检索结果-内蒙古大学图书馆

Discovering Social Media Influencers Using a Deep Regression Analysis

SN computer science 2025年第4期6卷 1-18页

作者： Ramya, G.R. Bagavathi Sivakumar, P. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

Highly influential users (IUs) play a vital role in disseminating information on online social networks (OSNs). Recognizing IUs is crucial for brand awareness, strategic marketing and consumer engagement. Researchers have developed the temporal influential model (TIM) and incremental logistic regression (ILLR) to find out the probability of a user being influential on Twitter. However, accurately identifying IUs requires considering multiple user and tweet attributes. This study proposes a model for predicting IUs by analyzing user and trend-based attributes from tweets, calculating a weighted associated influence (WAI) score for each user and enhancing IU prediction through user similarity, influence degree, and trustworthiness metrics. The goal is to combine the TIM with deep regression (TIM-DeepReg) to improve accuracy in predicting high IUs on OSNs while handling large amounts of data and attributes. The TIM-DeepReg model combines convolutional neural network (CNN) with regression to automatically learn user and tweet attributes and enhance IU prediction efficiency. Lastly, the experimental findings show that the TIM-DeepReg model surpasses other models in IU prediction for the Tariff, Service, and Punctuality topics of airline services on Twitter and Facebook, with 87.4%, 88.9%, and 88.8% of the most influential individuals predicted. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep regression Influencer on social networks Influencer prediction from Facebook and Twitter Temporal influential model Weighted associated influence score

来源：评论

学校读者我要写书评

暂无评论

Analyzing The Most Effective Algorithm For Knapsack Problems 3

Analyzing The Most Effective Algorithm For Knapsack Problems

引用

3rd International Conference on Smart Cities, Automation and Intelligent Computing Systems, ICON-SONICS 2023

作者： Boes, Devano Fernando Dewanto, Kenrick Panca Raushanfikir, Mahesa Insan Handoyo, Alif Tri Nurhasanah Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Statistics Department Jakarta11480 Indonesia

ISBN: (纸本)9781509062805

Knapsack problem is a classical optimization problem in computer science and programming. Knapsack problem main objective is to solve how much the maximum profit can be carried with the knapsack maximum capacity. The item has its own weight and profit. In this paper, we research which algorithm is most effective in solving the 0/1 knapsack and the fractional knapsack problem. The algorithm used for this research is brute force, greedy, dynamic programming, and branch and bound algorithm. Those algorithms will be tested on both knapsack problems, using several datasets on each problem. The program used to execute the algorithm is Python programming language. The results from this research are the dynamic programming has 100% success rate on both problem, the brute force has 100% success rate on the 0/1 knapsack however it only has 20% success rate on the fractional knapsack problem, the greedy algorithm surprisingly has 100% success rate on the fractional knapsack problem and 60% success rate on the 0/1 knapsack problem, and the branch and bound algorithm has 100% success rate on the fractional knapsack while has 0% success rate on the 0/1 knapsack problem. This research also considered the time complexity of each algorithm to make the conclusion. Graphs are provided for better visualization on the results. © 2023 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Fostering Digital Innovation in Indonesia: The Role of STEM-AI Skills in Overcoming Talent Deficits and Gender Stereotypes 4

Fostering Digital Innovation in Indonesia: The Role of STEM-...

引用

4th International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2024

作者： Halim, Erwin Zahra, Amalia Maryani Wulandhari, Lili Ayu Fitrianah, Devi Puspita, Virienia School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Communication Department Jakarta11480 Indonesia

