检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5844-5854页

作者： Patel, Manali Jariwala, Krupa Chattopadhyay, Chiranjoy Sardar Vallabhbhai National Institute of Technology Department of Computer Science and Engineering Surat395007 India FLAME University School of Computing and Data Sciences Pune412115 India

An accurate estimation of future stock prices can help investors maximize their profits. The current advancements in the area of artificial intelligence (AI) have proven prevalent in the financial sector. Besides, stock market prediction is difficult owing to the considerable volatility and unpredictability induced by numerous factors. Recent approaches have considered fundamental, technical, or macroeconomic variables to find hidden complex patterns in financial data. At the macro level, there exists a spillover effect between stock pairs that can explain the variance present in the data and boost the prediction performance. To address this interconnectedness defined by intrasector stocks, we propose a hybrid relational approach to predict the future price of stocks in the American, Indian, and Korean economies. We collected market data of large-, mid-, and small-capitalization peer companies in the same industry as the target firm, considering them as relational features. To ensure efficient feature selection, we have utilized a data-driven approach, i.e., random forest feature permutation (RF2P), to remove noise and instability. A hybrid prediction module consisting of temporal convolution and linear model (TCLM) is proposed that considers irregularities and linear trend components of the financial data. We found that RF2P-TCLM gave the superior performance. To demonstrate the real-world applicability of our approach in terms of profitability, we created a trading method based on the predicted results. This technique generates a higher profit than the existing approaches. © 2024 IEEE.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Real-Time Language Translation: A Server-Side Approach to Overcome Cross-Cultural Communication Challenges 4

Machine Learning for Real-Time Language Translation: A Serve...

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Elango, S. Mohanaprakash, T.A. Siva, D. Gowtham, A. Sasikumar, A.N. Sunitha, T. Department of Computer Science and Engineering SOET CMR University Bengaluru India Department of Computer Science and Applications SRM Institute of Science and Technology Chennai India Madanapalle Institute of Technology & Science AP India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Artificial Intelligence & Data Science Saveetha Engineering College Chennai India

ISBN: (纸本)9798331515720

The evolution of human civilization has been intrinsically linked to advancements in technology, leading to the development of multiple languages as mediums of communication. However, this linguistic diversity poses significant challenges in cross-cultural communication. Despite numerous efforts and achieving near state-of-The-Art results in language translation, a universal solution remains elusive. This research study proposes an advanced approach to machine translation by utilizing server-side machine learning to enable seamless communication across various languages. By sending GET or POST requests through JQuery, users can efficiently translate text. The process is structured into three key steps: speech recognition (conversion of spoken words to text), translation using machine learning algorithms, and speech synthesis (conversion of translated text to audio). This approach aims to enhance real-Time translation capabilities, offering a more effective and user-friendly solution for overcoming language barriers. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

M3Hop-CoT: Misogynous Meme Identification with Multimodal Multi-hop Chain-of-Thought

M3Hop-CoT: Misogynous Meme Identification with Multimodal Mu...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Kumari, Gitanjali Jain, Kirtan Ekbal, Asif Department of Computer Science and Engineering India Indian Institute of Technology Patna India School of AI and Data Science Indian Institute of Technology Jodhpur India

ISBN: (纸本)9798891761643

In recent years, there has been a significant rise in the phenomenon of hate against women on social media platforms, particularly through the use of misogynous memes. These memes often target women with subtle and obscure cues, making their detection a challenging task for automated systems. Recently, Large Language Models (LLMs) have shown promising results in reasoning using Chain-of-Thought (CoT) prompting to generate the intermediate reasoning chains as the rationale to facilitate multimodal tasks, but often neglect cultural diversity and key aspects like emotion and contextual knowledge hidden in the visual modalities. To address this gap, we introduce a Multimodal Multi-hop CoT (M3Hop-CoT) framework for Misogynous meme identification, combining a CLIP-based classifier and a multimodal CoT module with entity-object-relationship integration. M3Hop-CoT employs a three-step multimodal prompting principle to induce emotions, target awareness, and contextual knowledge for meme analysis. Our empirical evaluation, including both qualitative and quantitative analysis, validates the efficacy of the M3HopCoT framework on the SemEval-2022 Task 5 (MAMI task) dataset, highlighting its strong performance in the macro-F1 score. Furthermore, we evaluate the model's generalizability by evaluating it on various benchmark meme datasets, offering a thorough insight into the effectiveness of our approach across different datasets. © 2024 Association for Computational Linguistics.

