To see the other types of publications on this topic, follow the link: MACHINE ALGORITHMS.
Journal articles on the topic 'MACHINE ALGORITHMS'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'MACHINE ALGORITHMS.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Mishra, Akshansh, and Apoorv Vats. "Supervised Machine Learning Classification Algorithms for Detection of Fracture Location in Dissimilar Friction Stir Welded Joints." Frattura ed Integrità Strutturale 15, no. 58 (September 25, 2021): 242–53. http://dx.doi.org/10.3221/igf-esis.58.18.
Full textAbstract:
Machine Learning focuses on the study of algorithms that are mathematical or statistical in nature in order to extract the required information pattern from the available data. Supervised Machine Learning algorithms are further sub-divided into two types i.e. regression algorithms and classification algorithms. In the present study, four supervised machine learning-based classification models i.e. Decision Trees algorithm, K- Nearest Neighbors (KNN) algorithm, Support Vector Machines (SVM) algorithm, and Ada Boost algorithm were subjected to the given dataset for the determination of fracture location in dissimilar Friction Stir Welded AA6061-T651 and AA7075-T651 alloy. In the given dataset, rotational speed (RPM), welding speed (mm/min), pin profile, and axial force (kN) were the input parameters while Fracture location is the output parameter. The obtained results showed that the Support Vector Machine (SVM) algorithm classified the fracture location with a good accuracy score of 0.889 in comparison to the other algorithms.
2
Benbouzid, Bilel. "Unfolding Algorithms." Science & Technology Studies 32, no. 4 (December 13, 2019): 119–36. http://dx.doi.org/10.23987/sts.66156.
Full textAbstract:
Predictive policing is a research field whose principal aim is to develop machines for predicting crimes, drawing on machine learning algorithms and the growing availability of a diversity of data. This paper deals with the case of the algorithm of PredPol, the best-known startup in predictive policing. The mathematicians behind it took their inspiration from an algorithm created by a French seismologist, a professor in earth sciences at the University of Savoie. As the source code of the PredPol platform is kept inaccessible as a trade secret, the author contacted the seismologist directly in order to try to understand the predictions of the company’s algorithm. Using the same method of calculation on the same data, the seismologist arrived at a different, more cautious interpretation of the algorithm's capacity to predict crime. How were these predictive analyses formed on the two sides of the Atlantic? How do predictive algorithms come to exist differently in these different contexts? How and why is it that predictive machines can foretell a crime that is yet to be committed in a California laboratory, and yet no longer work in another laboratory in Chambéry? In answering these questions, I found that machine learning researchers have a moral vision of their own activity that can be understood by analyzing the values and material consequences involved in the evaluation tests that are used to create the predictions.
3
HE, YONG, SHUGUANG HAN, and YIWEI JIANG. "ONLINE ALGORITHMS FOR SCHEDULING WITH MACHINE ACTIVATION COST." Asia-Pacific Journal of Operational Research 24, no. 02 (April 2007): 263–77. http://dx.doi.org/10.1142/s0217595907001231.
Full textAbstract:
In this paper, we consider a variant of the classical parallel machine scheduling problem. For this problem, we are given m potential identical machines to non-preemptively process a sequence of independent jobs. Machines need to be activated before starting to process, and each machine activated incurs a fixed machine activation cost. No machines are initially activated, and when a job is revealed the algorithm has the option to activate new machines. The objective is to minimize the sum of the makespan and activation cost of machines. We first present two optimal online algorithms with competitive ratios of 3/2 and 5/3 for m = 2, 3 cases, respectively. Then we present an online algorithm with a competitive ratio of at most 2 for general m ≥ 4, while the lower bound is 1.88.
4
TURAN, SELIN CEREN, and MEHMET ALI CENGIZ. "ENSEMBLE LEARNING ALGORITHMS." Journal of Science and Arts 22, no. 2 (June 30, 2022): 459–70. http://dx.doi.org/10.46939/j.sci.arts-22.2-a18.
Full textAbstract:
Artificial intelligence is a method that is increasingly becoming widespread in all areas of life and enables machines to imitate human behavior. Machine learning is a subset of artificial intelligence techniques that use statistical methods to enable machines to evolve with experience. As a result of the advancement of technology and developments in the world of science, the interest and need for machine learning is increasing day by day. Human beings use machine learning techniques in their daily life without realizing it. In this study, ensemble learning algorithms, one of the machine learning techniques, are mentioned. The methods used in this study are Bagging and Adaboost algorithms which are from Ensemble Learning Algorithms. The main purpose of this study is to find the best performing classifier with the Classification and Regression Trees (CART) basic classifier on three different data sets taken from the UCI machine learning database and then to obtain the ensemble learning algorithms that can make this performance better and more determined using two different ensemble learning algorithms. For this purpose, the performance measures of the single basic classifier and the ensemble learning algorithms were compared
5
Ling, Qingyang. "Machine learning algorithms review." Applied and Computational Engineering 4, no. 1 (June 14, 2023): 91–98. http://dx.doi.org/10.54254/2755-2721/4/20230355.
Full textAbstract:
Machine learning is a field of study where the computer can learn for itself without a human explicitly hardcoding the knowledge for it. These algorithms make up the backbone of machine learning. This paper aims to study the field of machine learning and its algorithms. It will examine different types of machine learning models and introduce their most popular algorithms. The methodology of this paper is a literature review, which examines the most commonly used machine learning algorithms in the current field. Such algorithms include Nave Bayes, Decision Tree, KNN, and K-Mean Cluster. Nowadays, machine learning is everywhere and almost everyone using a technology product is enjoying its convenience. Applications like spam mail classification, image recognition, personalized product recommendations, and natural language processing all use machine learning algorithms. The conclusion is that there is no single algorithm that can solve all the problems. The choice of the use of algorithms and models must depend on the specific problem.
6
Sameer, S. K. L., and P. Sriramya. "Improving the Efficiency by Novel Feature Extraction Technique Using Decision Tree Algorithm Comparing with SVM Classifier Algorithm for Predicting Heart Disease." Alinteri Journal of Agriculture Sciences 36, no. 1 (June 29, 2021): 713–20. http://dx.doi.org/10.47059/alinteri/v36i1/ajas21100.
Full textAbstract:
Aim: The objective of the research work is to use the two machine learning algorithms Decision Tree(DT) and Support vector machine(SVM) for detection of heart disease on earlier stages and give more accurate prediction. Materials and methods: Prediction of heart disease is performed using two machine learning classifier algorithms namely, Decision Tree and Support Vector Machine methods. Decision tree is the predictive modeling approach used in machine learning, it is a type of supervised machine learning. Support-vector machines are directed learning models with related learning calculations that break down information for order and relapse investigation. The significance value for calculating Accuracy was found to be 0.005. Result and discussion: During the process of testing 10 iterations have been taken for each of the classification algorithms respectively. The experimental results shows that the decision tree algorithm with mean accuracy of 80.257% is compared with the SVM classifier algorithm of mean accuracy 75.337% Conclusion: Based on the results achieved the Decision Tree classification algorithm better prediction of heart disease than the SVM classifier algorithm.
