Intelligence Learning Algorithms Research Articles

Structural Optimization Design of MEMS Piezoelectric Hydrophones Based on Intelligent Learning Algorithm

Structural Optimization Design of MEMS Piezoelectric Hydrophones Based on Intelligent Learning Algorithm

Designing and Analysing an APP based on "Internet+" for Integrating Health Data of University Physical Classes

INTRODUCTION: University physical education programs still largely use traditional methods without significant innovation in teaching or health evaluation. With the growing capabilities of Internet technology and artificial intelligence, there's a critical need to leverage these advancements to enhance the physical health assessments of college students.OBJECTIVES: The study proposes an integrated APP design for health data collection and analysis both inside and outside physical education classes, utilizing Internet technologies and intelligent learning algorithms. This is aimed at precisely analyzing and improving the health outcomes of university students by fostering more tailored and responsive physical education experiences..METHODS: The method involves constructing an app design analysis index system, integrating a vulture search heuristic optimization algorithm with a convolutional neural network (CNN). This setup uses smart sports APP behavioral data as input to refine and optimize health data integration, aiming to enhance the analysis and feedback mechanisms within university sports programs.RESULTS: The implementation of this method showed that it meets real-time requirements while significantly improving the accuracy and efficiency of integrated APP design analyses for health data. The use of smart algorithms allows for more precise adjustments and feedback in physical education programs, suggesting a substantial improvement over traditional physical health monitoring and evaluation methods.CONCLUSION: The proposed APP design successfully integrates and analyzes health data, enhancing the management and evaluation of physical education programs. It represents a significant step forward in utilizing modern technology to address the stagnation in physical education health monitoring, with potential implications for broader educational and health management practices in universities. Future iterations of the APP could incorporate more diverse data inputs and advanced analytical features to further refine its effectiveness and usability.

Deep Learning Pricing of Processing Firms in Agricultural Markets

The pricing behavior of agricultural processing firms in input markets has large impacts on farmers’ and processors’ prosperity as well as the overall market structure. Despite analytical approaches to food processors’ pricing in agricultural input markets, the need for models to represent complex market features is urgent. Agent-based models (ABMs) serve as computational laboratories to understand complex markets emerging from autonomously interacting agents. Yet, individual agents within ABMs must be equipped with intelligent learning algorithms. In this paper, we propose supervised and unsupervised learning agents to simulate the pricing behavior of firms in agricultural markets’ ABMs. Supervised learning firms are pre-trained to accurately best respond to their competitors and are deemed to result in the market Nash equilibria. Unsupervised learning firms play a course of pricing interaction with their competitors without any pre-knowledge but based on deep reinforcement learning. The simulation results show that unsupervised deep learning firms are capable of approximating the pricing equilibria obtained by the supervised firms in different spatial market settings. Optimal discriminatory and uniform delivery pricing emerges in agricultural input markets with the high and intermediary importance placed on space. Free on board pricing emerges in agricultural input markets with small importance placed on space.

THE TEACHING OF DOUBLE EFFECT AND ARTIFICIAL INTELLIGENCE

This paper explores the possibility of applying existing ethical principles to artificial intelligence learning algorithms. The processes controlled by artificial intelligence will have a significant impact on the lives of all people in the future. Decision-making without consideration of moral and ethical principles may lead to catastrophic consequences not only as direct damage, but also in the form of degradation of certain ethical norms in general. An attempt to directly transfer universal moral principles to the ethics of artificial intelligence may lead to insurmountable obstacles due to the nature of artificial intelligence.

