检索结果-内蒙古大学图书馆

A Variational Inference-Based LSTM-enhanced Deep Neural Model for Sequential Recommendations

IEEE Access 2025年 13卷 95945-95962页

作者： Ngaffo, Armielle Noulapeu Kamgang, Ines Raissa Djouela Maka, Ebenezer Maka Malong, Yannick University of Douala Laboratory of Computer Science Data Science and Artificial Intelligence National Higher Polytechnic School of Douala Douala8580 Cameroon Department of computer engineering University of Buea Faculty of Engineering and Technology Cameroon

Long Short-Term Memory (LSTM) networks are particularly useful in recommender systems since user preferences change over time. Unlike traditional recommender models which assume static user-item interactions, LSTM models capture sequential dependencies and temporal dynamics, making them ideal for personalized, session-based, and sequential recommendation tasks. However, traditional LSTM-based recommender systems do not model uncertainty since they perform deterministic predictions. Moreover, those recommender models exhibit poor generalization on small datasets, and poor-handle cold-start and data sparsity problems. To overcome those limitations, this paper presents an LSTM-based recommender model that leverages an improved deep matrix factorization to accurately address the data sparsity problem. In addition, an enhanced variational inference coupled to the Evidence Lower Bound Optimization is applied on LSTM unit layers to perform uncertainty-aware predictions. Thereafter, latent vectors obtained from LSTM networks are effectively involved in the sequential recommendation process. Experiments have been conducted on several real-world datasets to evaluate our proposal and the results show the proposed model presents significant performances compared to state-of-the-art models. © 2013 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving Solar Efficiency via CNN-LSTM and Cloud-Integrated IoT Prediction 3

Improving Solar Efficiency via CNN-LSTM and Cloud-Integrated...

引用

3rd International Conference on Sentiment Analysis and Deep Learning, ICSADL 2024

作者： Varun, P. Sunitha, T. Nagalingam, Mythili Nithiya, P. Selvakumaran, S. Mohanaprakash, T.A. School of Computing SRM Institute of Science and Technology Department of Data Science and Business Systems Kattankulathur India St. Joseph's Institute of Technology OMR Department of Computer Science and Engineering Chennai600119 India Rajalakshmi Institue of Technology Department of Artificial Intelligence and Data Science Chennai India Department of Artificial Intelligence and Data Science Velammal Engineering College Chennai India Department of Artificial Intelligence and Data Science Rajalakshmi Institue of Technology Chennai India Panimalar Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350396157

Photovoltaic panel used in solar power generation is an environmentally beneficial and sustainable energy source that has been used to transform sunlight into electrical power. Arranged in large solar facilities, these panels are connected to a central inverter, which converts Direct Current (DC) to alternating current (AC) electricity with a small amount of energy loss. Clean surfaces, unhindered light exposure, and high solar irradiance are all necessary for optimal panel performance. It's critical to assess the inverter's efficiency by comparing its AC to DC power. Large-scale installations with sensor-equipped panels and inverters track performance to help with maintenance and forecasting of power generation. The Internet of Things (IoT) facilitates data accessibility and remote monitoring, which helps choose the best location for solar power generation. Smart system continuous monitoring expedites site inspections, which supports urban smart grid integration. In this research study, a hybrid machine learning model is presented by combining the attention processes, long short-term memory (LSTM) networks, and clustering approaches. This model is separated into different phases for forecasting, training, and cloud data clustering, finds pertinent historical data, builds a hybrid machine learning model, and chooses the best training model. In comparison to conventional approaches, this method significantly improves prediction accuracy, which is important for integrating photovoltaic systems into smart grids, particularly in smart cities. © 2024 IEEE.

关键词： Solar power generation

来源：评论

学校读者我要写书评

暂无评论

Predicting Agricultural Crop Damage Caused by Unexpected Rainfall Using Deep Learning

Predicting Agricultural Crop Damage Caused by Unexpected Rai...

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Fulkar, Bhushan Patil, Pawan Srivastav, Gaurav Mahale, Promod Maharashtra Wardha India Artificial Intelligence and Data Science Faculty of Engineering and Technology Maharashtra Wardha India Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha India

ISBN: (纸本)9798350375237

Efficient allocation of resources and timely agricultural interventions depend on the precise identification of crop loss at the field parcel level. Using recent data from 2018 to 2023, this study investigates the integration of deep learning techniques with real-time field photography to classify agricultural field parcels into those experiencing crop loss and those not. We build and assess deep learning models specifically for crop loss classification using a dataset from the Finnish Food Authority (FFA) that combines on-the-ground photos taken during field visits with comprehensive field parcel information. In this work, we use convolutional neural networks (CNNs) to examine the visual characteristics that we have extracted from field photos in order to identify the subtleties that may indicate crop health or possible loss. Our goal is to improve the model's generalization capabilities over a variety of crop types and agricultural landscapes by training it on a combination of field parcel data and corresponding photographs. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Efficient segmentation of exudates in color fundus images using wavelets and generative adversarial network