ISBN: (纸本)9798331506490

This research explores the optimization of digital talent in advanced industries, particularly in the context of rapid digital transformation. Despite the increasing importance of digital talent for gaining a competitive edge, several challenges persist. In Indonesia, for example, there is a significant shortage of digitally skilled workers, with the World Bank reporting a gap of 9 million skilled individuals over the past 15 years. Additionally, artificial intelligence (AI) is expected to impact 9.5 million jobs, further exacerbating the demand for digital skills. Furthermore, the employability of graduates remains low, largely due to inadequate training, poor language proficiency, and limited cultural sensitivity. Many companies face difficulties in finding qualified individuals, quickly upskilling their workforce, and fostering an innovative organizational culture. This study seeks to evaluate the factors influencing digital talent performance in the context of these challenges. It examines seven key variables: digital readiness, digital technology adoption, relevance of AI, digital skills, individual performance, problem-solving ability, and overall digital talent performance. Hypotheses were tested using Partial Least Squares Structural Equation Modeling (PLS-SEM). data was collected from 378 participants, primarily students with STEM backgrounds, in the Jabodetabek area of Indonesia in November 2024. The findings reveal that all hypotheses are significant, with results indicating that user satisfaction and the perceived value of digital talent in Indonesia have a notable impact on continued usage intentions in digital roles. © 2024 IEEE.

关键词： digital readiness digital talent performances digital technology individual performance STEM-AI

来源：评论

学校读者我要写书评

暂无评论

Variational Adapter: Improving CLIP in data-Imbalanced Scenarios

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 5251-5264页

作者： Lu, Ziqian Liu, Mushui Yu, Yunlong Wang, Zhao Li, Xi Han, Jungong Zhejiang University School of Aeronautics and Astronautics Hangzhou310027 China Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China Zhejiang University Ningbo Innovation Center Ningbo China Zhejiang University College of Computer Science Hangzhou310027 China The University of Sheffield Department of Computer Science Sheffield United Kingdom

In this paper, we propose the Prompt-based Variational Adapter (PVA), a novel approach designed to fine-tune the pre-trained Vision-Language Models (VLMs) in data-imbalanced scenarios. Unlike existing methods that focus primarily on pairwise alignment of visual-text relationships during fine-tuning, PVA relaxes pairwise explicit constrains and emphasizes the harmonization of visual and text modality distributions, enhancing generalization and cross-modal understanding. To realize this harmonization, we develop two variational adapters, which are appended separately to the visual and text encoders. These adapters transform the feature embeddings into latent spaces that implicitly align with the corresponding modality distributions. We then adopt a divide-and-conquer strategy, dividing classes into data-abundant and data-limited sets to reduce prediction bias. Within each set, we independently fine-tune the models by incorporating both the model's original general knowledge and specialized knowledge gained from training samples. Extensive experiments across two data-imbalanced scenarios validate the superiority of our approach, establishing a new state-of-the-art on popular benchmarks. © 1991-2012 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Heart Disease Risk Prediction using K-Nearest Neighbor: A Study of Euclidean and Cosine Distance Metrics 3

Heart Disease Risk Prediction using K-Nearest Neighbor: A St...

引用

3rd International Conference on Smart Cities, Automation and Intelligent Computing Systems, ICON-SONICS 2023

作者： Prasetyo, Simeon Yuda Kurniawan, Afdhal Sihotang, Erna Fransisca Angela Puspita, Rani Setiawan, Karli Eka Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Statistics Department Jakarta11480 Indonesia

ISBN: (纸本)9781509062805

Cardiovascular disease, with an annual fatality rate of 17.9 million individuals, poses a significant global health crisis. Swift and precise diagnosis is paramount, particularly in regions with limited access to advanced medical technology. This paper employs machine learning techniques to predict heart disease, emphasizing hyperparameter optimization for heightened accuracy. Utilizing a diverse dataset to address issues like duplicate data, we conduct a comparative analysis of Euclidean and Cosine distances within the K-Nearest Neighbor (KNN) algorithm, filling a research gap and providing a comprehensive evaluation of these distance metrics. Label Encoding is applied for categorical variables, and KNN is implemented with varying neighbor counts (1,3,5,7,9) using both Euclidean and Cosine distances. Evaluation metrics, including accuracy, precision, recall, and F1 score, gauge model performance. Our experiments reveal the highest accuracy of 90.761% when KNN is configured with 7 neighbors and the Cosine distance metric, surpassing the Euclidean distance. This underscores the criticality of careful distance metric selection in heart disease prediction models. The study offers insights into predictive modeling in healthcare, emphasizing the significance of distance metric choice. To streamline the abstract, omitting details related to future research and maintaining brevity is recommended. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Hierarchical multi-granularity classification based on bidirectional knowledge transfer