Research on a price prediction model for a multi-layer spot electricity market based on an intelligent learning algorithm

With the continuous promotion of the unified electricity spot market in the southern region, the formation mechanism of spot market price and its forecast will become one of the core elements for the healthy development of the market. Effective spot market price prediction, on one hand, can respond to the spot power market supply and demand relationship; on the other hand, market players can develop reasonable trading strategies based on the results of the power market price prediction. The methods adopted in this paper include: Analyzing the principle and mechanism of spot market price formation. Identifying relevant factors for electricity price prediction in the spot market. Utilizing a clustering model and Spearman’s correlation to classify diverse information on electricity prices and extracting data that aligns with the demand for electricity price prediction. Leveraging complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN) to disassemble the electricity price curve, forming a multilevel electricity price sequence. Using an XGT model to match information across different levels of the electricity price sequence. Employing the ocean trapping algorithm-optimized Bidirectional Long Short-Term Memory (MPA-CNN-BiLSTM) to forecast spot market electricity prices. Through a comparative analysis of different models, this study validates the effectiveness of the proposed MPA-CNN-BiLSTM model. The model provides valuable insights for market players, aiding in the formulation of reasonable strategies based on the market's supply and demand dynamics. The findings underscore the importance of accurate spot market price prediction in navigating the complexities of the electricity market. This research contributes to the discourse on intelligent forecasting models in electricity markets, supporting the sustainable development of the unified spot market in the southern region.

Intelligent Learning Algorithm and Intelligent Transportation-Based Energy Management Strategies for Hybrid Electric Vehicles: A Review

As one of the alternatives to conventional fuel vehicles, hybrid electric vehicles (HEV) offer lower fuel consumption and fewer exhaust emissions. To improve the performance of the HEV, the energy management strategy (EMS) is one of the most critical technologies. Classic EMS can be broadly classified into rule-based and optimization-based. With the development of machine learning technology, the deep reinforcement learning (DRL) algorithm of intelligent learning algorithms has been applied to the EMS. This paper mainly reviews the research progress of the EMS based on DRL from two aspects of the algorithm and training environment, and the EMS research involving combining the intelligent transportation system (ITS) is reviewed. In addition, the experimental test progress situations of DRL-based EMS research are discussed. Finally, the challenge of DRL-based EMSs is analyzed and some solutions are provided. In particular, it also involves some discussion about automotive cyber security in the intelligent transportation environment.

IRNetv: A deep learning framework for automated brain tumor diagnosis

A brain tumor is a severe disease that typically shortens life expectancy in most cases. Thus, early diagnosis of tumors is of paramount importance to reduce the mortality rate and revamp the quality of life. The emergence of intelligent learning algorithms can facilitate the automated diagnosis of tumors with high accuracy and efficiency. To this end, this study proposes a fully automated, interpretable deep learning-based model for brain tumor diagnosis. Convolutional Neural Network (CNN) model combining the advantages of inception modules and residual connections is designed and implemented. As CNN is employed for feature extraction and classification by analysis of medical images, the need for laborious feature extraction using statistical methods is mitigated. Also, the proposed architecture possesses the ability to extract diversified features by using various convolutional filters or kernel sizes. The experimental evaluations of the proposed architecture using two public datasets consisting of 4600 and 253 brain images achieved an overall classification accuracy of more than 99%, which is better than the previous studies.

Intelligent learning algorithms integrated with feature engineering for sustainable groundwater salinization modelling: Eastern Province of Saudi Arabia

Groundwater (GW) salinization refers to the natural or human-induced process of GW acquiring a higher level of salt content. While geological factors or proximity to the ocean can naturally cause this phenomenon, it can also be attributed to activities like irrigation, changes in land use, and the discharge of industrial or municipal waste. The following research employs the use of various feature extraction methods coupled with novel chemometrics approaches informed by machine learning (ML) techniques including; Gaussian Process Regression (GPR), Support Vector Regression (SVR), Regression tree (RT) and Robust linear regression (RLR). Based on the feature selection methods, the models were classified into three different combinations. The intelligent learning algorithms equally depict higher PCC values ranging from 0.935 to 1.00 in the training and 0.779 to 0.999 in the validation stage respectively, which depicts a higher relation between the experimental and simulated values. The performance results indicate that GPR-Comb-3 showed the highest performance in both the training and validation stages respectively. It is worth mentioning that even the RLR technique equally depicts exceptional prediction skills in both the training and validation steps. In conclusion, the outcomes of the current research depict the significance of these techniques in evaluating GW salinization.