7
Meena, Munesh, and Ruchi Sehrawat. "Breakdown of Machine Learning Algorithms." Recent Trends in Artificial Intelligence & it's Applications 1, no. 3 (October 16, 2022): 25–29. http://dx.doi.org/10.46610/rtaia.2022.v01i03.005.
Full textAbstract:
Machine Learning (ML) is a technology that can revolutionize the world. It is a technology based on AI (Artificial Intelligence) and can predict the outcomes using the previous algorithms without programming it. A subset of artificial intelligence is called machine learning (AI). A machine may automatically learn from data and get better at what it does thanks to machine learning. “If additional data can be gathered to help a machine perform better, it can learn. A developing technology called machine learning allows computers to learn from historical data. Machines can predict the outcomes by machine learning. For Nowadays machine learning is very important for us because it makes our work easy. to many companies are using machine learning in their products, like google is using google its google assistant, which takes our voice command and gives what do we want from it, and google is also using its goggle lens form which we can find anything just by clicking a picture, and Netflix is using machine learning for recommendation of any movies or series, Machine learning has a very deep effect on our life, like nowadays we are using selfdriving car’s.
8
Maitre, Julien, Sébastien Gaboury, Bruno Bouchard, and Abdenour Bouzouane. "A Black-Box Model for Estimation of the Induction Machine Parameters Based on Stochastic Algorithms." International Journal of Monitoring and Surveillance Technologies Research 3, no. 3 (July 2015): 44–67. http://dx.doi.org/10.4018/ijmstr.2015070103.
Full textAbstract:
Knowledge on asynchronous machine parameters (resistances, inductances…) has become necessary for the manufacturing industry in the interest of optimizing performances in a production system (roll-to-roll processing, wind generator…). Indeed, accurate values of this machine allow improving control of the torque, speed and position, managing power consumption in the best way possible, and predicting induction machine failures with great effectiveness. In these regards, the authors of this paper propose a black-box modeling for a powerful identification of asynchronous machine parameters relying on stochastic research algorithms. The algorithms used for the estimation process are a single objective genetic algorithm, the well-known NSGA II and the new ?-NSGA III (multi-objective genetic algorithms). Results provided by those show that the best estimation of asynchronous machines parameters is given by ?-NSGA III. In addition, this outcome is confirmed by performing the identification process on three different induction machines.
9
Castelo, Noah, Maarten W. Bos, and Donald Lehmann. "Let the Machine Decide: When Consumers Trust or Distrust Algorithms." NIM Marketing Intelligence Review 11, no. 2 (November 1, 2019): 24–29. http://dx.doi.org/10.2478/nimmir-2019-0012.
Full textAbstract:
AbstractThanks to the rapid progress in the field of artificial intelligence algorithms are able to accomplish an increasingly comprehensive list of tasks, and often they achieve better results than human experts. Nevertheless, many consumers have ambivalent feelings towards algorithms and tend to trust humans more than they trust machines. Especially when tasks are perceived as subjective, consumers often assume that algorithms will be less effective, even if this belief is getting more and more inaccurate.To encourage algorithm adoption, managers should provide empirical evidence of the algorithm’s superior performance relative to humans. Given that consumers trust in the cognitive capabilities of algorithms, another way to increase trust is to demonstrate that these capabilities are relevant for the task in question. Further, explaining that algorithms can detect and understand human emotions can enhance adoption of algorithms for subjective tasks.
10
K.M., Umamaheswari. "Road Accident Perusal Using Machine Learning Algorithms." International Journal of Psychosocial Rehabilitation 24, no. 5 (March 31, 2020): 1676–82. http://dx.doi.org/10.37200/ijpr/v24i5/pr201839.
Full text
11
Nair, Dr Prabha Shreeraj. "Analyzing Titanic Disaster using Machine Learning Algorithms." International Journal of Trend in Scientific Research and Development Volume-2, Issue-1 (December 31, 2017): 410–16. http://dx.doi.org/10.31142/ijtsrd7003.
Full text
12
Gupta, Monica. "A Comparative Study on Supervised Machine Learning Algorithm." International Journal for Research in Applied Science and Engineering Technology 10, no. 1 (January 31, 2022): 1023–28. http://dx.doi.org/10.22214/ijraset.2022.39980.
Full textAbstract:
Abstract: Machine learning enables computers to act and make data driven decisions rather than being explicitly programmed to carry out a certain task. It is a tool and technology which can answer the question from your data. These programs are designed to learn and improve over time when exposed to new data. ML is a subset or a current application of AI. It is based on an idea that we should be able to give machines access to data and let them learn from themselves. ML deals with extraction of patterns from dataset, this means that machines can not only find the rules for optimal behavior but also can adapt to the changes in the world. Many of the algorithms involved have been known for decades. In this paper various algorithms of machine learning have been discussed. Machine learning algorithms are used for various purposes but we can say that once the machine learning algorithm studies how to manage data, it can do its work accordingly by itself. Keywords: Linear Regression, Logistic Regression, KNN, Naive Bayes, Decision Trees, SVM, Random Forest
13
Zhang, Ruiting, and Zhijian Zhou. "A Fuzzy Least Squares Support Tensor Machines in Machine Learning." International Journal of Emerging Technologies in Learning (iJET) 10, no. 8 (December 14, 2015): 4. http://dx.doi.org/10.3991/ijet.v10i8.5203.
Full textAbstract:
In the machine learning field, high-dimensional data are often encountered in the real applications. Most of the traditional learning algorithms are based on the vector space model, such as SVM. Tensor representation is useful to the over fitting problem in vector-based learning, and tensor-based algorithm requires a smaller set of decision variables as compared to vector-based approaches. We also would require that the meaningful training points must be classified correctly and would not care about some training points like noises whether or not they are classified correctly. To utilize the structural information present in high dimensional features of an object, a tensor-based learning framework, termed as Fuzzy Least Squares support tensor machine (FLSSTM), where the classifier is obtained by solving a system of linear equations rather than a quadratic programming problem at each iteration of FLSSTM algorithm as compared to STM algorithm. This in turn provides a significant reduction in the computation time, as well as comparable classification accuracy. The efficacy of the proposed method has been demonstrated in ORL database and Yale database. The FLSSTM outperforms other tensor-based algorithms, for example, LSSTM, especially when training size is small.
14
Yuan, Hongyuan, Jingan Liu, Yu Zhou, and Hailong Pei. "State of Charge Estimation of Lithium Battery Based on Integrated Kalman Filter Framework and Machine Learning Algorithm." Energies 16, no. 5 (February 23, 2023): 2155. http://dx.doi.org/10.3390/en16052155.
