检索结果-内蒙古大学图书馆

8th International Conference on Natural Language Processing and Information Retrieval, NLPIR 2024

作者： Kuo, Yi-Hsuan Chang, Hsien-Tsung Department of Computer Science and Information Engineering Chang Gung University Taoyuan China Bachelor Program in Artificial Intelligence Chang Gung University Taoyuan China

ISBN: (纸本)9798400717383

This study presents a novel approach to analyzing and reconstructing AI-generated images using BLIP2 and CLIP models, focusing on a dataset of 268,000 Midjourney-generated images and prompts. We introduce a multi-level feature classification system encompassing 11 categories and 1,100 features, and employ BLIP2 for descriptive text generation and CLIP for feature similarity analysis. Our methodology involves image pre-processing, custom feature extraction, and image reconstruction under various conditions. The effectiveness of our approach is demonstrated through similarity scores between original and reconstructed images, ranging from 68.15 to 71.25 across different feature extraction conditions. This research contributes to the fields of natural language processing and information retrieval by offering insights into AI-generated image analysis, proposing new methods for feature extraction and reconstruction, and suggesting avenues for improving image generation models and multi-modal understanding. © 2024 Copyright held by the owner/author(s).

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Unified IoT-based Smart Home System: Integration of Security and Convenience Features for Consumer

A Unified IoT-based Smart Home System: Integration of Securi...

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： Moslema Hoque Oeishee Munyem Ahammad Muyeed Mishkat Alvi Md. Rejoan Mehedi Md. Shariar Emon Shaikat Md Nayan Molla Electrical and Electronic Engineering Department Brac University Dhaka Bangladesh Computer Science and Engineering Department United International University Dhaka Bangladesh Computer Science and Engineering Department Brac University Dhaka Bangladesh

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

Home automation is growing rapidly in the Fourth Industrial Revolution (4IR), providing users with unwavering convenience and enhanced security. This paper presents a comprehensive Internet of Things (IoT) smart home automation solution with a focus on energy management, user-friendliness, and security. Our system includes real-time integrated dashboards accessible via web and mobile interfaces, smart irrigation for indoor gardening, passkeys for door security, voice commands, fingerprint access, night security lighting, and morning alarms. The hardware consists of an Arduino MEGA microcontroller, various sensors (smoke, temperature, humidity, and soil), an ESP Wi-Fi module for connectivity, and additional components. The system demonstrated a satisfactory effectiveness level with an accuracy of 78% based on various tests. The voice assistant bot and accessible dashboard significantly improve user experience. Despite the complexity of home automation processes, increased affordability and accessibility are the aims of this paper. Future work will focus on enhancing real-time capabilities, integrated circuits, data security, and web-based functionalities to improve system performance, scalability, and user accessibility.

关键词： Temperature sensors Costs Accuracy Data security Smart homes Real-time systems Hardware Internet of Things Intelligent sensors Wireless fidelity

来源：评论

学校读者我要写书评

暂无评论

AI-driven EEG neuroscientific analysis for evaluating the influence of emotions on false memory

Neuroscience Informatics

引用

Neuroscience Informatics 2025年第2期5卷 100201-100201页

作者： Mahalakshmi, V. Department of Computer Science College of Engineering and Computer Science Jazan University Jazan Saudi Arabia

Investigating the brain mechanisms behind memory processing depends on an awareness of how emotions influence false memory. This study used AI-driven EEG microstate analysis to investigate how emotions affect the generation of false memories from both a temporal and a geographic perspective. Within emotional groups, AI-augmented computational models showed distinct brain processing patterns, particularly during the recall processing stage. By altering cognitive processing dynamics, these results support the hypothesis that AI-enhanced brain activity analysis can effectively mimic the influence of emotional states on the formation of false memories. This work explores emotional implications on false memory by combining artificial intelligence (AI) with EEG-based microstate analysis, therefore offering greater understanding of brain dynamics at several cognitive phases. EEG data collected under various emotional states were analyzed using AI-powered techniques to enable exact extraction of microstate templates (Microstates 1–5) for every emotional group. Phase-locked value (AI-PLV) brain functional networks were built inside microstates displaying notable temporal coverage variations. Driven by artificial intelligence, temporal and geographical analysis of EEG signals revealed different brain processing mechanisms among emotional groupings. The group with pleasant emotions showed continuous activity in prefrontal Microstates 3 and 5, therefore suggesting improved cognitive processing. Reflecting a concentration on information integration, the neutral group showed extended involvement in central-active Microstates 3 and 4. These results emphasize how artificial intelligence is helping neuroscientific research to progress by offering a strong framework for comprehending AI-driven emotional-based aberrations in memory recall. © 2025 The Author(s)

