检索结果-内蒙古大学图书馆

A survey on causal inference for recommendation

The Innovation 2024年第2期5卷 130-144页

作者： Huishi Luo Fuzhen Zhuang Ruobing Xie Hengshu Zhu Deqing Wang Zhulin An Yongjun Xu Institute of Artificial Intelligence Beihang UniversityBeijing 100191China Zhongguancun Laboratory Beijing 100094China WeChat Search Application Department TencentBeijing 100080China The Career Science Laboratory BOSS ZhipinBeijing 100028China SKLSDE School of Computer ScienceBeihang UniversityBeijing 100191China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China

Causal inference has recently garnered significant interest among recommender system(RS)researchers due to its ability to dissect cause-and-effect relationships and its broad applicability across multiple *** offers a framework to model the causality in RSs such as confounding effects and deal with counterfactual problems such as offline policy evaluation and data *** there are already some valuable surveys on causal recommendations,they typically classify approaches based on the practical issues faced in RS,a classification that may disperse and fragment the uni-fied causal *** RS researchers’unfamiliarity with causality,it is necessary yet challenging to comprehensively review relevant studies from a coherent causal theoretical perspective,thereby facilitating a deeper integration of causal inference in *** survey provides a systematic review of up-to-date papers in this area from a causal theory standpoint and traces the evolutionary development of RS methods within the same causal ***,we introduce the fundamental concepts of causal inference as the basis of the following ***,we propose a novel theory-driven taxonomy,categorizing existing methods based on the causal theory employed,namely those based on the potential outcome framework,the structural causal model,and general *** review then delves into the technical details of how existing methods apply causal inference to address particular recommender ***,we highlight some promising directions for future research in this *** papers and open-source resources will be progressively available at https://***/Chrissie-Law/Causal-Inference-forRecommendation.

关键词： survey details causal

来源：评论

学校读者我要写书评

暂无评论

Human-computer Interaction and Knowledge Transfer: Study of E-Learning Achievement 7

Human-Computer Interaction and Knowledge Transfer: Study of ...

引用

7th International Conference of computer and Informatics Engineering, IC2IE 2024

作者： Alamsyah, Doni Purnama Othman, Norfaridatul Ahkmaliah Kerta, Johan Muliadi Morika, Doni Ramdhani, Yudi Bina Nusantara University Binus Business School Creativepreneurship Department Jakarta Indonesia Universiti Teknikal Malaysia Melaka Department of Management Technology Melaka Malaysia Bina Nusantara University School of Computer Science Computer Science Department Jakarta Indonesia Bina Nusantara University School of Design Design Interior Department Jakarta Indonesia Satu University Information System Program Bandung Indonesia

ISBN: (纸本)9798331505530

Human-computer interaction influences the effectiveness of e-learning knowledge transfer, so it is necessary to pay attention to user engagement and achievement. The aim of this research is to examine the factors that support e-learning knowledge transfer through achievement and user engagement (self-efficacy, self-confidence, self-esteem). The research method was carried out by surveying e-learning users, namely students, data from students was collected through quantitative questionnaires. The data is then processed using the SmartPLS tool through two tests, namely the PLS Algorithm and Boostrapping. The model was tested using inner and outer tests, and the data was analyzed based on the research hypothesis design. Student interactions with e-learning influence several behaviors that can support e-learning knowledge transfer performance. The research results prove that student e-learning achievement has a positive impact on e-learning knowledge transfer. Several supporting factors play a role in increasing e-learning achievement, namely self-efficacy, self-confidence and self-esteem of students. However, the supporting factors for students are only self-efficacy and self-confidence which are directly able to increase e-learning knowledge transfer. It is known that students who are less able to respect themselves in interacting with e-learning are unable to support knowledge transfer. The rules of human-computer interaction play a role in supporting e-learning knowledge transfer, studies on user behavior need to be considered, especially self-efficacy and self-confidence to support online learning academic performance. © 2024 IEEE.