Full textAbstract:
Research on batteries’ State of Charge (SOC) estimation for equivalent circuit models based on the Kalman Filter (KF) framework and machine learning algorithms remains relatively limited. Most studies are focused on a few machine learning algorithms and do not present comprehensive analysis and comparison. Furthermore, most of them focus on obtaining the state space parameters of the Kalman filter frame algorithm models using machine learning algorithms and then substituting the state space parameters into the Kalman filter frame algorithm to estimate the SOC. Such algorithms are highly coupled, and present high complexity and low practicability. This study aims to integrate machine learning with the Kalman filter frame algorithm, and to estimate the final SOC by using different combinations of the input, output, and intermediate variable values of five Kalman filter frame algorithms as the input of the machine learning algorithms of six main streams. These are: linear regression, support vector Regression, XGBoost, AdaBoost, random forest, and LSTM; the algorithm coupling is lower for two-way parameter adjustment and is not applied between the machine learning and Kalman filtering framework algorithms. The results demonstrate that the integrated learning algorithm significantly improves the estimation accuracy when compared to the pure Kalman filter framework or the machine learning algorithms. Among the various integrated algorithms, the random forest and Kalman filter framework presents the highest estimation accuracy along with good real-time performance. Therefore, it can be implemented in various engineering applications.
15
Rostami, Soheil, Sajad Alabadi, Soheir Noori, Hayder Ahmed Shihab, Kamran Arshad, and Predrag Rapajic. "Spectrum Assignment Algorithm for Cognitive Machine-to-Machine Networks." Mobile Information Systems 2016 (2016): 1–8. http://dx.doi.org/10.1155/2016/3282505.
Full textAbstract:
A novel aggregation-based spectrum assignment algorithm for Cognitive Machine-To-Machine (CM2M) networks is proposed. The introduced algorithm takes practical constraints including interference to the Licensed Users (LUs), co-channel interference (CCI) among CM2M devices, and Maximum Aggregation Span (MAS) into consideration. Simulation results show clearly that the proposed algorithm outperforms State-Of-The-Art (SOTA) algorithms in terms of spectrum utilisation and network capacity. Furthermore, the convergence analysis of the proposed algorithm verifies its high convergence rate.
16
Yu, Yang, and Ping Liu. "Evaluation of Cutting Error in Five-Axis Free-Form Surface Milling for Table-Tilting Type Machine." Advanced Materials Research 472-475 (February 2012): 2125–28. http://dx.doi.org/10.4028/www.scientific.net/amr.472-475.2125.
Full textAbstract:
Accuracy of machined workpiece is one of the most important considerations for any manufacturer. The present study aims to establish a new algorithm for evaluating the cutting Error in five-axis free-form surface milling for table-tilting type machine. The cutting error evaluating algorithms consider the kinematics of the machine and the tool geometry as well as the local geometries of the machined free-form surface. Based on these algorithms, the present study develops a new error compensation method. Finally, experimental results show that the tool paths generated by the present procedure have better machining efficiency.
17
G, Mr Aniket. "A Comparative Study: Machine Learning Algorithms for Parkinson’s Disease Analysis." International Journal for Research in Applied Science and Engineering Technology 11, no. 5 (May 31, 2023): 6275–84. http://dx.doi.org/10.22214/ijraset.2023.53175.
Full textAbstract:
Abstract: Parkinson's disease (PD) is a complex neurodegenerative disorder that affects millions of people worldwide. Accurate diagnosis and monitoring of PD are essential for effective treatment and management of the disease. In recent years, machine learning algorithms have shown great promise in assisting with the analysis of PD data and aiding in diagnosis and prognosis. This study presents a comparative analysis of various machine learning algorithms for PD analysis, with the objective of identifying the most effective approach for detecting and predicting PD progression. Multiple machine learning algorithms, including decision trees, support vector machines, random forests, neural networks, and ensemble methods, are evaluated using a comprehensive dataset of PD patients and healthy individuals. The study in corporates feature selection and dimensionality reduction techniques to enhance the algorithms' performance and reduce computational complexity. The results of the comparative analysis reveal the strengths and weaknesses of each algorithm in PD analysis. In conclusion, this comparative study showcases the effectiveness of machine learning algorithms in the field of PD research. It emphasizes the importance of selecting appropriate algorithms and features for accurate diagnosis and prediction of PD, ultimately leading to improved patient outcomes and better management of the disease
18
Grzymala-Busse, Jerzy W. "Selected Algorithms of Machine Learning from Examples." Fundamenta Informaticae 18, no. 2-4 (April 1, 1993): 193–207. http://dx.doi.org/10.3233/fi-1993-182-408.
Full textAbstract:
This paper presents and compares two algorithms of machine learning from examples, ID3 and AQ, and one recent algorithm from the same class, called LEM2. All three algorithms are illustrated using the same example. Production rules induced by these algorithms from the well-known Small Soybean Database are presented. Finally, some advantages and disadvantages of these algorithms are shown.
19
Abbas, Muhammad Adeel, and Zeshan Iqbal. "Double Auction used Artificial Neural Network in Cloud Computing." Vol 4 Issue 5 4, no. 5 (June 30, 2022): 65–76. http://dx.doi.org/10.33411/ijist/2022040506.
Full textAbstract:
Double auction (DA) algorithm is widely used for trading systems in cloud computing. Distinct buyers request different attributes for virtual machines. On the other hand, different sellers offer several types of virtual machines according to their correspondence bids. In DA, getting multiple equilibrium prices from distinct cloud providers is a difficult task, and one of the major problems is bidding prices for virtual machines, so we cannot make decisions with inconsistent data. To solve this problem, we need to find the best machine learning algorithm that anticipates the bid cost for virtual machines. Analyzing the performance of DA algorithm with machine learning algorithms is to predict the bidding price for both buyers and sellers. Therefore, we have implemented several machine learning algorithms and observed their performance on the bases of accuracy, such as linear regression (83%), decision tree regressor (77%), random forest (82%), gradient boosting (81%), and support vector regressor (90%). In the end, we observed that the Artificial Neural Network (ANN) provided an astonishing result. ANN has provided 97% accuracy in predicting bidding prices in DA compared to all other learning algorithms. It reduced the wastage of resources (VMs attributes) and soared both users' profits (buyers & sellers). Different types of models were analyzed on the bases of individual parameters such as accuracy. In the end, we found that ANN is effective and valuable for bidding prices for both users.
20
Liu, Xiaonan, Haoshan Xie, Zhengyu Liu, and Chenyan Zhao. "Survey on the Improvement and Application of HHL Algorithm." Journal of Physics: Conference Series 2333, no. 1 (August 1, 2022): 012023. http://dx.doi.org/10.1088/1742-6596/2333/1/012023.
Full textAbstract:
Abstract Quantum computing is a new computing mode that follows the laws of quantum mechanics to control quantum information units for computation. In terms of computational efficiency, due to the existence of quantum mechanical superposition, some known quantum algorithms can process problems faster than traditional general-purpose computers. HHL algorithm is an algorithm for solving linear system problems. Compared with classical algorithms in solving linear equations, it has an exponential acceleration effect in certain cases and as a sub-module, it is widely used in some machine learning algorithms to form quantum machines learning algorithms. However, there are some limiting factors in the use of this algorithm, which affect the overall effect of the algorithm. How to improve it to make the algorithm perform better has become an important issue in the field of quantum computing. This paper summarizes the optimization and improvement of HHL algorithm since it was proposed, and the application of HHL algorithm in machine learning, and discusses some possible future improvements of some subroutines in HHL algorithm.
