Paper proposes a method to monitor research topic evolution.
problem Difficulty in tracking research topic diffusion and evolution.
method Deep Non-negative Autoencoder with information divergence measurement.
result Identifies evolution of research topics and discovers topic diffusions.
New framework aims to make neural network explanations more reliable.
problem Current interpretability methods rely on intuition and lack falsifiability.
method Proposes a framework for strongly falsifiable interpretability research.
result Falsifiable interpretability methods can generate meaningful advances in understanding DNNs.
Method predicts rarity of image features to support research integrity investigations.
problem Difficulty in determining if image reuse is by chance or intentional.
method Statistical estimation of ORB features' chance occurrence across PubMed Open Access Subset dataset.
result The method produces decreasingly smaller p-values for more complex imagery, supporting null hypothesis.
UniFeat is an open-source Java tool for feature selection.
problem Efficient feature selection in various research areas.
method Provides a set of advanced feature selection methods.
result Facilitates rapid development of new feature selection algorithms.
The authors discuss reproducibility in pattern recognition research.
problem Making pattern recognition research fully reproducible.
method Defined reproducibility, used tools, set up analysis, showed alternative analyses.
result Discussion on the trade-offs and benefits of reproducible research.
Breiman (2001) proposed to statisticians awareness of two cultures: 1. Parametric modeling culture, pioneered by R.A.Fisher and Jerzy Neyman; 2. Algorithmic predictive culture, pioneered by machine learning research. Parzen (2001), as a part of discussing Breiman (2001), proposed that researchers be aware of many cultu…
Review of modern computational optimal transport methods for biomedical applications.
problem Efficient computation of optimal transport for big data.
method Regularization-based and projection-based computational methods.
result Advancements in computational optimal transport methods for biomedical research.
A competition revealed that flexible modeling outperforms rigid methods in causal inference.
problem Comparing new causal inference methods to established ones in a realistic setting.
method 30 competitors submitted methods, some flexible, some rigid, tested on real data.
result Flexible modeling methods outperformed rigid methods overall.
Automates research and development process by evaluating model capabilities.
problem Expanding experimental burden due to reading and verifying research directions.
method Proposes RD2Bench, a benchmark for evaluating data-centric automatic R&D.
result Demonstrates promising potential of LLMs in automating R&D process.
Survey of deep learning methods for anomaly detection.
problem Detecting anomalies in various applications.
method Review of deep learning techniques for anomaly detection.
result Comprehensive overview of deep learning methods for anomaly detection.
A modular framework for knowledge distillation simplifies experiments and reproducibility.
problem Difficulty in reproducing knowledge distillation studies due to lack of generalized frameworks.
method A configuration-driven PyTorch framework for knowledge distillation studies.
result Demonstrates efficient training strategies and various knowledge distillation methods.
Research evaluates ANN stock price prediction system for Shanghai Stock Exchange.
problem Predicting exact stock prices in the Shanghai Stock Exchange.
method Feedforward multi-layer perceptron with error backpropagation, using 5:21:21:1 configuration with 80% training data.
result Neural networks can predict stock prices with low mean absolute percentage errors (1.95%).
Simplifies analysis of hyperbolic distributions in demographic and economic research.
problem Fundamental postulates of demographic and economic research contradicted by data.
method Simple method of reciprocal values for identifying and analyzing hyperbolic distributions.
result Fundamental postulates of demographic and economic research are incorrect.
learn2learn simplifies meta-learning research by providing a library and standardized interfaces.
problem Prototyping and reproducibility issues in meta-learning.
method Developed a library (learn2learn) with common routines and standardized interfaces.
result Fosters a community around standardized software for meta-learning research.
This paper reviews off-policy evaluation methods in reinforcement learning.
problem Efficiency and accuracy of off-policy evaluation methods in reinforcement learning.
method Discussion of existing OPE methods, their statistical properties, and related research directions.
result Efficiency bounds and state-of-the-art OPE methods in reinforcement learning.
