检索结果-内蒙古大学图书馆

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Teja, Nv Sai Kumar, Kuldeep Malarvel, Muthukumaran Hindustan Institute of Technology and Science Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350375190

This research work introduces MLTE - Multilingual Text Enhancer, a text enhancement model developed primarily to the enhance input text for text-to-image generation models. The existing text encoders in image generation models often have limited capabilities, and the quality of image generation depends on the prompt. If the prompt includes misspelled words, the encoder will create an irrelevant image. Most encoders are primarily based on English. MLTE effectively addresses multilingual prompts, misspelled words, overly verbose prompts, and creatively enhances the prompt to achieve improved results. MLTE employs sophisticated natural language processing algorithms to establish a link between unprocessed textual input and the production of highly precise visual content. MLTE is based on LLaMA2, which has the ability to handle numerous languages and enables the simple incorporation of content from diverse linguistic origins. Additionally, its spellchecking and correction functions ensure the quality and coherence of the prompt. Moreover, MLTE's scene and text augmentation features strengthen the visual richness and coherence of generated photos, thereby enhancing their overall quality and realism. Its summarizing capability condenses large paragraphs into concise yet helpful summaries, which assisting the image creation process by delivering more focused inputs. MLTE can be used with any text to image generating models. By undertaking empirical evaluation, this paper demonstrates the effectiveness of MLTE in boosting text quality for text-to-image synthesis tasks, leading to significantly improved image generation results. © 2024 IEEE.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

IWSLT 2024 Indic Track system description paper: Speech-to-Text Translation from English to multiple Low-Resource Indian Languages 21

IWSLT 2024 Indic Track system description paper: Speech-to-T...

引用

21st International Conference on Spoken Language Translation, IWSLT 2024

作者： Singh, Deepanjali Anand, Ayush Chaturvedi, Abhyuday Baliyan, Niyati Department of Computer Engineering National Institute of Technology Haryana Kurukshetra136118 India

ISBN: (纸本)9798891761414

Multi-Language Speech-to-Text Translation (ST) plays a pivotal role in bridging linguistic barriers by converting spoken language into written text across different languages. This project aims to develop a robust ST model tailored for low-resource Indian languages, specifically targeting the Indo-Aryan and Dravidian language families. The dataset used consists of speeches from conferences and TED Talks, along with their corresponding transcriptions in English (source language) and translations in Hindi, Bengali, and Tamil (target languages). By tackling the lack of data and disparities in attention within low-resource languages, the paper strives to create an efficient ST system capable of real-world deployment. Additionally, existing resources in related languages are leveraged and word-level translation resources are explored to enhance translation accuracy. ©2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Stock Market Prediction 2

Deep Learning for Stock Market Prediction

引用

2nd International Conference Computational and Characterization Techniques in engineering and Sciences, IC3TES 2024

作者： Raavihemalatha GodiAmulya Sailalitha, Ch.S.N. Vishnu Institute of Technology Department of Computer Science & Engineering Bhimavaram534202 India

ISBN: (纸本)9798350364699

This study investigates the operation of deep literacy methods to prognosticate stock request movements. The purpose of this investigation is to improve the delicacy of soothsaying and the decision-making processes they include. Exercising advanced neural network infrastructures, such as convolutional and intermittent networks, the study examines the usefulness of these networks in analyzing literal stock data and relating patterns that are reflective of future price developments. To capture both time dependencies and complicated request signals, the investigation incorporates several deep literacy models, which are analogous to Long Short-Term Memory (LSTM) networks and Motor infrastructures. In this research, the prophetic performance of these models is evaluated by conducting rigorous backtesting on real-world stock data. The results of this evaluation are compared with standard statistical and machine literacy methodologies. Deep literacy models have been shown to give considerable advancement, as demonstrated by the results, which emphasize their potential for providing practical perceptivity and strategic advantages in stock trading. Through the validation of the capacities of deep literacy in the management of the problems of fiscal request vaticination, this study contributes to the expanding field of fiscal analytics. © 2024 IEEE.

关键词： data analytics deep learning Financial forecasting LSTM machine learning market analysis neural networks predictive modeling Transformer models

来源：评论

学校读者我要写书评

暂无评论

Apple Leaf Disease Prediction Using modified YOLOv8 Algorithm

Apple Leaf Disease Prediction Using modified YOLOv8 Algorith...

