检索结果-内蒙古大学图书馆

A Deep Learning Framework for Hourly Bitcoin Price Prediction Using Bi-LSTM and Sentiment Analysis of Twitter Data

SN computer science 2024年第6期5卷 767页

作者： Patel, Raj Chauhan, Jaya Tiwari, Naveen Kumar Upaddhyay, Vipin Bajpai, Abhishek Computer Science and Engineering Rajkiya Engineering College Kannauj Electronics Engineering Harcourt Butler Technical University Kanpur

Cryptocurrencies like bitcoin predictions hold significant importance due to their impact on various stakeholders and aspects of the financial landscape. Investors heavily rely on the predictions to make effective and efficient conclusions about buying, selling, or holding Bitcoin as part of their investment portfolios. Accurate forecasts enable effective risk management, allowing individuals and institutions to confidently navigate the volatile cryptocurrency market. In this paradigm, our emphasis is on the prediction of the next hour’s bitcoin price. In most of the model, we give the bitcoin price as input but here along with the bitcoin price we are giving coin price and sentiments as input and it predicts the next hour’s output price. In this work, we have used bidirectional LSTM with preprocessed data. We have performed data cleansing and sentiment analysis as part of the data pretreatment step. Recent 90-days data have been selected for the prediction which is then fed to a bidirectional LSTM model. It is a specialized version of recurrent neural network (RNN) architecture that is often used in sequence-to-sequence tasks, including time series prediction. It can be applied to Bitcoin price prediction by leveraging its ability to capture dependencies in both past and future data. The source code of the project is available at: https://***/rajpatel4835/Forecasting-Bitcoin-Price. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Bidirectional LSTM Bitcoin (BTC) Recurrent neural network (RNN) Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Envisioning the interactive convergence of Generative AI and Facial Expression Recognition 9

Envisioning the interactive convergence of Generative AI and...

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Florance, G. Nirmala, M. Khan, Jumainah Saifudeen Hisham, K.M. New Horizon College of Engineering Computer Science And Engineering Bengaluru India

ISBN: (纸本)9798350394474

This paper explores and envisions a collaboration between Facial Expression Recognition (FER) and Generative Artificial Intelligence (GenAI) to create an advanced human-computer interaction (HCI) experience. Deep learning techniques are harnessed to interpret human emotions from facial expressions, using a structured approach that includes pre-processing, feature extraction, and classification. The data acquired from the FER stage informs GenAI systems - such as Generative Pre-trained Transformers (GPTs) - to produce contextually relevant and emotionally resonant responses. The proposed system leverages a sophisticated camera setup to capture facial data with high accuracy under diverse lighting conditions, ensuring robust and reliable emotion inference. Virtual avatars complete the multimodal experience by generating corresponding nonverbal cues. Special attention is given to creating a dynamic feedback loop for continuous learning and adaptation, leading to increasingly effective human-computer dialogues. Ethical implications, such as user privacy, data security, and bias mitigation, are central to the design and deployment of this system, underscoring the commitment to ethical standards and user empowerment. This paper aims to demonstrate how the convergence of FER and GenAI can revolutionize HCI, paving the way for enhanced empathetic and intelligent computing interfaces. © 2024 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Medical Images Using Deep Reinforcement Learning 2

Anomaly Detection in Medical Images Using Deep Reinforcement...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Rastogi, Divya Sharma, Aparna Yadav, R.K. Varshney, Neeraj Saraswat, Laxmi Computer Science and Application Sharda University UP Greater Noida India Electronics & Communication Engineering Raj Kumar Goel Institute of Technology UP Ghaziabad India Gla University Department of Computer Engineering and Applications UP Mathura India Abes Engineering College Department of Computer Science UP Ghaziabad India

ISBN: (纸本)9798350371055

Anomaly detection in clinical pix is vital to identify and diagnose diseases. Deep reinforcement gaining knowledge is a practical gadget-mastering approach implemented for more than a few medical obligations. This technique applies a synthetic intelligence version to research by revealing an iterative procedure to discover a set of top-of-the-line parameters for ultimate selection-making. The cause of this examination is to use deep reinforcement mastering for anomaly detection in medical pix. This approach is used to identify strange areas in clinical pix, including tumors, mental diseases, and other abnormalities. Deep reinforcement mastering is mixed with Convolutional Neural Networks (CNNs) to extract capabilities from the medical pictures and then classify them consistent with their deviation from normal. The detection accuracy is evaluated using a novel assessment metric, referred to as the precision-recollect (PR) curve, which is designed to degree the version's accuracy. The results show that deep reinforcement learning can gain high-performance anomaly detection accuracy compared with conventional methods. © 2024 IEEE.