关键词： Chains

来源：评论

学校读者我要写书评

暂无评论

Attention based 1-D CNN system for detection of Freezing of gait (FOG) in Parkinsons Patients 15

Attention based 1-D CNN system for detection of Freezing of ...

引用

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

作者： Pradeep Kumar, D. Sowmya, B.J. Vincent, Ashvin Pandiyan, Aravindh Ramaiah Institute of Technology Department of Computer Science and Engineering Bangalore India Ramaiah Institute of Technology Department of Artificial Intelligence and Data Science Bangalore India Bangalore India

ISBN: (纸本)9798350370249

One common clinical symptom seen in Parkinson's disease (PD) patients is freezing of gait (FOG). It manifests as an irregular gait, marked by abrupt, involuntary stopping of movement during gait episodes. FOG entails a major negative effect on PD patients' quality of life. In this work, we analyze the movement data that is collected using the lower-back 3D accelerometer worn by the patients during FOG episodes. By employing machine learning methods to classify this data, we aim to accurately detect FOG trends. In particular, we focus on Deep Learning-based techniques, specifically an attention-based 1D Convolutional Neural Network (1D-CNN), due to their capacity to extract intricate features from unprocessed sensor input. Our results indicate that the proposed model achieves AUC scores of 0.9032 with respect to the TDCSFOG dataset and 0.8682 for the DeFOG dataset, for a combined average AUC of 0.8857. Mean Average Precision (mAP) scores for TDCSFOG and DeFOG reach 0.8388 and 0.779, respectively, for an average of 0.8089, showing the ability of the model to predict FOG occurrences over time. These findings suggest techniques based on Deep Learning enhance FOG detection, allowing clinicians to more effectively tailor treatments and care strategies for Parkinson's patients, thus enhancing their ability to move and overall well-being. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Extracting Valuable Insights from The Handwritten Feedback 7

Extracting Valuable Insights from The Handwritten Feedback

引用

7th IEEE Pune Section International Conference, PuneCon 2024

作者： Chawale, Yugandhar Patwardhan, Prasanna Dewani, Rahul More, Ankit Jadhav, Varsha Pandey, Mrityunjoy Sharma, Neha Vishwakarma Institute of Information Technology Department of Artificial Intelligence and Data Science Maharashtra Pune India Army Institute of Technology Department of Computer Engineering Maharashtra Pune India Society for Data Science Pune India

ISBN: (纸本)9798331527822

This paper describes the collection and analysis of feedback data which is crucial for evaluating the success of any event and identifying areas of improvement. However, when feedback forms are distributed in paper format, extracting the text responses into a machine-readable format for analysis can be a tedious and error-prone manual process. Optical Character Recognition (OCR) Technology offers an automated solution for digitizing text from scanned documents, but its accuracy can be impacted by various factors like image quality, font styles, and language complexities. This study investigates the use of Gemini 1.5 Pro, a multimodal AI, to extract text data from PDF scans of collected handwritten feedback forms. After evaluation of Gemini's performance across a range of PDF qualities and comparing its output to manually transcribed data, the results demonstrate Gemini's high accuracy rates, even on lower quality scans, enabling efficient extraction of feedback responses while minimizing manual effort. This solution offers a scalable and reliable approach for educational institutions, professional organizations and other bodies to digitize survey responses for deeper qualitative and quantitative computational techniques. © 2024 IEEE.

关键词： data accuracy

来源：评论

学校读者我要写书评

暂无评论

Quantum-enhanced Vehicle Detection and Speed Monitoring using OpenCV

Quantum-enhanced Vehicle Detection and Speed Monitoring usin...

