Earticle

The purpose of the current study is to discuss the syntax of English Aspect from a generative framework, proposing“split aspect phrase.”English Perfective (exclusive of Progressives in this study) is so challenging for many learners who speak languages other than English. The speakers of other languages such as Japanese, Turkish, French, Brazilian Portuguese, Malay, and German face the same challenge and produce erroneous patterns in their interlanguage as well (Yoshimura, Nakayama, Fujimori, and Sawasaki 2010, 2014, Rocha 2004, Durich 2005, Payre-Ficout, Brissaud and Chevrot 2009, Lim 2010, Bulut 2011). This paper aims to provide a structural specification via feature system of English Perfectives. Within the Minimalist spirit by Adger(2003) and Adger & Svenonius (2010), it is proposed that English Outer Aspect is a functional Head rather than affix, as Chomsky(1995) has argued, and has a lot more intricate internal structure which is novel from a second language acquisitional perspective. “Split aspect hypothesis”is inspired by MacDonald(2006, 2008) and Mayshark(2010) and the semantics of the Aspect is more meticulously represented at syntax.

Identifying informative features in bioinformatics is challenging due to their small proportion within large datasets. We propose a scalable and interpretable feature selection framework for cancer RNA-seq by transforming non-image bio-data into 2D formats and applying convolutional neural networks (CNNs) with transfer learning for efficient classification. Explainable artificial intelligence (XAI) techniques identify and prioritize important features, while principal component analysis (PCA) determines the optimal number of selected features, ensuring transparency and reliability. Comparative analysis of CNN and XAI highlights the effectiveness of our approach, providing a robust framework for high-dimensional genomic data analysis with applications in cancer diagnosis and prognosis.

Deep convolution neural networks are the recent algorithms used for robotic vision. However, the complex crop?weed vegetation and the background interferences required a robust feature representation. Therefore, we proposed a Dual-branch Deep neural network for the semantic segmentation of crops and weeds. The branches utilized distinct feature extraction algorithms that extract essential semantic cues, and a decoder combined these features to improve the global contextual information. Finally, the hybrid feature selection module(HSFM) utilized the decoder features to complement one another. Experimental results show the proposed method obtained mean intersection of union scores of 0.8613 and 0.9099 on CWFID and BoniRob datasets, respectively.

"The extensive embrace of Android has amplified malware risks, resulting in a need for better detection methods. This article investigates the area of static analysis, which analyses applications without execution by examining code and manifest files. We focus on studies from 2022?2025, regarding the feature extraction, datasets, feature selection, and approaches based on Machine Learning (ML) and Deep Learning (DL). We conclude by defining the major limitations and research gaps presented in studies regarding static analysis, and many insights for potential development of detection models that are efficient, accurate, and lightweight to improve detection patterns of Android malware. 2018 The Korean Institute of Communications and Information Sciences. Publishing Services by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)."

Machine learning can detect variant malware files that can evade signature-based detection. Feature hashing is used to convert features into a fixed-length vector. In this paper, we study the appropriate vector size for feature hashing for a large dataset of malware files. Through exhaustive experiments on more than 280,000 real malware and benign files, we find for the first time that the default vector size of current feature hashing practices is unnecessarily large. We experimentally explore the appropriate vector size, which not only reduces memory space by 70% but also increases the detection accuracy, compared with the state-of-the-art scheme.

Due to the sensitivity of the information required to detect network intrusions efficiently, collecting huge amounts of network transactions is inevitable and the volume and details of network transactions available in recent years has been high. The meta-heuristic anomaly based assessment is vital in an exploratory analysis of intrusion related network transaction data. In order to forecast and deliver predictions about intrusion possibility from the available details of the attributes involved in network transaction. In this regard, a meta-heuristic assessment model called the feature correlation analysis and association impact scale is explored to estimate the degree of intrusion scope threshold from the optimal features of network transaction data available for training. With the motivation gained from the model called “network intrusion detection by feature association impact scale” that was explored in our earlier work, a novel and improved meta-heuristic assessment strategy for intrusion prediction is derived. In this strategy, linear canonical correlation for feature optimization is used and feature association impact scale is explored from the selected optimal features. The experimental result indicating that the feature correlation is has a significant impact towards minimizing the computational and time complexity of measuring the feature association impact scale.

