Data Selection Method Research Articles

A Small Database with an Adaptive Data Selection Method for Solder Joint Fatigue Life Prediction in Advanced Packaging.

There has always been high interest in predicting the solder joint fatigue life in advanced packaging with high accuracy and efficiency. Artificial Intelligence Plus (AI+) is becoming increasingly popular as computational facilities continue to develop. This study will introduce machine learning (a core component of AI). With machine learning, metamodels that approximate the attributes of systems or functions are created to predict the fatigue life of advanced packaging. However, the prediction ability is highly dependent on the size and distribution of the training data. Increasing the amount of training data is the most intuitive approach to improve prediction performance, but this implies a higher computational cost. In this research, the adaptive sampling methods are applied to build the machine learning model with a small dataset sampled from an existing database. The performance of the model will be visualized using predefined criteria. Moreover, ensemble learning can be used to improve the performance of AI models after they have been fully trained.

Landscape Analysis for Surrogate Models in the Evolutionary Black-Box Context.

Surrogate modeling has become a valuable technique for black-box optimization tasks with expensive evaluation of the objective function. In this paper, we investigate the relationships between the predictive accuracy of surrogate models, their settings, and features of the black-box function landscape during evolutionary optimization by the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) state-of-the-art optimizer for expensive continuous black-box tasks. This study aims to establish the foundation for specific rules and automated methods for selecting and tuning surrogate models by exploring relationships between landscape features and model errors, focusing on the behavior of a specific model within each generation in contrast to selecting a specific algorithm at the outset. We perform a feature analysis process, identifying a significant number of non-robust features and clustering similar landscape features, resulting in the selection of 14 features out of 384, varying with input data selection methods. Our analysis explores the error dependencies of four models across 39 settings, utilizing three methods for input data selection, drawn from surrogate-assisted CMA-ES runs on noiseless benchmarks within the Comparing Continuous Optimizers framework.

Revisiting the OBS seafloor compliance signal removal with a stationarity and stacking-based approach: the BRUIT-FM toolbox

Summary This study focuses on improving the seafloor compliance noise removal method, which relies on estimates of the compliance transfer function frequency response (the deformation of the seafloor under long-period pressure waves). We first propose a new multi-scale deviation analysis of broadband ocean bottom seismometer data to evaluate stationarity properties that are key to the subsequent analysis. We then propose a new approach to removing the compliance noise from the vertical channel data, by stacking daily estimated transfer function frequency responses over a period of time. We also propose an automated transient event detection and data selection method based on a cross-correlation criterion. As an example, we apply the method to data from the Cascadia Initiative (network 7D2011). We find that the spectral extent of long-period forcing waves varies significantly over time so that standard daily transfer function calculation techniques poorly estimate the transfer function frequency response at the lowest frequencies, resulting in poor denoising performance. The proposed method more accurately removes noise at these lower frequencies, especially where coherence is low, reducing the mean deviation of the signal in our test case by 27 % or more. We also show that our calculated transfer functions can be transfered across time periods. The method should allow better estimates of seafloor compliance and help to remove compliance noise at stations with low pressure-acceleration coherence. Our results can be reproduced using the BRUIT-FM Python toolbox, available at https://gitlab.ifremer.fr/anr-bruitfm/bruit-fm-toolbox.

A Study on Training Data Mixing and Selection Methods for Detecting the Sounds of Faulty Machinery

A Study on Training Data Mixing and Selection Methods for Detecting the Sounds of Faulty Machinery

Assisted Active Learning for Model-Based Method Development in Liquid Chromatography.

In recent decades, there has been a growing interest in fully automated methods for tackling complex optimization problems across various fields. Active learning (AL) and its variant, assisted active learning (AAL), incorporating guidance or assistance from external sources into the learning process, play key roles in this automation by enabling the autonomous selection of optimal experimental conditions to efficiently explore the problem space. These approaches are particularly valuable in situations wherein experimentation is costly or time-consuming. This study explores the application of AAL in model-based method development (MD) for liquid chromatography (LC) by using Bayesian statistics to incorporate historical data and analyte information for the generation of initial retention models. The process involves updating the model parameters based on new experiments, coupled with an active data selection method to choose the most informative experiment to run in a subsequent step. This iterative process balances model exploitation and experimental exploration until a satisfactory separation is achieved. The effectiveness of this approach is demonstrated via two practical examples, resulting in optimized separations in a limited number of experiments by optimizing the gradient slope. It is shown that the ability of AAL to leverage past knowledge and compound information to improve accuracy and reduce experimental runs offers a flexible alternative approach to fixed design methods.

