检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhang, Pengcheng Yu, Xiaohan Bai, Xiao Zheng, Jin Ning, Xin School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Jiangxi Research Institute Beihang University Beijing China School of Computing Macquarie University Sydney Australia Institute of Semiconductors Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798400706868

The development of person search techniques has been greatly promoted in recent years for its superior practicality and challenging goals. Despite their significant progress, existing person search models still lack the ability to continually learn from increasing real-world data and adaptively process input from different domains. To this end, this work introduces the continual person search task that sequentially learns on multiple domains and then performs person search on all seen domains. This requires balancing the stability and plasticity of the model to continually learn new knowledge without catastrophic forgetting. For this, we propose a Prompt-based Continual Person Search (PoPS) model in this paper. First, we design a compositional person search transformer to construct an effective pre-trained transformer without exhaustive pre-training from scratch on large-scale person search data. This serves as the fundamental for prompt-based continual learning. On top of that, we design a domain incremental prompt pool with a diverse attribute matching module. For each domain, we independently learn a set of prompts to encode the domain-oriented knowledge. Meanwhile, we jointly learn a group of diverse attribute projections and prototype embeddings to capture discriminative domain attributes. By matching an input image with the learned attributes across domains, the learned prompts can be properly selected for model inference. Extensive experiments are conducted to validate the proposed method for continual person search. The source code is available at https://***/PatrickZad/PoPS. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A survey of machine learning techniques for detecting and diagnosing COVID-19 from imaging

引用

Quantitative Biology 2022年第2期10卷 188-207页

作者： Aishwarza Panday Muhammad Ashad Kabir Nihad Karim Chowdhury Department of Computer Science&Engineering Stamford UniversityDhaka 1217Bangladesh School of Computing and Mathematics Charles Sturt UniversityNSW 2795Australia Department of Computer Science&Engineering University of ChittagongChittagong 4349Bangladesh

Background: Due to the limited availability and high cost of the reverse transcription-polymerase chain reaction (RT- PCR) test, many studies have proposed machine learning techniques for detecting COVID-19 from medical imaging. The purpose of this study is to systematically review, assess and synthesize research articles that have used different machine learning techniques to detect and diagnose COVID-19 from chest X-ray and CT scan ***: A structured literature search was conducted in the relevant bibliographic databases to ensure that the survey solely centered on reproducible and high-quality research. We selected papers based on our inclusion ***: In this survey, we reviewed 98 articles that fulfilled our inclusion criteria. We have surveyed a complete pipeline of chest imaging analysis techniques related to COVID-19, including data collection, pre-processing, feature extraction, classification, and visualization. We have considered CT scans and X-rays as both are widely used to describe the latest developments in medical imaging to detect ***: This survey provides researchers with valuable insights into different machine learning techniques and their performance in the detection and diagnosis of COVID-19 from chest imaging. At the end, the challenges and limitations in detecting COVID-19 using machine learning techniques and the future direction of research are discussed.

关键词： COVID-19 machine learning deep learning detection classification diagnosing X-ray CT scan

来源：评论

学校读者我要写书评

暂无评论

Hidden Emotion Detection from Speech and Text Using Deep Learning Approach

Hidden Emotion Detection from Speech and Text Using Deep Lea...

引用

Network, Multimedia and Information Technology (NMITCON) International Conference on

作者： Ravula Tarun Reddy Suja Palaniswamy Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita VishwaVidyapeetham India

ISBN: (数字)9798350372892

ISBN: (纸本)9798350372908

—The value that comes from accurate detection and understanding human emotions stands across a ton of domains. This paper details a few well-tested models applied in a unique way for discovering hidden emotion through audio and text data with the help of a custom dataset. Every sample in the dataset has an audio snippet and a Q&A pair which tries to evoke a certain emotion. The main goal lies in creating a model that can identify emotional indicators from diverse data sources. To achieve this a custom dataset was developed. The audio samples have been annotated with descriptions of emotions, and their corresponding transcripts have been similarly labeled for enhanced clarity and were able to achieve 81.44% accuracy in identifying hidden emotions.