Fall accidents are increasing, and monitoring them using real-time CCTV systems remains challenging. This paper compares the performance of YOLOv11 and RT-DETRv2 models for real-time fall detection. Experimental results show that YOLOv11 outperforms RT-DETRv2 in terms of inference speed, making it more suitable for real-time applications. Unlike earlier studies, we propose feature map-based knowledge distillation during the model training process to improve model performance. The proposed YOLO-based fall detection system transfers intermediate representations from a teacher to a student network and optimises two complementary objectives: spatial alignment via Mean-Squared-Error (MSE) loss and channel-wise distribution alignment via Kullback?Leibler (KL) divergence. Experiments improved the mean Average Precision (mAP) and reduced processing time by 0.8ms. Evaluation on AI-hub abnormal behavior datasets confirmed a 0.02 increase in accuracy and F1-score, demonstrating the effectiveness of the proposed distillation method in real-time environments.

Air traffic controller (ATC) fatigue is receiving considerable attention in recent studies because it represents a major cause of air traffic incidences. Research has revealed that the presence of fatigue can be detected by analysing speech utterances. However, constructing a complete labelled fatigue data set is very time-consuming. Moreover, a manually constructed speech collection will often contain only little key information to be used effectively in fatigue recognition, while multilevel deep models based on such speech materials often have overfitting problems due to an explosive increase of model parameters. To address these problems, a novel deep learning framework is proposed in this study to integrate active learning (AL) into complex speech features selected from a large set of unlabelled speech data in order to overcome the loss of information. A shallow feature set is first extracted using stacked sparse autoencoder networks, in which fatigue state challenge features from a manually selected speaker set of are exploited as the input vector. A densely connected convolutional autoencoder (DCAE) is then proposed to learn advanced features automatically from spectrograms of the selected data to supplement the fatigue features. The network can be effectively trained using a relatively small number of labelled samples with the help of AL sampling strategies, and the addition of a dense block to the convolutional automatic encoder can decrease the number of parameters and make the model easier to fit. Finally, the two above-mentioned features are combined using multiple kernel learning with a support-vector-machine classifier. A series of comparative experiments using the Civil Aviation Administration of China radiotelephony corpus demonstrates that the proposed method provides a significant improvement in the detection precision compared to current state-of-the-art approaches.

Radio maps are essential for electromagnetic spectrum awareness, supporting communication network optimization and spectrum management. However, existing methods often lack sufficient accuracy in complex propagation environments. To address this, we propose RMG-SRGAN, an improved radio map generation network based on an enhanced super-resolution generative adversarial network. The generator incorporates a Multi-scale Attention Aggregation (MAA) module that strengthens feature representation using multi-scale fusion and dual-path attention in spatial and channel dimensions. The discriminator includes a Feature Enhancement (FE) module to boost discriminative power through multi-stage feature processing.In our evaluation, we prioritize physical fidelity and structural reliability over generic perceptual metrics. Consequently, we employ Root Mean Square Error (RMSE) to quantify the precision of predicted signal strength and the F1-Score to assess the classification accuracy of coverage zones versus blind spots. Extensive experiments on the RadioMapSeer dataset demonstrate that RMG-SRGAN achieves state-of-the-art performance, securing the lowest RMSE and highest F1-Score compared to existing baselines.

플라스틱 사출 제품은 다양한 가전제품과 하이테크 제품에 널리 사용되고 있다. 그러나 현재의 치열한 경쟁적 비즈니스 환경에서 플라스틱 사출 제품 제조업자들은 고객을 만족시키면서 경쟁력을 얻기 위하여 다른 경쟁자들보다 먼저 새로운 제품을 시장에 출시하고 신제품의 개발기간을 줄이기 위한 노력을 할 여유가 부족하다. 따라서 무한 경쟁의 시장에서 살아남기 위해서는 제조업자들은 시장 마켓 점유를 빠르게 올리는 것과 동시에 제품의 가격 경쟁력을 가져야 한다. 특징기반 모델의 구조는 현재 연구에서 3D 제작 도구로서 일반적으로 적용되고 있으며 신제품 개발 엔지니어들이 새로운 제품의 개념을 개발하는 데에도 널리 사용되고 있다. 본 연구에서는 특징기반 플라스틱 사출제품을 위한 유전자 알고리즘과 Support Vector Regression (SVR) 기반의 새로운 하이브리드 비용 평가 모델을 제안한다. 제안하는 하이브리드 모델은 기존의 플라스틱 사출제품의 비용평가절차와 계산을 위해 필요로 하는 변수들을 극적으로 간단하게 하고 줄일 수 있다. 사례연구에서는 제안하는 하이브리드 모델과 기존의 multilayer perceptron networks (MLP) 및 pure SVR과의 비교분석을 통하여 제안모델이 플라스틱 사출 제품의 개발단계에서의 비용평가문제를 해결하는데 효율성과 효과성이 있음을 입증한다.

