检索结果-内蒙古大学图书馆

Social sciences and Intelligent Management (SSIM), IEEE International Conference on

作者： Greta V. Paramita Esther W. Andangsari Ade P. Kemala Moondore M. Ali Trisa M. Putri Katarina I. Puspita Psychology Department Faculty of Humanities Bina Nusantara University Jakarta Indonesia Data Science Program School of Computer Science Bina Nusantara University Jakarta Indonesia

Twitter is one of Indonesia's most widely used social media to express positive and negative emotions. Negative emotions are referred to as emotional reactivity, an example of which is depression. To detect emotional reactivity, Artificial Intelligence (AI) was used. With deep learning pretrained model methods (IndoBERT and IndoBERTweet), AI successfully classified emotional reactivity. AI satisfactorily detected emotional reactivity on Twitter.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantum variational autoencoder utilizing regularized mixed-state latent representations

引用

Physical Review A 2025年第4期111卷 042416-042416页

作者： Gaoyuan Wang Jonathan Warrell Prashant S. Emani Mark Gerstein Program in Computational Biology and Bioinformatics Yale University New Haven Connecticut 06520 USA Department of Molecular Biophysics and Biochemistry Yale University New Haven Connecticut 06520 USA NEC Laboratories America Princeton New Jersey 08540 USA Department of Computer Science Yale University New Haven Connecticut 06520 USA Department of Statistics & Data Science Yale University New Haven Connecticut 06520 USA Department of Biomedical Informatics & Data Science Yale University New Haven Connecticut 06520 USA

A major challenge in near-term quantum computing is its application to large real-world datasets due to scarce quantum hardware resources. One approach to enabling tractable quantum models for such datasets involves finding low-dimensional representations that preserve essential information for downstream analysis. In classical machine learning, variational autoencoders (VAEs) facilitate efficient data compression, representation learning for subsequent tasks, and novel data generation. However, no quantum model has been proposed that exactly captures all of these features for direct application to quantum data on quantum computers. Some existing quantum models for data compression lack regularization of latent representations, thus preventing direct use for generation and control of generalization. Others are hybrid models with only some internal quantum components, impeding direct training on quantum data. To address this, we present a fully quantum framework, ζ-QVAE, which encompasses all the capabilities of classical VAEs and can be directly applied to map both classical and quantum data to a lower-dimensional space, while effectively reconstructing much of the original state from it. Our model utilizes regularized mixed states to attain optimal latent representations. It accommodates various divergences for reconstruction and regularization. Furthermore, by accommodating mixed states at every stage, it can utilize the full data density matrix and allow for a training objective defined on probabilistic mixtures of input data. Doing so, in turn, makes efficient optimization possible and has potential implications for private and federated learning. In addition to exploring the theoretical properties of ζ-QVAE, we demonstrate its performance on representative genomics and synthetic data. Our results indicate that ζ-QVAE consistently learns representations that better utilize the capacity of the latent space and exhibits similar or better performance compared with

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Drivers of the Sustainability Performance of Induction Stove Conversion program in Indonesia

引用

International Journal of Sustainable Energy Planning and Management 2025年 43卷 5-30页

作者： Damayanti, Retno Wulan Safira, Silvia Dhea Laksono, Pringgo Widyo Setiadi, Haryono Entifar, Nisa Aqilla Ellenahaya Industrial Engineering Study Program Sebelas Maret University Ir.Sutami 36A Surakarta57121 – 57162 Indonesia Center of Technology Development and Industrial Collaboration Institute for Research and Community Service Sebelas Maret University Ir.Sutami 36A Surakarta57121 – 57162 Indonesia Informatics and Science Data Study Program Sebelas Maret University Ir.Sutami 36A Surakarta57121 – 57162 Indonesia Smart Green Technology Engineering Department Pukyong National University 45 Yongso-ro Nam-Gu Busan Korea Republic of

In 2022, Indonesia initiated a pilot project to transition from liquid petroleum gas (LPG) stoves to induction stoves, targeting 8.2 million households by 2025. While LPG is considered a clean cooking fuel by the World Health Organization due to its low PM2.5 emissions, this program aims to further reduce CO2 emissions from cooking activities, aligning with Indonesia’s clean energy transition and 2060 Net Zero Emission goals. Throughout the program, doubts and criticisms arose among various sectors of society, particularly concerning the sustainability of this program. This research aims to determine and analyze the driving factors that support the sustainability of the induction stove transition program. Five sustainability aspects, namely, economic, social, environmental, technical, and institutional, were analyzed. A total of 315 Indonesian citizens participated as respondents in this research survey. The Partial Least Squares-Structural Equation Model (PLS–SEM) method was utilized as the analytical approach for the study. The results revealed that nine factors significantly influenced program sustainability, with the strongest impacts from technology costs (path coefficient = 0.859), contextual factors (0.803), electrical infrastructure (0.792), and community perception (0.773). Economic sustainability was driven by technology costs and business opportunities (0.643), while environmental sustainability was strongly influenced by electrical infrastructure. Post-installation support (0.307) and financial management (0.391) significantly impacted technical and institutional sustainability respectively. These empirical findings improve previous research on the sustainability of an energy transition program, which provides insights for researchers and stakeholders in the energy management field, especially in developing countries, for policy determination and decision-making. © 2025, Aalborg University Press. All rights reserved.