Application of Intelligent Image Recognition and Digital Media Art in the Inheritance of Black Pottery Intangible Cultural Heritage

With the development of science and technology, intelligent image recognition and digital media art are gradually applied to the inheritance of intangible cultural heritage. In the inheritance of black pottery, intelligent image recognition can help identify the authenticity and age of black pottery, and digital media art can inject new vitality into black pottery culture. Digital media, which combines digitalization and mediaization, breaks the limitations of traditional media and provides ideological and technical guarantees for the reconstruction, dissemination and promotion of intangible cultural heritage protection. Image recognition technology is no longer limited to the auxiliary detection of images, on the contrary, it has become a recording and collection tool. With the promotion and development of science and technology, it can be more widely shared and disseminated in time and space. In this paper, the traditional machine learning algorithm and the intelligent learning algorithm are compared in image recognition, and the image information recognition rate, the number of iterations, the training time, and the information loss rate are compared in four aspects. The results have found that compared with the traditional learning algorithm, the number of iterations of the intelligent learning algorithm is reduced by 20%, the training time is reduced by 40%, the information loss rate is reduced by 6.3%, and the recognition accuracy rate is improved by 6.1%, which showed that under the current technology, intangible cultural heritage can be better inherited, and Chinese culture can be better promoted, so that more people can understand and join in the protection of intangible cultural heritage.

Multilayer neuroadaptive force control of electro-hydraulic load simulators with uncertainty rejection

In this paper, an innovative multilayer neuroadaptive controller is firstly proposed to further improve the output force tracking performance of electro-hydraulic load simulators with uncertainty rejection. Significantly, a highly nonlinear load simulator driven by the single-rod electro-hydraulic actuators is considered, which has universal research significance in relation to the relevant studies. Moreover, smooth endogenous uncertainties, non-smooth endogenous uncertainties in the load pressure dynamics, and exogenous disturbances can all be effectively compensated in a feedforward way, which makes it possess higher load simulation accuracy and wider applicability to working conditions. In detail, multilayer neural networks and extended state observer are employed to estimate endogenous uncertainties and exogenous disturbances, respectively. Specially, the neural network weights are on-line updated via the composite errors comprised of the force tracking and estimate errors, which can increase the resulting learning ability. The closed-loop stability is guaranteed via the strict Lyapunov stability analysis and extensive comparative application results are achieved to validate the high-performance efficacy of the proposed intelligent learning algorithm.

A New Algorithmic Trading Approach Based on Ensemble Learning and Candlestick Pattern Recognition in Financial Assets

Financial assets considered as time series are chaotic in nature. The main goal of investors is to take a position at the right time and in the right direction by making predictions about the future of this chaotic series. These time series consist of the opening, low, high, and closing prices of a certain period. The approaches used to make predictions about trend direction and strength using moving averages and indicators based on them have noise and lag problems as they are obtained statistically. Candlestick charts, on the other hand, reflect the price-based psychology of bear and bull investors, and facilitate the interpretation of price movements by consolidating the said opening, closing, lowest and highest prices in a single image. It is known that it was applied to Japanese rice markets for the first time in history and there are more than 100 candle patterns. In this study, an extensible architecture software framework using factory patterns and an object-oriented approach is proposed for defining candlestick patterns and developing intelligent learning algorithms based on them. In the studies carried out for financial assets, the profit factor, which shows the portfolio gain of the strategy, is used. It is desirable that this number of wins be greater than 1. When the proposed approach is tested for 5 major financial assets, this value was obtained as greater than 1 for all assets. The proposed software framework can also be used in the development of new robotic approaches in terms of being applicable to all kinds of financial assets in every period.