In English and Korean, addressee honorification is realized in the vocative construction. In the concept of Chomsky’s (1993, 1995) earlier version of Minimalist Program, checking is in the Spec-head relation between the subject and [uHon] of the subject-honorific marker si on T or between the vocative element and [uHon] on Voc. When the honorific vocative element appears in Korean, its corresponding verbal ending marker (e)yo occurs as a head of VocP. Other unchecked syntactic features, the residual unchecked honorific feature percolates up to higher level, let’s say, to Voc, head of VocP to discharge the unchecked feature for the vocative elements such as caney, Kim sepang, or a pen name, which induces the so-called si addressee honorification (i.e., si politeness). In English. Force on C triggers addressee honorification in that the unchecked honorific feature on C percolates up to Voc and discharges its feature in the Spec-head relation with the vocative element in Spec-Voc. The vocative element must appear overtly or covertly. The source of the unchecked honorific feature percolating up to Voc is C in English or T in si addressee honorification of Korean. The addressee honorific marker (e)yo is on Voc from which it discharges its honorific feature.

The goal of few-shot learning is to use limited labeled samples to achieve effective classification results. To mine the features of images in the limited number of samples, some researchers proposed to mine salient features to improve the classification effect. However, they ignore the use of secondary salient features. Therefore, we propose to use secondary salient features to supplement the deficiency of salient features. Combining with the foreground extraction network and the graph neural network, a better classification effect is obtained in the experiment.

This paper proposed a Feature-level fusion technique that combines facial expression and audio modalities for multimodal emotion recognition. The learning model utilizes a hybrid approach combining CNN and LSTM to learn the spatiotemporal characteristics of video and audio modalities effectively. Compared to a unimodal approach, speech emotion recognition achieved 74% accuracy, and facial emotion recognition achieved 83% accuracy, while the proposed multimodal approach achieved 93% accuracy, demonstrated that multimodal emotion recognition is more accurate than unimodal emotion recognition. Furthermore, in tests using the RAVDESS dataset, the proposed model achieved higher emotion recognition rates compared to related studies. This study demonstrated the possibility of multimodal emotion recognition and designed a model capable of recognizing emotions in various environments and situations. Through this, we aim to contribute to the advancement of emotion recognition technology.

본 논문은 음악 정보검색에 사용되는 효과적인 템포 특징 추출방식을 제안한다. 제안된 템포 정보는 협소 밴드상의 일시적인 변조 성분에 의해 형성된다. 이러한 변조 성분은 시간 축 상의 음악 신호로부터 스펙트럼을 구한 후, 각 스펙트럼 성분에 대한 주파수 영역 분석을 통해 획득된 변조 스펙트럼으로 구성된다. 실제 구현에 있어서는 MP3 음악파일로부터 부분 디코딩에 의해 출력된 변형된 이산 코사인 변환 계수에 퓨리에 변환을 취하여 변조스펙트럼을 구하였다. 획득된 변조 스펙트럼의 진폭으로부터 고속으로 추출된 음악 템포 특징값은 다양한 음악 정보 검색에 적용되었다. 음악 무드 및 장르 분류에서는 로그 변조 주파수 계수를 적용하여 분류 성능을 개선시켰으며, 적응 변조 스펙트럼에서 유도된 비트 벡터는 오디오 핑거프린팅에 적용되어 잡음환경 하에서도 검색 성능을 크게 향상시켰다.

This paper proposes an effective tempo feature extraction method for music information retrieval. The tempo information is modeled by the narrow-band temporal modulation components, which are decomposed into a modulation spectrum via joint frequency analysis. In implementation, the tempo feature is directly extracted from the modified discrete cosine transform coefficients, which is the output of partial MP3(MPEG 1 Layer 3) decoder. Then, different features are extracted from the amplitudes of modulation spectrum and applied to different music information retrieval tasks. The logarithmic scale modulation frequency coefficients are employed in automatic music emotion classification and music genre classification. The classification precision in both systems is improved significantly. The bit vectors derived from adaptive modulation spectrum is used in audio fingerprinting task That is proved to be able to achieve high robustness in this application. The experimental results in these tasks validate the effectiveness of the proposed tempo feature.

Customer Churn Prediction is the process of identifying customers who are likely to stop using a company's products or services in the near future that is critical for the long-term financial stability of a business. Retaining existing customers is often more cost-effective than acquiring new ones, making churn prediction a key focus for customer relationship management (CRM). This study aimed to identify customer churn in data source containing 8,047 sale transactions with various features such as sales, profit, and product category. The four techniques of churn labels generation were introduced base-on features of Time, Value, and Feedback. Additionally, a combination of Time and Value also used to test. The data was split into 80% training and 20% testing subsets, focusing on seven selected features and the Multiple Criteria churn label. Four machine learning models—Random Forest (RF), Logistic Regression (LR), Gradient Boosting (GB), and Support Vector Machines (SVM) were used to create model. The results showed that LR (73.60%) and SVM (71.70%) performed a good performance in terms of accuracy. However, to compare with dataset that included churn label as E-commerce Customer Behavior and Purchase Dataset [23] the results showed that the proposed techniques can be used to impute a churn label attribute which effecting to a classification model.