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

Edit-A-Video: Single Video Editing with Object-Aware Consistency

arXiv

引用

arXiv 2023年

作者： Shin, Chaehun Kim, Heeseung Lee, Che Hyun Lee, Sang-Gil Yoon, Sungroh Data Science and AI Lab ECE Seoul National University Seoul08826 Korea Republic of Data Science and AI Lab ECE and Interdisciplinary Program in AI Seoul National University Seoul08826 Korea Republic of

With advancements in text-to-image (TTI) models, text-to-video (TTV) models have recently been introduced. Motivated by approaches on TTV models adapting from diffusionbased TTI models, we suggest the text-guided video editing framework given only a pretrained TTI model and a single pair, which we term Edit-A-Video. The framework consists of two stages: (1) inflating the 2D model into the 3D model by appending temporal modules and tuning on the source video (2) inverting the source video into the noise and editing with target text through attention map injection. Each stage enables the temporal modeling and preservation of semantic attributes of the source video. One of the key challenges for video editing is a background inconsistency problem, where the regions unrelated to the edit suffer from undesirable and inconsistent temporal alterations. To mitigate this issue, we also introduce a novel mask blending method, termed as temporal-consistent blending (TC Blending). We improve previous mask blending methods to reflect the temporal consistency, ensuring that the area where the editing is applied exhibits smooth transition while also achieving spatio-temporal consistency of the unedited regions. We present extensive experimental results over various types of text and videos, and demonstrate the superiority of the proposed method compared to baselines in terms of background consistency, text alignment, and video editing quality. Our samples are available on https://***. © 2023, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Fitness Landscape Optimization Makes Stochastic Symbolic Search By Genetic programming Easier

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Huang, Zhixing Mei, Yi Zhang, Fangfang Zhang, Mengjie Banzhaf, Wolfgang Victoria University of Wellington Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand Michigan State University BEACON Center for the Study of Evolution in Action and Ecology Evolution and Behavior Program Department of Computer Science and Engineering East LansingMI48864 United States

Searching for symbolic models plays an important role in a wide range of domains such as neural architecture search and automatic program synthesis. Genetic programming is a promising stochastic method for searching effective symbolic models within an acceptable time. The genetic programming performance is closely related to the hardness of the fitness landscape. A better fitness landscape with less local optima normally implies that it is easier to search for better solutions. In recent years, there have been many studies enhancing genetic programming performance by forming better fitness landscapes. However, the better design of the fitness landscape highly relies on specific domain knowledge and consumes a lot of expert effort. This paper proposes a fitness landscape optimization method to automatically design better fitness landscapes for genetic programming search than the manually designed ones. We optimize the landscapes by optimizing the neighborhood structures of symbolic solutions. We verify the effectiveness of the proposed method in both supervised learning and combinatorial optimization problems. The results show that the proposed method significantly reduces the hardness of fitness landscapes. By simply searching against the automatically optimized fitness landscapes, a genetic programming method can have a very competitive performance with state-of-the-art methods. © 1997-2012 IEEE.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Accurate and precise quantum computation of valence two-neutron systems

引用

Physical Review C 2024年第6期109卷 064305-064305页

作者： Sota Yoshida (吉田聡太) Takeshi Sato (佐藤健) Takumi Ogata (緒方拓巳) Tomoya Naito (内藤智也) Masaaki Kimura (木村真明) Institute for Promotion of Higher Academic Education School of Data Science and Management for Accelerator-based Science RIKEN Wako 351-0198 Japan Graduate School of Engineering Photon Science Center School of Engineering Research Institute for Photon Science and Laser Technology RIKEN Interdisciplinary Theoretical and Mathematical Sciences Program (iTHEMS) RIKEN 2-1 Hirosawa Wako 351-0198 Japan Department of Physics Graduate School of Science