关键词： Deep learning Emotion recognition Accuracy Soft sensors Data models Information technology

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Recognition Using Machine Learning

Speech Emotion Recognition Using Machine Learning

引用

Innovative Practices in Technology and Management (ICIPTM), International Conference on

作者： Aman Kumar Vivek Kumar P Rajakumar School of Computing Science & Engineering Galgotias University UP India

In the field of human-computer interaction, identifying the emotions conveyed in a person's speech is a challenge that is both incredibly fascinating and challenging. Recent times have seen a significant uptick in people's interest in this topic. In the subject of speech emotion recognition, a wide variety of techniques have been applied in order to extract emotions from signals. These techniques include a number of well-known speech analysis and classification strategies. This paper provides an overview of the deep learning technique, which is based on a simple algorithm based on feature extraction and model creation that recognizes emotion. In the traditional method of speech emotion recognition, features are first extracted from the speech signals, then the features themselves are picked, collectively known as the selection module, and then the emotions are recognized.

关键词： Deep learning Emotion recognition Solid modeling Three-dimensional displays Speech analysis Speech recognition Feature extraction

来源：评论

学校读者我要写书评

暂无评论

CNN Based Handwritten Odia Character Recognition 1

CNN Based Handwritten Odia Character Recognition

引用

1st International Conference on Machine Learning, Computer Systems and Security, MLCSS 2022

作者： Panda, Rabinrayan Dash, Sachikanta Padhy, Sasmita Nayak, Mamata Computer Science and Engineering Giet University Odisha Gunupur India School of Computing Science and Engineering Vit Bhopal University MP Bhopal India Computer Science and Engineering Soa University Odisha Bhubaneswar India

ISBN: (纸本)9781665454933

Odia is a 44 million-strong Indo-Aryan language spoken mostly in Odisha, India. Some characters are made up of many symbols that are linked together. Because of its vast variety of applications, Handwritten Character Recognition (HCR) is critical in Optical Character Recognition (OCR) and Pattern Recognition (PR). HCR is employed in fields such as bank checks, medical prescriptions, and tax returns, and contributes greatly to the spread of automation. Handwritten characters are substantially more difficult to discern than printed characters since different people have different writing styles. Character recognition technology may be used to scan a wide range of documents, including handwritten and printed materials. This study investigates and analyses the application of deep learning techniques such as Convolutional Neural Networks for the recognition of Odia characters. CNNs categorise characters by using neurons coupled in several layers to achieve optimal efficiency, which is inspired by the structure of the brain. The goal of this work was to categorise Odia characters using 6 layers of neurons. This method was able to obtain a 95.6 percent accuracy rate. The handwritten Odia characters may be simply translated into English or any other language once they have been identified. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Layer Extraction for Efficient Plant Disease Classification using Efficientnet B1

引用

SN Computer science 2025年第4期6卷 1-15页

作者： Thakur, Arastu Thakur, Abhilasha Vivek, V. Mahesh, T.R. Krishna, K. Murali Department of Computer Science and Engineering Faculty of Engineering and Technology JAIN (Deemed-to-Be University) Bangalore 562112 India Department of Agriculture Marwadi University Gujarat Rajkot India Alliance School of Advanced Computing Alliance University Chandapura - Anekal Main Road Bengaluru Anekal 562106 India Department of Electrical and Electronics Engineering Faculty of Engineering and Technology JAIN (Deemed-to-Be University) Bangalore 562112 India