关键词： Accuracy Anomalous Evaluated Evaluation Measure

来源：评论

学校读者我要写书评

暂无评论

Double Enhanced Solution Quality Boosted RIME Algorithm with Crisscross Operations for Breast Cancer Image Segmentation

引用

Journal of Bionic engineering 2024年第6期21卷 3151-3178页

作者： Mengjun Sun Yi Chen Ali Asghar Heidari Lei Liu Huiling Chen Qiuxiang He Department of Computer Science and Artificial Intelligence Wenzhou UniversityWenzhou325035China School of Surveying and Geospatial Engineering College of EngineeringUniversity of TehranTehran***Iran College of Computer Science Sichuan UniversityChengdu610065China Department of Pathology The First Affiliated Hospital of Wenzhou Medical UniversityWenzhou325000China

The persistently high incidence of breast cancer emphasizes the need for precise detection in its ***-aided medical systems are designed to provide accurate information and reduce human errors,in which accurate and effective segmentation of medical images plays a pivotal role in improving clinical *** Threshold Image Segmentation(MTIS)is widely favored due to its stability and straightforward *** when dealing with sophisticated anatomical structures,high-level thresholding is a crucial technique in identifying fine *** enhance the accuracy of complex breast cancer image segmentation,this paper proposes an improved version of RIME optimizer EECRIME,denoted as the double Enhanced solution quality Crisscross RIME *** original RIME initially conducts an efficient optimization to target promising *** double-enhanced solution quality(EESQ)mechanism is proposed for thorough exploitation without falling into local *** contrast,the crisscross operations perform a further local exploration of the generated feasible *** performance of EECRIME is verified with basic and advanced algorithms on IEEE CEC2017 benchmark ***,an EECRIME-based MTIS method in combination with Kapur’s entropy is applied to segment breast Infiltrating Ductal Carcinoma(IDC)histology *** results demonstrate that the developed model significantly surpasses its competitors,establishing it as a practical approach for complex medical image processing.

关键词： Rime optimization algorithm Double-enhanced solution quality mechanism Crisscross optimization algorithm Image segmentation Breast cancer

来源：评论

学校读者我要写书评

暂无评论

Enhancing Acute Lymphoblastic Leukemia Diagnosis Through Dual Deep Learning Approaches 6

Enhancing Acute Lymphoblastic Leukemia Diagnosis Through Dua...

引用

6th IEEE International Conference on Recent Advances in Intelligent Computational Systems, RAICS 2024

作者： Muhammad Shameem, P. Jemsheer Ahmed, P. Nisa Parvin, K.P. Safa, M.T. Sahana, V.P. Hima Musthafa, T.H. Mea Engineering College Department of Computer Science & Engineering Malappuram India

ISBN: (数字)9798350381689

ISBN: (纸本)9798350381689

Leukemia, a life-threatening blood cancer, de-mands early and accurate diagnosis for effective treatment. This project aims to bring out the potential of dual deep learning techniques to enhance acute lymphoblastic leukemia detection. Our approach combines the capabilities of Convolutional Neural Networks (CNNs). We also propose a mobile application that integrates these dual deep learning models to provide a user-friendly and accessible solution for acute lymphoblastic leukemia detection. High-resolution medical images, such as peripheral blood smears undergo thorough examination using advanced CNN architectures. Sequential data, encompassing temporal information like cell morphology evolution, genetic markers, and patient histories, are systematically analyzed. The dual deep learning model is trained on an extensive and diverse leukemia dataset, encompassing various subtypes and disease stages. Fine-tuning and transfer learning techniques are employed to optimize model performance. Once trained, the system is assured to efficiently evaluate new patient data,providing rapid and highly accurate leukemia diagnosis. The app is trained by using a comprehensive dataset of annotated blood cell images. The app will be designed with a user-friendly interface, enabling medical professionals to easily upload and analyze blood samples. The system's output will provide rapid and accurate leukemia detection, reducing the time and subjectivity associated with manual diagnosis. In summary our project aims to advance acute lymphoblastic leukemia detection by combining two or more powerful deep learning methods to work together effectively. This system holds the promise of assisting healthcare practitioners in making more informed decisions, ultimately leading to improved patient outcomes and more effective management of this life-threatening disease © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Diagnosis Using Deep Learning: A Literature Review 2

Brain Tumor Diagnosis Using Deep Learning: A Literature Revi...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Bhuvaneswari, S. Thomas, Joel Nithish, S. Prithvi, S. Easwari Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350328202

Brain tumor diagnosis is a critical task in the field of medical imaging, with the potential to significantly impact patient outcomes and treatment planning. The use of deep learning has been more well-known within the last ten years as a potential method for improving and automating the detection and categorization of brain tumors. The goal of this literature review is to present a thorough overview of the application of deep learning to the diagnosis of brain tumors. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Automated Attendance Management System Using Face Recognition and Real-Time Biometric Authentication 4

