Earticle

As autonomous driving and connected car technology advance, various deep learning applications for autonomous vehicles and complex traffic situations are increasing. Autonomous vehicles must collect and process vast amounts of sensor data to support various deep learning applications, but vehicles have limited computing resources to perform complex deep learning operations. Therefore, edge computing is a promising solution to complement the limitations of autonomous vehicles. In this paper, we design edge computing for efficient task processing in an autonomous driving environment using a driving simulator. Also, we propose a task scheduling and offloading method which determines the target server to offload a task according to the characteristics of the task and the computing resources. The effectiveness of the proposed method is verified through experimental evaluation in an autonomous driving environment, supporting multiple deep learning services that we established by using a driving simulator.

Purpose: This study analyzed the methodological characteristics of machine learning (ML) applications in nursing research, evaluated their reporting quality against standardized guidelines, and assessed progress toward clinical implementation. Methods: A PRISMA-com pliant systematic review (PROSPERO CRD42024595877) searched nine English- and Ko rean-language databases through September 27, 2024. Included studies applied ML to a nursing question and had at least one nursing-affiliated author. Two reviewers independently extracted data following the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework. Reporting quality was appraised using the TRIPOD+AI checklist. Results: Of 125 included studies, supervised learning predominated (93.6%), with random forest, lo gistic regression, and support vector machines as common algorithms. The most frequent performance metrics were the area under the receiver operating curve and accuracy. Mean TRIPOD+AI compliance was 50.4% (standard deviation=9.37), with reporting quality lowest for data preparation (48.0%) and class imbalance handling (22.4%). Research focused on predicting pressure injuries, falls, and readmissions. Only seven studies described clinical deployment, often citing ethical or workflow barriers. Conclusion: While ML studies in nursing are increasing and show strong discriminatory accuracy, their impact is limited by inconsis tent reporting, limited external validation, and rare clinical deployment. Translating these al gorithms into practice requires adopting comprehensive reporting guidelines like TRIPOD+AI, documenting each CRISP-DM phase, and integrating nurse-centered decision-support path ways.

The rapid growth of web applications has increased the need for advanced features and strong security. Artificial intelligence (AI) and machine learning (ML) models play a crucial role in meeting these needs by improving efficiency and enhancing security. However, integrating these models into web applications can be challenging due to complex implementation and potential security risks. This paper compares Python and Node.js, two popular technology stacks, to determine their effectiveness in integrating ML models into web applications. It also explores the role of web application firewalls (WAF) and the ML algorithms that support them, analyzing current trends in their use and adoption. The overarching objective is to discern the technology stack that provides superior support for back-end ML integration and to identify the ML algorithms that are most effective in enhancing WAF capabilities against sophisticated security threats. By offering a synthesis of technical and security insights, this research seeks to empower developers and cybersecurity practitioners with the knowledge required to make well-informed decisions regarding technology stack selection and the implementation of ML-driven security mechanisms in web application development.

This review article explores and locates the current state-of-the-art related to application areas from freight transportation, supply chain and logistics that focuses on arrival time, demand forecasting, industrial processes optimization, traffic flow and location prediction, the vehicle routing problem and anomaly detection on transportation data. This review categorizes the related works according to machine learning methodologies so as to present the methods’ evolution through time, their combinations and their connection with the various applications in the specified fields. Thus, a reader would effortlessly get insights about the current state-of-the-art related to machine learning in freight transportation and related application areas.

Due to the complex functioning of Smart Healthcare Systems (SHS), many security concerns have been raised in the past. It provisions the attackers to hamper the working of SHS in a variety of ways, e.g., injection of false data to replace vital signs, tampering of medical devices to prevent informing critical situations, etc. In this work, a novel ML-based framework, i.e., SmartHealth is proposed to secure IoMT devices in SHS. SmartHealth watches the vital signs gathered through different IoMT to analyze the change in various body activities to differentiate between normal activities and dangerous security attacks. The performance of the SmartHealth is also analyzed for three different dangerous attacks. During performance analysis, it has been observed that SmartHealth can identify wicked activities in IoMT 92% times accurately with an F1-score of 90%.

