Earticle

인식 대상 학습 모델이 분류되어 있지 않거나 명확하게 분류되지 않은 경우 어휘 인식을 결정하지 못하여 인 식률이 저하되며 학습 모델 분류 형태가 변경되거나 새로운 학습 모델이 추가되면 인식 모델의 결정 트리 구조가 변 경되어야 하는 구조적 문제가 발생한다. 이러한 문제점을 해결하기 위하여 학습 모델 분류를 위한 결정 트리 학습 알 고리즘을 제안한다. 음운 현상이 충분히 반영된 음성 데이터베이스를 구성하고 학습 효과를 확보하기 위하여 학습 모 델 분류를 위한 결정 트리 방법을 사용하였다. 본 연구에서는 실내 환경에 대하여 어휘 종속 인식과 어휘 독립 인식 실험을 수행한 결과 실내 환경의 어휘 종속 실험에서는 98.3%의 인식 성능을 보였고, 어휘 독립 실험에서 98.4%의 인식 성능을 보였다.

Target learning model is not recognized in this category or not classified clearly failed to determine if the vocabulary recognition is reduced. Form of classification learning model is changed or a new learning model is added to the recognition decision tree structure of the model should be changed to a structural problem. In order to solve these problems, a decision tree learning model for classification learning algorithm is proposed. Phonological phenomenon reflected sound enough to configure the database to ensure learning a decision tree learning model for classifying method was used. In this study, the indoor environment-dependent recognition and vocabulary words for the experimental results independent recognition vocabulary of the indoor environment-dependent recognition performance of 98.3% in the experiment showed, vocabulary independent recognition performance of 98.4% in the experiment shown.

New incremental learning algorithm using extended data expression, based on probabilistic compounding, is presented in this paper. Incremental learning algorithm generates an ensemble of weak classifiers and compounds these classifiers to a strong classifier, using a weighted majority voting, to improve classification performance. We introduce new probabilistic weighted majority voting founded on extended data expression. In this case class distribution of the output is used to compound classifiers. UChoo, a decision tree classifier for extended data expression, is used as a base classifier, as it allows obtaining extended output expression that defines class distribution of the output. Extended data expression and UChoo classifier are powerful techniques in classification and rule refinement problem. In this paper extended data expression is applied to obtain probabilistic results with probabilistic majority voting. To show performance advantages, new algorithm is compared with Learn++, an incremental ensemble-based algorithm.

Federated learning (FL) has emerged as a promising distributed machine learning technique. It has the potential to play a key role in future Internet of Things (IoT) networks by ensuring the security and privacy of user data combined with efficient utilization of communication resources. This paper addresses the challenge of maximizing energy efficiency in FL systems. We employed simultaneous wireless information and power transfer (SWIPT) and multi-carrier non-orthogonal multiple access (MC-NOMA) techniques. Also, we jointly optimized power allocation and central processing unit (CPU) resource allocation to minimize latency-constrained energy consumption. We formulated an optimization problem using a Markov decision process (MDP) and utilized a deep deterministic policy gradient (DDPG) reinforcement learning algorithm to solve our MDP problem. We tested the proposed algorithm through extensive simulations and confirmed it converges in a stable manner and provides enhanced energy efficiency compared to conventional schemes.

Purpose: The purpose of this study was to investigate the availability of software for rehabilitation with the Kinect sensor by presenting an efficient algorithm based on machine learning when classifying the motion data of the PNF pattern if the subjects were wearing a patient gown. Methods: The motion data of the PNF pattern for upper extremities were collected by Kinect sensor. The data were obtained from 8 normal university students without the limitation of upper extremities. The subjects, wearing a T-shirt, performed the PNF patterns, D1 and D2 flexion, extensions, 30 times; the same protocol was repeated while wearing a patient gown to compare the classification performance of algorithms. For comparison of performance, we chose four algorithms, Naive Bayes Classifier, C4.5, Multilayer Perceptron, and Hidden Markov Model. The motion data for wearing a T-shirt were used for the training set, and 10 fold cross-validation test was performed. The motion data for wearing a gown were used for the test set. Results: The results showed that all of the algorithms performed well with 10 fold cross-validation test. However, when classifying the data with a hospital gown, Hidden Markov model (HMM) was the best algorithm for classifying the motion of PNF. Conclusion: We showed that HMM is the most efficient algorithm that could handle the sequence data related to time. Thus, we suggested that the algorithm which considered the sequence of motion, such as HMM, would be selected when developing software for rehabilitation which required determining the correctness of the motion.