关键词： Artificial intelligence EEG Emotions False memory Microstates Neuroscience Phase-locking value

来源：评论

学校读者我要写书评

暂无评论

Different architectures of thin film bilayers based on TiO2 and CuO for green hydrogen generation

引用

International Journal of Hydrogen Energy 2025年 136卷 1073-1085页

作者： Banaś-Gac, Joanna Radecka, Marta Llobet, Eduard Partyka-Jankowska, Ewa Zakrzewska, Katarzyna Faculty of Computer Science Electronics and Telecommunications AGH University of Krakow Krakow Poland Faculty of Materials Science and Ceramics AGH University of Krakow Krakow Poland Department of Electronic Electrical and Automatic Engineering Rovira i Virgili University Tarragona Spain SOLARIS National Synchrotron Radiation Centre Jagiellonian University Krakow Poland

Green hydrogen becomes one of the most important of all other forms due to ecological issues, described in directives requiring the transformation to energy sources with the lowest possible carbon footprint. The application of the PhotoElectrochemical Cell where hydrogen is produced with the direct use of solar energy is the best solution. Bilayer and multilayered systems based on CuO, especially in combination with TiO2 seem to be the most frequently studied of all heterostructured nanomaterials when considering green hydrogen generation. The interface created between rough surface of CuO and smooth TiO2 surface ensures the highest photocurrent when the top layer is of about 150 nm. For CuO(top)/TiO2 heterojunction characterized by rough/rough interface, photoeletrochemical performance also improves with increasing thickness of the top layer up to 100 nm. The cathodic character of the photocurrent is observed for both TiO2(top)/CuO and CuO(top)/TiO2 bilayers. © 2025 The Authors

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Brain Tumor Diagnosis with Convolutional Neural Networks

引用

Procedia computer science 2025年 259卷 562-571页

作者： Aryan Singh Mohd Shuaib Manoj Diwakar Aditya Joshi Prabhishek Singh Neha Pandey Department of Computer Application Graphic Era Deemed to be University Dehradun 248001 India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun 248001 India School of Computer Science Engineering and Technology Bennett University Greater Noida 201310 India Department of Biotechnology Graphic Era Deemed to be University Dehradun 248001 India

Historically, the diagnosis of brain tumors from magnetic resonance imaging (MRI) images has been a careful and extended endeavor that relies heavily on the expertise of radiologists and neurologists. In addition to being time-consuming, the complex nature of brain image analysis makes it vulnerable to cognitive biases and human error, which can affect the precision and effectiveness of diagnosis. Moreover, manual MRI scan interpretation might result in discrepancies between practitioners, which makes diagnosis even more difficult. These difficulties highlight the need for innovative approaches to improve the accuracy and speed of brain tumor identification as the need for quicker and more accurate medical evaluations keeps rising. To meet these difficulties, an innovative method based on image-driven Convolutional Neural Networks (CNNs) has been developed. Meningiomas, pituitary, gliomas, and absence tumors are the four major brain cancer groups that this research focuses on. With the basis of the EfficientNetB3 framework which had been pre-trained on the large-scale ImageNet dataset, the model uses a transfer learning method using a brain tumor dataset of 7023 images by adding extra layers that are exclusively meant to enhance classification and improved performance. The proposed method secures a notable accuracy of 99.84% and a precision of 99.33%. This advanced approach not only improves diagnostic precision but also significantly reduces the time required for neurologists to examine scans, enabling them to focus more on patient care and the development of preventive strategies. The efficiency of the proposed model underlines that it can become a breakthrough in clinical diagnostics and stimulate the progress of medical disciplines’ development. For a comprehensive overview of the model architecture and implementation, please visit the GitHub repository https://***/Aryansin1234/*** . Additionally, a live demonstration of

关键词： Brain Tumor classification Deep Learning Convolutional Neural Network Transfer Learning Magnetic Resonance Imaging

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Solutions for Predictive Maintenance in Smart Transportation Systems

AI-Driven Solutions for Predictive Maintenance in Smart Tran...

