1
|
Federated Split Learning Model for Industry 5.0: A Data Poisoning Defense for Edge Computing. ELECTRONICS 2022. [DOI: 10.3390/electronics11152393] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/04/2022]
Abstract
Industry 5.0 provides resource-efficient solutions compared to Industry 4.0. Edge Computing (EC) allows data analysis on edge devices. Artificial intelligence (AI) has become the focus of interest in recent years, particularly in industrial applications. The coordination of AI at the edge will significantly improve industry performance. This paper integrates AI and EC for Industry 5.0 to defend against data poisoning attacks. A hostile user or node injects fictitious training data to distort the learned model in a data poisoning attack. This research provides an effective data poisoning defense strategy to increase the learning model’s performance. This paper developed a novel data poisoning defense federated split learning, DepoisoningFSL, for edge computing. First, a defense mechanism is proposed against data poisoning attacks. Second, the optimal parameters are determined for improving the performance of the federated split learning model. Finally, the performance of the proposed work is evaluated with a real-time dataset in terms of accuracy, correlation coefficient, mean absolute error, and root mean squared error. The experimental results show that DepoisoningFSL increases the performance accuracy.
Collapse
|
2
|
Demir E. Weiszfeld, tree-seed, and whale optimization algorithms comparison via locating transportation facilities with weightings considering the vulnerability and uncertainty. PLoS One 2022; 17:e0269808. [PMID: 35700219 PMCID: PMC9197024 DOI: 10.1371/journal.pone.0269808] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2022] [Accepted: 05/30/2022] [Indexed: 11/19/2022] Open
Abstract
Searching for an optimum transportation facility location with emergency equipment and staff is essential for a specific region or a country. In this direction, this study addresses the following problems. First, the performances of the Weiszfeld, tree–seed, and whale optimization algorithms are compared, which is the first of its kind in the literature. Second, a new approach that tests the importance parameters’ effectiveness in searching for an optimum transportation facility location with emergency equipment and staff is proposed. The Weiszfeld algorithm finds viable solutions with compact data, but it may not handle big data. In contrast, the flexibility of the tree–seed and whale optimization algorithm is literally an advantage when the number of parameters and variables increases. Therefore, there is a notable need to directly compare those algorithms’ performances. If we do, the significance of extending the number of parameters with multiple weightings is appraised. According to the results, the Weiszfeld algorithm can be an almost flexible technique in continuous networks; however, it has reasonable drawbacks with discrete networks, while the tree–seed and whale optimization algorithms fit such conditions. On the other hand, these three methods do not show a fluctuating performance compared to one another based on the locating transportation facilities, and thus they deliver similar performance. Besides, although the value of accuracy is high with the application of the conventional technique Weiszfeld algorithm, it does not provide a significant performance accuracy advantage over the meta-heuristic methods.
Collapse
Affiliation(s)
- Emre Demir
- Department of Civil Engineering, Faculty of Engineering and Natural Sciences, Antalya Bilim University, Antalya, Turkey
- * E-mail:
| |
Collapse
|
3
|
Chintakindi S, Alsamhan A, Abidi MH, Kumar MP. Annealing of Monel 400 Alloy Using Principal Component Analysis, Hyper-parameter Optimization, Machine Learning Techniques, and Multi-objective Particle Swarm Optimization. INT J COMPUT INT SYS 2022. [DOI: 10.1007/s44196-022-00070-z] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022] Open
Abstract
AbstractThe purpose of this paper is to investigate the effect of the annealing process at 1000 °C on machining parameters using contemporary techniques such as principal component analysis (PCA), hyper-parameter optimization by Optuna, multi-objective particle swarm optimization, and theoretical validation using the machine learning method. Results after annealing show that there will be a reduction in surface roughness values by 19.61%, tool wear by 6.3%, and an increase in the metal removal rate by 14.98%. The PCA results show that the feed is more significant than the depth of cut and speed. The higher value of the composite primary component will represent optimal factors such as speed of 80, feed of 0.2 and depth of cut of 0.3, and values of principal components like surface roughness (Ψ1 = 64.5), tool wear (Ψ2 = 22.3) and metal removal rate (Ψ3 = 13.2). Hyper-parameter optimization represents speed is directly proportional to roughness, tool wear, and metal removal rate, while feed and depth of cut are inversely proportional. The optimization history plot will be steady, and the prediction accuracy will be 96.96%. Machine learning techniques are employed through the Python language using Google Colab. The estimated values from the decision tree method for surface roughness and tool wear predictions using the AdaBoost algorithm match well with actual values. As per MOPSO (multi-objective particle swarm optimization), the predicted responses are as follows; surface roughness (2.5 μm, 100, 02, 0.45), tool wear (0.31 mm, 40, 0.40, 0.60), and MRR (material removal rate) (5145 mm3/min, 100, 0.4, 0.15). As validated by experimentation, there are small variations as the surface roughness varied by 1.56%, tool wear by 6.8%, and MRR by 2.57%.