Research on the Application of Animation Design Based on Machine Learning and Dynamic Image Index.

With the development of computer technology, animation is more and more used because of its simple, effective, and higher performance. Machine learning has become the core of artificial intelligence at present. Intelligent learning algorithms are widely used in practical problems such as evaluation. Knowledge-based automatic animation production system faces two challenges: (1) lack of learning ability and waste of data on the website; (2) the quality of animation produced that depends on the level of system designer and the inability of system users to participate in animation production.In order to solve these two problems, an active animation learning system enables the animation system to constantly learn experience and produce the most popular animation, for the first time, for animation production system design and implementation of applied research. Image retrieval technology is a research center in the field of image application. It is widely used in many fields, such as electronic commerce. Animation design will use dynamic image and machine learning to innovate.

Research on the Design of English Comprehensive Learning Activities Based on Deep Learning

To explore the application ways and effects of in-depth learning in English Teaching for Non-English Majors in Colleges and universities, 419 students are selected for the experiment, 205 students from grade 2018 were used as the reference group and 214 students from grade 2019 were used as the observation group to observe the effect of examination-oriented education and the impact of quality through in-depth learning. The performance of students of grade 2019 in examination-oriented education performance data and quality education performance data was significantly better than that of students of grade 2018, T < 10.000, P < 0.01 , which was statistically significant, Finally, it is found that the intelligent deep learning algorithm is applied to the analysis of the knowledge structure of non-English students’ English papers, and the application scenarios of the analysis results are widely developed, which is helpful to improve the English teaching effect of non-English students, improve students’ learning efficiency and reduce students’ pressure.

Smart Cities: Intelligence, Framework and Machine Learning Algorithm

The first definition about the smart cities was put forward by Caragliu as “The city is considered smart when its investment in man, socially improves quality of life through co-management.” In this paper we will discuss about the technologies used in smart cities. A collection of varied variables established to the concept of the smart city and key elements of the identified city’s success was identified by examining current definitions of smart city performance and the diversity of different concepts such as the smart city. This paper describes about the intelligence technologies used in various smart cities to make the one.

Learn to Machine Learn via Games in the Classroom

Artificial Intelligence (AI) and Machine Learning (ML) algorithms are increasingly being adopted to create and filter online digital content viewed by audiences from diverse demographics. From an early age, children grow into habitual use of online services but are usually unaware of how such algorithms operate, or even of their presence. Design decisions and biases inherent in the ML algorithms or in the datasets they are trained on shape the everyday digital lives of present and future generations. It is therefore important to disseminate a general understanding of AI and ML, and the ethical concerns associated with their use. As a response, the digital game ArtBot was designed and developed to teach fundamental principles about AI and ML, and to promote critical thinking about their functionality and shortcomings in everyday digital life. The game is intended as a learning tool in primary and secondary school classrooms. To assess the effectiveness of the ArtBot game as a learning experience we collected data from over 2,000 players across different platforms focusing on the degree of usage, interface efficiency, learners' performance and user experience. The quantitative usage data collected within the game was complemented by over 160 survey responses from teachers and students during early pilots of ArtBot. The evaluation analysis performed in this paper gauges the usability and usefulness of the game, and identifies areas of the game design which need improvement.

Abstract 460: Tools for collecting pathologist annotations and understanding interobserver variability