关键词： Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

Representing Multiview Time-Series Graph Structures for Multivariate Long-Term Time-Series Forecasting

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2651-2662页

作者： Wang, Zehao Fan, Jin Wu, Huifeng Sun, Danfeng Wu, Jia Hangzhou Dianzi University Department of Computer Science and Technology Hangzhou310018 China Zhejiang Provincial Key Laboratory of Industrial Internet in Discrete Industries Hangzhou310018 China Zhejiang Normal University Laboratory of Intelligent Education Technology and Application of Zhejiang Province Hangzhou310018 China Macquarie University School of Computing SydneyNSW2113 Australia

Multivariate long-term time-series forecasting tasks are very challenging tasks in many real-world application areas. Recently, researchers focus on designing robust and effective methods, and have made considerable progress. However, there are several issues with existing models that need to be overcome. First, the lack of a relationship structure between multivariate variables needs to be addressed. Second, most models only have a weak ability to capture local dynamic changes across the entire long-term time-series. Third, current models suffer from high computational complexity and unsatisfactory accuracy. To figure out the abovementioned issues, we propose an effective and efficient method called multiview time-series graph structure representation (MTGSR). MTGSR uses GCNs to construct topological relationships in the multivariate time-series from three different perspectives: time, dimension, and crossing segments. Variation trends in different dimensions are extracted through a difference operation to construct topological maps that reflect the correlations between different dimensions. To capture the dynamically changing characteristics of fluctuation correlations between adjacent local sequences, MTGSR constructs a cross graph by calculating correlation coefficients between adjacent local sequences. Extensive experiments show that MTGSR reduces errors by 17.41% over the state of the art. In addition, memory use is decreased by 66.52% and the running time is reduced by 78.09%. © 2020 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Approach for Threat Detection in Cyber Security using AI algorithm 1

A Novel Hybrid Approach for Threat Detection in Cyber Securi...

引用

1st International Conference on Computing, sciences and Communications, ICCSC 2024

作者： Gupta, Abhishek Kumar Dixit, Neetu Kumar, Sujeet Rawat, Priyanka Madhumita Jagannath International Management School Department of Information Technology New Delhi110070 India RBMI Department of Computer Application Greater Noida201306 India GL Bajaj Institute of Management Greater Noida201306 India Lingaya's Vidyapeeth Department of Computer Science & Engineering Faridabad121002 India

ISBN: (纸本)9798350353648

The dynamic cyber-attack landscape might require more traditional ways of detecting and preventing threats. It has also paved the way for new hybrid approaches that merge attributes of two or more different methods, enabling a better and more efficient cyber defence. Such an approach would be to apply artificial intelligence (AI) algorithms to detect threats. In this way, organizations can apply various capabilities to automatically scan network traffic round-the-clock for indicators of suspicious activities, notifying security teams immediately. Despite this, a system that relies entirely on AI algorithms gets many false positives, increasing the time and effort required by security personnel. Our hybrid approach includes human expertise and input to help detect potential risks. This comes as a human-in-the-loop solution, where AI algorithms identify suspicious signals, and humans then corroborate those leads before making an arrest. Combining human and AI intelligence results in a far more accurate and efficient threat detection system. Our strategy incorporates big data analytics and anomaly detection methods to highlight unusual behaviours that suggest a risk is forming. This allows our system to discover and eliminate these cyber attacks in real-time instead of merely reacting after a breach. By leveraging our novel hybrid approach, you can have better coverage and a more robust cyber security plan in the face of threats, giving you a higher level of protection and peace of mind about future attacks. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Evaluating Glucocorticoid Toxicity Index as a Predictor of Intestinal Adhesion Formation After Abdominal Surgery 5th

Evaluating Glucocorticoid Toxicity Index as a Predictor of I...

引用

5th International Conference on Data science, Machine Learning and applications, ICDSMLA 2023

作者： Tyagi, Pankaj Kumar Beemkumar, N. Agarwal, Ankita Kaushik, Harshita Department of Biotechnology Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science and Application Vivekananda Global University Jaipur India

ISBN: (纸本)9789819780426

Stomach surgical operation can cause damage to intestinal tissue and is associated with a better risk of adhesive intestinal ailment. The main symptom of the adhesive intestinal disorder is intestinal adhesion, a continual and probably life-threatening hassle. Glucocorticoid use at the time of abdominal surgical procedures has been related to an increase in the danger of adhesive intestinal sickness. In addition to recognizing this disorder’s threat and protecting factors, the existing examination evaluated the Glucocorticoid Toxicity Index (GTI) as a predictor of intestinal adhesion formation in patients’ present process of stomach surgical operation. A prospective discussion was conducted on 220 sufferers who underwent stomach surgical treatment at an urban coaching hospital. The GTI change was measured at the time of the surgical treatment, and the patients were accompanied for one year after their surgery. The consequences of the look showed that there had been a statistically significant affiliation between higher GTI and the occurrence of postoperative intestinal adhesion after a stomach surgical operation. Moreover, the facts confirmed that there had been an additive effect of other chance factors, together with the acute inflammatory procedure or impaired wound healing, on the hazard of adhesion formation while blended with GTI. Those results propose that GTI is a dependable predictor of intestinal adhesion formation after a belly operation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Transplantation (surgical)