21
Kumar, Awnish. "Machine Learning Based Heat Transfer Optimization of Nano-fluid flow in a Helically Coiled Pipe." International Journal for Research in Applied Science and Engineering Technology 9, no. 12 (December 31, 2021): 1717–31. http://dx.doi.org/10.22214/ijraset.2021.39576.
Full textAbstract:
Abstract: Machine Learning algorithms are widely used in various fields such as energy sectors, manufacturing sectors and aerospace sectors. These algorithms are used mainly in predictive and optimization purpose. The present study deals with the application of two machine learning algorithms i.e. Random Forest algorithm and Support Vector Machine Algorithm to predict the heat transfer efficiency of a flowing nano-fluid in a helically coiled pipe. Keywords: Machine Learning; Optimization; Nano-fluid; Heat Transfer
22
Todorov, Dimitar Georgiev, and Karova Milena. "Appropriate Conversion of Machine Learning Data." ANNUAL JOURNAL OF TECHNICAL UNIVERSITY OF VARNA, BULGARIA 6, no. 2 (December 31, 2022): 63–76. http://dx.doi.org/10.29114/ajtuv.vol6.iss2.262.
Full textAbstract:
Data is an important part of computer technology and, as such, explains the strong dependence of machine learning algorithms on it. The operation of any corresponding algorithm is directly dependent on the type of data and the proper data representation increases the productivity of these algorithms. Advanced in the present article is an algorithm for data pre-processing in a form that is most suitable for machine learning algorithms, with cryptographic secret keys being used as input data. The experimental results were satisfactory, and with the utilization of secret keys with significant differences, the recognition obtained is about 100%.
23
Barbosa, Flávio, Arthur Vidal, and Flávio Mello. "Machine Learning for Cryptographic Algorithm Identification." Journal of Information Security and Cryptography (Enigma) 3, no. 1 (September 3, 2016): 3. http://dx.doi.org/10.17648/enig.v3i1.55.
Full textAbstract:
This paper aims to study encrypted text files in order to identify their encoding algorithm. Plain texts were encoded with distinct cryptographic algorithms and then some metadata were extracted from these codifications. Afterward, the algorithm identification is obtained by using data mining techniques. Firstly, texts in Portuguese, English and Spanish were encrypted using DES, Blowfish, RSA, and RC4 algorithms. Secondly, the encrypted files were submitted to data mining techniques such as J48, FT, PART, Complement Naive Bayes, and Multilayer Perceptron classifiers. Charts were created using the confusion matrices generated in step two and it was possible to perceive that the percentage of identification for each of the algorithms is greater than a probabilistic bid. There are several scenarios where algorithm identification reaches almost 97, 23% of correctness.
24
Li, Chunjiang. "Application of Machine Learning Algorithms in the Stock Market Analysis." Highlights in Business, Economics and Management 10 (May 9, 2023): 352–58. http://dx.doi.org/10.54097/hbem.v10i.8119.
Full textAbstract:
With the development of deep learning and machine learning, more new methods have been produced in the economic and financial fields. When talking about machines, one thing that comes to people’s minds is what they can do with machines to solve problems that need machines. The people in the stock market always want to find ways to forecast the stock trend, the pattern of stock, and the stock value. Before the development of machine learning algorithms, stock market predictions could be made in limited ways, and those methods usually did not produce accurate predictions. However, machine learning algorithms changed the phenomenon and offered people novel ways to analyze the stock market. This paper will discuss three research in which authors have implemented machine learning algorithms into stock market analyses. From analyzing the research, this paper tries to investigate the extent of applying machine learning algorithms in the stock market and how the algorithms have helped investors make improvements in stock market analysis.
25
Golden, Richard M. "Adaptive Learning Algorithm Convergence in Passive and Reactive Environments." Neural Computation 30, no. 10 (October 2018): 2805–32. http://dx.doi.org/10.1162/neco_a_01117.
Full textAbstract:
Although the number of artificial neural network and machine learning architectures is growing at an exponential pace, more attention needs to be paid to theoretical guarantees of asymptotic convergence for novel, nonlinear, high-dimensional adaptive learning algorithms. When properly understood, such guarantees can guide the algorithm development and evaluation process and provide theoretical validation for a particular algorithm design. For many decades, the machine learning community has widely recognized the importance of stochastic approximation theory as a powerful tool for identifying explicit convergence conditions for adaptive learning machines. However, the verification of such conditions is challenging for multidisciplinary researchers not working in the area of stochastic approximation theory. For this reason, this letter presents a new stochastic approximation theorem for both passive and reactive learning environments with assumptions that are easily verifiable. The theorem is widely applicable to the analysis and design of important machine learning algorithms including deep learning algorithms with multiple strict local minimizers, Monte Carlo expectation-maximization algorithms, contrastive divergence learning in Markov fields, and policy gradient reinforcement learning.
26
Grgić-Hlača, Nina, Claude Castelluccia, and Krishna P. Gummadi. "Taking Advice from (Dis)Similar Machines: The Impact of Human-Machine Similarity on Machine-Assisted Decision-Making." Proceedings of the AAAI Conference on Human Computation and Crowdsourcing 10, no. 1 (October 14, 2022): 74–88. http://dx.doi.org/10.1609/hcomp.v10i1.21989.
Full textAbstract:
Machine learning algorithms are increasingly used to assist human decision-making. When the goal of machine assistance is to improve the accuracy of human decisions, it might seem appealing to design ML algorithms that complement human knowledge. While neither the algorithm nor the human are perfectly accurate, one could expect that their complementary expertise might lead to improved outcomes. In this study, we demonstrate that in practice decision aids that are not complementary, but make errors similar to human ones may have their own benefits. In a series of human-subject experiments with a total of 901 participants, we study how the similarity of human and machine errors influences human perceptions of and interactions with algorithmic decision aids. We find that (i) people perceive more similar decision aids as more useful, accurate, and predictable, and that (ii) people are more likely to take opposing advice from more similar decision aids, while (iii) decision aids that are less similar to humans have more opportunities to provide opposing advice, resulting in a higher influence on people’s decisions overall.
27
Thomas, Philip S., Bruno Castro da Silva, Andrew G. Barto, Stephen Giguere, Yuriy Brun, and Emma Brunskill. "Preventing undesirable behavior of intelligent machines." Science 366, no. 6468 (November 21, 2019): 999–1004. http://dx.doi.org/10.1126/science.aag3311.
Full textAbstract:
Intelligent machines using machine learning algorithms are ubiquitous, ranging from simple data analysis and pattern recognition tools to complex systems that achieve superhuman performance on various tasks. Ensuring that they do not exhibit undesirable behavior—that they do not, for example, cause harm to humans—is therefore a pressing problem. We propose a general and flexible framework for designing machine learning algorithms. This framework simplifies the problem of specifying and regulating undesirable behavior. To show the viability of this framework, we used it to create machine learning algorithms that precluded the dangerous behavior caused by standard machine learning algorithms in our experiments. Our framework for designing machine learning algorithms simplifies the safe and responsible application of machine learning.
