Using the proximal policy optimization and prospect theory to train a decision-making model for managing personal finances by Vladyslav Didkivskyi, Dmytro Antoniuk, Tetiana Vakaliuk, Yevhen Ohinskyi

“…The tasks can be formulated as follows: 1) design a reinforcement learning environment featuring different investment options with varying average returns and volatility levels; 2) train the reinforcement learning agent using the Proximal Policy Optimization algorithm to learn recommended investment allocations; 3) implement a reward function based on Prospect Theory, incorporating parameters that reflect different investor risk profiles, such as loss aversion and diminishing sensitivity to gains and losses. …”
Get full text

Technological Innovation in Pencak Silat Training as a Component of Indonesian Cultural Heritage: A Systematic Literature Review by Bahtiar Hari Hardovi, Heny Setyawati, Rumini Rumin, Cahyo Yuwono, Harry Pramono, Donny Wira Yudha Kusuma, Andi Anshari Bausad

“…The study aimed to evaluate the effectiveness of augmented reality (AR), virtual reality (VR), and sensor-based systems in improving skill acquisition, performance monitoring, and training customization. …”
Get full text

Toward lightweight intrusion detection systems using the optimal and efficient feature pairs of the Bot-IoT 2018 dataset by Erman Özer, Murat İskefiyeli, Jahongir Azimjonov

“…Next, 10 full-feature-based intrusion detection systems were developed by training the 10 machine learning algorithms with the 12 full features. …”
Get full text

Leveraging two-dimensional pre-trained vision transformers for three-dimensional model generation via masked autoencoders by Muhammad Sajid, Kaleem Razzaq Malik, Ateeq Ur Rehman, Tauqeer Safdar Malik, Masoud Alajmi, Ali Haider Khan, Amir Haider, Seada Hussen

“…We employ the adept 2D information to direct a 3D masking-based autoencoder, which uses an encoder-decoder architecture to rebuild the masked point tokens through self-supervised pre-training. …”
Get full text

Creating controversy: developing a virtual reality training tool with 360° film to engage in ethnic profiling reform by Bas Böing, Bas Böing, Peter W. De Vries, Ellen Giebels

“…We describe the foundations of a Virtual Reality based training prototype that seeks to encourage active participation in ethnic profiling dialogue. …”
Get full text

Prediction of pathogenic mutations in human transmembrane proteins and their associated diseases via utilizing pre-trained Bio-LLMs by Lexin Cao, Lijun Quan, Qiufeng Chen, Bei Zhang, Zhijun Zhang, Liangchen Peng, Junkai Wang, Yelu Jiang, Liangpeng Nie, Geng Li, Tingfang Wu, Qiang Lyu

“…MutDPAL utilizes two pre-trained biological large language models (Bio-LLMs), one for raw sequence features and the other for encoding transmembrane environment features. …”
Get full text

Efficient incremental training using a novel NMT-SMT hybrid framework for translation of low-resource languages by Kumar Bhuvaneswari, Murugesan Varalakshmi

“…SMT-integrated incremental training demonstrates a substantial difference in translation performance as compared to the existing approaches for incremental training. …”
Get full text

A Realistic Image Generation of Face From Text Description Using the Fully Trained Generative Adversarial Networks by Muhammad Zeeshan Khan, Saira Jabeen, Muhammad Usman Ghani Khan, Tanzila Saba, Asim Rehmat, Amjad Rehman, Usman Tariq

“…Most of the work for text to face generation until now is based on the partially trained generative adversarial networks, in which the pre-trained text encoder has been used to extract the semantic features of the input sentence. …”
Get full text

SpecPT (Spectroscopy Pre-trained Transformer) Model for Extragalactic Spectroscopy. I. Architecture and Automated Redshift Measurement by Rohan Pattnaik, Jeyhan S. Kartaltepe, Clive Binu

“…We introduce the Spectroscopy Pre-trained Transformer (SpecPT), a transformer-based model designed to analyze spectroscopic data, with applications in spectrum reconstruction and redshift measurement. …”
Get full text