The paper attempts to document the application of relevant Machine Learning (ML) models on Yelp (a crowd-sourced local business review and social networking site) dataset to analyze, predict and recommend business. Strategically using two cloud platforms to minimize the effort and time required for this project. Seven machine learning algorithms in Azure ML of which four algorithms are implemented in Databricks Spark ML. The analyzed Yelp business dataset contained 70 business attributes for more than 350,000 registered business. Additionally, review tips and likes from 500,000 users have been processed for the project. A Recommendation Model is built to provide Yelp users with recommendations for business categories based on their previous business ratings, as well as the business ratings of other users. Classification Model is implemented to predict the popularity of the business as defining the popular business to have stars greater than 3 and unpopular business to have stars less than 3. Text Analysis model is developed by comparing two algorithms, uni-gram feature extraction and n-feature extraction in Azure ML studio and logistic regression model in Spark. Comparative conclusions have been made related to efficiency of Spark ML and Azure ML for these models.

본 논문에서는 기계학습과 관련된 다양한 사례들에 대한 연구를 바탕으로 기계학습 응용 및 학습 알고리즘의 성능 개선 방안을 제시한다. 이를 위해 기계학습 기법을 적용하여 결과를 얻어낸 문헌을 자료로 수집하고 학문 분야로 나누어 각 분야에서 적합한 기계학습 기법을 선택 및 추천하였다. 공학에서는 SVM, 의학에서는 의사결정나무, 그 외 분야에서는 SVM이 빈번한 이용 사례와 분류/예측의 측면에서 그 효용성을 보였다. 기계학습의 적용 사례 분석을 통해 응용 방안의 일반적 특성화를 꾀할 수 있었다. 적용 단계는 크게 3단계로 이루어진다. 첫째, 데이터 수집, 둘째, 알고리즘을 통한 데이터 학습, 셋째, 알고리즘에 대한 유의미성 테스트 이며, 각 단계에서의 알고리즘의 결합을 통해 성능을 향상시킨다. 성능 개선 및 향상의 방법은 다중 기계학습 구조 모델링과 +α 기계학습 구조 모델링 등으로 분류한다.

This paper aims to present the way to bring about significant results through performance improvement of learning algorithm in the research applying to machine learning. Research papers showing the results from machine learning methods were collected as data for this case study. In addition, suitable machine learning methods for each field were selected and suggested in this paper. As a result, SVM for engineering, decision-making tree algorithm for medical science, and SVM for other fields showed their efficiency in terms of their frequent use cases and classification/prediction. By analyzing cases of machine learning application, general characterization of application plans is drawn. Machine learning application has three steps: (1) data collection; (2) data learning through algorithm; and (3) significance test on algorithm. Performance is improved in each step by combining algorithm. Ways of performance improvement are classified as multiple machine learning structure modeling, +α machine learning structure modeling, and so forth.

고성능 CPU/GPU의 개발과 심층신경망 등의 인공지능 알고리즘, 그리고 다량의 데이터 확보를 통해 기계학습이 다양한 응용 분야로 확대 적용되고 있다. 특히, 사물인터넷, 사회관계망서비스, 웹페이지, 공공데이터로부터 수집된 다량의 데이터들이 기계학습의 활용에 가속화를 가하고 있다. 기계학습을 위한 학습 데이터세트는 응용 분야와 데이터 종류에 따라 다양한 형식으로 존재하고 있어 효과적으로 데이터를 처리하고 기계학습에 적용하기에 어려움이 따른다. 이에 본 논문은 표준화된 절차에 따라 기계학습을 위한 학습 데이터세트를 구축하기 위한 방안을 연구하였다. 먼저 학습 데이터세트가 갖추 어야할 요구사항을 문제 유형과 데이터 유형별로 분석하였다. 이를 토대로 기계학습 활용을 위한 학습 데이터세트 구축에 관한 참조모델을 제안하였다. 또한 학습 데이터세트 구축 참조모델을 국제 표준으로 개발하기 위해 대상 표준화 기구의 선 정 및 표준화 전략을 제시하였다.

With the development of high performance CPU / GPU, artificial intelligence algorithms such as deep neural networks, and a large amount of data, machine learning has been extended to various applications. In particular, a large amount of data collected from the Internet of Things, social network services, web pages, and public data is accelerating the use of machine learning. Learning data sets for machine learning exist in various formats according to application fields and data types, and thus it is difficult to effectively process data and apply them to machine learning. Therefore, this paper studied a method for building a learning data set for machine learning in accordance with standardized procedures. This paper first analyzes the requirement of learning data set according to problem types and data types. Based on the analysis, this paper presents the reference model to build learning data set for machine learning applications. This paper presents the target standardization organization and a standard development strategy for building learning data set.