引用

Computational, Communication and Information Technology (ICCCIT), International Conference on

作者： Sheela Hundekari Tanusha Mittal Amit Dutt Munugapati Bhavana Rakesh Kumar Ginni Nijhawan School of Computer Applications Pimpri Chinchwad University Pune Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Lovely Professional University Phagwara India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Telangana Department of Computer Engineering & Applications GLA University Mathura

ISBN: (数字)9798331512965

ISBN: (纸本)9798331512972

Predictive maintenance: A game changer in infrastructure and vehicle management, and able to cut maintenance expenses and downtime of smart transportation systems. This study explores ways in which smart transportation systems might use AI in order to plan maintenance schedules and forecast equipment breakdowns. Predictive algorithms, that can detect potential problems before raising to expensive repair or system breakdown, use real time sensor data from infrastructure and vehicles. Decision trees and neural networks are two of these models. By allowing AI driven solutions, transportation systems may transition from a reactive to a proactive maintenance practice which may support efficiency, safety, and reliability. Unsupervised learning methods are used to do anomaly detection for real time operations, and we examine the patterns in previous maintenance data with supervised learning approaches. The use of AI for predictive maintenance is also being studied for use in smart cities, where transportation networks are becoming more interconnected by IoT. The paper also considers challenges on data integration as well as the importance of scaling the algorithms and guaranteeing cybersecurity in these systems. Based on our research, smart transportation systems could benefit from AI to increase operational efficiency, reduce the cost of material and labor to maintain and repair equipment systems, and decrease the rate of disruptions.

关键词： Costs Electric breakdown Games Prediction algorithms Real-time systems Maintenance Smart transportation Internet of Things Unsupervised learning Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

An advanced attack categorization in NIDS using enhanced deep learning based EOptResfEANet methodology with hybrid feature extraction

引用

Cluster Computing 2025年第5期28卷 1-28页

作者： Moudiappa, Vinolia Alexander Nataraj, Kanya Rajavarman, Veeramalai Natarajan Department of Information Technology Dr. M.G.R. Educational and Research Institute Maduravoyal Tamil Nadu Chennai600095 India Department of Computer Science and Engineering Dr. M.G.R. Educational and Research Institute Maduravoyal Tamil Nadu Chennai600095 India

Every day, there are more and more intrusions, which result in numerous privacy violations, financial loss, and unauthorized information transfers, etc. While the hackers may concentrate on stealing private information, trade secrets, and confidential data to be sold to third parties for illicit profit, each type of intrusion has a specific task in mind. Limitations such as data lag on actual attacks and financial damages are caused by the false detection of assaults in the security and modifying environmental fields. Automatic abnormality detection techniques are needed to secure the necessary computing power and analyze the attacks. Therefore, this research paper proposes an effective automated detection system for intrusions utilizing a novel enhanced methodology. To address the low minority attack detection rate caused by the unbalanced training data, we employ Conditional Wasserstein GAN- Gradient Penalty (CWGAN-GP) technology to increase the minority samples. Next, the temporal features are retrieved using Res4Net, and the spatial characteristics are extracted using the Deep Concatenate Attention Augmented Convolution model (Deep CAC). With Res4Net efficiently modelling temporal dependencies and Deep CAC capturing intricate spatial patterns, this dual approach enables more accurate feature extraction. The Novel Quantized Salp Swarm Algorithm (NQSSA) is used to choose the key features. Finally, we employed a Novel Enhanced DL-based ResNet-fused External Attention Network (EResfEANet) for classifying attack categories, achieving superior categorization efficiency. Additionally, to further improve classification performance, hyperparameters were tuned using the Gooseneck Barnacle Optimization Algorithm (GBOA). The results from experimental verification on the proposed data sets demonstrate that applying oversampling techniques can enhance the detection rate of minority samples, increasing the overall accuracy rate. The proposed approach outperforms other current

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

AI-driven churn prediction in subscription services: addressing economic metrics, data transparency, and customer interdependence

引用

Neural Computing and Applications 2025年第14期37卷 8651-8676页

作者： Talaat, Fatma M. Aljadani, Abdussalam Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Faculty of Computer Science & Engineering New Mansoura University Gamasa35712 Egypt Department of Management College of Business Administration in Yanbu Taibah University Al-Madinah Al-Munawarah41411 Saudi Arabia

This study aims to improve customer churn prediction by integrating machine learning algorithms and evaluating their performance using criteria like accuracy, profit, and Customer Lifetime Value (CLV). Using a Telecom Customer Churn Prediction dataset, the study analyzes the efficiency of various models such as XGBoost, Linear Regression, Decision Tree Regressor, Lasso, Random Forest, and Gradient Boosting Regressor. This study introduces an Adaptive Profit-Centric Churn Prediction Engine (APCPE), an innovative churn prediction system that evaluates profitability and adapts to changing customer behavior. Each model’s accuracy, profit, and CLV are assessed, revealing that the proposed APCPE is the most accurate model, with a 97.01% accuracy rate, a profit of $606.3125, and a CLV of $1212.625. Convergence curves, including R2 convergence curves, show the model’s performance and convergence rates for each algorithm. Convergence curves, including R2 convergence curves, show the model’s performance and convergence rates for each algorithm. The study digs deeper into interdependence modeling, which involves finding and measuring consumer interactions or dependencies such as social network linkages and product co-occurrence. The study adds insights into modeling customer behavior dependencies and their impact on churn prediction, providing a holistic approach to improving corporate tactics for customer retention. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Reward invigorates isometric gripping actions