In the classifier which is constructed with a fully connected layer connected to an output layer the weight vector W creates a decision boundary between each. The learning of a feature vector influences the model to extract unique features of the class during the learning process which moves the distribution of the initial feature vector into the decision boundary of the class. When the similarity between the initial feature vector and the weight vector is high, it can be expected that the effect on the model is low because the loss value is small. On the other hand, if the similarity is low, it means that the interval between the feature vector and the weight vector is large and the loss value is high, which can be expected to have a higher effect on the model than when the similarity is high in the learning process of the model. In this paper, we verify how much the similarity between the initial feature vector and the weight vector before learning affects model learning. In order to confirm the effect of similarity, the model is learned by assigning an arbitrary fixed value so that the weight vectors W of the fully connected layer make different similarities. Both VGG16 and VGG19 models are used to compare the Recall and the Precision values of the class as a learning result of each model.

고령화 사회의 가속화로 치매 조기 선별의 중요성이 강조되는 가운데, 음성 기반 인공지능은 비침습적·저비 용 대안으로 주목받고 있다. 선행 연구에서는 음성 신호를 멜 스펙트로그램(Mel-Spectrogram)으로 변환하여 CNN, ViT 모델 등에 적용하였으나, 분류 정확도가 약 61~62% 수준에 머물며 음향적 특징만으로는 치매 특유의 인지 저 하를 포착하는 데 구조적 한계가 있음을 확인하였다. 본 연구는 이러한 한계를 극복하기 위해 ADRESS-2020 데이 터셋을 기반으로 전사 텍스트에서 추출한 언어적 특징을 결합한 다중모달 분석 접근을 제안하였다. 연구 결과, 어휘 다양성, 문장 복잡도, 의미적 응집성 등 14개의 언어적 변수만으로도 교차검증 정확도 76.8%를 달성하며 선행 연구 의 음향 기반 모델 성능을 크게 상회하였다. 특히 특징 수 대비 성능 효율성 측면에서 언어적 특징은 고차원 딥러닝 특징보다 월등히 높은 수치를 기록하여, 소규모 의료 데이터 환경에서 특징의 질적 설계가 중요함을 입증하였다. 음 향과 언어 특징의 결합은 안정성과 분산 측면에서 가장 균형 잡힌 결과를 나타냈으나, 모든 특징을 결합한 고차원 환경에서는 차원의 저주로 인한 성능 저하가 관찰되었다. 모델 비교에서는 로지스틱 회귀가 가장 우수한 일반화 성 능을 보였으며, 이는 실제 임상 현장에서 해석 가능하고 단순한 모델의 실용성이 높음을 시사한다. 본 연구는 언어적 특징 중심의 다중모달 분석이 치매 조기 선별의 정확성과 신뢰성을 높이는 핵심 전략임을 실증하였다.

As the acceleration of population aging intensifies the importance of early dementia screening, voice-based artificial intelligence is gaining significant attention as a non-invasive and cost-effective alternative. A previous study utilized voice signals converted into Mel-spectrograms and applied them to models such as CNN and ViT, but found that classification accuracy remained at approximately 61–62%, confirming structural limitations in capturing dementia-specific cognitive decline using only acoustic features . To overcome these limitations, this study proposes a multimodal analysis approach that integrates linguistic features extracted from transcribed text using the ADRESS-2020 dataset. The experimental results demonstrated that just 14 linguistic variables—including lexical diversity, syntactic complexity, and semantic coherence—achieved a cross-validation accuracy of 76.8%, significantly outperforming the acoustic-based models from the previous study. In terms of performance efficiency relative to the number of features, linguistic features recorded substantially higher values than high-dimensional deep learning features, proving that qualitative feature engineering is crucial in small-scale medical data environments. While the combination of acoustic and linguistic features yielded the most balanced results in terms of stability and variance, a performance decline due to the "curse of dimensionality" was observed when all high-dimensional features were combined. In model comparisons, logistic regression exhibited the most superior generalization performance, suggesting that simple, interpretable models are more practical for real-world clinical settings. This study empirically validates that multimodal analysis centered on linguistic features is a core strategy for enhancing the accuracy and reliability of early dementia screening.