引用

2024 International Conference on Integrated Circuits, Communication, and Computing Systems, ICIC3S 2024

作者： Tamana Sharma, Sangeeta National Institute of Technology Department of Computer Science and Engineering HP Hamirpur India

ISBN: (数字)9798350364088

ISBN: (纸本)9798350364088

Apple orchards face formidable challenges in disease management, with black rot, apple scab, and cedar apple rust being prominent fungal adversaries. Dealing with such an apple orchard disease are no small feat. This study introduces a sophisticated methodology to accurately spot and classify these diseases using the YOLOv8 model. The YOLOv8 model is fine-tuned, tweaking specific parts to make it more responsive to the unique traits of black rot, apple scab, and cedar apple rust leveraging in the PlantVillage dataset. The YOLOv8 model represents a better evolution within the YOLO series, developed to increase the detection speed while maintaining a great level of accuracy. The architecture consists of numerous convolutional layers, which enable feature extraction from input images, resulting in pinpoint accuracy in disease identification, the model undergoes end-to-end training, and it acquires the ability to learn from input data, improving its predictive performance for leaf disease instances, boosting an impressive accuracy rate of 99.5 %, demonstrating its ability to pinpoint and categorize apple leaf diseases with exceptional precision. Additionally, the model showcases a strong recall rate of 97.43%, confirming its effectiveness in accurately identifying instances of the targeted diseases. The outstanding accuracy and recall rates highlight the potential of our improved YOLOv8 model as a crucial asset in monitoring and controlling fungal infections impacting apple crops using artificial intelligence. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing–Based UAV Imaging in Heat Pattern Analysis Impact on Climate Change Detection Using Fuzzy Stacked Lasso Elastic-Net Model

引用

Remote Sensing in Earth Systems Sciences 2024年第4期7卷 699-708页

作者： Sailaja, M. Kumar, M. Prema Jyothi, B. Swarna Vanguri, G. L. Narasamba Manjula, S. Priya, D. Divya Department of Computer Science and Engineering Ravindra College of Engineering for Women Andhra Pradesh Kurnool India Dept. of ECE Shri Vishnu Engineering College for Women (A) Andhra Pradesh Bhimavaram 534202 India Department of Computer Science & amp Engineering Madanapalle Institute of Technology & amp Science Andhra Pradesh Madanapalle India Information Technology Aditya College of Engineering & amp Technology(A) Andhra Pradesh Surampalem 533437 India Department of Computer Science and Business Systems Nehru Institute of Engineering and Technology Coimbatore India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

Urban heat islands raise surface temperatures, which has an effect on city dwellers’ health and welfare. Urbanisation-related changes to the land surface, which are especially notable right after sunset, have an impact on radiative forcing. Recently, there has been a surge in the usage of unmanned aerial vehicle (UAV) technology, particularly for precision agriculture and plant phenotyping. This is due to the declining cost and increased accessibility of both UAVs and thermal imaging sensors. This interruption affects subsequent operations like target item categorisation and water quality parameter inversion. The goal of this study was to evaluate the potential for combining machine learning (ML) with unmanned aerial vehicle (UAV)–based imaging technology. In this research, the novel technique in UAV image–based temperature pattern detection of various regions of earth and their sea level rise analysis using image classification by machine learning model. Here, the input is collected as UAV images which have been processed for noise removal and normalisation. These image features have been extracted using convolutional active contour–based kernel component analysis and classified using region-based fuzzy stacked lasso elastic-net model. The classified output shows temperature analysis with sea level rise based on image analysis. The experimental analysis has been carried out for various UAV image dataset in terms of detection accuracy, RMSE, F-measure, mean average precision (MAP), and recall. Proposed technique F-measure of 89%, detection accuracy of 96%, MAP of 94%, recall of 92%, and RMSE of 60%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Convolutional active contour Heat pattern detection Kernel component analysis Lasso elastic-net model Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Point spread function modeling and engineering in black-box lens systems

引用

Optics Express 2025年第3期33卷 4211-4224页

作者： Xiao, Dafei Kedem, Reut Orange Shechtman, Yoav Russell Berrie Nanotechnology Institute Technion–Israel Institute of Technology Haifa Israel Faculty of Biomedical Engineering Technion–Israel Institute of Technology Haifa Israel Faculty of Electrical and Computer Engineering Technion–Israel Institute of Technology Haifa Israel

Point spread function (PSF) engineering in an imaging system involves the introduction of additional optical components to efficiently encode object information. It typically relies on a well-established mapping relation between object space, PSF engineering plane, and image plane. However, this reliance can limit its application in imaging systems with unknown ("black box") attributes, e. g. commercial photographic lenses, where a theoretical imaging model is not readily available. To address this limitation, we conduct wave-optics analysis of general lens systems, explicitly derive a general imaging model based on scaled Fourier transform, and develop an overall pipeline for automatic parameter determination of the model. When applied to a photographic lens, this pipeline demonstrates high PSF modeling accuracy, showcasing the capability of "seeing what you design". We then implemented PSF engineering in this lens to find its optimal PSF for 3D localization. This work improves computational imaging by enabling accurate wavefront shaping design in arbitrary imaging systems. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Optical transfer function

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis for Citizen Feedback in Smart Cities with XLNet-BiLSTM: Delhi Metro as a Case Study★ 3

Sentiment Analysis for Citizen Feedback in Smart Cities with...