28
A, Ms Vidhya, Dr Parameswari R, and Ms Sathya S. "Brain Tumor Classification Using Various Machine Learning Algorithms." International Journal of Research in Arts and Science 5, Special Issue (August 30, 2019): 258–70. http://dx.doi.org/10.9756/bp2019.1002/25.
Full text
29
Zhou, Shuni, Guangxing Wu, Yehong Dong, Yuanxiang Ni, Yuheng Hao, Yunhe Jiang, Chuang Zhou, and Zhiyu Tao. "Evaluations on supervised learning methods in the calibration of seven-hole pressure probes." PLOS ONE 18, no. 1 (January 23, 2023): e0277672. http://dx.doi.org/10.1371/journal.pone.0277672.
Full textAbstract:
Machine learning method has become a popular, convenient and efficient computing tool applied to many industries at present. Multi-hole pressure probe is an important technique widely used in flow vector measurement. It is a new attempt to integrate machine learning method into multi-hole probe measurement. In this work, six typical supervised learning methods in scikit-learn library are selected for parameter adjustment at first. Based on the optimal parameters, a comprehensive evaluation is conducted from four aspects: prediction accuracy, prediction efficiency, feature sensitivity and robustness on the failure of some hole port. As results, random forests and K-nearest neighbors’ algorithms have the better comprehensive prediction performance. Compared with the in-house traditional algorithm, the machine learning algorithms have the great advantages in the computational efficiency and the convenience of writing code. Multi-layer perceptron and support vector machines are the most time-consuming algorithms among the six algorithms. The prediction accuracy of all the algorithms is very sensitive to the features. Using the features based on the physical knowledge can obtain a high accuracy predicted results. Finally, KNN algorithm is successfully applied to field measurements on the angle of attack of a wind turbine blades. These findings provided a new reference for the application of machine learning method in multi-hole probe calibration and measurement.
30
Coe, James, and Mustafa Atay. "Evaluating Impact of Race in Facial Recognition across Machine Learning and Deep Learning Algorithms." Computers 10, no. 9 (September 10, 2021): 113. http://dx.doi.org/10.3390/computers10090113.
Full textAbstract:
The research aims to evaluate the impact of race in facial recognition across two types of algorithms. We give a general insight into facial recognition and discuss four problems related to facial recognition. We review our system design, development, and architectures and give an in-depth evaluation plan for each type of algorithm, dataset, and a look into the software and its architecture. We thoroughly explain the results and findings of our experimentation and provide analysis for the machine learning algorithms and deep learning algorithms. Concluding the investigation, we compare the results of two kinds of algorithms and compare their accuracy, metrics, miss rates, and performances to observe which algorithms mitigate racial bias the most. We evaluate racial bias across five machine learning algorithms and three deep learning algorithms using racially imbalanced and balanced datasets. We evaluate and compare the accuracy and miss rates between all tested algorithms and report that SVC is the superior machine learning algorithm and VGG16 is the best deep learning algorithm based on our experimental study. Our findings conclude the algorithm that mitigates the bias the most is VGG16, and all our deep learning algorithms outperformed their machine learning counterparts.
31
Idris, Syed Mohammed. "PRACTICAL CLASSIFICATION TEMPLATE FOR DATASETS IN MACHINE LEARNING." International Journal of Engineering Applied Sciences and Technology 7, no. 10 (February 1, 2023): 110–16. http://dx.doi.org/10.33564/ijeast.2023.v07i10.014.
Full textAbstract:
In this work, different Machine Learning (ML) algorithms are used and evaluated based on their performance of classifying peer reviewed content of the dataset provided. The ultimate objective is to extract meaningful information from the classification of the given dataset. In pursuing this objective, the ML techniques are utilized to classify different datasets into: Validation Dataset and Test Dataset. The ML techniques applied in this work are Logistic Regression, Support Vector Machines, Naïve Bayes, Linear Discriminant Analysis, KNearest Neighbor, and Decision Tree. In addition to the description of the utilized ML algorithms, the methodology and algorithms for classification using the aforementioned ML techniques are provided. The comparative study based on six different performance measures suggests that - with the exception of Support Vector Machines algorithm - the proposed ML techniques with the detailed pre-processing algorithms may or may not work well for classifying the iris flower dataset.
32
Liu, Guo-Sheng, Jin-Jin Li, and Ying-Si Tang. "Minimizing Total Idle Energy Consumption in the Permutation Flow Shop Scheduling Problem." Asia-Pacific Journal of Operational Research 35, no. 06 (December 2018): 1850041. http://dx.doi.org/10.1142/s0217595918500410.
Full textAbstract:
In this paper, we investigate the well-known permutation flow shop (PFS) scheduling problem with a particular objective, the minimization of total idle energy consumption of the machines. The problem considers the energy waste induced by the machine idling, in which the idle energy consumption is evaluated by the multiplication of the idle time and power level of each machine. Since the problem considered is NP-hard, theoretical results are given for several basic cases. For the two-machine case, we prove that the optimal schedule can be found by employing a relaxed Johnson’s algorithm within O([Formula: see text]) time complexity. For the cases with multiple machines (not less than 3), we propose a novel NEH heuristic algorithm to obtain an approximate energy-saving schedule. The heuristic algorithms are validated by comparison with NEH on a typical PFS problem and a case study for tire manufacturing shows an energy consumption reduction of approximately [Formula: see text] by applying the energy-saving scheduling and the proposed algorithms.
33
Madhumala, R. B., Harshvardhan Tiwari, and Verma C. Devaraj. "Virtual Machine Placement Using Energy Efficient Particle Swarm Optimization in Cloud Datacenter." Cybernetics and Information Technologies 21, no. 1 (March 1, 2021): 62–72. http://dx.doi.org/10.2478/cait-2021-0005.
Full textAbstract:
Abstract Efficient resource allocation through Virtual machine placement in a cloud datacenter is an ever-growing demand. Different Virtual Machine optimization techniques are constructed for different optimization problems. Particle Swam Optimization (PSO) Algorithm is one of the optimization techniques to solve the multidimensional virtual machine placement problem. In the algorithm being proposed we use the combination of Modified First Fit Decreasing Algorithm (MFFD) with Particle Swarm Optimization Algorithm, used to solve the best Virtual Machine packing in active Physical Machines to reduce energy consumption; we first screen all Physical Machines for possible accommodation in each Physical Machine and then the Modified Particle Swam Optimization (MPSO) Algorithm is used to get the best fit solution.. In our paper, we discuss how to improve the efficiency of Particle Swarm Intelligence by adapting the efficient mechanism being proposed. The obtained result shows that the proposed algorithm provides an optimized solution compared to the existing algorithms.