Collapse
|
4
|
Supply Chain Management Optimization and Prediction Model Based on Projected Stochastic Gradient. SUSTAINABILITY 2022. [DOI: 10.3390/su14063486] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
Supply chain management (SCM) is considered at the forefront of many organizations in the delivery of their products. Various optimization methods are applied in the SCM to improve the efficiency of the process. In this research, the projected stochastic gradient (PSG) method was proposed to increase the efficiency of the SCM analysis. The key objective of an efficient supply chain is to find the best flow patterns for the best products in order to select the suppliers to different customers. Hence, the focus of this research is on developing an efficient multi-echelon supply chain using factors such as cost, time, and risk. In the convex case, the proposed method has the advantage of a weakly convergent sequence of iterates to a point in the set of minimizers with probability one. The developed method achieves strong sequence convergence to the unique optimum, with probability one. The SCM dataset was utilized to assess the proposed method’s performance. The proposed PSG method has the advantage of considering the holding cost in the profit analysis of the company. The results of the developed PSG method are analyzed according to the product’s profit, stock, and demand. The proposed PSG method also provides the prediction of demand to increase profit.
Collapse
|
5
|
Predictive Maintenance Planning for Industry 4.0 Using Machine Learning for Sustainable Manufacturing. SUSTAINABILITY 2022. [DOI: 10.3390/su14063387] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
With the advent of the fourth industrial revolution, the application of artificial intelligence in the manufacturing domain is becoming prevalent. Maintenance is one of the important activities in the manufacturing process, and it requires proper attention. To decrease maintenance costs and to attain sustainable operational management, Predictive Maintenance (PdM) has become important in industries. The principle of PdM is forecasting the next failure; thus, the respective maintenance is scheduled before the predicted failure occurs. In the construction of maintenance management, facility managers generally employ reactive or preventive maintenance mechanisms. However, reactive maintenance does not have the ability to prevent failure and preventive maintenance does not have the ability to predict the future condition of mechanical, electrical, or plumbing components. Therefore, to improve the facilities’ lifespans, such components are repaired in advance. In this paper, a PdM planning model is developed using intelligent methods. The developed method involves five main phases: (a) data cleaning, (b) data normalization, (c) optimal feature selection, (d) prediction network decision-making, and (e) prediction. Initially, the data pertaining to PdM are subjected to data cleaning and normalization in order to arrange the data within a particular limit. Optimal feature selection is performed next, to reduce redundant information. Optimal feature selection is performed using a hybrid of the Jaya algorithm and Sea Lion Optimization (SLnO). As the prediction values differ in range, it is difficult for machine learning or deep learning face to provide accurate results. Thus, a support vector machine (SVM) is used to make decisions regarding the prediction network. The SVM identifies the network in which prediction can be performed for the concerned range. Finally, the prediction is accomplished using a Recurrent Neural Network (RNN). In the RNN, the weight is optimized using the hybrid J-SLnO. A comparative analysis demonstrates that the proposed model can efficiently predict the future condition of components for maintenance planning by using two datasets—aircraft engine and lithium-ion battery datasets.
Collapse
|
6
|
Determination of Business Intelligence and Analytics-Based Healthcare Facility Management Key Performance Indicators. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12020651] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
The use of digital technologies such as Internet of Things (IoT) and smart meters induces a huge data stack in facility management (FM). However, the use of data analysis techniques has remained limited to converting available data into information within activities performed in FM. In this context, business intelligence and analytics (BI&A) techniques can provide a promising opportunity to elaborate facility performance and discover measurable new FM key performance indicators (KPIs) since existing KPIs are too crude to discover actual performance of facilities. Beside this, there is no comprehensive study that covers BI&A activities and their importance level for healthcare FM. Therefore, this study aims to identify healthcare FM KPIs and their importance levels for the Turkish healthcare FM industry with the use of the AHP integrated PROMETHEE method. As a result of the study, ninety-eight healthcare FM KPIs, which are categorized under six categories, were found. The comparison of the findings with the literature review showed that there are some similarities and differences between countries’ FM healthcare ranks. Within this context, differences between countries can be related to the consideration of limited FM KPIs in the existing studies. Therefore, the proposed FM KPIs under this study are very comprehensive and detailed to measure and discover healthcare FM performance. This study can help professionals perform more detailed building performance analyses in FM. Additionally, findings from this study will pave the way for new developments in FM software and effective use of available data to enable lean FM processes in healthcare facilities.