Effects of an emotional intelligence training program on alleviating internet addiction of college students at the risk of internet addiction in China by Chunlin Yao, Yan Zhang, Haili Hou

“…The study employs an experimental design featuring pre-test, post-test, and after-test phases. …”
Get full text

Feature-Level Fusion Network for Hyperspectral Object Tracking via Mixed Multi-Head Self-Attention Learning by Long Gao, Langkun Chen, Yan Jiang, Bobo Xi, Weiying Xie, Yunsong Li

“…In order to address these challenges, a new mixed multi-head attention-based feature fusion tracking (MMFT) algorithm for hyperspectral videos is proposed. …”
Get full text

Comparative Feature-Guided Regression Network with a Model-Eye Pretrained Model for Online Refractive Error Screening by Jiayi Wang, Tianyou Zheng, Yang Zhang, Tianli Zheng, Weiwei Fu

“…This paper designs an online refractive error screening solution centered on the CFGN (Comparative Feature-Guided Network), a refractive error screening network based on the eccentric photorefraction method. …”
Get full text

Classification of Prominent Cacao Pod Diseases Using Multi-Feature Visual Analysis and k-Nearest Neighbors Algorithm by Earl Clarence San Diego, Seph Gerald Rodrin, Edwin Arboleda

“…The machine training model was preceded with visual feature extraction of color and texture parameters representing the cacao pod samples. …”
Get full text

Enhancing land cover object classification in hyperspectral imagery through an efficient spectral-spatial feature learning approach. by Masud Ibn Afjal, Md Nazrul Islam Mondal, Md Al Mamun

“…Traditional CNN-based methods predominantly utilize 2D CNNs for feature extraction, which inadequately exploit the inter-band correlations in HSIs. …”
Get full text

Brain image registration optimization method via SAM-Med3D multi-scale feature migration by Mo Nan

“…Aiming at the problems of insufficient anatomical structure constraints and limited feature expression ability in medical image registration, this paper proposes a registration optimization method based on SAM-Med3D and dynamic large kernel convolution. …”
Get full text

Monopulse Feature Extraction and Fault Diagnosis Method of Rolling Bearing under Low-Speed and Heavy-Load Conditions by Chang Liu, Gang Cheng, Xihui Chen, Yong Li

“…According to the rolling bearing local fault vibration mechanism, a monopulse feature extraction and fault diagnosis method of rolling bearing under low-speed and heavy-load conditions based on phase scan and CNN is proposed. …”
Get full text

Text mining approach for feature extraction and cartilage disease grade classification using knee MRI radiology reports by Antonio Saverio Valente, Teresa Angela Trunfio, Marco Aiello, Dario Baldi, Marilena Baldi, Silvio Imbò, Mario Alessandro Russo, Carlo Cavaliere, Monica Franzese

Get full text

Enhancing classification of active and non-active lesions in multiple sclerosis: machine learning models and feature selection techniques by Atefeh Rostami, Mostafa Robatjazi, Amir Dareyni, Ali Ramezan Ghorbani, Omid Ganji, Mahdiye Siyami, Amir Reza Raoofi

“…Abstract Introduction Gadolinium-based T1-weighted MRI sequence is the gold standard for the detection of active multiple sclerosis (MS) lesions. …”
Get full text

GLTDNet: Cross-Domain Road Extraction Through Collaborative Optimization of Global-Local Feature Enhancement and Topological Decoupling by Jie Chen, Changxian He, Hao Wu, Jun Zhang, Siqiang Rao, Songshan Zhou, Jingru Zhu

“…This approach leverages a hybrid CNN-Transformer architecture and incorporates a global-local feature enhancement unit designed to effectively capture both the intricate local detail features and the overarching global topological structures of roads. …”
Get full text

Optimized feature selection and advanced machine learning for stroke risk prediction in revascularized coronary artery disease patients by Yong Si, Armin Abdollahi, Negin Ashrafi, Greg Placencia, Elham Pishgar, Kamiar Alaei, Maryam Pishgar

“…Initially, 35 features were identified based on expert opinion and a comprehensive literature review; the integrated results of the feature selection methods reduced the feature set to 14. …”
Get full text