본 연구는 3차원 게임 캐릭터가 지닌 특징 정보를 기반으로 하여 연필 효과를 표현하는 렌더링 기법을 제안한다. 특징 정보를 추출하기 위해서 시선 의존성이 높은 특징은 시선 벡터를 이용하고, 시선 의존성이 낮은 특징은 캐릭터의 주곡률 방향을 이용한다. 노이즈는 캐릭터의 각 면에 다트 던지기 알고리즘을 이용하여 충분한 노이즈를 생성하며, 캐릭터의 기하학적 특성으로 시선의 의존성이 낮은 주요 특징과 카메라의 정보를 통해 시선의 의존성이 높은 주요 특징을 고려하여 검은색 또는 흰색으로 노이즈 값을 결정한 후 이를 영상 공간에 투영한다. 본 논문에서는 투영된 노이즈를 영상에서 벡터를 시각화하기 위해 흔히 사용되는 선적분회선 (line integral convolution, LIC) 기법에 적용함으로써 연필 효과를 구현한다.

We present a feature-based pencil rendering algorithm for a game character. We use two types of features: view-dependent features are computed from the view vectors and view-independent features are from the principal directions on the character. The noise particles are generated on the face of the mesh according to the strength of the features using dart throwing algorithm. After projecting the geometric information of the character and the noise particles into an image space, we execute a line integral convolution algorithm to produce pencil drawing effects from the noise particles.

행동 효과(action effect)란 선행자극(prime)에 대한 반응 이후 시각 탐색 과제에서 선행자극과 동일한 자극 위에 제시되는 표적에 대하여 반응시간이 빨라지는 현상을 이야기한다(Buttaccio & Hahn, 2011; Weidler & Abrams, 2014). 본 연구는 선행자극에 대한 주의가 행동 효과에 미치는 영향을 알아보기 위하여 진행되었다. Weidler와 Abrams(2014)는 행동 효과에 대한 설명으로, 선행자극에 대한 주의나 평가 없이 물리적인 행위를 하는 것만으로 이후 시각 탐색 과제에서 선행자극과 동일한 자극이 우선적으로 처리될 수 있다고 제안하였다. 이에 착안하여, 본 연구에서는 선행자극에 대해 행위하는 동안의 주의 효과가 특징 기반으로 작동하는지, 혹은 객체 기반으로 작동하는지 여부를 탐구하였다. 실험 자극은 조도를 통제한 다섯 가지 색과 면적을 통제한 다섯 가지 도형으로 구성되었다. 반응 과제에서 참가자들은 키보드를 사용하여 색 도형(선행자극)이 반응하되(행동 조건), 선행자극 위에 단서가 함께 제시되면 반응하지 않도록(비행동 조건) 지시받았다. 시각 탐색 과제에서 참가자들은 제시되는 선분 중에서 기울어진 선분을 찾아 방향을 판단하는 과제를 수행하였다. 표적이 선행자극과 특징을 공유하는 자극 위에 나타나는 타당(valid) 조건과 특징을 공유하지 않는 자극 중 한 곳에 위치하는 비타당(invalid) 조건의 반응 속도 차이를 분석하였다. 실험 결과, 행동 조건에서의 타당도 효과가 비행동 조건에서의 타당도 효과보다 더 강한 것을 확인할 수 있었다. 이러한 결과는 행동효과에서 선행자극에 대한 주의가 중요한 요소이며, 이러한 주의가 이후 시각 탐색 과제에서 특징 기반으로 작용함을 시사한다.

Previous research has demonstrated how a simple motoric response towards an object (the prime) can prioritize the allocation of attention to that same object in a subsequent unrelated visual search task (Buttaccio & Hahn, 2011; Weidler & Abrams, 2014). This phenomenon, known as the “action effect”, results in faster reaction times (RT) only when the target is located within the object that was acted upon. To explore the attentional selection mechanism involved in the action effect, we examined how attention is allocated at the precise moment of action. Participants were instructed to respond (go) when the prime (a colored shape) appeared and withhold a response when “X” was displayed on the prime. Subsequently, participants were asked to search for a tilted line and report its orientation in the following visual search task. In valid trials, the target appeared on an object that shared a feature with the prime (either in terms of both-, color-, or shape-sharing), while in invalid trials, the target appeared on an object that did not share any features with the prime. The results revealed that visual features of the prime object guided visual attention to the location of the object that shared at least one feature with the prime. Therefore, the allocation of attention to specific features of the prime during the action task plays a critical role in inducing an attentional boost in the subsequent attentional selection process and it is suggested that this selection process occurs in a feature-based manner.