引用

Multimedia Systems 2024年第4期30卷 1-12页

作者： Jiang, Juan Yang, Jingmin Zhang, Wenjie Zhang, Hongbin School of Computer Science Minnan Normal University Fujian Zhangzhou363000 China Key Laboratory of Data Science and Intelligence Application Fujian Province University Fujian Zhangzhou363000 China Department of Electronic Engineering National Taipei University of Technology Taipei China

Hierarchical multi-granularity classification is the task of classifying objects according to multiple levels or granularities. The class hierarchy is vital side information for hierarchical multi-granularity classification. The existing hierarchical multi-granularity classification research utilizes class hierarchy to classify from coarse to fine or fine to coarse. Although these methods are effective in many cases, there are still two issues: (1) multi-task learning for hierarchical multi-granularity classification leads to decreased classification performance;(2) class hierarchy transfer learning is prone to error propagation. In this paper, we propose a bidirectional knowledge transfer model framework to address these issues. Firstly, we improve classification performance through data augmentation. Specifically, by learning the similarity between the original image and the enhanced image, better learn discriminative features, which is beneficial for subsequent classification. Secondly, using class hierarchy trees, we propose reverse hierarchical knowledge transfer to correct some errors in forward hierarchical propagation and improve hierarchical consistency. In addition, we also construct a hierarchical network that adds features from coarse-grained levels to fine-grained levels. The experimental results on six datasets with different class hierarchies demonstrate the effectiveness and superiority of the proposed model. Especially on the CUB-200-2011 and Cifar-100 datasets, our model improved classification accuracy by 3.61% and 4.17% compared to the suboptimal model. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

An Improved Churn Prediction Model using Relevance Feature Identification and Personalized Modeling Technique with Optimized Retention Strategies 8

An Improved Churn Prediction Model using Relevance Feature I...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Pratheebha, T. Megala, S. Santhana Indumathi, V. Rvs College of Arts and Science School of Computer Studies Coimbatore India P.A College of Education Computer Science Pollachi India Hindusthan College of Arts and Science Department of Computer Technology Coimbatore India

ISBN: (纸本)9798350367904

Churn prediction is vital in customer retention strategies, helping businesses proactively address customer dissatisfaction. In this research, we propose a comprehensive churn prediction model that addresses these challenges by integrating advanced techniques, including handling imbalanced data, feature relevance identification, new feature generation, incorporating temporal patterns, and personalized modeling for customer segments. By applying advanced techniques such as SMOTE-ENN for balancing, RFE-RF for feature elimination, and K-Means clustering for segmentation, the model improves predictive accuracy and provides actionable insights for targeted retention strategies. The proposed model effectively enhances prediction accuracy and provides actionable insights for customer groups, optimizing retention strategies. With the proposed Model Logistic Regression performs better across all segments in terms of AUC-ROC and precision particularly for high-value and frequent users with 0.91 % and 0.80 % respectively. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Task Offloading and Resource Management for IIoT with Satellite-Terrestrial Integrated Computing Power Network Based on D3QN

引用

IEEE Internet of Things Journal 2025年第12期12卷 21770-21783页

作者： Li, Meng Li, Meihui Wang, Kan Yu, F. Richard Wang, Zhuwei Si, Pengbo Beijing University of Technology School of Information Science and Technology Beijing100124 China Xi'an University of Technology School of Computer Science and Engineering Xi'an710048 China Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada

The management of computing resources through the computing power network (CPN) has gradually become a focal point of research. With the development of the 6th generation (6G) mobile networks, some promising technologies such as satellite-terrestrial integrated network (STIN) and smart endogenous network driven by artificial intelligence (AI) are increasingly being applied in Industrial Internet of Things (IIoT). However, several issues in current studies are worthy of attention: 1) the large number of devices powered by battery in IIoT, 2) the complex communication environments, 3) the finite computing resources for task data processing. To cope with these challenges, a satellite-terrestrial integrated computing power network (STICPN) framework is introduced in this article. Within this framework, a task offloading link selection scheme is proposed, which minimizes the delay and the consumption of energy. The task offloading optimization problem is modeled as a Markov Decision Process (MDP). Meanwhile, deep reinforcement learning (DRL) algorithm is employed to adapt to the dynamic states of environment. Specifically, a Dueling Double Deep Q Network (D3QN) is used to make optimal decisions and delay as well as energy consumption can be reduced significantly. Moreover, the D3QN-based scheme extends the usage time of IIoT devices. The simulation results indicate that the proposed scheme outperforms the comparison schemes significantly. © 2025 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Multi-class Chest Radiograph Classification Using Deep Convolutional Generative Adversarial Networks 6th

Multi-class Chest Radiograph Classification Using Deep Convo...

引用

6th International Conference on Recent Innovations in Computing, ICRIC 2023

作者： Kaushik, Hariharan Natarajan, B. Annamalai, R. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India School of Computer Science and Engineering VIT University Chennai India

ISBN: (纸本)9789819778614

The urgency for precise diagnostics during the COVID-19 pandemic has driven advancements in imaging and deep learning tools. However, progress is impeded by limited access to medical imaging data. This study employs cutting-edge deep learning techniques to identify chest diseases, including COVID-19 and various lung conditions. State-of-the-art Generative Adversarial Networks (GANs), including CycleGAN, Super-Resolution GAN (SRGAN), and Deep Convolutional GAN (DCGAN), are used to synthesize medical images, augmenting the dataset and enhancing model robustness. VGG-19 achieves a remarkable 91% accuracy and an F1-score of 0.98 across diverse chest-related diseases. Saliency Maps and Grad-CAM graphics improve interpretability, showcasing the model’s healthcare potential. The study encompasses diseases such as Pneumonia and COVID-19, contributing to a comprehensive classification task. These findings underscore the impact of deep learning in medical imaging, promising improved patient care and healthcare accessibility. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of the 5Rs in Thailand Medication Error Classification through Natural Language Processing 20

Analysis of the 5Rs in Thailand Medication Error Classificat...

引用

20th International Joint Conference on computer science and Software Engineering, JCSSE 2023

作者： Udomnuchaisup, Peachyasitt Imsombut, Aurawan Suwannahitatorn, Picha Saethang, Thammakorn Kasetsart University Biomedical Data Science Master's Program Faculty of Science Bangkok Thailand Kasetsart University Faculty of Science Department of Computer Science Bangkok Thailand Bangkok Thailand

ISBN: (纸本)9798350300505

Medication errors threaten patient safety considerably, underscoring the necessity for enhanced detection and prevention techniques. A prevalent classification system in hospitals relies on the standard practice of medication administration known as the Five Rights (5R). This study seeks to develop an NLP-based tool designed to expand 5R error categorization coverage and alleviate the workload of medical professionals. The proposed method focuses on Thai medical text, incorporating Thai and English vocabulary. In this investigation, we developed a supervised learning classification framework using the Universal Sentence Encoder (USE) for sentence embedding, followed by an Artificial Neural Network (ANN) for model training. Additionally, we explored a zero-shot classification model employing pre-trained Large Language Models (PLMs). Our findings reveal that the supervised learning classification model provides the most favorable performance, albeit with the limitation of reliance on labeled datasets, which can be resource intensive. Conversely, the zero-shot classification framework's performance is less optimal. However, future advancements in Thai medical PLMs may improve efficacy and present a viable alternative for medical data analysis without dependence on labeled datasets. This initiative lays the groundwork for potential future applications and advantages within Thailand's medical domain. © 2023 IEEE.

关键词： Neural networks

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：