来源：评论

学校读者我要写书评

暂无评论

A New Heterogeneous Hybrid Massive MIMO Receiver With an Intrinsic Ability of Removing Phase Ambiguity of DOA Estimation via Machine Learning

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine Learning in Communications and Networking 2025年 3卷 17-29页

作者： Shu, Feng Shi, Baihua Chen, Yiwen Bai, Jiatong Li, Yifan Liu, Tingting Han, Zhu You, Xiaohu Hainan University School of Information and Communication Engineering Haikou570228 China Nanjing University of Science and Technology School of Electronic and Optical Engineering Nanjing210094 China Hainan University Collaborative Innovation Center of Information Technology Haikou570228 China Nanjing University of Posts and Telecommunications School of Computer Science Nanjing210003 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Southeast University National Mobile Communications Research Laboratory Nanjing210096 China Purple Mountain Laboratories Nanjing211111 China

Massive multiple input multiple output (MIMO) antenna arrays eventuate a huge amount of circuit costs and computational complexity. To satisfy the needs of high precision and low cost in future green wireless communication, the conventional hybrid analog and digital MIMO receive structure emerges a natural choice. But it exists an issue of the phase ambiguity in direction of arrival (DOA) estimation and requires at least two time-slots to complete one-time DOA measurement with the first time-slot generating the set of candidate solutions and the second one to find a true direction by received beamforming over this set, which will lead to a low time-efficiency. To address this problem,a new heterogeneous sub-connected hybrid analog and digital ( H2 AD) MIMO structure is proposed with an intrinsic ability of removing phase ambiguity, and then a corresponding new framework is developed to implement a rapid high-precision DOA estimation using only single time-slot. The proposed framework consists of two steps: 1) form a set of candidate solutions using existing methods like MUSIC;2) find the class of the true solutions and compute the class mean. To infer the set of true solutions, we propose two new clustering methods: weight global minimum distance (WGMD) and weight local minimum distance (WLMD). Next, we also enhance two classic clustering methods: accelerating local weighted k-means (ALW-K-means) and improved density. Additionally, the corresponding closed-form expression of Cramer-Rao lower bound (CRLB) is derived. Simulation results show that the proposed frameworks using the above four clustering can approach the CRLB in almost all signal to noise ratio (SNR) regions except for extremely low SNR (SNR © 2024 The Authors.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Impact of Glucocorticoid Toxicity Index on Immunosuppressive Management of Inflammatory Bowel Disease 5th

Impact of Glucocorticoid Toxicity Index on Immunosuppressive...

引用

5th International Conference on Data science, Machine Learning and applications, ICDSMLA 2023

作者： Yadav, Dhyan Chandra Sharma, Sunil Agarwal, Chhaya Mehta, Deepak Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science and Application Vivekananda Global University Jaipur India Department of Biotechnology Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India

ISBN: (纸本)9789819780426

Glucocorticoid toxicity index (GTI) is a useful degree proposed by using a meta-evaluation to assess the chance of systemic glucocorticoid exposure in sufferers laid low with inflammatory bowels illnesses (IBD). The GTI is computed based totally on cumulative glucocorticoid cumulative dose and duration within the first yr. After a prognosis of IBD. The contemporary take a look at objectives to check the literature to decide the utility of GTI in predicting the danger of glucocorticoid toxicity in IBD patients. A literature search turned into conducted to pick out research that evaluated the predictive price of GTI for toxicity in IBD patients. The retrieved articles suggest that cumulative glucocorticoid dose and length prior to three hundred and sixty five days of the diagnosis of IBD have been massive factors related to the prevalence of glucocorticoid toxicity in IBD sufferers. However, different next elements may additionally have an effect on the toxicity of glucocorticoid exposure in IBD patients, along with age, comorbidities, and genetic polymorphisms. Moreover, some of the research, the outcomes validated that GTI can be a valuable device for immunosuppressive management in IBD sufferers to be able to discover patients who're much more likely to revel in systemic toxicity at some stage in immunosuppressive treatment. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cumulative Exposure Glucocorticoid

来源：评论

学校读者我要写书评

暂无评论

Automated Anomaly Detection in Medical Imaging Using Support Vector Machines 5th

Automated Anomaly Detection in Medical Imaging Using Support...

