scholarly journals Distribution Transformer Parameters Detection Based on Low-Frequency Noise, Machine Learning Methods, and Evolutionary Algorithm

Sensors ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 4332
Author(s):  
Daniel Jancarczyk ◽  
Marcin Bernaś ◽  
Tomasz Boczar
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Input Data ◽  
Learning Algorithms ◽  
Low Frequency ◽  
Machine Learning Algorithms ◽  
Frequency Noise ◽  
Low Frequency Noise ◽  
Distribution Transformer ◽  
Transformer Model

The paper proposes a method of automatic detection of parameters of a distribution transformer (model, type, and power) from a distance, based on its low-frequency noise spectra. The spectra are registered by sensors and processed by a method based on evolutionary algorithms and machine learning. The method, as input data, uses the frequency spectra of sound pressure levels generated during operation by transformers in the real environment. The model also uses the background characteristic to take under consideration the changing working conditions of the transformers. The method searches for frequency intervals and its resolution using both a classic genetic algorithm and particle swarm optimization. The interval selection was verified using five state-of-the-art machine learning algorithms. The research was conducted on 16 different distribution transformers. As a result, a method was proposed that allows the detection of a specific transformer model, its type, and its power with an accuracy greater than 84%, 99%, and 87%, respectively. The proposed optimization process using the genetic algorithm increased the accuracy by up to 5%, at the same time reducing the input data set significantly (from 80% up to 98%). The machine learning algorithms were selected, which were proven efficient for this task.

scholarly journals Classification of Low Frequency Signals Emitted by Power Transformers Using Sensors and Machine Learning Methods

Sensors ◽  
2019 ◽  
Vol 19 (22) ◽  
pp. 4909 ◽  
Author(s):  
Daniel Jancarczyk ◽  
Marcin Bernaś ◽  
Tomasz Boczar
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Low Frequency ◽  
Optimization Techniques ◽  
Machine Learning Algorithms ◽  
Power Transformers ◽  
Frequency Noise ◽  
Frequency Interval ◽  
Low Frequency Noise ◽  
Frequency Spectra

This paper proposes a method of automatically detecting and classifying low frequency noise generated by power transformers using sensors and dedicated machine learning algorithms. The method applies the frequency spectra of sound pressure levels generated during operation by transformers in a real environment. The spectra frequency interval and its resolution are automatically optimized for the selected machine learning algorithm. Various machine learning algorithms, optimization techniques, and transformer types were researched: two indoor type transformers from Schneider Electric and two overhead type transformers manufactured by ABB. As a result, a method was proposed that provides a way in which inspections of working transformers (from background) and their type can be performed with an accuracy of over 97%, based on the generated low-frequency noise. The application of the proposed preprocessing stage increased the accuracy of this method by 10%. Additionally, machine learning algorithms were selected which offer robust solutions (with the highest accuracy) for noise classification.

scholarly journals Diagnosis of breast cancer using machine learning algorithms based on features selected by Genetic Algorithm: Assessed on five datasets

2021 ◽  
Vol 23 (11) ◽  
pp. 749-758
Author(s):  
Saranya N ◽  
◽  
Kavi Priya S ◽  
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Genetic Algorithm ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Cancer Prognosis ◽  
Support Vector ◽  
Breast Cancer Dataset ◽  
Human Beings ◽  
Original Dataset

Breast Cancer is one of the chronic diseases occurred to human beings throughout the world. Early detection of this disease is the most promising way to improve patients’ chances of survival. The strategy employed in this paper is to select the best features from various breast cancer datasets using a genetic algorithm and machine learning algorithm is applied to predict the outcomes. Two machine learning algorithms such as Support Vector Machines and Decision Tree are used along with Genetic Algorithm. The proposed work is experimented on five datasets such as Wisconsin Breast Cancer-Diagnosis Dataset, Wisconsin Breast Cancer-Original Dataset, Wisconsin Breast Cancer-Prognosis Dataset, ISPY1 Clinical trial Dataset, and Breast Cancer Dataset. The results exploit that SVM-GA achieves higher accuracy of 98.16% than DT-GA of 97.44%.

scholarly journals Exact Techniques for Hardware Modelling of Machine Learning Algorithms with Building of Neuron Network

2022 ◽  
pp. 89-95
Author(s):  
Ms. Amita P. Thakare ◽  
Dr. Sunil Kumar
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Stock Market ◽  
Travelling Salesman Problem ◽  
Learning Algorithms ◽  
Market Price ◽  
Machine Learning Algorithms ◽  
Neuron Network ◽  
Travelling Salesman ◽  
Simple Arithmetic