引用

Multimedia Tools and Applications 2025年 1-31页

作者： Kar, Mithun Kumar Nath, Malaya Kumar Neog, Debanga Raj Amrita School of Artificial Intelligence Coimbatore Amrita Vishwa Vidyapeetham Coimbatore641112 India Department of Electronics and Communication Engineering National Institute of Technology Puducherry Karaikal609609 India Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Guwahati Guwahati781039 India

Due to the progression of diabetic retinopathy (DR), retinal features change and lead to the appearance of microaneurysms, hemorrhages, and exudates on its surface. The presence of exudates appears over the retina, giving a clear early sign of diabetic retinopathy, which is an irreversible eye disease. Automatic segmentation and detection of exudates enhance the computer-aided diagnosis of the disease. Various deep learning techniques are employed for the automatic detection and segmentation of exudates, but their performance is unsatisfactory due to the small size of exudates. Here, a novel method is proposed, using generative adversarial network on wavelet subbands. Wavelet decomposition un-correlates exudates from other retinal features in subbands due to its frequency-selective nature. Generative adversarial network (GAN) is employed with modified loss function with multi-scale residual convolutional neural network (MSR-Net) to accurately segment exudates. The proposed method is experimented on using IDRiD and e-optha databases, and different quantitative and qualitative performance measures are computed and compared with state-of-the-art methods. The proposed method achieves an accuracy, sensitivity, and F1Score of 0.9886, 0.8306, and 0.8246, respectively, for the IDRiD database. For the e-ophtha database, the above-mentioned performance measures are reported to be 0.9861, 0.8512, and 0.8444, respectively. This method performed well in presence of other features. For generalization purposes, the proposed method is applied for skin cancer cell segmentation using University of Waterloo’s skin cancer database. It achieved highest accuracy of 0.9943 and sensitivity of 0.9885 for segmenting the skin cancer cells. It has the potential for analyzing the diagnostic information about various ophthalmic diseases such as: glaucoma and diabetic retinopathy (DR). © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Product Quality Enhancement in Social Media using Emotion-Enhanced Bert (EE-BERT) Model 2

Product Quality Enhancement in Social Media using Emotion-En...

引用

2nd International Conference on Self Sustainable artificial intelligence Systems, ICSSAS 2024

作者： Raj Kumar, V.S. Kumaresan, T. Mythily, V. Raghavendran, N. Bannari Amman Institute of Technology Department of Artificial Intelligence and Data science Sathyamangalam India Bannari Amman Institute of Technology Department of Computer Science and Engineering Sathyamangalam India Nandha Engineering College Department of Computer Science and Engineering Erode India Rmk college of Engineering and Technology Department of Artificial Intelligence and Data science Chennai India

ISBN: (纸本)9798350368413

Twitter plays an important role in understanding the consumer sentiment about the products. The advanced analytics and Natural Language Processing (NLP) are used to extract actionable insights from this data and useful for a business to improve features and address issues on time for better customer satisfaction and brand loyalty. Most of the current models suffer from a lack of effective ways to handle subtle sentiment analysis because of a lack of contextual understanding and proper feature extraction. Most traditional models cannot combine and optimize features that lead to obtaining sentiments. This leads to overfitting and problems caused by local minima. The proposed Emotion-Enhanced BERT (EE-BERT) model is an extension of the standard BERT to learn contextual embeddings in user sentiment. In this work, data preprocessing includes text cleaning, tokenization, dealing with emojis and emoticons, and lemmatization with the best quality data. The proposed work is basically a dual-stream architecture extended with butterfly optimizer. First, the advanced tokenization and semantic understanding techniques is used for extracting textual features. Second, the emotion-enhanced features extracted through emotion-hash vectorization to enhance the model's contextual awareness in social media data. This provides a unified framework that combines the feature extraction methods to enhance the accuracy in sentiment analysis. It demonstrated with an impressive accuracy of 98.2% on sentiment in posts and comments with 0.15 losses. The proposed work is free from overfitting and local minima in product quality enhancement. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Credit Endorsement Forecast Utilizing Troupe Learning and XGBoost

Credit Endorsement Forecast Utilizing Troupe Learning and XG...

引用

2024 IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems, SPICES 2024

作者： Pamula, Narendra Babu Suhana Begum, Shaik Kanakapudi, Upendra Koparaju, Vamsi Krishna Repudi, Rajesh Lakireddy Bali Reddy College of Engineering Department of Artificial Intelligence and Data Science Andhra Pradesh Mylavaram India

ISBN: (纸本)9798350376135

The current approaches to predicting loan approval frequently depend on oversimplified models that are unable to account for the complexity of borrower behaviour and financial risk assessment. One disadvantage is that the model's capacity to identify various patterns and subtleties in the data is restricted by its dependence on a single machine learning technique. This research proposes a framework for predicting loan acceptance that optimizes bank resources by reducing the risk involved in choosing safe candidates for loans through the use of ensemble learning techniques, specifically XGBoost. We make use of a Kaggle dataset with 4269 observations and 13 characteristics, including financial and demographic data. We obtain promising accuracies of 98% and 95%, respectively, by utilizing XGBoost and ensemble learning techniques as Random Forest, SVC, KNN, and Logistic Regression. Our research highlights how machine learning may improve the loan approval process, which can lead to better resource allocation and decision-making in banking operations. © 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

Streamlining Deep Learning Based Alzheimers Disease Classification: A Simplified Approach with ADASYN

Streamlining Deep Learning Based Alzheimers Disease Classifi...

