检索结果-内蒙古大学图书馆

15th IEEE International Conference on Knowledge Graph, ICKG 2024

作者： Deng, Zewen Zhang, Zan Dong, Bingbing Zheng, Xiulin Wu, Xindong School of Computer Science and Information Engineering Hefei China

ISBN: (纸本)9798331508821

Multi-modal entity alignment (MMEA) aims to identify equivalent entities across different multi-modal knowledge graphs. In these graphs, entities are enriched with information from various modalities, such as text, images, and numerical data, making the alignment task both challenging and crucial for improving knowledge graph quality. Current MMEA algorithms typically encode entity information separately for each modality using corresponding encoders, and then integrate these representations through various modal fusion strategies. However, these methods often fail to fully exploit the multi-modal information of entities. To address this issue, we propose a feature-enhanced multi-modal entity alignment transformer (FEMEAT). FEMEAT enhances entity attribute information by incorporating modal distribution data, which captures the inherent distribution of different modalities for each entity. This inclusion allows the model to have a richer understanding of entity characteristics across modalities. Additionally, FEMEAT utilizes an Optical Character Recognition (OCR) model to extract and incorporate textual information from images. By integrating this text extracted from images, the model can better utilize the visual modality, enhancing its ability to understand and process multi-modal information. Furthermore, FEMEAT employs a multi-head cross-modal attention (MHCA) mechanism for modal fusion to achieve comprehensive multi-modal entity representation. This mechanism enables the model to attend to different modalities simultaneously and learn a detailed representation of entities by considering the interactions between modalities. The multi-head cross-modal attention mechanism facilitates a nuanced understanding and integration of multi-modal data. Experimental results demonstrate that our model achieves state-of-the-art (SOTA) performance across various training scenarios. The code and datasets used in this study can be accessed at https://***/zewenD/FEMEAT. ©

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Optimizing Article Screening and Information Extraction: A Hybrid Approach with GeminiAI and Vector Database 4

Optimizing Article Screening and Information Extraction: A H...

引用

4th International Conference on Digital Futures and Transformative Technologies, ICoDT2 2024

作者： Qudisa, Mammona Fraz, Muhammad Maozam School of Electrical Engineering and Computer Science Islamabad Pakistan

ISBN: (纸本)9798350391862

The exponential growth of scientific literature poses a significant challenge to researchers, resulting in redundancy in R&D due to inefficient review mechanisms. Manual literature reviews are time-consuming and resource-intensive, particularly when screening abstracts and titles, highlighting the need for innovative solutions to optimize the review process. This study introduces a three-step methodology using the GeminiAI model to streamline literature reviews: (1) Initial Screening, (2) Abstract Detail Extraction, and (3) Final Integration, with a Vector Database enabling efficient semantic searches in PDF files. In the first phase, GeminiAI achieved an accuracy of 88.66% in evaluating titles and abstracts based on specific inclusion and exclusion criteria, demonstrating its capability to filter relevant literature efficiently. The second phase enhanced this process by extracting key details, such as research-related modalities, thereby significantly reducing the pool of relevant papers. In the final step, the integration of the Vector Database with GeminiAI excelled, achieving an 80% similarity score in extracting detailed information, which greatly facilitated review writing and minimized manual effort. The user-friendly website designed for this purpose enables seamless paper uploads, with the Vector Database automatically extracting relevant details to streamline the workflow and accelerate innovation. This approach underscores the power of AI in optimizing literature reviews, reducing manual screening time and resources, and mitigating the risk of overlooking critical information. The entire system, including source code and supplementary materials, is available on our publicly accessible GitHub repository. https://***/mammona/*** © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

CNN-Based Machine Learning Model for Disease Prediction in Crops

CNN-Based Machine Learning Model for Disease Prediction in C...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Choudhary, Vijay Thakur, Archana Bhalse, Nisha IPS Academy Institute of Engineering & Science Department of Computer Science & Engineering Indore India School of Computer Science & IT Devi Ahilya University Indore India

ISBN: (纸本)9798331512965

Potato crops are vital to global food security, but they are susceptible to several diseases that hinder growth and yield. Traditional methods of detecting these diseases rely on labor-intensive lab tests and human observation. This research presents an enhanced machine learning model for detecting and categorizing potato leaf diseases, specifically early blight and late blight, using Convolutional Neural Networks (CNN). The model is trained on various datasets of potato leaf images, utilizing techniques such as hyper-parameter tuning, data augmentation, and transfer learning. The proposed model attains an accuracy of 96.11%, significantly improving upon existing methods. Image processing techniques, Segmentation is performed using K-means technique and feature extraction is done by utilizing gray-level co-occurrence matrix, along with multi-class support vector machines for classification, are employed. Additionally, the study shows that CNN performs better than Artificial Neural Networks (ANN) in image classification. The study demonstrates how AI and deep learning technology can be used in agriculture to improve crop management and enable early disease prediction. Experiments have been conducted using the real image dataset. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Predicting Stock Market Prices Using a Hybrid of High-Order Neural Networks and Barnacle Mating Optimization 7th

Predicting Stock Market Prices Using a Hybrid of High-Order ...