Collapse
|
7
|
Jain S, Singhania U, Tripathy B, Nasr EA, Aboudaif MK, Kamrani AK. Deep Learning-Based Transfer Learning for Classification of Skin Cancer. SENSORS (BASEL, SWITZERLAND) 2021; 21:8142. [PMID: 34884146 PMCID: PMC8662405 DOI: 10.3390/s21238142] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/01/2021] [Revised: 11/30/2021] [Accepted: 11/30/2021] [Indexed: 11/16/2022]
Abstract
One of the major health concerns for human society is skin cancer. When the pigments producing skin color turn carcinogenic, this disease gets contracted. A skin cancer diagnosis is a challenging process for dermatologists as many skin cancer pigments may appear similar in appearance. Hence, early detection of lesions (which form the base of skin cancer) is definitely critical and useful to completely cure the patients suffering from skin cancer. Significant progress has been made in developing automated tools for the diagnosis of skin cancer to assist dermatologists. The worldwide acceptance of artificial intelligence-supported tools has permitted usage of the enormous collection of images of lesions and benevolent sores approved by histopathology. This paper performs a comparative analysis of six different transfer learning nets for multi-class skin cancer classification by taking the HAM10000 dataset. We used replication of images of classes with low frequencies to counter the imbalance in the dataset. The transfer learning nets that were used in the analysis were VGG19, InceptionV3, InceptionResNetV2, ResNet50, Xception, and MobileNet. Results demonstrate that replication is suitable for this task, achieving high classification accuracies and F-measures with lower false negatives. It is inferred that Xception Net outperforms the rest of the transfer learning nets used for the study, with an accuracy of 90.48. It also has the highest recall, precision, and F-Measure values.
Collapse
Affiliation(s)
- Satin Jain
- Department of Information Technology and Engineering, Vellore Institute of Technology, Vellore 632014, Tamil Nadu, India; (S.J.); (B.T.)
| | - Udit Singhania
- Department of Computer Science and Engineering, Vellore Institute of Technology, Vellore 632014, Tamil Nadu, India;
| | - Balakrushna Tripathy
- Department of Information Technology and Engineering, Vellore Institute of Technology, Vellore 632014, Tamil Nadu, India; (S.J.); (B.T.)
| | - Emad Abouel Nasr
- Industrial Engineering Department, College of Engineering, King Saud University, Riyadh 11421, Saudi Arabia;
| | - Mohamed K. Aboudaif
- Industrial Engineering Department, College of Engineering, King Saud University, Riyadh 11421, Saudi Arabia;
| | - Ali K. Kamrani
- Industrial Engineering Department, College of Engineering, University of Houston, Houston, TX 77204-4008, USA;
| |
Collapse
|
8
|
EWOA-OPF: Effective Whale Optimization Algorithm to Solve Optimal Power Flow Problem. ELECTRONICS 2021. [DOI: 10.3390/electronics10232975] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Abstract
The optimal power flow (OPF) is a vital tool for optimizing the control parameters of a power system by considering the desired objective functions subject to system constraints. Metaheuristic algorithms have been proven to be well-suited for solving complex optimization problems. The whale optimization algorithm (WOA) is one of the well-regarded metaheuristics that is widely used to solve different optimization problems. Despite the use of WOA in different fields of application as OPF, its effectiveness is decreased as the dimension size of the test system is increased. Therefore, in this paper, an effective whale optimization algorithm for solving optimal power flow problems (EWOA-OPF) is proposed. The main goal of this enhancement is to improve the exploration ability and maintain a proper balance between the exploration and exploitation of the canonical WOA. In the proposed algorithm, the movement strategy of whales is enhanced by introducing two new movement strategies: (1) encircling the prey using Levy motion and (2) searching for prey using Brownian motion that cooperate with canonical bubble-net attacking. To validate the proposed EWOA-OPF algorithm, a comparison among six well-known optimization algorithms is established to solve the OPF problem. All algorithms are used to optimize single- and multi-objective functions of the OPF under the system constraints. Standard IEEE 6-bus, IEEE 14-bus, IEEE 30-bus, and IEEE 118-bus test systems are used to evaluate the proposed EWOA-OPF and comparative algorithms for solving the OPF problem in diverse power system scale sizes. The comparison of results proves that the EWOA-OPF is able to solve single- and multi-objective OPF problems with better solutions than other comparative algorithms.
Collapse
|