Three data-selection approaches for beam position monitor offline calibration

In this study, we describe the fabrication of an electrostatic beam position monitor (BPM) for beam diagnostic systems. Calibration of the BPM pickup requires both sensitivity and curve fitting owing to manufacturing tolerances following fabrication. To calibrate the BPM, we developed a BPM calibration system that comprises a wire-based test bench and readout electronics. We considered three difference-over-sum (DOS) data selection methods: DOSdiag, DOSaxis, and DOSall, to understand their impact on calibration accuracy. Each method selected specific DOS data, and we compared their characteristic curves. Consequently, we analyzed the calibration results by performing linear, 3rd-order, 5th-order, and two-dimensional (2D) 3rd-order polynomial fitting. Each of the three DOS data selection methods was examined to illustrate their advantages and limitations in terms of calibration accuracy and required amount of data. The results obtained demonstrated that choosing the appropriate DOS data-selection approach could be employed for the BPM offline calibrations, achieving minimized calibration errors and optimized response characteristics with polynomial curve fitting.

A case study on scenario-based optimization for axle load survey data selection for flexible pavement design in Vietnam

The unique traffic patterns in Vietnam, characterized by a mix of vehicle types, axle configurations, and overloading, pose challenges to current flexible pavement design methods. This study investigates how selecting different vehicle axle load survey data scenarios impacts the accuracy of pavement design and rehabilitation for roads in Vietnam. Evaluation of various data selection methods and their influence on pavement response using the current flexible pavement calculation procedure in Vietnam. By comparing the pavement design criteria calculated under each scenario, this research aims to provide clear guidelines for engineers choosing appropriate axle load data for pavement design. This, in turn, will lead to the design and maintenance of more durable and sustainable pavements, ultimately promoting a more efficient and resilient transportation infrastructure in Vietnam. The research approach involves analyzing various axle load survey data scenarios, including those representing typical traffic conditions, overloaded vehicles, and specific vehicle types. The calculated pavement responses under each scenario are then compared to assess the impact of data selection on design outcomes. This study's findings are expected to provide valuable insights for pavement engineers in Vietnam, enabling them to select appropriate axle load data for accurate pavement design and rehabilitation. This will contribute to building more durable and sustainable road infrastructure, resulting in a more efficient and resilient transportation network

A Human-In-One-Loop Active Domain Adaptation Framework for Digit Recognition

ABSTRACT Domain adaptation can effectively enhance a model’s performance on target domain data with limited data. However, when some target domain labels are obtainable, training the model with both source and target domain data simultaneously can lead to worse performance due to the lower density of target domain data. If a large amount of target domain data is labeled without discrimination, it will necessitate a considerable expenditure of human resources. To address this issue, this paper proposes a human-in-one-loop active domain adaptation framework based on Target Domain Feature Generation to solve the problems. The oracle participates in only one iteration of data labeling, and a target domain classifier will take over the subsequent rest iterations. An image generator based on multiple CycleGANs forms an iterative co-training mechanism, which can continuously generate more high-quality labeled fake target domain data in iterations to improve the performance of the target domain classifier. The Top-N labeled data selection method with high confidence is devised to select the most accurately predicted data for labeling, reducing manual labeling workload. This framework can achieve an average accuracy of 0.8869 on six domain pairs, doubling the classical domain adaptation method DSN, requiring only a small amount of manual labeling.

Analysis Factors of Individual Tourists for Cultural Tourism in U Thong District Suphanburi Province

The purpose of this research had analyzed the affecting the decision of individual tourists visiting U Thong District Suphanburi Province. This research used quantitative research, and the research tool was questionnaires. Collected data from 400 Thai tourists. Used data selection method by Purposive sampling. Analysis of Data by factor analysis. Results indicated that there are seven factors that affect the decision-making of individual tourists. 1) Service and Physical of tourist attractions 2) Public relations for tourist attractions 3) Price 4) convenience of traveling 5) Souvenirs 6) Accommodation in tourist attractions 7) History and reputation of tourist attractions. Suggestions of this study 1) People in the community should show good hosts in welcoming tourists. 2) People in the community should pay attention to cleanliness within the community 3) There should be more public relations for Cultural Tourism. and 4) Should study causal factors influencing individual tourism, U Thong District, Suphanburi Province.