34
Khan, Dr Rafiqul Zaman, and Haider Allamy. "Training Algorithms for Supervised Machine Learning: Comparative Study." INTERNATIONAL JOURNAL OF MANAGEMENT & INFORMATION TECHNOLOGY 4, no. 3 (July 25, 2013): 354–60. http://dx.doi.org/10.24297/ijmit.v4i3.773.
Full textAbstract:
Supervised machine learning is an important task for learning artificial neural networks; therefore a demand for selected supervised learning algorithms such as back propagation algorithm, decision tree learning algorithm and perceptron algorithm has been arise in order to perform the learning stage of the artificial neural networks. In this paper; a comparative study has been presented for the aforementioned algorithms to evaluate their performance within a range of specific parameters such as speed of learning, overfitting avoidance, and their accuracy. Besides these parameters we have included their benefits and limitations to unveil their hidden features and provide more details regarding their performance. We have found the decision tree algorithm is the best as compared with other algorithms that can solve the complex problems with a remarkable speed.
35
Li, Haoxuan, Xueyan Zhang, Ziyan Li, and Chunyuan Zheng. "Overview of Machine Learning for Stock Selection Based on Multi-Factor Models." E3S Web of Conferences 214 (2020): 02047. http://dx.doi.org/10.1051/e3sconf/202021402047.
Full textAbstract:
In recent years, many scholars have used different methods to predict and select stocks. Empirical studies have shown that in multi-factor models, machine learning algorithms perform better on stock selection than traditional statistical methods. This article selects six classic machine learning algorithms, and takes the CSI 500 component stocks as an example, using 19 factors to select stocks. In this article, we introduce four of these algorithms in detail and apply them to select stocks. Finally, we back-test six machine learning algorithms, list the data, analyze the performance of each algorithm, and put forward some ideas on the direction of machine learning algorithm improvement.
36
Chaulwar, Amit. "Sampling Algorithms Combination with Machine Learning for Efficient Safe Trajectory Planning." International Journal of Machine Learning and Computing 11, no. 1 (January 2021): 1–11. http://dx.doi.org/10.18178/ijmlc.2021.11.1.1007.
Full textAbstract:
The planning of safe trajectories in critical traffic scenarios using model-based algorithms is a very computationally intensive task. Recently proposed algorithms, namely Hybrid Augmented CL-RRT, Hybrid Augmented CL-RRT+ and GATE-ARRT+, reduce the computation time for safe trajectory planning drastically using a combination of a deep learning algorithm 3D-ConvNet with a vehicle dynamic model. An efficient embedded implementation of these algorithms is required as the vehicle on-board micro-controller resources are limited. This work proposes methodologies for replacing the computationally intensive modules of these trajectory planning algorithms using different efficient machine learning and analytical methods. The required computational resources are measured by downloading and running the algorithms on various hardware platforms. The results show significant reduction in computational resources and the potential of proposed algorithms to run in real time. Also, alternative architectures for 3D-ConvNet are presented for further reduction of required computational resources.
37
Slemenšek, Jan, Iztok Fister, Jelka Geršak, Božidar Bratina, Vesna Marija van Midden, Zvezdan Pirtošek, and Riko Šafarič. "Human Gait Activity Recognition Machine Learning Methods." Sensors 23, no. 2 (January 9, 2023): 745. http://dx.doi.org/10.3390/s23020745.
Full textAbstract:
Human gait activity recognition is an emerging field of motion analysis that can be applied in various application domains. One of the most attractive applications includes monitoring of gait disorder patients, tracking their disease progression and the modification/evaluation of drugs. This paper proposes a robust, wearable gait motion data acquisition system that allows either the classification of recorded gait data into desirable activities or the identification of common risk factors, thus enhancing the subject’s quality of life. Gait motion information was acquired using accelerometers and gyroscopes mounted on the lower limbs, where the sensors were exposed to inertial forces during gait. Additionally, leg muscle activity was measured using strain gauge sensors. As a matter of fact, we wanted to identify different gait activities within each gait recording by utilizing Machine Learning algorithms. In line with this, various Machine Learning methods were tested and compared to establish the best-performing algorithm for the classification of the recorded gait information. The combination of attention-based convolutional and recurrent neural networks algorithms outperformed the other tested algorithms and was individually tested further on the datasets of five subjects and delivered the following averaged results of classification: 98.9% accuracy, 96.8% precision, 97.8% sensitivity, 99.1% specificity and 97.3% F1-score. Moreover, the algorithm’s robustness was also verified with the successful detection of freezing gait episodes in a Parkinson’s disease patient. The results of this study indicate a feasible gait event classification method capable of complete algorithm personalization.
38
Brady, Eoghan S., Jonathon P. Leider, Beth A. Resnick, Y. Natalia Alfonso, and David Bishai. "Machine-Learning Algorithms to Code Public Health Spending Accounts." Public Health Reports 132, no. 3 (March 31, 2017): 350–56. http://dx.doi.org/10.1177/0033354917700356.
Full textAbstract:
Objectives: Government public health expenditure data sets require time- and labor-intensive manipulation to summarize results that public health policy makers can use. Our objective was to compare the performances of machine-learning algorithms with manual classification of public health expenditures to determine if machines could provide a faster, cheaper alternative to manual classification. Methods: We used machine-learning algorithms to replicate the process of manually classifying state public health expenditures, using the standardized public health spending categories from the Foundational Public Health Services model and a large data set from the US Census Bureau. We obtained a data set of 1.9 million individual expenditure items from 2000 to 2013. We collapsed these data into 147 280 summary expenditure records, and we followed a standardized method of manually classifying each expenditure record as public health, maybe public health, or not public health. We then trained 9 machine-learning algorithms to replicate the manual process. We calculated recall, precision, and coverage rates to measure the performance of individual and ensembled algorithms. Results: Compared with manual classification, the machine-learning random forests algorithm produced 84% recall and 91% precision. With algorithm ensembling, we achieved our target criterion of 90% recall by using a consensus ensemble of ≥6 algorithms while still retaining 93% coverage, leaving only 7% of the summary expenditure records unclassified. Conclusions: Machine learning can be a time- and cost-saving tool for estimating public health spending in the United States. It can be used with standardized public health spending categories based on the Foundational Public Health Services model to help parse public health expenditure information from other types of health-related spending, provide data that are more comparable across public health organizations, and evaluate the impact of evidence-based public health resource allocation.
39
Li, Kai, Hui Li, Bayi Cheng, and Qing Luo. "Uniform Parallel Machine Scheduling Problem with Controllable Delivery Times." Journal of Systems Science and Information 3, no. 6 (December 25, 2015): 525–37. http://dx.doi.org/10.1515/jssi-2015-0525.