引用

2024 International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational intelligence, RAEEUCCI 2024

作者： Saravanan, V. Sidharth, T. Vijay, S. Sankar Ganesh, S. KPR Institute of Engineering and Technology Department of Artificial Intelligence and Data Science Tamil Nadu Coimbatore641407 India

ISBN: (纸本)9798350354539

Consuming and complex, while existing deep learning (DL) methods may suffer from complexity and overfitting issues. This study proposes an integrated approach that combines Convolutional Neural Networks (CNNs) with the Adaptive Synthetic Sampling (ADASYN) algorithm to address class imbalance and enhance AD classification accuracy. This model architecture prioritizes simplicity and efficiency, utilizing an optimal number of layers to achieve effectiveness. Experimental results on a dataset of brain MRI images demonstrate the efficacy of this approach, with a classification accuracy of 98%. By integrating machine learning techniques with advanced sampling strategies, this research contributes to advancing early detection and diagnosis of Alzheimer's Disease, fostering strides towards improved patient care and management. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

ViGT: proposal-free video grounding with a learnable token in the transformer

引用

science China(Information sciences) 2023年第10期66卷 196-212页

作者： Kun LI Dan GUO Meng WANG School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province Institute of Artificial Intelligence Hefei Comprehensive National Science Center

The video grounding(VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in the complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely video grounding transformer(ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows.(1) The token is unrelated to the video or the query and avoids data bias toward the original video and query.(2) The token simultaneously performs global context aggregation from video and query ***, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention(i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets:ANet-Captions, TACoS, and YouCookⅡ. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT.

关键词： video grounding temporal sentence grounding boundary regression token learning proposal-free

来源：评论

学校读者我要写书评

暂无评论

Reflecting real-time monitoring of Agricultural equipment in Rythu Bharosa Kendra 2

Reflecting real-time monitoring of Agricultural equipment in...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024

作者： Vasavi, S. Mupparisetty, Bhargav Reddy Vemula, Narasimha Rao, A. Nageswara Velagapudi Ramakrishna Siddhartha Engineering College Department of Artificial Intelligence & Data Science Vijayawada India Vijayawada India

ISBN: (纸本)9798350360523

The Rythu Bharosa Kendra (RBK), an initiative by the Andhra Pradesh government, seeks to bolster farming communities by supplying quality seeds, fertilizers, and agricultural supplements while offering vital extension advisories at the village level. To modernize their operations, a proposed automated system will replace manual record-keeping by storing data directly into a database, facilitating seamless facility transactions, and generating comprehensive service reports. By outfitting RBK vehicles with GPS devices and integrating React technology for a user interface, administrators gain real-time insights into vehicle movements, optimize routes, and efficiently monitor the distribution of agricultural resources. This innovative approach not only streamlines RBK's processes but also ensures timely and effective support to farmers while minimizing paperwork and enhancing overall operational efficiency. © 2024 IEEE.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

A Surrogate-assisted Multi-objective Grey Wolf Optimizer for Empty-heavy Train Allocation Considering Coordinated Line Utilization Balance

引用

Journal of Bionic engineering 2025年第1期22卷 383-397页

作者： Zhigang Du Shaoquan Ni Jeng-Shyang Pan Shuchuan Chu School of Transportation and Logistics Southwest Jiaotong UniversityChengdu610031China School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing210044China National and Local Joint Engineering Lab for Integrated Transportation Intelligence Chengdu610031China National Engineering Lab of Comprehensive Transportation Big Data Application Technology Chengdu610031China

This paper introduces the Surrogate-assisted Multi-objective Grey Wolf Optimizer(SMOGWO)as a novel methodology for addressing the complex problem of empty-heavy train allocation,with a focus on line utilization *** integrating surrogate models to approximate the objective functions,SMOGWO significantly improves the efficiency and accuracy of the optimization *** effectiveness of this approach is evaluated using the CEC2009 multi-objective test function suite,where SMOGWO achieves a superiority rate of 76.67%compared to other leading multi-objective ***,the practical applicability of SMOGWO is demonstrated through a case study on empty and heavy train allocation,which validates its ability to balance line capacity,minimize transportation costs,and optimize the technical combination of heavy *** research highlights SMOGWO's potential as a robust solution for optimization challenges in railway transportation,offering valuable contributions toward enhancing operational efficiency and promoting sustainable development in the sector.

关键词： Surrogate-assisted model Grey wolf optimizer Multi-objective optimization Empty-heavy train allocation

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：