Deep learning enhances business analytics and operations research performance.
problem Scarcity of deep learning research in business analytics and operations research.
method Review and analysis of existing literature, computational experiments, case studies.
result Deep neural networks improve operational performance in business analytics and operations research.
GCNN research tackles graph data topology and prediction.
problem Graphs' irregularity and complexity make traditional CNN methods unsuitable.
method Review and categorization of GCNN techniques.
result TAGCN approach shows promise for improving graph data prediction.
New pipeline for causal research in psychology and social sciences.
problem Underuse of causal approaches in psychology and social science.
method Formal specification of theories, reduction of complexity, estimation of causal effects.
result Facilitates scientific inquiry compatible with testing causal theories.
This study analyzes EU ETS literature trends using bibliometric methods.
problem Understanding the evolving research landscape of EU ETS.
method Bibliometric analysis of Scopus database, focusing on publication trends, themes, influential authors, and journals.
result Notable increase in research activity over two decades, particularly during policy changes and economic events.
EasyTime simplifies time series forecasting for researchers and practitioners.
problem Ease of use and accuracy in time series forecasting.
method One-click evaluation, automated ensemble, natural language Q&A.
result Superior forecasting accuracy compared to individual methods.
The study reveals nations drive scientific research for social and economic interests.
problem Why do nations produce scientific research?
method Synthesizes previous concepts of science and scientific research, defines them, and identifies key drivers.
result Scientific research is driven by nations' social and economic interests, not just for philosophical inquiries.
New method explains complex fuel compound classifications.
problem Understanding complex quantitative structure-activity relationship models.
method Locally Interpretable Machine-Agnostic Explanations (LIME) applied to 2-D chemical structures.
result Replicates chemical intuition, allowing direct acceptance/rejection of decisions.
Since their emergence in the 1990's, the support vector machine and the AdaBoost algorithm have spawned a wave of research in statistical machine learning. Much of this new research falls into one of two broad categories: kernel methods and ensemble methods. In this expository article, I discuss the main ideas behind t…
This paper reviews state-of-the-art mixed data clustering algorithms.
problem Clustering mixed data is challenging due to the difficulty in applying mathematical operations to feature values.
method Taxonomy and state-of-the-art review of mixed data clustering algorithms.
result Identification of five major research themes and analysis of strengths and weaknesses of methods.
Chainer accelerates deep learning research with a flexible framework.
problem Slow development and application of deep learning models.
method Flexible, intuitive, high-performance framework with GPU acceleration and dynamic models.
result Accelerates deep learning research and development.
AI enhances microbiology and microbiome research through machine learning.
problem Understanding microbial life and its impact on health and the environment.
method AI-driven approaches including machine learning and deep learning.
result Transformative role in enhancing microbial life understanding.
The aim of this work is to develop a systematic manner to close overdetermined systems arising from conformal Killing tensors (CKT). The research performs this action for 1-tensor and 2-tensors. This research makes it possible to develop a new general method for any rank of CKT. This method can also be applied to other…
This paper reviews adversarial attacks on ML and DL models.
problem Adversarial attacks on ML and DL models.
method Review of existing adversarial attacks and perturbations.
result Comprehensive understanding of adversarial security attacks on ML and DL.
Paper proposes a method to discover topic evolutions from text data.
problem Difficulty in identifying new research topics from large text data.
method Uses sparseness-constrained Non-negative Matrix Factorization with generalized Jensen-Shannon divergence.
result Extracts more prominent topics and visualizes term-topic relationships.
Unified platform for statistical and machine learning in bioinformatics.
problem Workflow inefficiencies in using multiple tools for data analysis.
method Automated hyperparameter optimization, feature importance analysis, statistical tests.
result Accelerates biological discovery workflows with methodological soundness.
ImJoy simplifies deep learning for biomedical research.
problem Computational barriers limit deep learning adoption in biomedical research.
method Open-source browser-based platform for deep learning.
result Facilitates widespread reuse of deep learning solutions.
Paper uses AI methods to forecast Bitcoin prices.
problem Inaccurate Bitcoin price predictions in previous studies.
method Combines EEMD and LSTM for next-day price forecast.
result Improves Bitcoin price prediction accuracy.