引用

3rd International Symposium on Smart Cities Challenges Technologies and Trends Technologies, SCCTT 2024

作者： Shukla, Vaibhav Kuanr, Dibyalochan Juneja, Shallu Sharma, Ajit K. Department of Computer Science and Engineering Maharaja Agrasen Institute of Technology Delhi India

In recent years, smart cities have increasingly recognized the importance of citizen input in enhancing public services and optimizing urban infrastructure. As urban populations grow and services become more complex, understanding resident sentiments and opinions is crucial for effective governance. Sentiment analysis, a technique rooted in natural language processing (NLP), serves as a powerful tool for gauging public opinion on urban services, particularly public transportation. This paper presents a sentiment analysis framework using an advanced XLNet-Bidirectional Long Short-Term Memory (BiLSTM) model, developed with a custom dataset of citizen reviews related to the Delhi Metro, a key element of India’s public transportation. The dataset was meticulously scraped from various platforms and manually labeled for accuracy. Initially, the model was trained on the IMDb dataset, achieving an impressive accuracy of 93.1%. It was then evaluated on the Delhi Metro dataset, yielding an accuracy of 1.00. However, this high accuracy may indicate overfitting due to the small dataset size, suggesting the findings are exploratory. This study highlights how sentiment analysis can improve decision- making and enhance public transportation services. By analyzing feedback on the Delhi Metro, city planners can identify areas for improvement and address citizen concerns. In conclusion, the paper underscores the potential of advanced sentiment analysis techniques in understanding public opinion and calls for further research with larger, more diverse datasets and refined models to assess citizen sentiment in smart cities comprehensively. © 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Mass transportation

来源：评论

学校读者我要写书评

暂无评论

CodeSense: Code Summarizer for JavaScript

CodeSense: Code Summarizer for JavaScript

引用

2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2024

作者： Vikram, K.R. Balaji, J. Vishnu Vani, V. Karthik, N. National Institute of Technology Puducherry Department of Computer Science and Engineering Karaikal India

ISBN: (纸本)9798331540685

In many software projects, especially large and complex ones, there often exists a significant gap in documentation. This can lead to a lack of understanding among developers, especially when they encounter unfamiliar code or need to debug and maintain legacy systems. By building a code summarizer model, developers can automatically generate concise and informative summaries for different sections of code. These summaries serve as on-demand documentation, providing clear explanations of the code's purpose and functionality, making it easier for developers to navigate, maintain, and extend the codebase. So, for making the job for the developers simple we have built this code summarizer model which will help the developers to understand the purpose and functionality of different parts of the code. Automatically generated comments can serve as an initial draft for code documentation, making it easier to keep documentation up to date. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Silent Alert: Advancing Women's Security through Smart Sign Recognition and AI

Silent Alert: Advancing Women's Security through Smart Sign ...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Senthilkumar, Dheeptha Bhavana, Lone Ranjana, P. Hindustan Institute Of Technology And Science Department Of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350364828

In today's world, many technologically innovative solutions are developed to prioritize women's safety solutions, especially during nighttime. This research's main aim is to focus on addressing crucial safety issues like emergencies and harassment in public spaces. To build an efficient model the proposed system uses technologies like MediaPipe and machine learning algorithms like random forest, decision tree, support vector machine (SVM), gaussian naive bayes, k-nearest neighbor (KNN), gradient boosting and stacking classifier (hybrid model). Rigorous testing ensures the selection of the most effective model, assessed through metrics like F1 score, precision, and recall. By integrating technology and machine learning, apart from raising awareness and fostering safe environments the proposed work also aims to empower women and enhance their safety. MediaPipe significantly enhances the accuracy of sign language recognition and also plays a vital role in improving the system's effectiveness. At the same time, OpenCV enables real-time video capture for comparison with the trained model. To enhance the system, predictions are made based on the recognized sign language gestures. In the system, predictions are improved by analyzing recognized sign language gestures. It also incorporates a database matching system that activates an alarm and sends a mail with a screenshot upon detecting predefined gestures. This function ensures prompt notifications, enabling authorities to respond promptly to identified incidents concerning women's safety. The system's ability to instantly recognize and react to specific gestures makes it an effective tool for addressing safety issues for women. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Demystifying XAI: Understanding of Applications, Limitations, Challenges, and Future Perspectives

Demystifying XAI: Understanding of Applications, Limitations...

引用

2024 International Conference on Advances in Computing Research on Science engineering and technology, ACROSET 2024

作者： Varshney, Pratham Singh Rathore, Narendra Pal Sethi, Kamal Kumar Rajput, Shiv Shankar Acropolis Institute of Technology and Research Department of Computer Science and Engineering Indore India

ISBN: (纸本)9798350388800

Artificial Intelligence (AI) appears to be omnipresent, but its usability is currently a pain point as seen with automation bias. The General Data Protection Regulation (GDPR) has started solving this problem. The premise behind Explainable AI (XAI) is described as making AI decisions interpretable, gaining user trust and robustness of applications in healthcare and finance. This paper gives a survey of recent XAI advancements, providing types of algorithms, and examples of tasks. Despite the concept of XAI, we still have the black-box issue of AI, and especially in critical areas like healthcare with sensitive information, we need to protect user privacy. It is proposed that XAI can expose the decision-making process of the AI, to make the AI decision-making more reliable and trustworthy. Evaluation metrics and potential future directions for XAI are discussed, with a guiding principle: AI needs to be ethical, trustworthy, and user-friendly. © 2024 IEEE.

关键词： Decentralized finance

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：