Full textAbstract:
AbstractThis paper considers the uniform parallel machine scheduling problem with controllable delivery times, which assumes that the delivery times of jobs are linear decreasing functions of the consumed resource. It aims to minimize the maximum completion time under the constraint that the total resource consumption does not exceed a given limit. For this NP-hard problem, we propose a resource allocation algorithm, named RAA, according to the feasible solution of the uniform parallel machine scheduling problem with fixed delivery times. It proves that RAA algorithm can obtain the optimal resource allocation scheme for any given scheduling scheme inO(nlogn)time. Some algorithms based on heuristic algorithm LDT, heuristic algorithm LPDT and simulated annealing are proposed to solve the uniform parallel machine scheduling problem with controllable delivery times. The accuracy and efficiency of the proposed algorithms are tested based on those data with problem sizes varying from 40 to 200 jobs and 2 to 8 machines. The computational results indicate that the SA approach is promising and capable of solving large-scale problems in a reasonable time.
40
Ajani, Taiwo Samuel, Agbotiname Lucky Imoize, and Aderemi A. Atayero. "An Overview of Machine Learning within Embedded and Mobile Devices–Optimizations and Applications." Sensors 21, no. 13 (June 28, 2021): 4412. http://dx.doi.org/10.3390/s21134412.
Full textAbstract:
Embedded systems technology is undergoing a phase of transformation owing to the novel advancements in computer architecture and the breakthroughs in machine learning applications. The areas of applications of embedded machine learning (EML) include accurate computer vision schemes, reliable speech recognition, innovative healthcare, robotics, and more. However, there exists a critical drawback in the efficient implementation of ML algorithms targeting embedded applications. Machine learning algorithms are generally computationally and memory intensive, making them unsuitable for resource-constrained environments such as embedded and mobile devices. In order to efficiently implement these compute and memory-intensive algorithms within the embedded and mobile computing space, innovative optimization techniques are required at the algorithm and hardware levels. To this end, this survey aims at exploring current research trends within this circumference. First, we present a brief overview of compute intensive machine learning algorithms such as hidden Markov models (HMM), k-nearest neighbors (k-NNs), support vector machines (SVMs), Gaussian mixture models (GMMs), and deep neural networks (DNNs). Furthermore, we consider different optimization techniques currently adopted to squeeze these computational and memory-intensive algorithms within resource-limited embedded and mobile environments. Additionally, we discuss the implementation of these algorithms in microcontroller units, mobile devices, and hardware accelerators. Conclusively, we give a comprehensive overview of key application areas of EML technology, point out key research directions and highlight key take-away lessons for future research exploration in the embedded machine learning domain.
41
Raja, Hadi Ashraf, Karolina Kudelina, Bilal Asad, Toomas Vaimann, Ants Kallaste, Anton Rassõlkin, and Huynh Van Khang. "Signal Spectrum-Based Machine Learning Approach for Fault Prediction and Maintenance of Electrical Machines." Energies 15, no. 24 (December 15, 2022): 9507. http://dx.doi.org/10.3390/en15249507.
Full textAbstract:
Industrial revolution 4.0 has enabled the advent of new technological advancements, including the introduction of information technology with physical devices. The implementation of information technology in industrial applications has helped streamline industrial processes and make them more cost-efficient. This combination of information technology and physical devices gave birth to smart devices, which opened up a new research area known as the Internet of Things (IoT). This has enabled researchers to help reduce downtime and maintenance costs by applying condition monitoring on electrical machines utilizing machine learning algorithms. Although the industry is trying to move from scheduled maintenance towards predictive maintenance, there is a significant lack of algorithms related to fault prediction of electrical machines. There is quite a lot of research going on in this area, but it is still underdeveloped and needs a lot more work. This paper presents a signal spectrum-based machine learning approach toward the fault prediction of electrical machines. The proposed method is a new approach to the predictive maintenance of electrical machines. This paper presents the details regarding the algorithm and then validates the accuracy against data collected from working electrical machines for both cases. A comparison is also presented at the end of multiple machine learning algorithms used for training based on this approach.
42
Agárdi, Anita, and Károly Nehéz. "PARALLEL MACHINE SCHEDULING WITH MONTE CARLO TREE SEARCH." Acta Polytechnica 61, no. 2 (April 30, 2021): 307–12. http://dx.doi.org/10.14311/ap.2021.61.0307.
Full textAbstract:
In this article, a specific production scheduling problem (PSP), the Parallel Machine Scheduling Problem (PMSP) with Job and Machine Sequence Setup Times, Due Dates and Maintenance Times is presented. In this article after the introduction and literature review the mathematical model of the Parallel Machines Scheduling Problem with Job and Machine Sequence Setup Times, Due Dates and Maintenance Times is presented. After that the Monte Carlo Tree Search and Simulated Annealing are detailed. Our representation technique and its evaluation are also introduced. After that, the efficiency of the algorithms is tested with benchmark data, which result, that algorithms are suitable for solving production scheduling problems. In this article, after the literature review, a suitable mathematical model is presented. The problem is solved with a specific Monte Carlo Tree Search (MCTS) algorithm, which uses a neighbourhood search method (2-opt). In the article, we present the efficiency of our Iterative Monte Carlo Tree Search (IMCTS) algorithm on randomly generated datasets.
43
Reddy, V. Sandeep Kumar, Saravanan T., N. T. Velusudha, and T. Sunder Selwyn. "Smart Grid Management System Based on Machine Learning Algorithms for Efficient Energy Distribution." E3S Web of Conferences 387 (2023): 02005. http://dx.doi.org/10.1051/e3sconf/202338702005.
Full textAbstract:
This abstract describes the smart grid management system is an emerging technology that utilizes machine learning algorithms for efficient energy distribution. The paper presents an overview of the architecture, benefits, and challenges of smart grid management systems. The paper also discusses various machine learning algorithms used in smart grid management systems such as neural networks, decision trees, and Support Vector Machines (SVM). The advantages of using machine learning algorithms in smart grid management systems include increased energy efficiency, reduced energy wastage, improved reliability, and reduced costs. The challenges in implementing machine learning algorithms in smart grid management systems include data security, privacy, and scalability. The paper concludes by discussing future research directions in smart grid management systems based on machine learning algorithms.
44
Li, Yuping. "Similar Classification Algorithm for Educational and Teaching Knowledge Based on Machine Learning." Wireless Communications and Mobile Computing 2022 (May 23, 2022): 1–9. http://dx.doi.org/10.1155/2022/7222236.
Full textAbstract:
From ancient times, machines did adhere to the commands that a human or a user prepared. According to the program, the machines are controlled by implementing machine learning (ML). It plays a significant part in the development of information technology (IT) companies and the rise of the education system. Using stored memories, people learn new things, making them feel better than before. Machines are pretty different from human knowledge. Instead of using memory power, they use statistical comparison to analyze the data. Here, the amount of data is stored in a database, and according to the reaction received from the user, it gets additional data to create new data. For example, once a person hears music using the application, they will hear repeated music before further entry. In this case, the application is working based on the machine learning algorithm. First, it collects the information from the user, and then, it uses the same information (data) to make the user’s work more efficient when they return. The existing system like Support Vector Machine (SVM) and learning management system approaches the necessity and development of the higher education system using machine learning algorithms. This proposed system focuses on classifying education and teaching knowledge by implementing the machine learning-based similar classification algorithm (ML-SCA). ML-SCA focuses on classifying similar teaching videos and the recommendations to improve the teaching and academic knowledge for the teachers and the students. ML-SCA is compared with the existing neural network and K -means algorithms. Based on the efficiency results, it is observed that the proposed ML-SCA has achieved 92% higher than the existing algorithms.