In recent years, the rapid development of artificial intelligence technology has brought new opportunities to the meteorological field. Specifically, machine learning (ML) algorithms have proven valuable tools in rainfall retrievals, demonstrating the practicability of using ML algorithms when facing high-dimensional and complex data. By collecting data and using ML algorithms to mine and analyze the data, ML models can solve the problem of rainfall prediction in meteorology. Spurred by this advantage, this paper compared five ML algorithms for rainfall prediction using the National Population Health Science data from China, and the five ML algorithms were optimized appropriately. The data employed was first preprocessed to find and fill in the missing values, remove duplicate values, mine the correlation between data features, and generate visual results. Then, logistic regression, k-nearest neighbor algorithm, naive Bayes, decision tree algorithms, and random forest were used to mine and analyze the meteorological data for weather prediction. Finally, the performance of the models before and after optimization is compared to provide decision support for rainfall prediction.

This paper is an attempt to design segmentation method based on fully convolutional networks (FCN) and attention mechanism. The first five layers of the Visual Geometry Group (VGG) 16 network serve as the coding part in the semantic segmentation network structure with the convolutional layer used to replace pooling to reduce loss of image feature extraction information. The up-sampling and deconvolution unit of the FCN is then used as the decoding part in the semantic segmentation network. In the deconvolution process, the skip structure is used to fuse different levels of information and the attention mechanism is incorporated to reduce accuracy loss. Finally, the segmentation results are obtained through pixel layer classification. The results show that our method outperforms the comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU).

Wireless sensor networks are susceptible to a variety of network attacks. Due to the limited energy of nodes and selfish nodes in the network, the packet delivery rate is lower. To address these issues, we innovatively propose an energy-harvesting Q-learning secure routing algorithm with authenticated-encryption. The algorithm uses physical unclonable functions and optimized Q-learning to ensure that the transmission path is reliable. Meanwhile, we combine the LSTM-based prediction model to predict the energy value that the nodes replenish. In addition, simulations are performed to compare the performances of the proposed algorithm with other algorithms under different attacks. The proposed algorithm has greater improvements in the packet delivery rate, filtering selfish nodes, and reducing node energy consumption.

Aiming at the poor compression quality of traditional image compression coding (ICC) algorithm, a multi-description ICC algorithm based on depth learning is put forward in this study. In this study, first an image compression algorithm was designed based on multi-description coding theory. Image compression samples were collected, and the measurement matrix was calculated. Then, it processed the multi-description ICC sample set by using the convolutional self-coding neural system in depth learning. Compressing the wavelet coefficients after coding and synthesizing the multi-description image band sparse matrix obtained the multi-description ICC sequence. Averaging the multi-description image coding data in accordance with the effective single point's position could finally realize the compression coding of multi-description images. According to experimental results, the designed algorithm consumes less time for image compression, and exhibits better image compression quality and better image reconstruction effect.

To address the problems of the gravitational search algorithm (GSA) in which the population is prone to converge prematurely and fall into the local solution when solving the single-objective optimization problem, a sine map jumping gravity search algorithm based on asynchronous learning is proposed. First, a learning mechanism is introduced into the GSA. The agents keep learning from the excellent agents of the population while they are evolving, thus maintaining the memory and sharing of evolution information, addressing the algorithm's shortcoming in evolution that particle information depends on the current position information only, improving the diversity of the population, and avoiding premature convergence. Second, the sine function is used to map the change of the particle velocity into the position probability to improve the convergence accuracy. Third, the Levy flight strategy is introduced to prevent particles from falling into the local optimization. Finally, the proposed algorithm and other intelligent algorithms are simulated on 18 benchmark functions. The simulation results show that the proposed algorithm achieved improved the better performance.

This investigation explores the use of mixed-reality in collaborative diagnosis by sharing medical data in real-time between multiple physicians using Head-Mounted Display (HMD) devices. Object detection and alignment of the digitized data with the object are the backbone in any mixed-reality application. In this paper, deep-learning networks are used in detecting the patient’s face in the physical world and the medical data is aligned to the patient via the Region-Enhanced-Weight-and-Perturb Iterative-Closest-Point (RE-WAPICP) algorithm. Experiments were performed by sharing a 3D digital model of intracerebral vascular with multi-viewers in a mix-reality environment and the results show that this approach is feasible.

This study presents a systematic review of deep learning applications in dermatological diagnosis, analyzing 212 peer-reviewed studies published from 2019 to 2025. A structured search across major scientific databases identified methods, performance trends, and clinical relevance. Advanced architectures such as Vision Transformers, multimodal fusion models, and few-shot learning demonstrate substantial improvements in detecting both common and rare skin conditions. Despite these advances, challenges related to dataset imbalance, clinical integration, and fairness remain significant. The review outlines key research priorities to guide the development of equitable and clinically reliable AI-based dermatological solutions.

