检索结果-内蒙古大学图书馆

2023 7th International Conference On Computing, Communication, Control And Automation, ICCUBEA 2023

作者： Bera, Ankan Das, Rik Ghosh, Sayantani Chakraborty, Raktim Mitra, Indranil Nandy, Prasun Data & Analytics Advanced Analytics PwC India

ISBN: (纸本)9798350304268

Pharmacovigilance plays an important role in monitoring safety of pharmaceutical products. There is an abundance of unstructured data available in social media and online reviews that can provide valuable insights into adverse drug reaction (ADR). This research paper aims to explore the efficient techniques of pharmacovigilance in identifying ADRs from unstructured data available in social media and reviews. This research work proposes the use of a transformer-based model for ADR classification, followed by named entity recognition (NER) to identify the causality between drugs and adverse effects. Furthermore, the output of NER is provided as a customized prompt to the generative AI model to generate a user interpretable explanation. Enhancing the accuracy of NER is carried out using the SciBERT model, which is specifically designed to capture drug and effect names. By utilizing this combination of techniques, the research aims to improve the efficiency and effectiveness of pharmacovigilance processes, enabling earlier detection and reporting of ADRs. To our knowledge, previous works have not explored the application of generative AI based customized explanation of causality. Patients, healthcare professionals, regulatory agencies, and pharmaceutical companies can benefit from the timely and accurate identification of ADRs, allowing for improved drug safety monitoring, better decision-making regarding drug usage, and the development of proactive measures to mitigate risks. © 2023 IEEE.

关键词： ADR BERT Generative AI GPT Named Entity Recognition Pharmacovigilance Text Classification Transformers

来源：评论

学校读者我要写书评

暂无评论

Fostering Sustainable Poultry Farming: Chicken Disease Classification through Ensemble Techniques and Local Attention-Based Fused Descriptor Definition 2

Fostering Sustainable Poultry Farming: Chicken Disease Class...

引用

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Ghosh, Sayantani Chakraborty, Anik Das, Rik Mitra, Indranil Chakraborty, Raktim Nandy, Prasun Data & Analytics Advanced Analytics PwC India

ISBN: (纸本)9798350305418

Chicken disease classification assumes a vital role in maintaining the health and productivity of poultry farms. By accurately identifying diseases through automated image analysis, the poultry industry can take prompt preventive measures, reduce economic losses, and improve flock management practices. This approach offers a cost-effective solution for the pharmaceutical industry by reducing the need for expensive manual diagnosis and enabling targeted drug development, ultimately increasing sales revenue. Deep learning-based feature extraction plays a crucial role in chicken disease classification from poultry fecal images. By employing advanced techniques such as vision transformers and EfficientNet-B0-B0, intricate features can be extracted from the images, allowing for more accurate disease classification. To the best of our knowledge, none of the previous work has evaluated vision transformer in capturing global contextual information for chicken disease classification from fecal images. On the other hand, EfficientNetB0-B0 offers efficient and scalable feature extraction. Therefore, both the techniques are vital for analyzing complex patterns within the images. Hence, the work has explored early and late ensembling techniques to investigate feature generalization as well as decision fusion of diverse classifiers for enhanced precision in classification results of the chicken diseases. The classification process is carried out using classical algorithms viz, Support Vector Machine (SVM), Logistic Regression(LR) and Random Forest(RF) instead of transfer learning since traditional classifiers offer greater flexibility in evaluating tailored approaches like feature fusion and decision fusion. The late ensembling with classifier decision fusion has outclassed all the other classification techniques in efficiently identifying chicken diseases from fecal images. © 2023 IEEE.

关键词： chicken disease classification classifier ensemble computer vision feature ensemble representation learning vision transformers

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Customer Segmentation and Product Recommendation to Boost Sales using Machine Learning 10

A Novel Approach for Customer Segmentation and Product Recom...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Chakraborty, Anik Dey, Krishnendu Ghosh, Sayantani Chakraborty, Raktim Mitra, Indranil Nandy, Prasun Data and Analytics Advanced Analytics PwC India Kolkata India

ISBN: (纸本)9789380544472

Personalized marketing is one of the most important marketing strategies which drives sales for a business by recommending the right products to the right customers. With the growing volume of consumers, it becomes necessary to divide them into suitable groups to take appropriate action for the correct set of customers. The prime objective of this study is to segment the customers into meaningful groups, suggest different marketing strategies for various segments, and recommend suitable products for each customer within the groups. This paper analyses historical sales and customer interaction data of the business to derive the right attributes. This study has used K-Means clustering, an unsupervised machine learning algorithm, to obtain five separable clusters with a silhouette score of 0.57. For product recommendation, a voting ensemble-based recommendation system has been used to suggest up to the top 10 products for each customer. The ensemble method consists of four techniques: user-based collaborative filtering, LightFM algorithm, KNNWithMeans algorithm, and neural network. The paper aims to amalgamate customer segmentation and product recommendation problem statements for developing a single solution to help businesses design personalized marketing strategies. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A comprehensive study on fault tolerance in stream processing systems