Abstract Background: The High Throughput Truthing (HTT) project is assessing pathologist agreement estimates of stromal tumor-infiltrating lymphocytes (sTILs) density in hematoxylin and eosin (H&E) stained breast cancer biopsy slides. The HTT project will create a validation dataset for artificial intelligence and machine learning (AI/ML) algorithms in digital pathology fit for a training, proficiency testing, and regulatory purpose. Methods: The pilot study crowdsourced pathologists to estimate sTIL density in 640 regions of interest (ROIs) across 64 slides via two modalities: an optical microscope (eeDAP) and two digital platforms (caMicroscope and PathPresenter). eeDAP is a hardware-software interface that presents the observer with pre-defined fields of view on H&E slides that corresponds to the ROI on a whole slide image. The PathPresenter and caMicroscope web-applications replicate the eeDAP workflow on the whole slide image without microscope hardware. In the workflow, pathologists evaluated the eligibility of an ROI for sTILs content then estimated the densities of tumor-associated stroma and sTILs in the ROI. Inter-pathologist agreement within ROIs was characterized with the root mean-squared difference. Using 72 of the highest variability ROIs selected from the pilot study, seven practicing pathologists participated in a subsequent focus group to improve the clinical training and data-collection workflows. Results: The pilot study collected 7,373 sTIL density estimates from 35 pathologists between February 2020 and May 2021. The focus group provided an additional 411 evaluations on 72 ROIs and in-depth discussions to identify pitfalls, gaps in training, and workflow improvements. Installation of eeDAP for physical data collection guided improvements in documentation and operation capabilities. Updated training materials refine the definition of tumor-associated stroma, provide reference images to differentiate sTILs from other cell types, and provide feedback during training. Digital and microscope platforms benefitted from enforcing registration and training, standardizing workflows, and accelerating eeDAP slide-image registration. Conclusions: The slides, images, and annotations provided by volunteer collaborators and participants for our pilot study led to improvements in data collection tools and crowdsourcing workflows to ensure consistency and minimize annotation variability. Our pilot dataset and analysis methods are available on a public HTT Github repository to allow open access to our methodology and feedback from the digital pathology and statistics communities. These data-collection and analysis methods are applicable to other quantitative biomarkers for validation of AI/ML algorithms. The lessons learned from this work will be applied to the HTT pivotal study and inform future quality data-collection methods of pathologist annotations. Citation Format: Katherine N. Elfer, Kim Blenman, Sarah N. Dudgeon, Victor Garcia, Anna Ehinger, Xiaoxian Li, Amy Ly, Dieter Peeters, Bruce Werness, Matthew Hanna, Roberto Salgado. Tools for collecting pathologist annotations and understanding interobserver variability [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 460.

Google search engine analytics for cancer immunotherapy: What patients are searching for on the internet and where they find answers.

11036 Background: Immunotherapy in the treatment of cancer has been on the rise and is on the forefront of current cancer research. As such, patients are increasingly turning to the Internet and online resources to answer their questions. For any given Google search, artificial intelligence and machine learning algorithms generate a “People Also Ask” (PAA) section which returns the most commonly associated questions to the original search query, with corresponding websites to answer those questions. Using a search engine optimization (SEO) tool, we determined the most frequently searched terms and questions regarding cancer immunotherapy online, and the websites used to answer them. Methods: The top Google search queries and PAA questions with associated volume metrics were extracted for the terms “immunotherapy” and “cancer immunotherapy” using an SEO tool. PAA questions and corresponding websites were categorized by specific topic and Rothwell’s classification system. Websites were further quality assessed using the Journal of the American Medical Association (JAMA) benchmark criteria. Results: Global searches for cancer immunotherapy increased significantly each year since 2015. Countries with the most search volume were the U.S. (44%), the U.K. (12%), and India (11%). PAAs (n = 674) and the most frequently searched questions regarding cancer immunotherapy, by average monthly search volume (searches per month), were on: definitions/how it works (n = 6.6K, 21.3%), side effects (n = 4.4K, 14.2%), cost (n = 2.9K, 9.4%), immunotherapy vs. chemotherapy (n = 1.8K, 5.8%), drug options (n = 1.7K, 5.5%), signs immunotherapy is working (n = 1.2K, 3.9%), different types of immunotherapy (n = 1.1K, 3.5%), route of administration (n = 800, 2.6%), efficacy/success rate (n = 800, 2.6%), and effect on life expectancy (n = 300, 1.0%). The top cancers that patients searched immunotherapy treatments for were: lung (n = 1.9K, 23.2%), melanoma (n = 1.5K, 18.3%), pancreatic (n = 700, 8.5%), breast (n = 600, 7.3%), and bladder (n = 500, 6.1%). The most queried immunotherapy drugs were Pembrolizumab/Keytruda (n = 87K), Nivolumab/Opdivo (n = 33K), and Ipilimumab/Yervoy (n = 11.1K). Websites used to answer PAA questions were mostly those of academic institutions (n = 294, 43.6%), commercial organizations (n = 167, 24.8%), and government databases (n = 126, 18.7%). Conclusions: The field of cancer immunotherapy is rapidly evolving and patients often look to the Internet to answer their latest questions. Using our findings, academic institutions, commercial organizations, and physicians involved in multi-disciplinary cancer care can cater their patient communications and websites to more directly align with patients’ most common questions and concerns on immunotherapy.