Survey on Gaussian processes and their deep variants.
problem Limitations of Gaussian processes and their derivatives.
method Comprehensive review of existing methods and research themes.
result Advancements in Deep Gaussian Processes over the past decade.
This paper surveys enterprise financial risk analysis from Big Data and LLMs perspectives.
problem Predicting future financial risk of enterprises.
method Systematic literature review of enterprise financial risk analysis approaches from Big Data and LLMs perspectives.
result Offers a holistic synthesis of research methods and key insights.
Survey evaluates 20 anomaly detection methods for time-series data.
problem Comparing statistical, machine learning, and deep learning methods for anomaly detection.
method Comprehensive evaluation of 20 methods from three categories on public datasets.
result Provides insights into the performance and suitability of anomaly detection methods.
CA connects visual concepts to neural network representations.
problem Global association of human interpretable concepts with neural network internals.
method Established a taxonomy for CA methods and reviewed state-of-the-art research.
result Unified understanding of CA methods and datasets.
L2O uses machine learning to design optimization methods.
problem Designing efficient optimization methods for specific problem distributions.
method Data-driven approach to automate optimization method design.
result L2O methods are practical for specific problem distributions but fail on out-of-distribution problems.
The study shows interest rates impact investment and funding negatively but positively on dividend decisions.
problem The effect of interest rates on financial decisions like investment, funding, and dividend.
method Correlation coefficient analysis and descriptive methods.
result Interest rates have a negatively insignificant effect on investment and funding decisions, but positively moderate effect on dividend decisions.
This paper summarizes AI methods for detecting credit card fraud.
problem Detecting credit card fraud from millions of transactions.
method Rule-based and AI approaches, addressing imbalanced datasets, real-time scenarios, and feature engineering.
result Summarizes state-of-the-art AI methods for fraud detection.
Research compares ML and Time Series methods for generating trading signals.
problem Efficiency of on-line learning Algorithms in generating trading signals.
method Used technical indicators and ensemble of Random Forests, also Kalman Filter.
result Kalman Filter outperformed Random Forests in on-line learning predictions of stock prices.
Scoping review finds EEG key in MCI research, identifying ERP/EEG, QEEG, and machine learning.
problem Identifying MCI early and accurately.
method Scoping review with co-occurrence analysis and PAGER framework.
result Main research themes identified: ERP/EEG, QEEG, and EEG-based machine learning.
SparseVM registers clinical 3D scans faster and more accurately.
problem Inaccurate and slow registration of sparse clinical 3D scans.
method Learning-based registration method tailored for clinical sparse MRI.
result Orders of magnitude faster and more accurate than existing methods.
Enhancement attacks can falsely improve machine learning model performance in biomedical research.
problem The trustworthiness of machine learning in biomedical research is threatened by enhancement attacks.
method Developed two techniques to enhance prediction performance with minimal changes to features.
result Falsely improved classifiers' accuracy from 50% to almost 100% while maintaining high feature similarities.
TSGM generates synthetic time series data for ML research.
problem Scarce or sensitive real-time series data.
method Generative models, probabilistic, and simulator-based approaches.
result Framework evaluates data quality from multiple angles.
This survey categorizes IRL challenges and methods.
problem Inferring reward functions from observed behavior.
method Categorizes and discusses existing IRL methods.
result Challenges and solutions in IRL.
Paper semantifies bioassay text using neural networks.
problem Semantifying unstructured bioassay text descriptions.
method Neural-network-based approach to automatically semantify bioassay text.
result Neural-based semantification significantly outperforms a frequency-based baseline (72% F1 vs 47% F1).
ECGID research focuses on rest but not exercise, this study evaluates both.
problem ECGID performance under exercise is insufficiently studied.
method Various learning methods applied to ECG dataset.
result Current ECGID methods fail under exercise conditions.
Survey on causal inference methods for observational data.
problem Estimating causal effects from observational data.
method Comprehensive review of causal inference methods under the potential outcome framework.
result Various causal effect estimation methods have been developed and compared.