引用

Frontiers of Computer Science 2022年第2期16卷 80-97页

作者： Xiaotong WANG Chunxi ZHANG Junhua FANG Rong ZHANG Weining QIAN Aoying ZHOU School of Data Science and Engineering East China Normal UniversityShanghai 200062China Advanced Data Analytics Laboratory of Soochow University Suzhou 215006China

Stream processing has emerged as a useful technology for applications which require continuous and low latency computation on infinite streaming *** stream processing systems(SPSs)usually require distributed deployment on clusters of servers in face of large-scale of data,it is especially common to meet with failures of processing nodes or communication networks,but should be handled seriously considering service quality.A failed system may produce wrong results or become unavailable,resulting in a decline in user experience or even significant financial ***,a large amount of fault tolerance approaches have been proposed for *** approaches often have their own priorities on specific performance concerns,e.g.,runtime overhead and recovery ***,there is a lack of a systematic overview and classification of the state-of-the-art fault tolerance approaches in SPSs,which will become an obstacle for the development of ***,we investigate the existing achievements and develop a taxonomy of the fault tolerance in ***,we propose an evaluation framework tailored for fault tolerance,demonstrate the experimental results on two representative open-sourced SPSs and exposit the possible disadvantages in current ***,we specify future research directions in this domain.

关键词： fault tolerance performance evaluation stream processing

来源：评论

学校读者我要写书评

暂无评论

A Survey and Experimental Review on data Distribution Strategies for Parallel Spatial Clustering Algorithms

引用

Journal of Computer Science & Technology 2024年第3期39卷 610-636页

作者： Jagat Sesh Challa Navneet Goyal Amogh Sharma Nikhil Sreekumar Sundar Balasubramaniam Poonam Goyal Advanced Data Analytics and Parallel Technologies Laboratory Birla Institute of Technology and Science Pilani 333031India Uber New York 11101U.S.A. Computer Science and Engineering Department University of MinnesotaMinneapolis 55455U.S.A.

The advent of Big data has led to the rapid growth in the usage of parallel clustering algorithms that work over distributed computing frameworks such as MPI,MapReduce,and *** important step for any parallel clustering algorithm is the distribution of data amongst the cluster *** step governs the methodology and performance of the entire *** typically use random,or a spatial/geometric distribution strategy like kd-tree based partitioning and grid-based partitioning,as per the requirements of the ***,these strategies are generic and are not tailor-made for any specific parallel clustering *** this paper,we give a very comprehensive literature survey of MPI-based parallel clustering algorithms with special reference to the specific data distribution strategies they *** also propose three new data distribution strategies namely Parameterized Dimensional Split for parallel density-based clustering algorithms like DBSCAN and OPTICS,Cell-Based Dimensional Split for dGridSLINK,which is a grid-based hierarchical clustering algorithm that exhibits efficiency for disjoint spatial distribution,and Projection-Based Split,which is a generic distribution *** of these preserve spatial locality,achieve disjoint partitioning,and ensure good data load *** experimental analysis shows the benefits of using the proposed data distribution strategies for algorithms they are designed for,based on which we give appropriate recommendations for their usage.

关键词： parallel data mining data distribution parallel clustering spatial locality preservation

来源：评论

学校读者我要写书评

暂无评论

Fostering Sustainable Poultry Farming: Chicken Disease Classification through Ensemble Techniques and Local Attention-Based Fused Descriptor Definition

Fostering Sustainable Poultry Farming: Chicken Disease Class...

引用

International Conference on Smart Technologies For Smart Nation (SmartTechCon)

作者： Sayantani Ghosh Indranil Mitra Anik Chakraborty Raktim Chakraborty Rik Das Prasun Nandy Data & Analytics Advanced Analytics PwC India

Chicken disease classification assumes a vital role in maintaining the health and productivity of poultry farms. By accurately identifying diseases through automated image analysis, the poultry industry can take prompt preventive measures, reduce economic losses, and improve flock management practices. This approach offers a cost-effective solution for the pharmaceutical industry by reducing the need for expensive manual diagnosis and enabling targeted drug development, ultimately increasing sales revenue. Deep learning-based feature extraction plays a crucial role in chicken disease classification from poultry fecal images. By employing advanced techniques such as vision transformers and EfficientNet-B0-B0, intricate features can be extracted from the images, allowing for more accurate disease classification. To the best of our knowledge, none of the previous work has evaluated vision transformer in capturing global contextual information for chicken disease classification from fecal images. On the other hand, EfficientNet-B0-B0 offers efficient and scalable feature extraction. Therefore, both the techniques are vital for analyzing complex patterns within the images. Hence, the work has explored early and late ensembling techniques to investigate feature generalization as well as decision fusion of diverse classifiers for enhanced precision in classification results of the chicken diseases. The classification process is carried out using classical algorithms viz, Support Vector Machine (SVM), Logistic Regression(LR) and Random Forest(RF) instead of transfer learning since traditional classifiers offer greater flexibility in evaluating tailored approaches like feature fusion and decision fusion. The late ensembling with classifier decision fusion has outclassed all the other classification techniques in efficiently identifying chicken diseases from fecal images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MULABS: Multi-Task Learning with Attention-Based Scoring for Click-Through Rate Prediction on Sparse data in Healthcare Real-World Scenarios