Students Performance Analysis System Using Cumulative Predictor Algorithm

Abstract: Towards automation to do mundane tasks and the expectations for students already equipped with good programming skills is on the rise. In parallel, there has been a rising number of students who find it difficult to attain the skills necessary in order to get the dream IT job they desire. The aim of this project is to bridge the gap between the employer and the future employee of the company by the use of SPAS at college level. Student performance analysis system (SPAS) is an online web application system which enables students to know prior hand if their level of skills for the placement is enough to get placed or not, given the necessary inputs. SPAS has an intelligent learning algorithm which utilises a rich database, analyses the records of previous students' traits and develops a model for further prediction. The performance evaluation of students by SPAS is by the cumulative predictor algorithm involving generation of several random forest trees on the available data. SPAS learns and creates its model reaching higher accuracy with increasing data availability.

Log interpretation for lithofacies classification with a robust learning model using stacked generalization

Currently, the common step of intelligent learning application in reservoir characterization is to study its performance in intelligent computing directly. When the specific task is relatively simple and the adequate learning samples are not beyond reach, the model established by the intelligent learning algorithm can often achieve satisfying results. However, small labeled samples are usually the majority in reservoir characterization, making the method with stronger learning ability more likely to fall into the trap of noise in data, which further results in the poor or unstable performance of the model in practice. In this paper, we propose a learning method that aggregates k-Nearest Neighbors (kNN), Decision Tree (DT), Random Forest (RF), and XGBoost by stacked generalization (Stacking) to obtain a more robust model. We adopted this model to classify the lithofacies of a real well log data and compared it with the models established by the above four learning methods and the Soft Voting ensemble, through a statistical test measured by F1 score. The results show that compared with other methods, the proposed method can establish a more robust model with higher prediction accuracy for logging lithofacies classification with limited data.

Potential and impact of artificial intelligence algorithms in dento-maxillofacial radiology

Novel artificial intelligence (AI) learning algorithms in dento-maxillofacial radiology (DMFR) are continuously being developed and improved using advanced convolutional neural networks. This review provides an overview of the potential and impact of AI algorithms in DMFR. A narrative review was conducted on the literature on AI algorithms in DMFR. In the field of DMFR, AI algorithms were mainly proposed for (1) automated detection of dental caries, periapical pathologies, root fracture, periodontal/peri-implant bone loss,and maxillofacial cysts/tumors; (2) classification of mandibular third molars, skeletal malocclusion, and dental implant systems; (3) localization of cephalometric landmarks; and (4) improvement of image quality. Data insufficiency, overfitting, and the lack of interpretability are the main issues in the development and use of image-based AI algorithms. Several strategies have been suggested to address these issues, such as data augmentation, transfer learning, semi-supervised training, few-shot learning, and gradient-weighted class activation mapping. Further integration of relevant AI algorithms into one fully automatic end-to-end intelligent system for possible multi-disciplinary applications is very likely to be a field of increased interest in the future. This review provides dental practitioners and researchers with a comprehensive understanding of the current development, performance, issues, and prospects of image-based AI algorithms in DMFR.