최근 빅데이터 관련 산업 활성화에 따라 글로벌 보안 업체들은 지능적인 보안 위협 모니터링과 예방을 위 해 분석 데이터의 범위를 정형/비정형 데이터로 확대하고, 보안 예방을 목적으로 사용자의 성향 분석 기법을 활용하 려는 추세이다. 이는 기존 정형 데이터(기존 수치화 가능한 자료)의 분석 결과에서 추론할 수 있는 정보의 범위가 한 정적이기 때문이다. 본 논문은 빅데이터 환경에서 기계학습 알고리즘(Naïve Bayes, Decision Tree, K-nearest neighbor, Apriori)을 효율적으로 응용하여 보안 성향(목적 별 항목 분류, 긍정·부정 판단, 핵심 키워드 연관성 분석)을 분석하 는데 활용한다. 성능 분석 결과 보안 성향 판단을 위한 보안항목 및 특정 지표를 정형/비정형 데이터에서 추출할 수 있음을 확인하였다.

Recently, with the activation of the industry related to the big data, the global security companies have expanded their scopes from structured to unstructured data for the intelligent security threat monitoring and prevention, and they show the trend to utilize the technique of user's tendency analysis for security prevention. This is because the information scope that can be deducted from the existing structured data(Quantify existing available data) analysis is limited. This study is to utilize the analysis of security tendency(Items classified purpose distinction, positive, negative judgment, key analysis of keyword relevance) applying the machine learning algorithm(Naïve Bayes, Decision Tree, K-nearest neighbor, Apriori) in the big data environment. Upon the capability analysis, it was confirmed that the security items and specific indexes for the decision of security tendency could be extracted from structured and unstructured data.

탄소중립과 에너지 전환에 따라 리튬·코발트·니켈·구리·흑연·희토류 등 핵심광물 수요가 급증하고 있다. 그러나 지표에 노출된 광상이 고갈되면서 신규 발견이 어려워져, 탐사의 중심은 피복층하부의 은폐형 광상으로 이동하고 있다. 이에 머신러닝·딥러닝(ML·DL) 기반 접근법이 전통적 지질·지화학·지구물리·원격탐사 기법을 보완하는 핵심 도구로 부상하였다. 본 논문은 최근 인공지능(AI) 기반 광상 탐사 연구를 이론적 배경, 자료 유형별 적용, 광상부존가능성지도(MPM), 광상유형별 응용, 최신 동향의 다섯 측면에서 종합하였다. CNN·오토인코더·GAN·트랜스포머·그래프신경망은 패턴 인식과 이종 자료 융합, 자동화에 강점을 보이며, 설명가능 AI(XAI)·물리정보 신경망(PINN)·자기지도학습·파운데이션 모델은 자료 부족과 블랙박스 문제를 완화한다. 반암동Cu-Mo, 조산형 금, 퇴적암 내 Zn-Pb, 희토류, 리튬 페그마타이트 등 광상 유형별 차별화 전략이 정립되면서, AI 기반 탐사는 은폐형 심부 광상 발견과 핵심광물 공급망 안정화에 핵심적 역할을 할전망이다.

Driven by carbon neutrality policies and energy transitions, the demand for critical minerals, including lithium, cobalt, nickel, copper, graphite, and rare earth elements, is rising rapidly, and exploration has shifted toward concealed deposits beneath cover sequences. Currently, machine and deep learning complement conventional geological, geochemical, geophysical, and remote sensing techniques. This review synthesizes a decade of research on AI-based mineral exploration across five dimensions: theoretical foundations, data modality applications, mineral prospectivity mapping, deposit-type-specific applications, and emerging trends. DL architectures, such as CNNs, autoencoders, GANs, transformers, and graph neural networks, exhibit strong performance in pattern recognition, data fusion, and workflow automation. Emerging paradigms, including explainable AI, physics-informed neural networks, self- supervised learning, and foundation models, address data scarcity and black-box challenges. Different strategies have emerged for porphyry Cu-Mo, orogenic gold, sediment-hosted Zn-Pb, rare-earth elements, and lithium pegmatites. AI-based exploration is expected to play a decisive role in discovering concealed deposits and stabilizing critical mineral supply chains.