The Role of Islamic Economics in Overcoming Economic Inequality and Realizing Development in Indonesia

Islamic economic development does not only measure the level of prosperity in the world, but is much more important than that, namely how prosperity will be in the afterlife. Economic inequality is a serious problem faced in many countries, including Indonesia. The application of Islamic economics can be a solution to overcome this problem with the principles of justice and fair distribution. Even though in Indonesia, Islamic economics is increasingly gaining attention with government initiatives and sharia financial institutions, there are still challenges such as a lack of understanding, regulations and policies that support the comprehensive development of Islamic economics. Research on the role of Islamic economics in overcoming economic inequality and realizing development in Indonesia is important to provide a deeper understanding of the implementation of Islamic economics and the steps that need to be taken for inclusive and sustainable development. The research method used in making this journal is the data selection method. Namely carrying out a systematic search for various journals relevant to the research topic using data analysis such as Google Scholar. In conclusion, the implementation of Islamic economics can be a sustainable and fair solution to overcome economic inequality. By applying the principles of justice, sustainability and transparency in economic practices, Indonesia can create a more just and sustainable society and achieve inclusive and sustainable development goals.

Reliable Data Generation and Selection for Low-Resource Relation Extraction

Automated construction of annotated data holds significant importance in Relation Extraction (RE) tasks due to the hardness and cost of human annotation. In this work, we propose Self-RDGS, a method for Self-supervised Reliable Data Generation and Selection in low-resource RE tasks. At first, we fully utilize the knowledge of triplets as prompts to generate sentences by employing the Large Language Models (LLMs). Since the auto-generated data contains noise, we then propose a ranking-based data selection method to select reliable sentences. Finally, we integrate the data selection and RE model training within a self-supervised iterative framework. Through experimentation on three datasets with low-resource settings, we demonstrate the effectiveness of our proposed approach in constructing annotated data and achieving noteworthy improvements in comparison to multiple baselines. Code, data and models are available at https://github.com/jjyunlp/GenerationRE.

Incorporating frailty to address the key challenges to geriatric economic evaluation

BackgroundThe multidimensional and dynamically complex process of ageing presents key challenges to economic evaluation of geriatric interventions, including: (1) accounting for indirect, long-term effects of a geriatric shock such as a fall; (2) incorporating a wide range of societal, non-health outcomes such as informal caregiver burden; and (3) accounting for heterogeneity within the demographic group. Measures of frailty aim to capture the multidimensional and syndromic nature of geriatric health. Using a case study of community-based falls prevention, this article explores how incorporating a multivariate frailty index in a decision model can help address the above key challenges.MethodsA conceptual structure of the relationship between geriatric shocks and frailty was developed. This included three key associations involving frailty: (A) the shock-frailty feedback loop; (B) the secondary effects of shock via frailty; and (C) association between frailty and intervention access. A case study of economic modelling of community-based falls prevention for older persons aged 60 + was used to show how parameterising these associations contributed to addressing the above three challenges. The English Longitudinal Study of Ageing (ELSA) was the main data source for parameterisation. A new 52-item multivariate frailty index was generated from ELSA. The main statistical methods were multivariate logistic and linear regressions. Estimated regression coefficients were inputted into a discrete individual simulation with annual cycles to calculate the continuous variable value or probability of binary event given individuals’ characteristics.ResultsAll three conceptual associations, in their parameterised forms, contributed to addressing challenge (1). Specifically, by worsening the frailty progression, falls incidence in the model increased the risk of falling in subsequent cycles and indirectly impacted the trajectories and levels of EQ-5D-3 L, mortality risk, and comorbidity care costs. Intervention access was positively associated with frailty such that the greater access to falls prevention by frailer individuals dampened the falls-frailty feedback loop. Association (B) concerning the secondary effects of falls via frailty was central to addressing challenge (2). Using this association, the model was able to estimate how falls prevention generated via its impact on frailty paid and unpaid productivity gains, out-of-pocket care expenditure reduction, and informal caregiving cost reduction. For challenge (3), frailty captured the variations within demographic groups of key model outcomes including EQ-5D-3 L, QALY, and all-cause care costs. Frailty itself was shown to have a social gradient such that it mediated socially inequitable distributions of frailty-associated outcomes.ConclusionThe frailty-based conceptual structure and parameterisation methods significantly improved upon the methods previously employed by falls prevention models to address the key challenges for geriatric economic evaluation. The conceptual structure is applicable to other geriatric and non-geriatric intervention areas and should inform the data selection and statistical methods to parameterise structurally valid economic models of geriatric interventions.