引用

2024 International Conference on Integration of Emerging Technologies for the Digital World, ICIETDW 2024

作者： Simonthomas, S. Naresh, B. Rohith, K. Aarupadai Veedu Institute of Technology Department of Computer Science and Engineering Chennai India Aarupadai Veedu Institute of Technology Department of Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798331541170

Quantum based vehicle detection is the innovative integration of Quantum Machine Learning (QML) techniques with classical computer vision methods to enhance vehicle detection and speed tracking systems using OpenCV. Traditional approaches in vehicle detection and speed tracking are often hindered by computational inefficiencies and accuracy limitations in complex traffic scenarios. Our proposed hybrid quantum-classical framework aims to overcome these complications by exploiting the computational advantages of quantum computing. In this study, we employ Quantum Principal Component Analysis (QPCA) for feature extraction and data dimensionality reduction, optimizing the input data for improved processing efficiency. The core detection mechanism integrates Quantum Neural Networks (QNNs) with classical Convolutional Neural Networks (CNNs), enhancing the model's accuracy in identifying vehicles within video frames. For speed tracking, we apply quantum optimization techniques to refine the tracking of vehicle positions across consecutive frames, ensuring precise speed calculation. Using OpenCV for real-time video processing and Qiskit for quantum computations, the findings from the experiments indicate significant improvements in both detection a precision, accuracy and computational efficiency. The hybrid quantum-classical model showcases the potential of quantum computing in advancing computer vision applications, particularly in intelligent transportation systems. This research highlights the transformative impact of QML techniques on practical applications and paves the way for further advancements in quantum-enhanced vehicle detection and speed tracking. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Robustness of Explainable AI Algorithms for Disease Biomarker Discovery from Functional Connectivity datasets

Robustness of Explainable AI Algorithms for Disease Biomarke...

引用

2024 IEEE-EMBS International Conference on Biomedical and Health Informatics, BHI 2024

作者： Girish, Deepank Chan, Yi Hao Gupta, Sukrit Xia, Jing Rajapakse, Jagath C. College of Computing and Data Science Nanyang Technological University Singapore Indian Institute of Technology Department of Computer Science and Engineering Ropar India

ISBN: (纸本)9798350351552

Machine learning (ML) models have been used in functional neuroimaging for wide-ranging tasks, ranging from disease diagnosis to disease prognosis. There have been successive functional connectivity-based ML studies focused on improving model performances for disease detection. An increasing number of such studies use their trained models to detect and evaluate salient features that could be potential biomarkers of these neuro-logical conditions. The evaluation of these salient features is often qualitative and limited to cross-referencing existing literature for similar findings. In this study, we present objective quantitative metrics to evaluate the robustness of these salient features. Building upon existing generic evaluation metrics, we propose metrics that capture topological properties known to be characteristic of brain functional connectomes. Using existing and newly proposed measures on a set of baselines and state-of-the-art graph neural networks (GNN) models, we found that when GNNExplainer is used with models that incorporate attention, the scores produced are relatively more robust than other combinations. On datasets of patients with Autism Spectrum Disorder (ASD) or Attention-deficit Hyperactivity Disorder (ADHD), our proposed metrics highlighted that salient features identified in both disorders are highly involved in functional specialization, while salient ASD features expressed stronger functional integration than ADHD. We package these existing and novel metrics together in the RE-CONFIRM framework that holds promise to set the foundations for the quantitative evaluation of salient features detected by future studies. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Automated AI-Powered Fruit Identification Using Convolutional Neural Network

Automated AI-Powered Fruit Identification Using Convolutiona...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Sai Tejasree, K. Surendran, R. Rajakumar, B. Gomathi, R.M. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India J.N.N Institute of Engineering Department of Artificial Intelligence and Data Science Chennai India School of Computing Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509828