System getting to know algorithms are complicated to version on hardware. that is due to the truth that those algorithms require quite a few complicated design systems, which are not effort lessly synthesizable. Therefore, through the years, multiple researchers have developed diverse kingdom-of-the artwork techniques, every of them has sure distinct advantages over the others. In this newsletter, we compare the specific strategies for hardware modelling of the various device gaining knowledge of machine learning algorithms, and their hardware-stage overall performance. this newsletter could be useful for any researcher or gadget dressmaker that needs to first evaluate the superior techniques for ML layout, and then inspired with the aid of this, they are able to similarly enlarge it and optimize the device’s performance. Our assessment is based on the 3 number one parameters of hardware layout; that is; place, power and postpone. Any layout approach that can find a stability among those three parameters may be termed as greatest. This work additionally recommends sure enhancements for some of the techniques, which can be taken up for similarly studies. Machine Learning is a concept to find out from examples and skill, while not being expressly programmed. Rather than writing code, you feed knowledge to the generic formula, and it builds logic supported the info given. for instance, one reasonably formula could be a classification formula. It will place knowledge into totally different teams. The classification formula accustomed notice written alphabets may even be accustomed classifies emails into spam and not-spam. Machine learning has resolve many errors ranging from simple arithmetic problems like TSP (Travelling Salesman Problem) to complex issues like predicting the variations in stock market price, Machine learning algorithms like genetic algorithm, particles swarm optimization, deep nets and Q-learning are currently being developed on software platforms due to the ease of implementation. But the full utilization of core algorithms can only be possible. If they are designed & integrated inside the silicon chip. Companies like Apple, Google and Snapdragon etc. are continuously updating their ICs to incorporate these algorithms. But there is no standard architecture defined to implement these algorithms at chip level, due to these inefficiencies of every alternative multiply when these devices connected together. In this research work, we plan to develop a standard architecture for implementation of machine learning algorithms on integrated circuits so that these circuits. connected together work seamlessly with each other & improve the overall system performance. Finally, we planned to implement at least two algorithms on the proposed architecture & verify its optimization capability for practical systems. Our assessment is based on the 3 number one parameters of hardware layout; i.e.; place, power and postpone. Any layout approach that can find a stability among those three parameters may be termed as greatest. This work additionally recommends sure enhancements for some of the techniques, which can be taken up for similarly studies. Machine learning has solved many problems ranging from simple arithmetic problems like TSP (Travelling Salesman Problem) to complex issues like predicting the variations in stock market price, Machine learning algorithms like genetic algorithm.

Neuronal Communication Genetic Algorithm-Based Inductive Learning

2021 ◽  
pp. 244-259
Author(s):  
Abdiya Alaoui ◽  
Zakaria Elberrichi
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Predictive Accuracy ◽  
Inductive Learning ◽  
Learning Algorithms ◽  
Hybrid Approach ◽  
Machine Learning Algorithms ◽  
Rule Based ◽  
Neuronal Communication ◽  
Robust Model

The development of powerful learning strategies in the medical domain constitutes a real challenge. Machine learning algorithms are used to extract high-level knowledge from medical datasets. Rule-based machine learning algorithms are easily interpreted by humans. To build a robust rule-based algorithm, a new hybrid metaheuristic was proposed for the classification of medical datasets. The hybrid approach uses neural communication and genetic algorithm-based inductive learning to build a robust model for disease prediction. The resulting classification models are characterized by good predictive accuracy and relatively small size. The results on 16 well-known medical datasets from the UCI machine learning repository shows the efficiency of the proposed approach compared to other states-of-the-art approaches.

Neuronal Communication Genetic Algorithm-Based Inductive Learning

2020 ◽  
Vol 13 (2) ◽  
pp. 141-154
Author(s):  
Abdiya Alaoui ◽  
Zakaria Elberrichi
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Learning Strategies ◽  
Predictive Accuracy ◽  
Inductive Learning ◽  
Learning Algorithms ◽  
Hybrid Approach ◽  
Machine Learning Algorithms ◽  
Rule Based ◽  
High Level

The development of powerful learning strategies in the medical domain constitutes a real challenge. Machine learning algorithms are used to extract high-level knowledge from medical datasets. Rule-based machine learning algorithms are easily interpreted by humans. To build a robust rule-based algorithm, a new hybrid metaheuristic was proposed for the classification of medical datasets. The hybrid approach uses neural communication and genetic algorithm-based inductive learning to build a robust model for disease prediction. The resulting classification models are characterized by good predictive accuracy and relatively small size. The results on 16 well-known medical datasets from the UCI machine learning repository shows the efficiency of the proposed approach compared to other states-of-the-art approaches.

scholarly journals Towards Intelligent Regulation of Artificial Intelligence

2019 ◽  
Vol 10 (1) ◽  
pp. 41-59 ◽  
Author(s):  
Miriam C BUITEN
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Input Data ◽  
Decision Model ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Daily Lives ◽  
Fast Pace ◽  
The Law ◽  
Legal Contexts

Artificial intelligence (AI) is becoming a part of our daily lives at a fast pace, offering myriad benefits for society. At the same time, there is concern about the unpredictability and uncontrollability of AI. In response, legislators and scholars call for more transparency and explainability of AI. This article considers what it would mean to require transparency of AI. It advocates looking beyond the opaque concept of AI, focusing on the concrete risks and biases of its underlying technology: machine-learning algorithms. The article discusses the biases that algorithms may produce through the input data, the testing of the algorithm and the decision model. Any transparency requirement for algorithms should result in explanations of these biases that are both understandable for the prospective recipients, and technically feasible for producers. Before asking how much transparency the law should require from algorithms, we should therefore consider if the explanation that programmers could offer is useful in specific legal contexts.

Sign in / Sign up

Export Citation Format

Share Document