Agriculture is crucial for the global economy, providing sustenance and resources for various industries. However, plant diseases threaten crop quality and yield, risking severe economic impacts. Traditional plant disease diagnosis methods, like manual inspection or basic machine learning, are slow, require expertise, and struggle with scalability and adapting to new diseases. This study introduces a deep learning model using convolutional neural networks (cnns) to autonomously detect and classify plant diseases from images, enhancing speed, scalability, and accuracy. We utilize the efficientnetb1 architecture, pretrained on imagenet and fine-tuned on a dataset of bell pepper, potato, and tomato diseases, recognizing 14 diseases plus healthy plants. The model achieves 98.80% accuracy on the test dataset, with high precision, recall, and F1-scores, demonstrating its effectiveness in plant disease diagnosis. This advancement marks a significant step in automating plant disease diagnosis, offering a robust tool for effective disease management in agriculture. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Agriculture Automated diagnosis Deep learning Disease management Efficientnetb1 Image classification Plant disease detection Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Bidirectional LSTM-Based Energy Consumption Forecasting:Advancing AI-Driven Cloud Integration for Cognitive City Energy Management

引用

Computers, Materials & Continua 2025年第5期83卷 2907-2926页

作者： Sheik Mohideen Shah Meganathan Selvamani Mahesh Thyluru Ramakrishna Surbhi Bhatia Khan Shakila Basheer Wajdan Al Malwi Mohammad Tabrez Quasim Department of Computer Science and Engineering Srinivasa Ramanujan CentreSASTRA Deemed UniversityKumbakonam612001India Department of Computer Science and Engineering Faculty of Engineering and TechnologyJAIN(Deemed-to-be University)Bangalore562112India School of Science Engineering and EnvironmentUniversity of SalfordManchesterM54WTUK University Centre for Research and Development Chandigarh UniversityMohali140413PunjabIndia Centre for Research Impact and Outcome Chitkara University Institute of Engineering and TechnologyChitkara UniversityRajpura140401PunjabIndia Department of Information Systems College ofComputer and Information SciencePrincessNourah bintAbdulrahmanUniversityP.O.Box 84428Riyadh11671Saudi Arabia College of Computer Science Informatics and Computer Systems Department King Khalid UniversityAbha61421Saudi Arabia Department of Computer Science and Artificial Intelligence College of Computing and Information TechnologyUniversity of BishaBisha61922Saudi Arabia

Efficient energy management is a cornerstone of advancing cognitive cities,where AI,IoT,and cloud computing seamlessly integrate to meet escalating global energy *** this context,the ability to forecast electricity consumption with precision is vital,particularly in residential settings where usage patterns are highly variable and *** study presents an innovative approach to energy consumption forecasting using a bidirectional Long Short-Term Memory(LSTM)*** a dataset containing over twomillionmultivariate,time-series observations collected froma single household over nearly four years,ourmodel addresses the limitations of traditional time-series forecasting methods,which often struggle with temporal dependencies and non-linear *** bidirectional LSTM architecture processes data in both forward and backward directions,capturing past and future contexts at each time step,whereas existing unidirectional LSTMs consider only a single temporal *** design,combined with dropout regularization,leads to a 20.6%reduction in RMSE and an 18.8%improvement in MAE over conventional unidirectional LSTMs,demonstrating a substantial enhancement in prediction accuracy and *** to existing models—including SVM,Random Forest,MLP,ANN,and CNN—the proposed model achieves the lowest MAE of 0.0831 and RMSE of 0.2213 during testing,significantly outperforming these *** results highlight the model’s superior ability to navigate the complexities of energy usage patterns,reinforcing its potential application in AI-driven IoT and cloud-enabled energy management systems for cognitive *** integrating advanced machine learning techniqueswith IoT and cloud infrastructure,this research contributes to the development of intelligent,sustainable urban environments.

关键词： Deep learning bidirectional LSTM energy consumption forecasting time-series analysis predictive modeling machine learning in energy management

来源：评论

学校读者我要写书评

暂无评论

Research on the Evolutionary Path of Public Opinion in Networked Emergencies Based on Large Models——Taking the Gansu earthquake as an example 24

Research on the Evolutionary Path of Public Opinion in Netwo...