引用

5th International Conference on Data science, Machine Learning and applications, ICDSMLA 2023

作者： Goyal, Manish Kumar Shahid, Mohammad Karthikeyan, M.P. Kumar, Ritesh Department of Computer Science & Application Vivekananda Global University Jaipur India Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India

ISBN: (纸本)9789819780426

Clinical imaging techniques such as X-ray, Magnetic Resonance Imaging (MRI), and laptop Tomography (CT) scanners are used to diagnose, compare, and deal with sufferers. Automatic Anomaly Detection is an automatic technique for identifying and diagnosing abnormalities in clinical imaging. It has been diagnosed that Support Vector Machines (SVM) can be effectively used to generate correct automatic anomaly detection for scientific imaging. SVM is an approach that uses supervised getting-to-know to create a choice boundary between classes, with the decision primarily based on the information to be had. The gain of SVM is that it plays an automatic function extracting from the medical imaging facts and uses those extracted capabilities for anomaly detection. It combines photograph segmentation and classification to classify the abnormal regions in an image. So one can enhance the accuracy of SVM;it's miles viable to use an expansion of kernel capabilities and unique parameter tuning. Moreover, introducing an automatic pipeline from training to deploying SVM reduces the efforts of manual feature extraction from photos. Consequently, aid Vector Machines is a feasible approach for automatic anomaly detection in scientific imaging. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Improving Medical Image Classification Through Transfer Learning and Meta Learning 5th

Improving Medical Image Classification Through Transfer Lear...

引用

5th International Conference on Data science, Machine Learning and applications, ICDSMLA 2023

作者： Arora, Sonia Jebakumari, S. Adlin Singh, Vaishali Kharbas, Vikas Kumar Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science and Application Vivekananda Global University Jaipur India

ISBN: (纸本)9789819780426

This paper presents an observation of improving clinical picture classification via transfer getting to know and meta-studying. Switching getting-to-know and meta-learning methods are usually employed in medical imaging class tasks. Transfer studying objectives to switch information and illustration from a properly-trained version and mildew that expertise to higher healthy the problem at hand, while meta-gaining knowledge is a version of switch gaining knowledge of which targets to seize and adapt the generalizable expertise of a project domain, and to allow a progressed impact for the goal tasks. Inside the clinical imaging scenario, the two procedures can dig deeper into the several layers which might be involved in gaining deep knowledge of algorithms. The authors compare the effectiveness of the proposed strategies in five publicly available medical imaging datasets. Effects have shown that the proposed techniques notably advanced the usual type accuracy for a few datasets. Furthermore, it was found that the 2-step technique showed higher performance than the one-step technique. This study presents a higher understanding of the efficacy of transfer learning and meta-mastering techniques for clinical photo-type tasks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Noise-robust neural networks for medical image segmentation by dual-strategy sample selection

Noise-robust neural networks for medical image segmentation ...

引用

作者： Shi, Jialin Yang, Youquan Zhang, Kailai School of Computer and Communication Engineering Shunde Innovation School University of Science and Technology Beijing Beijing China Shunde Innovation School ByteDance Beijing China Department of Networks China Mobile Communications Group Co Ltd Beijing China

Deep neural networks for medical image segmentation often face the problem of insufficient clean labeled data. Although non-expert annotations are more readily accessible, these low-quality annotations lead to significant performance degradation of existing neural network methods. In this paper, we focus on robust learning of medical image segmentation with noisy annotations and propose a novel noise-tolerant framework based on dual-strategy sample selection, which selects the informative samples to provide effective supervision information. First, we propose the first round of sample selection by designing a novel joint loss, which includes conventional supervised loss and regularization loss. To further select information-rich samples, we propose confidence-based pseudo-label sample selection from a novel perspective as the complement. The dual strategies are used in a collaborative manner and the network is optimized with mined informative samples. We conducted extensive experiments on datasets with both simulated noisy labels and real-world noisy labels. For instance, on a simulated dataset with 25% noise ratio, our method achieves segmentation Dice value with 90.56% (Formula presented.) 0.03%. Furthermore, increasing the noise ratio to 95%, our method still maintains a high Dice value of 73.85% (Formula presented.) 0.28% compared to other baselines. Extensive results have demonstrated that our method can weaken the effects of noisy labels on medical image segmentation. © 2024 John Wiley & Sons Ltd.

关键词： deep learning medical image segmentation noisy labels sample selection

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：