引用

7th International Conference on Soft Computing: Theories and Applications, SoCTA 2023

作者： Behera, Sudersan Pavan Kumar, A.V.S. Nayak, Sarat Chandra Department of Computer Science and Engineering School of Engineering and Technology GIET University Gunupur India Department of Computer Science and Engineering School of Technology GITAM Hyderabad Campus Hyderabad India

ISBN: (纸本)9789819720880

Predicting stock market movements presents a formidable challenge due to the inherent nonlinearity and ever-changing nature of financial markets. In this research endeavor, we employ an innovative approach, harnessing the power of an evolutionary algorithm called barnacle mating optimization (BMO), to fine-tune the optimal parameters of a sophisticated neural network known as the Pi-Sigma neural network (PSNN). This intricate optimization process results in the development of a hybrid model, aptly named BMO-PSNN. We put BMO-PSNN to the test by utilizing it for predicting the closing prices of five widely tracked stock indices. In order to provide a comprehensive comparison, we also implement the traditional gradient descent (GD) optimization technique to train the PSNN network for the same predictive task. The performance evaluation is carried out using the average percentage error (APE) metric. Remarkably, the results conclusively demonstrate that BMO-PSNN outshines GD-PSNN in its ability to make more accurate predictions, underscoring the effectiveness of the evolutionary BMO algorithm in tackling the complexities of stock market forecasting. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Method and Algorithm of Enrichment of High-Frequency Multidimensional Signals on the Example of Diagnosing the Technical Condition of Centrifugal Pump and Rolling Bearings 27

Method and Algorithm of Enrichment of High-Frequency Multidi...

引用

27th International Conference on Soft Computing and Measurements, SCM 2024

作者： Qodirov, Shahboz Sh. Shestakov, Aleksandr L. School of Electronic Engineering and Computer Science Chelyabinsk Russia

ISBN: (纸本)9798350363708

This paper is devoted to methods and algorithms of enriching high-frequency multidimensional signals, which are a key aspect of data analysis in the field of equipment condition diagnostics, where high sensitivity to changes in signals is required. High-frequency signals are characterised by fast changes in time and may contain a large amount of information, requiring special processing techniques to extract meaningful patterns. In this paper, we consider various approaches to enrichment of high-frequency multidimensional signals used in modern methods of diagnosing the technical condition of rotating mechanisms on the basis of machine learning algorithms and deep neural networks. In particular, this concerns the diagnosing of the technical condition of centrifugal pumps and rolling bearings. In our research, we propose new method and algorithm for enrichment of high-frequency multidimensional signals on the example of diagnosing the technical condition of a centrifugal pump and rolling bearings using machine learning algorithms. The suggested method and algorithm have a wide range of applications: from real-time signal processing to the analysis of high-frequency time series. The development of new approaches to the enrichment of high-frequency multidimensional signals is an important task that opens new prospects for research in data analysis and decision-making based on high-frequency data. © 2024 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

SRF: Enhancing Document-Level Relation Extraction with a Novel Secondary Reasoning Framework

SRF: Enhancing Document-Level Relation Extraction with a Nov...

引用

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

作者： Zhang, Fu Miao, Qi Cheng, Jingwei Yu, Hongsen Yan, Yi Li, Xin Wu, Yongxue School of Computer Science and Engineering Northeastern University China

ISBN: (纸本)9798891761643

Document-level Relation Extraction (DocRE) aims to extract relations between entity pairs in a document and poses many challenges as it involves multiple mentions of entities and cross-sentence inference. However, several aspects that are important for DocRE have not been considered and explored. Existing work ignore bidirectional mention interaction when generating relational features for entity pairs. Also, sophisticated neural networks are typically designed for cross-sentence evidence extraction to further enhance DocRE. More interestingly, we reveal a noteworthy finding: If a model has predicted a relation between an entity and other entities, this relation information may help infer and predict more relations between the entity's adjacent entities and these other entities. Nonetheless, none of existing methods leverage secondary reasoning to exploit results of relation prediction. To this end, we propose a novel Secondary Reasoning Framework (SRF) for DocRE. In SRF, we initially propose a DocRE model that incorporates bidirectional mention fusion and a simple yet effective evidence extraction module (incurring only an additional learnable parameter overhead) for relation prediction. Further, for the first time, we elaborately design and propose a novel secondary reasoning method to discover more relations by exploring the results of the first relation prediction. Extensive experiments show that SRF achieves SOTA performance and our secondary reasoning method is both effective and general when integrated into existing models. © 2024 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Zero-Day Attack Detection with XAI-Driven ML Models and SMOTE Analysis 3

Enhancing Zero-Day Attack Detection with XAI-Driven ML Model...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Sruthi, C.K. Ravikumar, Aswathy Sriraman, Harini VIT School of Computer Science & Engineering Chennai India

ISBN: (纸本)9798350372120

Zero-day attacks, which are defined by their abrupt appearance without any previous detection mechanisms, present a substantial obstacle in the field of network security. To address this difficulty, a wide variety of machine learning and deep learning models have been used to identify and minimize zeroday assaults. The models have been assessed for both binary and multi-class classification situations, The objective of this work is to do a thorough comparison and analysis of these models, including the impact of class imbalance and utilizing SHAP (SHapley Additive exPlanations) explainability approaches. Class imbalance is a prevalent problem in cybersecurity datasets, characterized by a considerable disparity between the number of attack cases and non-attack instances. By equalizing the dataset, we guarantee equitable depiction of both categories, so preventing prejudice towards the dominant category throughout the training and assessment of the model. Moreover, the application of SHAP XAI facilitates a more profound comprehension of model predictions, empowering analysts to analyze the fundamental aspects that contribute to the detection of zero-day attacks. © 2024 IEEE.