Clever system that can look at pictures of fruits and figure out what kind of fruit each picture shows. AI algorithms like deep learning, which is like giving the Machine learning model a crash course in fruit recognition. This method teaches the ML Model we clearly explained the Model using application's agent using PEAS and the application's task environment using the 6 dimensions by showing it tons of fruit images, so over time, it gets really good at spotting the differences and similarities between, say, a banana and a grape. We also used another technique called pattern recognition, which helps the computer pay attention to specific details like the fruit's color, shape, size and texture. Overcoming multiple obstacles in order to automatically identify the type of fruit from the picture. The variety of images is influencing the color, texture, and shape of many different types of fruits. When it came to fruit picture detection, Convolutional Neural Network (CNN) Algorithm outperformed standard support-vector-machine-based approaches using handcrafted features in terms of accuracy also, it is a lot faster to implement for new fruits. By integrating deep learning and pattern recognition techniques such as Convolutional Neural Network Algorithm we have got the accuracy of 84%, our system efficiently identified different fruit types from images, demonstrating the power and effectiveness of our methods. The goal of our project is to create a tool that can quickly and correctly identify many types of fruits in photos, which could be useful for things like sorting fruits in a grocery store or helping people learn about different fruits by using Convolutional Neural Network Algorithm. This is not just about teaching a computer to recognize fruits;it is about making technology that can understand and interact with the world in a way that is helpful to us. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent Chatbot for Hospital Recommendation System 2

Intelligent Chatbot for Hospital Recommendation System

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Rajkumar, K. Ragupathi, T. Karthikeyan, S. School of Computing Srm Institute of Science and Technology Department of Data Science and Business Systems Tamil Nadu Kattankulathur India Department of Computer Science and Engineering Bangalore562112 India

ISBN: (纸本)9798350371055

The main objective of this project is to create a user-friendly intelligent chatbot for Medical guidance and support. This application has been classified into two different modes based on user preference, those are Online and Offline modes of interaction. In the Online mode of interaction, there is no need for any automation, there will be a real person at the other end answering user queries. Users can even ask for untrained data and will receive instant replies. This application is similar to a normal chat application, but the main disadvantage is that a real person is needed at the other end at all times. In the Offline mode of conversation which is entirely automated the user will be performing an interaction with the chatbot itself. The chatbot must consist of data sets and trained data collection, in this process there is no need for any real person, the chatbot itself will reply instantly based on the trained data. The chatbot will be more accurate when a large number of data is trained. This application is compatible with working in various browsers and varied networks. The Admin of the application plays a significant role. Admin can access all the given functions and is responsible for data training. data training plays a vital role in this application, the trained data will be used by the chatbot while answering user queries i.e. Offline mode. This chatbot application can be accessed by several users at the same time, where IP address plays the main role. The main function of this application is that user can post their corresponding queries and the application will be providing relevant information based on queries. The Latest Modern chatbots are used in applications where simple interaction is needed, for example, service and marketing technology to provide answers such as products, services, and consultancy. If the customer's queries don't match with the trained data sets, the customer will be escalated to manual interaction i.e. Online mode. © 2024 IE

关键词： Automated Intelligent Chat IP Address Offline mode Online mode Trained data

来源：评论

学校读者我要写书评

暂无评论

Hybrid RNN Based Text Classification Model for Unstructured data

引用

SN computer science 2024年第6期5卷 726页

作者： Sunagar, Pramod Sowmya, B.J. Pruthviraja, Dayananda Supreeth, S. Mathew, Jimpson Rohith, S. Shruthi, G. Cloudthat Technologies Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education School of Computer Science and Engineering REVA University Department of Computer Science and Engineering Indian Institute of Technology Patna Department of ECE Nagarjuna College of Engineering and Technology

The volume of social media posts is on the rise as the number of social media users expands. It is imperative that these data be analyzed using cutting-edge algorithms. This goal is handled by the many techniques used in text categorization. There are a variety of text categorization techniques available, ranging from machine learning to deep learning. Numerical crunching has become easier with less processing time since the emergence of high-end computer facilities. This has led to the development of sophisticated network architectures that can be trained to achieve higher precision and recall. The performance of neural network models which was evaluated by the F1 score is affected by cumulative performance in precision and recall. The current study intends to analyze and compare the performance of the neural network proposed, A Hybrid RNN model that has two layers of BiLSTM and two layers of GRU to that of previous hybrid models. GloVE dataset is used to train the models and their accuracy, precision, recall, and F1 score are used to assess performance. Except for the RNN + GRU model, the RNN + BILSTM + GRU model has a precision of 0.767, a recall of 0.759, and an F1-score of 0.7585. This hybrid model outperforms the others. © The Author(s) 2024.

关键词： Bidirectional long-short-term memory (BiLSTM) Gated recurrent units (GRU) Recurrent neural networks (RNN) Region-based convolutional neural networks (RCNN) Text classification

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：