Adaptive beamforming is a fundamental technique in digital radar signal processing that suppresses interference while enhancing desired signal components. However, the conventional Least Mean Square (LMS) algorithm has inherent limitations in dynamic Multiple Input Multiple Output (MIMO) radar environments, which degrade the balance between convergence speed and steady state stability. To overcome these issues, we introduce a new method called MomentumLMD, which enhances the standard LMS by integrating Momentum and weight Decay. The Momentum component enhances the initial convergence speed, whereas the weight decay mechanism controls the excess kinetic energy to prevent overshoots and oscillations. The simulation results demonstrate that the proposed Least Mean Square with Momentum and Decay algorithm (LMD) outperforms the traditional LMS and standard Momentum + LMS, achieving the lowest Mean Square Error MSE in the steady state and maintaining robustness across a significantly wider hyperparameter range. Therefore, the LMD algorithm is established as the optimal choice for high precision, real-time Multiple Input Multiple Output (MIMO) radar applications.

For the mobile edge computing (MEC) system supporting dense network, a joint allocation algorithm of computing and communication resources based on reinforcement learning is proposed. The energy consumption of task execution is defined as the maximum energy consumption of each user's task execution in the system. Considering the constraints of task unloading, power allocation, transmission rate and calculation resource allocation, the problem of joint task unloading and resource allocation is modeled as a problem of maximum task execution energy consumption minimization. As a mixed integer nonlinear programming problem, it is difficult to be directly solve by traditional optimization methods. This paper uses reinforcement learning algorithm to solve this problem. Then, the Markov decision-making process and the theoretical basis of reinforcement learning are introduced to provide a theoretical basis for the algorithm simulation experiment. Based on the algorithm of reinforcement learning and joint allocation of communication resources, the joint optimization of data task unloading and power control strategy is carried out for each terminal device, and the local computing model and task unloading model are built. The simulation results show that the total task computation cost of the proposed algorithm is 5%-10% less than that of the two comparison algorithms under the same task input. At the same time, the total task computation cost of the proposed algorithm is more than 5% less than that of the two new comparison algorithms.

Clustering is a NP-hard problem that is used to find the relationship between patterns in a given set of patterns. It is an unsupervised technique that is applied to obtain the optimal cluster centers, especially in partitioned based clustering algorithms. On the other hand, cat swarm optimization (CSO) is a new meta-heuristic algorithm that has been applied to solve various optimization problems and it provides better results in comparison to other similar types of algorithms. However, this algorithm suffers from diversity and local optima problems. To overcome these problems, we are proposing an improved version of the CSO algorithm by using opposition-based learning and the Cauchy mutation operator. We applied the opposition-based learning method to enhance the diversity of the CSO algorithm and we used the Cauchy mutation operator to prevent the CSO algorithm from trapping in local optima. The performance of our proposed algorithm was tested with several artificial and real datasets and compared with existing methods like K-means, particle swarm optimization, and CSO. The experimental results show the applicability of our proposed method.

To solve the general problems surrounding the application of genetic algorithms in stereo matching, two measures are proposed. Firstly, the strategy of simplified population-based incremental learning (PBIL) is adopted to reduce the problems with memory consumption and search inefficiency, and a scheme for controlling the distance of neighbors for disparity smoothness is inserted to obtain a wide-area consistency of disparities. In addition, an alternative version of the proposed algorithm, without the use of a probability vector, is also presented for simpler set-ups. Secondly, programmable graphics-hardware (GPU) consists of multiple multi-processors and has a powerful parallelism which can perform operations in parallel at low cost. Therefore, in order to decrease the running time further, a model of the proposed algorithm, which can be run on programmable graphics-hardware (GPU), is presented for the first time. The algorithms are implemented on the CPU as well as on the GPU and are evaluated by experiments. The experimental results show that the proposed algorithm offers better performance than traditional BMA methods with a deliberate relaxation and its modified version in terms of both running speed and stability. The comparison of computation times for the algorithm both on the GPU and the CPU shows that the former has more speed-up than the latter, the bigger the image size is.