引用

Proceedings of the 2024 5th International Conference on Big Data Economy and Information Management

作者： Juan Gao Xiangyun Guo Tianqi Xiang School of Computing Beijing Information Science & Technology University Beijing China School of Management Science and Engineering Beijing Information Science & Technology University Beijing China

ISBN: (纸本)9798400711862

Construct a rational map of online public opinion on emergencies, reveals the evolutionary paths and developmental contexts of public opinion incidents, providing decision support for government departments in managing and guiding public sentiments. Select Sina Weibo as the data source, use octopus collector to collect Gansu earthquake Weibo data, and then perform data preprocessing. The causal relationships of the events were determined based on a rule-based template matching method, and a multi-round dialogue mechanism based on large language models was used to automatically extract causal event pairs. The K-means++ clustering algorithm was employed to generalize the events and construct a network public opinion event logic graph, analyzing the evolutionary paths of online public sentiments. The research findings indicate that public sentiment regarding the Gansu earthquake is characterized by multiple levels and complex causal relationships. The involvement of multiple causal chains contributes to a high degree of complexity in the evolution of public sentiment. By constructing an event logic graph, the development process of the Gansu earthquake public opinion event has been demonstrated, which can provide technical support for real-time monitoring, in-depth analysis, and precise response of public opinion.

关键词： Multiple rounds of dialogue

来源：评论

学校读者我要写书评

暂无评论

Multilabel Classifier Using DenseNet-169 for Alzheimer's disease

Multilabel Classifier Using DenseNet-169 for Alzheimer's dis...

引用

Intelligent engineering and Management (ICIEM), International Conference on

作者： Rachna Joshi Priyanka Negi T. Poongodi School of Computing Science and Engineering Galgotias University Greater Noida

Alzheimer's disease is one of the most recurrent type of mental illness leading to dementia amongst old-age people. With age, the chances of getting this brain disease are: 17% people between the age group 65 to 74,47% of individuals between age group 75 to 84 and 36% with age 85 or over suffered from this disease. Each year an estimated 44 million people are diagnosed with Alzheimer's worldwide. A total of 3.7 million people in India have Alzheimer's disease and related problems, and the number is likely to double by 2030. Alzheimer's disease is not completely cured but if diagnosed early, it can help to delay the progression of the disease and prevent further damage to the brain tissue. In the proposed work, a Deep Learning Classifier using Convolutional Neural Network is proposed for classifying the stage of Alzheimer's disease in a patient by using the DenseNet-169 CNN classifier with an accuracy of 91.80%. The model is trained on a MRI image database that contains MRI images of patients diagnosed with Alzheimer's disease.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rule-oriented Approach for Knowledge acquisition from Database 15

Rule-oriented Approach for Knowledge acquisition from Databa...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Aakash, B. Uma Sankari, S.S. Thangavel, Senthil Kumar Palanisamy, T. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Coimbatore India Vikram Sarabhai Space Centre ISRO Scientist Thiruvananthapuram India Amrita Vishwa Vidyapeetham Amrita School of Physical Sciences Department of Mathematics Coimbatore India

ISBN: (纸本)9798350370249

In today's world, where importance is provided more towards knowledge rather than just information, the need for transformation of databases to knowledgebase in an efficient way such that data is not lost during the process of transformation. This paper explores the scalability of the rule-based approach, demonstrating its effectiveness across various domains and dataset sizes. Through illustrative examples and case studies, it elucidates how this methodology can adapt to evolving data structures and accommodate complex relationships within the information ecosystem. Moreover, the research investigates the interpretability and transparency of the transformed knowledge base. By harnessing the explicit logic encoded in PROLOG rules, users gain insights into the underlying reasoning process, fostering trust and facilitating collaboration between domain experts and data practitioners. The research highlights the practical implications of deploying a rule-oriented transformation strategy in real-world scenarios. From facilitating decision support systems to enabling semantic search functionalities, the transformed knowledge base serves as a valuable asset for organizations seeking to unlock the latent insights buried within their data repositories. This paper discusses one such possible way which is Rule-oriented Approach where the Database transform to Knowledgebase through PROLOG script which has more advantages like Improved Data Understanding, Enhanced Querying and Retrieval and steps of the transformation are well defined in this paper. © 2024 IEEE.

关键词： Latent semantic analysis

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：