关键词： Zero-day attack

来源：评论

学校读者我要写书评

暂无评论

Stock market price forecasting

Stock market price forecasting

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Jadon, Raja Yadav, Shivam Aleem, Abdul School of Computer Science and Engineering Galgotias University India

ISBN: (纸本)9781032669663

Nowadays almost 98% people in India deposit their money in banks, insurance, mutual fund, and soon rather than investing their money in Stock Market. As they know it is easiest way to earn some interest on wealth, they only need some prior knowledge like they certified from RBI, when people choose them for gaining some extra worth on their wealth. The main reason we found during our research they have lack of knowledge, as well as some of them, are not aware of Stock Market. Those who know about Stock Market but they didn’t want to spend their time on researching about how they invest their money in Stock Market that’s why here we are for helping them out of this curiosity. We are currently introducing a new stock market price forecasting model using machine learning technique. This model predicts the next week’s stock market price outcome and is trained by looking at previous data to obtain information that can be used to predict in an accurate manner. As peoples know it’s hard to predict with 100% accuracy because the stock market price depends on various factors like Human Psychology, Natural Calamities, Political factors, Current Events, etcetera. There is so many methods for stock market price forecasting like Support Vector Machine (SVM), Reinforcement learning, etcetera. We proposed our model through Machine Learning pipeline method where we are using long short-term memory (LSTM) because as per our research we find out LSTMis better method than others to StockMarket Price Forecasting of NSE_TATA. © 2024 The Author(s).

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

Enhancing Hydroponic Systems with IoT: Optimizing pH, Temperature, and Humidity Parameters 3

Enhancing Hydroponic Systems with IoT: Optimizing pH, Temper...

引用

3rd Odisha International Conference on Electrical Power engineering, Communication and Computing Technology, ODICON 2024

作者： Debdas, Subhra Jain, Akshat Mariam, Anika Maiti, Anurati Borah, Anushka School of Electrical Engineering Kiit University Bhubaneshwar India School of Computer Science Engineering Kiit University Bhubaneshwar India School of Computer Science Engineering Kiit Kiit University Bhubaneshwar India

ISBN: (纸本)9798350354379

Hydroponic systems integrated with Internet of Things (IoT) technology offer precise monitoring and control capabilities vital for optimizing plant growth. This research paper investigates the implementation of IoT in hydroponic setups, fo- cusing on monitoring pH, temperature, and humidity parameters to ensure optimal growth conditions. The IoT system continuously measures these parameters and compares them against prede- fined optimal ranges. If the measured values deviate from the optimum, the system triggers an error notification, indicating the need for corrective action. Through a series of experiments and simulations, this study evaluates the effectiveness of the IoT-based monitoring system in maintaining ideal environmental conditions for hydroponic cultivation. The research aims to contribute to the advancement of precision agriculture by providing insights into the integration of IoT technologies to enhance crop yield and quality in hydroponic farming. © 2024 IEEE.

关键词： Hydroponics

来源：评论

学校读者我要写书评

暂无评论

Cryptanalysis in e-commerce: A novel arrangement procedure using DHEC-SAT upon elliptic curve cryptography

引用

Multimedia Tools and Applications 2025年第8期84卷 5377-5395页

作者： Fauziyah Wang, Zhaoshun School of Computer and Communication Engineering University of Science and Technology Beijing 30 Xueyuan Road Haidian District Beijing China

Cryptanalytic innovations are considered the most economical and useful method for guaranteeing information security across shared networks. Despite the tinier key magnitude of Elliptic Curve Cryptography (ECC) compared to common cryptanalysis schemes, the majority of scholars have employed cryptanalysis methods to deliver data reliability and verification. Besides, the computation attempt needed by Diffie Hellman-Elliptic Curve (DH-EC) for equal key dimensions is similar and delivers extra security advantages. The research offers a novel key arrangement procedure using DH-EC in the secure automatic transactions (SAT) setting (DHEC-SAT) to enhance data safety. The DHEC-SAT procedure effectively applied the keys in the SAT setting for online payment and was employed to decode and encode the validation data. The DHEC-SAT procedure is implemented for an entry of e-commerce payments to deliver great-degree security examination, fast verification, and the safety of the suggested Cryptanalytic scheme. The suggested DHEC-SAT generates highly secure systems regarding data size (168 bytes), computational period (4.34 ms), and communication costs (1271 bits), as contrasted to extant ECC procedures and PIN-enabled key arrangements. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Electronic commerce

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：