引用

Journal of Neurophysiology 2025年第4期133卷 1282-1294页

作者： Marbaker, Rachel M. Schmad, Ryan C. Al-Ghamdi, Razan A. Sukumar, Shruthi Ahmed, Alaa A. Department of Mechanical Engineering University of Colorado Boulder Boulder CO United States Department of Electrical Engineering University of Colorado Boulder Boulder CO United States Department of Computer Science University of Colorado Boulder Boulder CO United States Biomedical Engineering Program University of Colorado Boulder Boulder CO United States

Individuals exhibit a propensity to move faster toward more rewarding stimuli. Although this phenomenon has been observed in movements, the effect of reward on implicit control of isometric actions, such as gripping or grasping, is relatively unknown. How reward-related invigoration generalizes to other effortful actions is an important question. Reward invigorates reaching movements and saccades, supporting the idea that reward pays the additional effort cost of moving faster. Effort in isometric force generation is less understood, so here we ask whether and how reward-related invigoration generalizes to isometric force gripping. And if so, what implicit characteristics of gripping change when there is a prospect of reward? Participants (n = 19) gripped a force transducer and the force applied was mapped to radial position of an onscreen cursor. Each trial, a target appeared in one of four locations;increasing grip force moved the cursor toward the target. The gripping action was interchangeable for all target positions. In each block of 100 trials, one target was consistently rewarded, whereas the other targets were not. When gripping to acquire the rewarded target, participants reacted faster, generated force more rapidly and to a greater extent, without increasing variance and without increasing the rising force-time integral. These findings support the generalization of reward-related invigoration in isometric force tasks, and that the brain exquisitely trades-off reward and effort costs to obtain reward more rapidly without increasing variance and without more effort costs than necessary. NEW & NOTEWORTHY Gripping actions are important for day-to-day tasks, for medical diagnostics like strength and force control, and for choice selection in decision-making experiments. Comparing isometric gripping responses to reward and nonreward cues, we observed reward-based invigoration mediated by selective increases in effort. These findings can be leveraged to provide

关键词： decision making effort grasping movement vigor speed-accuracy tradeoff

来源：评论

学校读者我要写书评

暂无评论

Enhancing Financial Sentiment Analysis: Integrating the LoughranMcDonald Dictionary with BERT for Advanced Market Predictive Insights

引用

Procedia computer science 2025年 258卷 2244-2257页

作者： Sheetal R Prakash K. Aithal Department of Computer Science & Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal 576104 India Member of IEEE Department of Computer Science & Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal 576104 India

One critical aspect of financial markets is understanding investor sentiment to facilitate effective decision-making. This study integrates traditional sentiment analysis methods, such as the Loughran-McDonald (LM) dictionary— designed for financial sentiment—with advanced Natural Language Processing (NLP) techniques using Bidirectional Encoder Representations from Transformers (BERT). The LM dictionary provides domain-specific word lists to label sentiment, whereas BERT enhances this by capturing nuanced meanings and semantic relationships in financial texts. It involves pre-processing Financial NewsHeadlines, applying the LM dictionary for sentiment scoring, and finetuning a pretrained BERT model to classify sentiment. A PyTorch dataset was created, tokenized using BERT, and processed through the model using techniques like dropout regularization and cross-entropy loss for optimization. The hybrid approach yields promising results: a classification accuracy of 97%, precision of 0.98, recall of 0.93, and an F1 score of 0.95, confirming its effectiveness in capturing sentiment polarity. In addition, comparisons between dictionary-labelled and pre-annotated datasets demonstrate the model’s improved generalization ability. The results also show that our hybrid model outperformed various other existing models. This hybrid approach attempts to improve accuracy in capturing sentiment polarity by implementing methods to overcome imbalanced dataset, thereby facilitating a better understanding of sentiment in financial reports and facilitating informed decision-making. The integration of Named Entity Recognition (NER) with sentiment analysis based on sentiment polarity (positive, negative, or neutral) enables a more granular view of how specific companies are perceived in financial reports by highlighting the entities that are most affected by market sentiment.

关键词： Lexicon-based Analysis Sentiment Analysis NER Financial Reports Loughran-McDonald BERT Natural Language Processing

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：