MULABS: Multi-Task Learning with Attention-Based Scoring for...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Tu, Tu Zhang, Jing Wang, Yue Jin, Hui He, Megan Weihong IQVIA Inc. Data Science and Advanced Analytics Shanghai China

ISBN: (纸本)9781665468190

Personalized recommender systems have found wide applications in healthcare since it has the potential to inform individual users about the most needed medical resources. However, most recommender systems levering deep learning techniques demand a rich amount of data to learn patterns. In this paper, we aim to improve the performance of a recommender system when data are sparse and in low volume. In particular, we introduce a multi-task learning approach to alleviate the learning pressure and propose an attention-based scheme to boost the model performance by fully utilizing users' historical data. In the experiments, we develop a novel dataset from a public dataset to mimic the real-world scenarios in healthcare. The results demonstrate that this multi-task learning with attention-based scoring (MULABS) aided recommender system is more accurate in predicting user preference with an AUC of 0.7541, requiring limited computation and memory resources. © 2022 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Harnessing Transformers for Detecting Adverse Drug Reaction and Customized Causality Explanation using Generative AI

Harnessing Transformers for Detecting Adverse Drug Reaction ...

引用

International Conference on Computing Communication Control and Automation (ICCUBEA)

作者： Ankan Bera Rik Das Sayantani Ghosh Raktim Chakraborty Indranil Mitra Prasun Nandy Data & Analytics Advanced Analytics PwC India

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluating Objective vs. Subjective Questionnaire Difficulty in Virtual Reality and 2D Web Scenarios 15

Evaluating Objective vs. Subjective Questionnaire Difficulty...

引用

15th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2024

作者： Sudár, Anna Corvinus Institute for Advanced Studies Institute of Data Analytics and Information Systems Corvinus University of Budapest Budapest Hungary Hungarian Research Network HUN-REN Budapest Hungary

ISBN: (纸本)9798350378245

The study contributes to the field of Cognitive Infocommunications (CogInfoCom) by highlighting the importance of interface design in managing cognitive load and enhancing user experience. It evaluates task difficulty in virtual reality (VR) and traditional 2D web environments through subjective measures. It explores users’ evaluations of task difficulty, aiming to correlate these perceptions with the complexity of different digital interfaces. Results indicate significant differences in perceived difficulty across environments, with VR generally leading to higher difficulty ratings. Findings suggest that VR environments, particularly those with higher complexity, can increase perceived task difficulty, underscoring the need for careful design to optimize cognitive support and user satisfaction. © 2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Trends in the Adoption of VR Technologies for Online Conferences 15

Trends in the Adoption of VR Technologies for Online Confere...

引用

15th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2024

作者： Horváth, Ildikó Sudár, Anna Baranyi, Péter Corvinus Institute for Advanced Studies Institute of Data Analytics and Information Systems Corvinus University of Budapest Budapest Hungary Hungarian Research Network HUN-REN Budapest Hungary

ISBN: (纸本)9798350378245

This paper examines the trends in the adoption of VR technologies for online conferences, comparing the use of simple 2D online meeting software with more sophisticated VR systems. The authors aim to evaluate the effectiveness of 2D online meeting platforms (e.g., Zoom, Teams) versus advanced VR systems (e.g., AltspaceVR, Horizon Workrooms) in virtual conference settings. The study highlights the limitations of 2D platforms in terms of engagement and interaction while showcasing the immersive benefits of VR environments. The goal is to provide a framework for understanding the evolving landscape of virtual conferences and leveraging VR technologies to enhance overall conference effectiveness. Case studies from the 2020 and 2021 conference cycles illustrate the practical implementation of VR environments, demonstrating how these spaces facilitate the entire conference process. Key findings indicate that VR platforms significantly improve participant engagement and interaction compared to 2D platforms. The paper also discusses hybrid models that combine 2D and VR elements, offering flexibility and maximizing participant engagement throughout the Pre-Conference, In-Conference, and Post-Conference phases. © 2024 IEEE.

关键词： Virtual environments

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：