Developing methods to solve nuclear many-body problems with quantum computers is an imperative pursuit within the nuclear physics community. Here, we introduce a quantum algorithm to accurately and precisely compute the ground state of valence two-neutron systems leveraging presently available noisy intermediate-scale quantum devices. Our focus lies on the nuclei having a doubly magic core plus two valence neutrons in the p, sd, and pf shells, i.e., He6, O18, and Ca42, respectively. Our ansatz, quantum circuit, is constructed in the pair-wise form, taking into account the symmetries of the system in an explicit manner, and enables us to reduce the number of qubits and the number of CNOT gates required. The results on a real quantum hardware by IBM Quantum Platform show that the proposed method gives very accurate results of the ground-state energies, which are typically within 0.1% error in the energy for He6 and O18 and at most 1% error for Ca42. Furthermore, our experiments using real quantum devices also show the pivotal role of the circuit layout design, attuned to the connectivity of the qubits, in mitigating errors.

关键词： Nuclear many-body theory Quantum simulation Shell model

来源：评论

学校读者我要写书评

暂无评论

Yale at "Discharge Me!": Evaluating Constrained Generation of Discharge Summaries with Unstructured and Structured Information 23

Yale at "Discharge Me!": Evaluating Constrained Generation o...

引用

23rd Meeting of the ACL Special Interest Group on Biomedical Natural Language Processing, BioNLP 2024

作者： Socrates, Vimig Huang, Thomas Ai, Xuguang Fereydooni, Soraya Chen, Qingyu Taylor, R. Andrew Chartash, David Department of Biomedical Informatics and Data Science Yale University School of Medicine United States Department of Emergency Medicine Yale School of Medicine United States Program of Computational Biology and Bioinformatics Yale University United States School of Medicine University College Dublin National University of Ireland Dublin Ireland

ISBN: (纸本)9798891761308

In this work, we propose our top-ranking (2nd place) pipeline for the generation of discharge summary subsections as a part of the BioNLP 2024 Shared Task 2: "Discharge Me!". We evaluate both encoder-decoder and state-of-the-art decoder-only language models on the generation of two key sections of the discharge summary. To evaluate the ability of NLP methods to further alleviate the documentation burden on physicians, we also design a novel pipeline to generate the brief hospital course directly from structured information found in the EHR. Finally, we evaluate a constrained beam search approach to inject external knowledge about relevant patient problems into the text generation process. We find that a BioBART model fine-tuned on a larger fraction of the data without constrained beam search outperforms all other models.. ©2024 Association for Computational Linguistics.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Synergetic effects of multiple junction and surface hydroxyl in Cu/CuO/Cu2O/TiO2 heterostructures towards highly efficient photocatalysts for hydrogen generation

引用

Materials science for Energy Technologies 2025年 8卷 131-142页

作者： Subagyo, Riki Anindika, Garcelina Rizky Aufkani, Afif Akmal Zhang, Lei Ardhyananta, Hosta Burhan, R.Y. Perry Nugraheni, Zjahra Vianita Akhlus, Syafsir Bahruji, Hasliza Prasetyoko, Didik Wellia, Diana Vanda Ivansyah, Atthar Luqman Arramel Kusumawati, Yuly Department of Chemistry Faculty of Science and Analytic Data Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia Center of Excellence Applied Physics and Chemistry Nano Center Indonesia Jl PUSPIPTEK South Tangerang Banten15314 Indonesia Department of Physics National University of Singapore Singapore117551 Singapore Department of Materials and Metallurgical Engineering Faculty of Industrial Technology and Systems Engineering Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia Centre of Advanced Material and Energy Science Universiti Brunei Darussalam Jalan Tungku Link BE 1410 Brunei Department of Chemistry Faculty of Mathematics and Natural Sciences Universitas Andalas Padang25163 Indonesia Master Program in Computational Science Faculty of Mathematics and Natural Science Institut Teknologi Bandung Jalan Ganesha No. 10 Bandung40132 Indonesia Instrumentation and Computational Physics Research Group Department of Physics Faculty of Mathematics and Natural Sciences Institut Teknologi Bandung Jalan Ganesha No.10 West Java Bandung40132 Indonesia