Automated Attendance Management System Using Face Recognitio...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Ida Christy, J. Abisha, D. Mithunkumar, C. Navedha Evanjalin, R. Ajith, S. Dharun Ram, K. National Engineering College Department of Computer Science and Engineering Kovilpatti India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529635

Tracking attendance in educational institutions is an extremely time-consuming and labor-intensive process, and the task seems to be plagued by inaccuracies and inefficiencies at all times. Techniques such as manual roll calls or traditional paper-based attendance systems often face problems like proxy attendance and human error, coupled with delays due to the processing of a large volume of data. The more the number of students, especially with an increasing need to operate with fewer numbers of people, there is a growing need for more efficient, reliable, and secure attendance tracking. Also, the growing administrative and academic interests of accurate attendance records affirms that current techniques of recording attendance lack the necessary level of efficiency. Attendance management systems in the conventional sense faced problems and constraints, and this paper specifically on the pressures toward discovering a solution that can automate the process yet has validity, security, and scalability issues. © 2024 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

An optimized multi-scale convolutional autoencoder for efficient abnormal event detection using rgb, depth and optical flow data

引用

Multimedia Tools and Applications 2025年 1-35页

作者： Alqahtani, Abdullah Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University KSA Al-Kharj Saudi Arabia

In this study, we propose a novel framework for detecting abnormal events in surveillance videos, a critical yet challenging task in security applications. This research introduces a robust and efficient solution for video anomaly detection, offering substantial improvements in surveillance systems' ability to detect abnormal events, thereby contributing to enhanced security measures in public spaces. The proposed framework utilizes a Multiscale Convolutional Autoencoder (MSCAE) that processes inputs from RGB, depth, and optical flow video clips, enhancing the detection accuracy in complex scenes characterized by varying object scales, aspect ratios, and occlusions. To address the challenge of noise and preserve edges in video data, we implement a two-pass bilateral smooth filtering method, which is effective for noise-invariant, edge-preserving image smoothing. For object detection within these complex scenes, an enhanced Faster R-CNN model is employed. This model's performance is further refined through transfer learning on a dataset specifically composed of abnormal event videos. We also introduce significant improvements to the region proposal network (RPN) of the Faster R-CNN, particularly in non-maximum suppression (NMS) and anchor generation techniques, to better detect anomalies in diverse and complex environments. Furthermore, the MSCAE is integrated with Long Short-Term Memory (LSTM) neural networks to classify the detected anomalies, creating an end-to-end solution for video anomaly detection. Hyperparameter optimization for our deep learning models is performed using the Chameleon Swarm Algorithm, ensuring optimal model performance. Our framework was rigorously tested on the CUHK Avenue dataset, where it achieved a remarkable 99.5% accuracy, significantly outperforming existing methods and demonstrating the effectiveness of our approach. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Gesture-Driven Virtual Mouse: Empowering Accessibility through Hand Movements 5

Gesture-Driven Virtual Mouse: Empowering Accessibility throu...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Julian, Anitha Suresh, Danush Ramyadevi, R. Saveetha Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350383522

The mouse has been a vital tool for human-computer interaction, with wired, wireless, and Bluetooth variations requiring power to connect a dongle to a PC. The proposed work uses the latest technology in computer vision and machine learning to recognize hand movements without needing extra equipment. Compatible with CNN models through mediapipe implementation, it enables various actions via various hand movements, all on a single computer. Utilizing a camera as the input device, the system relies on Python and OpenCV. The camera's output is displayed on the system's screen, allowing users to fine-tune their interactions. © 2024 IEEE.

关键词： computer vision gesture recognition hand gestures interaction Virtual mouse

来源：评论

学校读者我要写书评

暂无评论

Multimodal Conversational Bot for Multilingual Personalized Song Recommendation

Multimodal Conversational Bot for Multilingual Personalized ...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable Technology, ICRISST 2024

作者： Keerthana, E. Rekha, K.S. Saveetha Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350309140

Advanced Multimodal Conversational Bot powered by the LLama 2 model, which has 13 billion parameters. The bot can provide personalized song recommendations that are flexible across languages. It uses text, and audio inputs to understand users from different linguistic backgrounds. It accurately assesses the user's mood in multiple languages through sentiment analysis and refines emotional context using image and video analysis. This allows it to offer song recommendations considering the user's mood, preferences, and realtime context, regardless of their chosen language. The bot also handles incomplete or unclear queries in multiple languages, ensuring precise and relevant song suggestions. A custom dataset tailored for music recommendations is used for finetuning, enhancing the bot's ability to provide personalized and contextually relevant song suggestions. © 2024 IEEE.

关键词： Bot (Internet)

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：