A very complex task in deep learning such as image classification must be solved with the help of neural networks and activation functions. The backpropagation algorithm advances backward from the output layer towards the input layer, the gradients often get smaller and smaller and approach zero which eventually leaves the weights of the initial or lower layers nearly unchanged, as a result, the gradient descent never converges to the optimum. We propose a two-factor non-saturating activation functions known as Bea-Mish for machine learning applications in deep neural networks. Our method uses two factors, beta (β) and alpha (α), to normalize the area below the boundary in the Mish activation function and we regard these elements as Bea. Bea-Mish provide a clear understanding of the behaviors and conditions governing this regularization term can lead to a more principled approach for constructing better performing activation functions. We evaluate Bea-Mish results against Mish and Swish activation functions in various models and data sets. Empirical results show that our approach (Bea-Mish) outperforms native Mish using SqueezeNet backbone with an average precision (AP50val) of 2.51% in CIFAR-10 and top-1accuracy in ResNet-50 on ImageNet-1k. shows an improvement of 1.20%.

머신러닝과 같은 소프트웨어가 일상생활에 매우 큰 영향력을 발휘하고 있는 상황에서, 소프트웨어의 개발비용 을 평가하는 비용 모델의 중요성이 지속적으로 증가하고 있다. 비용 모델로서 LOC(Line of Code)와 M/M(Man-Month) 모델은 소프트웨어의 양적인 요소들을 측정하는 비용모델이다. 이와는 달리, FP(Function Point) 는 소프트웨어의 기능적 특징들을 평가하는 비용모델로서 소프트웨어의 질적인 요소를 평가한다는 점에서 효과적이 다. 그러나 FP는 머신러닝 소프트웨어의 주요한 요소들을 평가하지 않기 때문에 머신러닝 소프트웨어를 평가하는데 한계를 가진다. 본 논문은 확장형 FP(Extended Function Point, ExFP)를 제안한다. 확장형 FP는 머신러닝의 주요 특징인 하이퍼 파라미터와 그것의 최적화에 대한 복잡도를 반영하여 소프트웨어의 기능적 요소를 평가하도록 확장하 였기 때문에 머신러닝과 같은 최신 소프트웨어에의 비용 평가에 적합하다. 머신러닝 소프트웨어의 특징을 반영한 평 가를 통해 제안된 확장형 FP의 효용성을 보였다.

Softwares, especially like machine learning applications, affect human’s life style tremendously. Accordingly, the importance of the cost model for softwares increases rapidly. As cost models, LOC(Line of Code) and M/M(Man-Month) estimates the quantitative aspects of the software. Differently from them, FP(Function Point) focuses on estimating the functional characteristics of software. FP is efficient in the aspect that it estimates qualitative characteristics. FP, however, has a limit for evaluating machine learning softwares because FP does not evaluate the critical factors of machine learning software. In this paper, we propose an extended function point(ExFP) that extends FP to adopt hyper parameter and the complexity of its optimization as the characteristics of the machine learning applications. In the evaluation reflecting the characteristics of machine learning applications. we reveals the effectiveness of the proposed ExFP.

최근 머신러닝의 높은 관심과 더불어 물리적 장치에 연동하기 위한 교육용 컨트롤러의 필요성이 증대되고 있다. 하지만 기존 컨트롤러는 교육용으로서의 고비용과 활용 영역면에서 제한적이다. 본 논문에서는 학생들의 머신 러닝 학습을 목적으로 뇌파를 이용한 동작 제어 컨트롤러를 제안한다. 특정 행위를 상상할 때 발생하는 뇌의 동작 상상 뇌파를 측정하여 표본화 한 후, Tensor Flow를 통하여 표본값을 학습시키고 게임 등의 콘텐츠에서 동작을 인식할 수 있도록 설계하였다. 동작 인식을 위한 움직임 변이는 상하좌우의 방향성과 점프 동작으로 구성된다. 인식 동작의 식별 정보를 언리얼 엔진으로 제작한 게임에 전송하여 게임 속 캐릭터를 동작시키는 절차로 이루어 진다. 구현된 컨트롤러는 뇌파 외에도 입력 신호에 따라 다양한 분야에 활용될 수 있으며 머신 러닝 학습 등의 교육적 용도로 사용될 수 있을 것이다.