The implementation of titanium dioxide (TiO2) as a photocatalyst material in hydrogen (H2) evolution reaction (HER) has embarked renewed interest in the past decade. Rapid electron-hole pairs recombination and wide band gap of a photo-sensitive material of TiO2 are detrimental toward the targeted catalytical reaction. In this study, we present the rational design, fabrication, photocatalytic performance of TiO2-Cu/CuO/Cu2O heterostructures (CuTi) using viable chemical reduction method. The Z-scheme and S-scheme are succesfully generated across the TiO2/CuO/Cu2O interfaces, while the Schottky junction arises on the Cu perimeters. This is evidenced from the blue shifted about 0.3 eV of Cu 2p core level determined by using X-ray photoemission spectroscopy (XPS), in combination with the formation of inverse V-shape of the Mott-Schottky plots. In addition, we find that Cu/CuO/Cu2O facilitates photon absorption range up to the visible region. The multiple heterojunction and the large number of OHsurface enhanced charge carrier transfer are associated to the suppression of photoluminescence (PL) intensity, high surface hydroxyl (OHsurface) density in CuTi probed by XPS, and fast electron transfer based on the electrochemical measurements. The presence of OHsurface inhibits the recombination of electron. A significant H2 photogeneration rate enhancement is achieved when an optimized 5 wt% Cu/CuO/Cu2O concentration is used on TiO2 to achieve 7,157.19 μmol·g−1 (1,789.30 μmol·g−1·h−1). Based on this finding, zero emission energy innitiative could be materialized under multiple heterojunctions in photocatalytic process is beneficial for enhancing the H2 production. © 2025 The Authors

关键词： Titanium dioxide

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approach for Single Nucleotide Polymorphism Selection in Genetic Testing Results

引用

Procedia Computer science 2023年 227卷 46-54页

作者： Joko Pebrianto Trinugroho Alam Ahmad Hidayat Mahmud Isnan Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Department of Mathematics School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta 11480 Indonesia

Lactose intolerance is a type of digestive problem that may threaten the population because milk and dairy products compose of nutrients that are essential for human body. Genetic tests possess a great potential to detect lactose intolerance as it can be used in children and even infants. However, a new approach to analyze the genetic test results is needed to elucidate the Single Nucleotide Polymorphisms (SNPs) that are related to lactose intolerance. In this work, we utilized the machine learning based feature selection to select the SNPs associated with lactose tolerance trait from genotyping samples of direct-to-customer (DTCG genetic tests, obtained from the public database. Recursive Feature Elimination (RFE) with XGBoost model was used to perform feature selection. We also compared three different models, such as XGBoost, support vector machine (SVM), and random forest (RF) for training the selected features. Our findings revealed that 20 SNPs (out of 3501) were chosen, with rs4394668 as the most important variables (F-score 0.009). Furthermore, when compared to the RF and SVM models, the XGBoost model had the highest accuracy (0.87). Further studies should be undertaken to elucidate how the selected SNPs may lead to the lactose intolerance trait.

关键词： lactose intolerance SNP genetic test feature selection

来源：评论

学校读者我要写书评

暂无评论

Vision-Language Models for Autonomous Driving: CLIP-Based Dynamic Scene Understanding

arXiv

引用

arXiv 2025年

作者： Elhenawy, Mohammed Ashqar, Huthaifa I. Rakotonirainy, Andry Alhadidi, Taqwa I. Jaber, Ahmed Tami, Mohammad Abu CARRS-Q and Centre for Data Science Queensland University of Technology Kelvin GroveQLD4059 Australia Data Science and AI Department Arab American University P.O Box 240 Jenin Palestine Artificial Intelligence Program Fu Foundation School of Engineering and Applied Science Columbia University New YorkNY10027 United States

Scene understanding is essential for enhancing driver safety, generating human-centric explanations for Automated Vehicle (AV) decisions, and leveraging Artificial Intelligence (AI) for retrospective driving video analysis. This study developed a dynamic scene retrieval system using Contrastive Language–Image Pretraining (CLIP) models, which can be optimized for real-time deployment on edge devices. The proposed system outperforms state-of-the-art in-context learning methods, including the zero-shot capabilities of GPT-4o, particularly in complex scenarios. By conducting frame-level analysis on the Honda Scenes dataset, which contains a collection of about 80 hours of annotated driving videos capturing diverse real-world road and weather conditions, our study highlights the robustness of CLIP models in learning visual concepts from natural language supervision. Results also showed that fine-tuning the CLIP models, such as ViT-L/14 and ViT-B/32, significantly improved scene classification, achieving a top F1-score of 91.1%. These results demonstrate the ability of the system to deliver rapid and precise scene recognition, which can be used to meet the critical requirements of Advanced Driver Assistance Systems (ADAS). This study shows the potential of CLIP models to provide scalable and efficient frameworks for dynamic scene understanding and classification. Furthermore, this work lays the groundwork for advanced autonomous vehicle technologies by fostering a deeper understanding of driver behavior, road conditions, and safety-critical scenarios, marking a significant step toward smarter, safer, and more context-aware autonomous driving systems. © 2025, CC BY.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：