The role of guest houses in the development of rural tourism in the Almaty region

The article examines the role of guesthouses in the development of rural tourism in the Almaty region. The aim of this article is to explore and analyze the role of guesthouses in the development of rural tourism in the Almaty region. The research employs methods of systematization, analysis, data selection, and grouping, as well as statistical and comparative analysis. Domestic and international literature were reviewed, and a SWOT analysis and surveys were conducted. The study highlights that guesthouses play a key role in the development of rural tourism by creating attractive conditions for tourists and contributing to the economic growth of rural areas. An analysis of the operation of guesthouses in the Almaty region was conducted, identifying their strengths and weaknesses. The study also examined international practices in the development of guesthouses for rural tourism. Recommendations for improving the management of guesthouses were proposed, including methods to enhance their competitiveness, improve service quality, and foster a welcoming atmosphere.

DynImpt: A Dynamic Data Selection Method for Improving Model Training Efficiency

DynImpt: A Dynamic Data Selection Method for Improving Model Training Efficiency

Rice growing industry of the Kyzylorda region of Kazakhstan: ways to increase competitiveness

The goal is to analyze the current state of the rice growing industry in the Kyzylorda region and develop recommendations for its further development. Methods – during the study, a systematic approach to data selection, quantitative and qualitative methods, methods of comparison and generalization, logical, statistical, correlation and regression analysis were used. Results - the authors show the importance of the development of rice farming in this region, present the dynamics of rice production and sales, and assess the effectiveness of rice farming in the region. It has been established that in recent years the production of this crop has been declining, and the performance indicators of the rice complex are correspondingly decreasing. Due to the fact that the rice growing sector is characterized by competitive advantages, the article analyzes the level of activity of three competing companies - leaders in this market segment of Kazakhstan. The strengths and weaknesses are identified, as well as the opportunities and threats of the rice growing industry. Conclusions - the importance of rice growing for ensuring food security, social stability and overall economic growth in the country has been proven. The priority is to implement a set of measures to optimize sown areas, use modern technologies and equipment, and introduce innovations to increase the gross yield and yield of rice crop rotations. This traditional field of activity is promising and has export potential. There is a need to increase demand for products, create a system for promoting them to the market in order to increase exports, state support in the reconstruction of rice irrigation systems, subsidizing seed production, updating mechanization equipment, regulatory and methodological support, and personnel training.

Self-Supervised On-Device Federated Learning From Unlabeled Streams

The ubiquity of edge devices has led to a growing amount of unlabeled data produced at the edge. Deep learning models deployed on edge devices are required to learn from these unlabeled data to continuously improve accuracy. Self-supervised representation learning has achieved promising performances using centralized unlabeled data. However, the increasing awareness of privacy protection limits centralizing the distributed unlabeled image data on edge devices. While federated learning has been widely adopted to enable distributed machine learning with privacy preservation, without a data selection method to efficiently select streaming data, the traditional federated learning framework fails to handle these huge amounts of decentralized unlabeled data with limited storage resources on edge. To address these challenges, we propose a Self-supervised On-device Federated learning framework with coreset selection, which we call SOFed, to automatically select a coreset that consists of the most representative samples into the replay buffer on each device. It preserves data privacy as each client does not share raw data while learning good visual representations. Experiments demonstrate the effectiveness and significance of the proposed method in visual representation learning.