본 연구의 목적은 한국의료패널 2012년 자료를 이 용하여 고지혈증 유병에 영향을 미치는 변수를 확인 하고 이를 예측하는 분류모형을 개발하는데 있다. 분류모형에 투입되는 변수 선정을 위해 로지스틱 회 귀분석, 의사결정트리 c4.5, 유전자 알고리즘을 각 각 적용하여 선정하였다. 고지혈증 유병을 예측하기 위해 SVM과 meta learning 알고리즘을 이용하였다. 먼저 SVM의 경우 변수를 6개만 투입하였을 때 정확도가 가장 높았으 며, meta learning의 경우 메타분류기를 SVM으로 하 여 변수 6개를 투입한 경우가 가장 높았다. 본 연구는 기존 연구에서 많이 다루지 않은 고지 혈증을 예측하는 모형을 개발했다는 점과 여러 변수 기법을 적용하여 모델 정확도를 기여하였다. 그러나 메타러닝 성과가 크게 향상되지 않은 점은 본 연구 의 한계이자 추후 관련 연구에서 보완되어야 할 부분이다.

Climate change and invasive alien plant species (IAPs) are having a significant impact on mountain ecosystems. The combination of climate change and socio-economic development is exacerbating the invasion of IAPs, which are a major threat to biodiversity loss and ecosystem functioning. Species distribution modelling has become an important tool in predicting the invasion or suitability probability under climate change based on occurrence data and environmental variables. MaxEnt modelling was applied to predict the current suitable distribution of most noxious weed A. adenophora (Spreng) R. King and H. Robinson and analysed the changes in distribution with the use of current (year 2000) environmental variables and future (year 2050) climatic scenarios consisting of 3 representative concentration pathways (RCP 2.6, RCP 4.5 and RCP 8.5) in Bhutan. Species occurrence data was collected from the region of interest along the road side using GPS handset. The model performance of both current and future climatic scenario was moderate in performance with mean temperature of wettest quarter being the most important variable that contributed in model fit. The study shows that current climatic condition favours the A. adenophora for its invasion and RCP 2.6 climatic scenario would promote aggression of invasion as compared to RCP 4.5 and RCP 8.5 climatic scenarios. This can lead to characterization of the species as preferring moderate change in climatic conditions to be invasive, while extreme conditions can inhibit its invasiveness. This study can serve as reference point for the conservation and management strategies in control of this species and further research.

최근 인공지능의 딥러닝과 머신러닝을 이용한 예측시스템에 관한 연구가 활발히 진행되고 있다. 인공지능의 발전으로 인해 투자관리자의 역할을 인공지능을 대신하고 있으며, 투자관리자보다 높은 수익률로 인해 점차 인공지능 으로 거래를 하는 알고리즘 거래가 보편화하고 있다. 알고리즘 매매는 인간의 감정을 배제하고 조건에 따라 기계적으로 매매를 진행하기 때문에 장기적으로 접근했을 때 인간의 매매 수익률보다 높게 나온다. 인공지능의 딥러닝 기법은 과거 의 시계열 데이터를 학습하고 미래를 예측하여 인간처럼 학습하게 되고, 변화하는 전략에 대응할 수 있어 활용도가 증가하고 있다. 특히 LSTM기법은 과거의 데이터 일부를 기억하거나 잊어버리는 형태로 최근의 데이터의 비중으로 높 여 미래 예측에 사용하고 있다. 최근 facebook에서 개발한 인공지능 알고리즘인 fbprophet은 높은 예측 정확도를 자랑하며 주가나 암호화폐 시세 예측에 사용되고 있다. 따라서 본 연구는 fbprophet을 활용하여 실제 값과 차이를 분석하고 정확한 예측을 위한 조건들을 제시하여 암호화폐 자동매매를 하기 위한 새로운 알고리즘을 제공하여 건전한 투자 문화를 정착시키는 데 이바지하고자 한다.

Recently, research on predictive systems using deep learning and machine learning of artificial intelligence is being actively conducted. Due to the development of artificial intelligence, the role of the investment manager is being replaced by artificial intelligence, and due to the higher rate of return than the investment manager, algorithmic trading using artificial intelligence is becoming more common. Algorithmic trading excludes human emotions and trades mechanically according to conditions, so it comes out higher than human trading yields when approached in the long term. The deep learning technique of artificial intelligence learns past time series data and predicts the future, so it learns like a human and can respond to changing strategies. In particular, the LSTM technique is used to predict the future by increasing the weight of recent data by remembering or forgetting part of past data. fbprophet, an artificial intelligence algorithm recently developed by Facebook, boasts high prediction accuracy and is used to predict stock prices and cryptocurrency prices. Therefore, this study intends to establish a sound investment culture by providing a new algorithm for automatic cryptocurrency trading by analyzing the actual value and difference using fbprophet and presenting conditions for accurate prediction.