45
Ma, Chunzhu. "Comparison of machine learning algorithms over prediction of Titanic database." Applied and Computational Engineering 5, no. 1 (June 14, 2023): 340–44. http://dx.doi.org/10.54254/2755-2721/5/20230593.
Full textAbstract:
With the popularize of artificial intelligent, algorithms such as machine learning algorithm takes an important part in many fields. In terms of data prediction, it is important to know which machine learning algorithm fits the specific dataset the most. Comparison between machine learning algorithms helps us figure out the advantage and disadvantage of them and thus save time, and money during the working process. In this paper, this paper will be comparing K-nearest neighbours algorithm, Random Forest algorithm, and Support vector machine algorithm mostly focusing on their performance over the survival prediction of Titanic dataset. It could be seen that algorithm with more adjustable hyper parameters could produce more accurate result. However, finding the suitable hyper parameters is time consuming. In the future, this paper may try to explore ensembled algorithms for better result.
46
Börger, Egon, and Klaus-Dieter Schewe. "A Behavioural Theory of Recursive Algorithms." Fundamenta Informaticae 177, no. 1 (December 18, 2020): 1–37. http://dx.doi.org/10.3233/fi-2020-1978.
Full textAbstract:
“What is an algorithm?” is a fundamental question of computer science. Gurevich’s behavioural theory of sequential algorithms (aka the sequential ASM thesis) gives a partial answer by defining (non-deterministic) sequential algorithms axiomatically, without referring to a particular machine model or programming language, and showing that they are captured by (nondeterministic) sequential Abstract State Machines (nd-seq ASMs). However, recursive algorithms such as mergesort are not covered by this theory, as has been pointed out by Moschovakis, who had independently developed a different framework to mathematically characterize the concept of (in particular recursive) algorithm. In this article we propose an axiomatic definition of the notion of sequential recursive algorithm which extends Gurevich’s axioms for sequential algorithms by a Recursion Postulate and allows us to prove that sequential recursive algorithms are captured by recursive Abstract State Machines, an extension of nd-seq ASMs by a CALL rule. Applying this recursive ASM thesis yields a characterization of sequential recursive algorithms as finitely composed concurrent algorithms all of whose concurrent runs are partial-order runs.
47
Židek, Kamil, Alexander Hošovský, and Ján Dubják. "Diagnostics of Surface Errors by Embedded Vision System and its Classification by Machine Learning Algorithms." Key Engineering Materials 669 (October 2015): 459–66. http://dx.doi.org/10.4028/www.scientific.net/kem.669.459.
Full textAbstract:
The Article deals with usability and advantages of embedded vision systems for surface error detection and usability of advanced algorithms, technics and methods from machine learning and artificial intelligence for error classification in machine vision systems. We provide experiments with following classification algorithms: Support Vector Machines (SVM), Random Threes, Gradient Boosted Threes, K-Nearest Neighbor and Normal Bayes Classifier. Next comparison experiment was conducted with multilayer perceptron (MLP), because currently it is very popular for classification in the field of artificial intelligence. These classification approaches are compared by precision, reliability, speed of teaching and algorithm implementation difficulty.
48
Smolarczyk, Milosz, Jakub Pawluk, Alicja Kotyla, Sebastian Plamowski, Katarzyna Kaminska, and Krzysztof Szczypiorski. "Machine Learning Algorithms for Identifying Dependencies in OT Protocols." Energies 16, no. 10 (May 12, 2023): 4056. http://dx.doi.org/10.3390/en16104056.
Full textAbstract:
This study illustrates the utility and effectiveness of machine learning algorithms in identifying dependencies in data transmitted in industrial networks. The analysis was performed for two different algorithms. The study was carried out for the XGBoost (Extreme Gradient Boosting) algorithm based on a set of decision tree model classifiers, and the second algorithm tested was the EBM (Explainable Boosting Machines), which belongs to the class of Generalized Additive Models (GAM). Tests were conducted for several test scenarios. Simulated data from static equations were used, as were data from a simulator described by dynamic differential equations, and the final one used data from an actual physical laboratory bench connected via Modbus TCP/IP. Experimental results of both techniques are presented, thus demonstrating the effectiveness of the algorithms. The results show the strength of the algorithms studied, especially against static data. For dynamic data, the results are worse, but still at a level that allows using the researched methods to identify dependencies. The algorithms presented in this paper were used as a passive protection layer of a commercial IDS (Intrusion Detection System).
49
Atiyah, Oqbah Salim, and Saadi Hamad Thalij. "Evaluation of COVID-19 Cases based on Classification Algorithms in Machine Learning." Webology 19, no. 1 (January 20, 2022): 4878–87. http://dx.doi.org/10.14704/web/v19i1/web19326.
Full textAbstract:
COVID-19 has appeared in china, spread rapidly the world wide and caused with many injuries, deaths between humans. It is possible to avoid the spread of the disease or reduce its spread with the machine learning and the diagnostic techniques, where the use classification algorithms are one of the fundamental issues for prediction and decision-making to help of the early detection, diagnose COVID-19 cases and identify dangerous cases that need admit Intensive Care Unit to provide treatment in a timely manner. In this paper, we use the machine learning algorithms to classify the COVID-19 cases, the dataset got from dataset search on google and used four algorithms, as (Logistic Regression, Naive Bayes, Random Forest, Stochastic Gradient Descent), the result of algorithms accuracy was 94.82%, 96.57%, 98.37%, 99.61% respectively and the execution time of each algorithm were 0.7s, 0.04s, 0.20s,0.02s respectively, and with the mislabeling Stochastic Gradient Descent algorithm was better.
50
Tornede, Alexander, Viktor Bengs, and Eyke Hüllermeier. "Machine Learning for Online Algorithm Selection under Censored Feedback." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 9 (June 28, 2022): 10370–80. http://dx.doi.org/10.1609/aaai.v36i9.21279.
Full textAbstract:
In online algorithm selection (OAS), instances of an algorithmic problem class are presented to an agent one after another, and the agent has to quickly select a presumably best algorithm from a fixed set of candidate algorithms. For decision problems such as satisfiability (SAT), quality typically refers to the algorithm's runtime. As the latter is known to exhibit a heavy-tail distribution, an algorithm is normally stopped when exceeding a predefined upper time limit. As a consequence, machine learning methods used to optimize an algorithm selection strategy in a data-driven manner need to deal with right-censored samples, a problem that has received little attention in the literature so far. In this work, we revisit multi-armed bandit algorithms for OAS and discuss their capability of dealing with the problem. Moreover, we adapt them towards runtime-oriented losses, allowing for partially censored data while keeping a space- and time-complexity independent of the time horizon. In an extensive experimental evaluation on an adapted version of the ASlib benchmark, we demonstrate that theoretically well-founded methods based on Thompson sampling perform specifically strong and improve in comparison to existing methods.