of ML over traditional approaches. The benefits of ML may emerge when numerous usage pattern variables are modeled, although this validation in larger datasets before stronger conclusions can be made. © 2022 The Authors. International Journal of Eating Disorders published by Wiley Periodicals LLC.
- Authors: Linardon, Jake , Fuller-Tyszkiewicz, Matthew , Shatte, Adrian , Greenwood, Christopher
- Date: 2022
- Type: Text , Journal article
- Relation: International Journal of Eating Disorders Vol. 55, no. 6 (2022), p. 845-850
- Full Text:
- Reviewed:
- Description: Objective: Digital interventions show promise to address eating disorder (ED) symptoms. However, response rates are variable, and the ability to predict responsiveness to digital interventions has been poor. We tested whether machine learning (ML) techniques can enhance outcome predictions from digital interventions for ED symptoms. Method: Data were aggregated from three RCTs (n = 826) of self-guided digital interventions for EDs. Predictive models were developed for four key outcomes: uptake, adherence, drop-out, and symptom-level change. Seven ML techniques for classification were tested and compared against the generalized linear model (GLM). Results: The seven ML methods used to predict outcomes from 36 baseline variables were poor for the three engagement outcomes (AUCs = 0.48–0.52), but adequate for symptom-level change (R2 =.15–.40). ML did not offer an added benefit to the GLM. Incorporating intervention usage pattern data improved ML prediction accuracy for drop-out (AUC = 0.75–0.93) and adherence (AUC = 0.92–0.99). Age, motivation, symptom severity, and anxiety emerged as influential outcome predictors. Conclusion: A limited set of routinely measured baseline variables was not sufficient to detect a performance benefit of ML over traditional approaches. The benefits of ML may emerge when numerous usage pattern variables are modeled, although this validation in larger datasets before stronger conclusions can be made. © 2022 The Authors. International Journal of Eating Disorders published by Wiley Periodicals LLC.