Recently, with the high interest of machine learning, the need for educational controllers to interface with physical devices has increased. However, existing controllers are limited in terms of high cost and area of utilization for educational purposes. In this paper, motion control controllers using brain waves are proposed for the purpose of students' machine learning applications. The brain motion that occurs when imagining a specific action is measured and sampled, then the sample values were learned through Tensor Flow and the motion was recognized in contents such as games. Movement variation for motion recognition consists of directionality and jump motion. The identification of the recognition behavior is sent to a game produced by an Unreal Engine to operate the character in the game. In addition to brain waves, the implemented controller can be used in various fields depending on the input signal and can be used for educational purposes such as machine learning applications.

We present results from our two experiments of using machine learning algorithms in processing and analyzing the KMTNet imaging data. First, density estimation and clustering methods find meaningful structures in the metric space of imaging quality measurements described by photometric quantities. Second, we also develop a method to separate out light curves of reliable microlensing event candidates from spurious events, estimating reliability scores of the candidates.

Recently, an analysis method using machine learning for solving problems in coastal and ocean engineering has been highlighted. Machine learning models are effective modeling tools for predicting specific parameters by learning complex relationships based on a specified dataset. In coastal and ocean engineering, various studies have been conducted to predict dependent variables such as wave parameters, tides, storm surges, design parameters, and shoreline fluctuations. Herein, we introduce and describe the application trend of machine learning models in coastal and ocean engineering. Based on the results of various studies, machine learning models are an effective alternative to approaches involving data requirements, time-consuming fluid dynamics, and numerical models. In addition, machine learning can be successfully applied for solving various problems in coastal and ocean engineering. However, to achieve accurate predictions, model development should be conducted in addition to data preprocessing and cost calculation. Furthermore, applicability to various systems and quantifiable evaluations of uncertainty should be considered.

Artificial intelligence (AI) and machine learning (ML) are transforming cervical cancer research and offering advancements in diagnosis, prognosis, screening, and treatment. This review explores ML applications with particular emphasis on prediction models. A comprehensive literature search identified studies using ML for survival prediction, risk assessment, and treatment optimization. ML-driven prognostic models integrate clinical, histopathological, and genomic data to improve survival prediction and patient stratification. Screening methods, including deep-learning-based cytology analysis and human papillomavirus detection, enhance accuracy and efficiency. ML-driven imaging techniques facilitate early and precise cancer diagnosis, while risk prediction models assess susceptibility based on demographic and genetic factors. AI also optimizes treatment planning by predicting therapeutic responses and guiding personalized interventions. Despite significant progress, challenges remain regarding data availability, model interpretability, and clinical implementation. Standardized datasets, external validation, and cross-disciplinary collaborations are crucial for implementing ML innovations in clinical settings. Subsequent investigations should prioritize joint initiatives among data scientists, healthcare providers, and health authorities to translate AI innovations into real-world applications and to enhance the impact of ML on cervical cancer care. By synthesizing recent developments, this review highlights the potential of ML to improve clinical outcomes and shaping the future of cervical cancer management.

Recently, artificial intelligence has reached the level of top information technologies that will have significant influence over many aspects of our future lifestyles. In particular, in the fields of machine learning technologies for classification and decision-making, there have been a lot of research efforts for solving estimation and control problems that appear in the various kinds of portfolio management problems via data-driven approaches. Note that these modern data-driven approaches, which try to find solutions to the problems based on relevant empirical data rather than mathematical analyses, are useful particularly in practical application domains. In this paper, we consider some applications of modern data-driven machine learning methods for portfolio management problems. More precisely, we apply a simplified version of the sparse Gaussian process (GP) classification method for classifying users' sensitivity with respect to financial risk, and then present two portfolio management issues in which the GP application results can be useful. Experimental results show that the GP applications work well in handling simulated data sets.

Approximating a divergence between two probability distributions from their samples is a fundamental challenge in statistics, information theory, and machine learning. A divergence approximator can be used for various purposes, such as two-sample homogeneity testing, change-point detection, and class-balance estimation. Furthermore, an approximator of a divergence between the joint distribution and the product of marginals can be used for independence testing, which has a wide range of applications, including feature selection and extraction, clustering, object matching, independent component analysis, and causal direction estimation. In this paper, we review recent advances in divergence approximation. Our emphasis is that directly approximating the divergence without estimating probability distributions is more sensible than a naive two-step approach of first estimating probability distributions and then approximating the divergence. Furthermore, despite the overwhelming popularity of the Kullback-Leibler divergence as a divergence measure, we argue that alternatives such as the Pearson divergence, the relative Pearson divergence, and the $L^2$-distance are more useful in practice because of their computationally efficient approximability, high numerical stability, and superior robustness against outliers.