SYSTEM FOR DATA SELECTION AND ANALYSIS FOR SCIENTIFIC RESEARCH

The paper introduces a sophisticated system designed for the meticulous selection and analysis of data in the realm of scientific research. This system empowers researchers to perform various data operations, including sorting, duplicate removal, data clustering, parameter-based filtration, elimination of empty records, and more. Data Selection System, Data Analysis in Scientific Research, Data Selection Methods for Scientific Research, Systems for Scientific Research, Data Processing and Interpretation. In this work, a robust system is presented to facilitate the systematic selection and analysis of data, catering specifically to the intricacies of scientific research. The system offers a comprehensive suite of operations, allowing researchers to perform essential tasks such as sorting data for improved organization, eliminating duplicate entries to enhance data integrity, clustering data to uncover patterns, filtering based on specific parameters to focus on relevant subsets, and clearing empty records for a refined dataset. Researchers can leverage advanced sorting functionalities to organize data based on specified parameters, enhancing data readability and facilitating a structured approach to analysis. The system incorporates mechanisms for identifying and removing duplicate entries, ensuring data accuracy and reliability in scientific investigations. Advanced clustering algorithms empower researchers to discern patterns within datasets, providing valuable insights crucial for scientific exploration. A key feature enables researchers to apply targeted filters based on specific parameters, refining datasets to focus on subsets of information relevant to their research objectives. Recognizing the importance of data completeness, the system adeptly manages and clears empty records, ensuring the integrity of analyses and facilitating more accurate research outcomes. A comprehensive tool designed for the purposeful extraction and refinement of data in scientific research workflows. The systematic examination and interpretation of data to derive meaningful insights within the context of scientific investigations. Varied approaches and techniques employed to selectively curate and prepare data for rigorous scientific analysis. Technological frameworks developed to enhance efficiency and effectiveness in scientific inquiry. The systematic manipulation and understanding of data to extract valuable information and insights. This framework represents a pivotal advancement in the realm of scientific data management, providing researchers with a versatile toolset to elevate the precision and efficiency of their data-driven investigations.

Influences of non-landslide sample selection strategies on landslide susceptibility mapping by machine learning

Landslide susceptibility mapping is crucial in mitigating the risk of regional landslide hazards. The main objectives of this study are to design and analyze the impact of three non-landslide data generation methods on landslide susceptibility mapping. The specific non-landslide data selection methods are the random generation of non-landslide points through different distance landslide buffers, by selecting areas with low landslide influence in the landslide condition factor layer, and based on the results of the information value model partitioning by selecting low to medium susceptibility zones. There were 14 landslide condition factors used for the landslide susceptibility mapping, and correlations between landslides and condition factors were analyzed using the Gini index. The 70% dataset was modelled using a logistic regression model as well as an artificial neural network model. Finally, statistical metrics and AUC values were used for the 30% validation data for comparing the predictive performances of different non-landslide data generation strategies in the model. Based on the validation results, models A6 and B6 performed the best, with respective AUC values of 0.997 and 0.995. The findings show that the non-landslide samples generated using the low susceptibility interval of the information value model have the best performance.

Micro-fault identification for lithium-ion batteries in electric vehicles based on similarity measurement of the charging sequence

Battery fault diagnosis is critical to safeguard the safety of electric vehicles. Since lithium-ion battery cells are usually inconsistent and difficult to distinguish from faults, existing micro-fault identification methods are difficult to detect faults as early as possible based on real-world vehicle data. In contrast to the operation process, the voltage and temperature changes are more regular since the current relatively remains constant and the charging strategy is fixed, which is conducive to accurate micro-fault identification. According to the charging strategy of electric vehicles, charging data extraction and selection methods are introduced. Considering the practicality and the difficulty of threshold value determination, the micro-fault identification approach based on DBSCAN is proposed. Normalized IAVs and LIP distances are utilized as features, which come from charging sequences. The results of the thermal runaway vehicle show that the method can effectively find fault cells in voltage signals 18 days before thermal runaway occurs.

Evaluating the accuracy of predicted bridge condition using machine learning: the role of condition history

Effective maintenance decisions for bridges depend on accurate performance prediction. Machine learning (ML) models use historical bridge performance data to learn and predict performance. However, in many agencies, the condition history of bridges is limited and does not go beyond a few years. The question, therefore, is, to what extent does condition history help us make better predictions? To address this question, a ML model was developed that analysed more than 600,000 bridge decks with 27 years of condition history. Two data selection methods were designed: non-overlapping and overlapping data. The non-overlapping data are typically used to train the model. The overlapping data introduced in this study uses the data more efficiently for model training recognising that strings of historical data convey more information. Longer term predictions were found to be positively impacted by every additional year of condition history. Short-term condition prediction (one or two years) does not need significant historical data. It was also found that overlapping data, compared to non-overlapping data, produced larger training samples and had higher prediction accuracy in the majority of experiments, but at the cost of higher running time due to a larger sample size.