检索结果-内蒙古大学图书馆

1st International Conference on AIML-Applications for engineering and Technology, ICAET 2025

作者： Deshpande, Anjali Deshmukh, Pratiksha COEP Technological University Dept. of Computer Science and Engineering Pune India PICT Dept. of AI & DS Pune India School of Computational Sciences COEP Technological University Dept. of Computer Science and Engineering Pune India

ISBN: (纸本)9798350355611

Natural Language Processing (NLP) is revolutionizing the legal domain, enabling tasks such as predicting legal outcomes, summarizing complex documents, identifying key entities, and assessing bail risks. This survey paper presents a comprehensive review of the existing research on NLP tasks applied to legal documents and judgments across various languages, with a special emphasis on low-resource languages. Despite the extensive work done in widely spoken languages like English, there remains a critical need to extend these advancements to languages with limited resources and data availability. This paper categorizes and analyzes the NLP tasks in the legal domain based on the languages they target. It highlights the methodologies employed, datasets utilized, and the performance of different models across diverse languages. Furthermore, it identifies the gaps in current research and proposes potential directions for future work, particularly in improving the accessibility and applicability of NLP solutions for legal texts in underrepresented languages. By providing a comprehensive overview of advancements and obstacles, this survey seeks to assist future research endeavors that bridge the disparity between high-resource and low-resource languages in legalAI applications. © 2025 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Collating Random Forest Classifier and Artificial Neural Networks for the Risk Detection of Maternal Health

Collating Random Forest Classifier and Artificial Neural Net...

引用

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

作者： Nahatkar, Sneha Belhe, Adityaraj Sanjay Ganthade, Vedant Vinay Uravane, Prathamesh Suhas Pattewar, Tareek PICT Pune Electronics & Comp Engg Department Pune India Vishwakarma University Pune AIDS Department Pune India Vishwakarma University Pune Computer Engineering Department Pune India

ISBN: (纸本)9798331512965

This paper compares the performance of ANN models to Random Forests on benchmarking a test dataset against the risk levels of maternal health as low, mid, or high. The features considered are clinical features, namely age, blood pressure, and heart rate. The dataset was imbalanced and needed adapting the ANN architecture by fitting class weights and dropout regularization. The best test accuracy obtained in this fashion was 73%. As the ANN had learned many of the complex data patterns in the dataset, it was, however, still limited by the moderate size and skewness of the dataset. The Random Forest model with grid search produced a much better accuracy of 85.71% compared with ANN, thereby suggesting relatively high generalization across all the classes for better minority risk level classes. An ensemble approach of the Random Forest method appears to better serve toward high accuracy along with interpretability for clinical decision support in maternal health risk assessment. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Understanding Unnatural Mortality: A Comprehensive Analysis of Machine Learning Approach for Classification of Causes 3rd

Understanding Unnatural Mortality: A Comprehensive Analysis ...

引用

3rd International Conference on Advancements in Smart Computing and Information Security, ASCIS 2024

作者： Gunje, Shamali Waghmare, Kalyani Sonawane, Sheetal Department of Computer Engineering PICT Pune India

ISBN: (纸本)9783031862892

Death is a tragedy regardless of its form, time, or manner in which it occurs. Death can be natural, unnatural through deliberate action of other, self-inflicted, or it can be due to the environmental factors. The primary aim of this paper lies in the comprehensive analysis and synthesis of existing literature concerning unnatural mortality. The literature is surveyed from various digital repositories for analyzing the trends and patterns of unnatural deaths. The study of literature identified the common causes of deaths. This paper offers a comprehension of the existing literature by combining and summarizing the patterns, trends, and contributing elements of unnatural fatalities. Additionally, a machine learning classification model is built to categorize news articles from the dataset into five different categories based on death causes. We conducted a comparative analysis using machine learning classifiers on 20,000 news articles from the Indian Express dataset. The Decision Tree model emerged as the most effective, with an accuracy of 90%. This comparison analysis demonstrates the various strengths and shortcomings of different classifiers in categorizing death causes. Our findings shed light on mortality patterns and show how machine learning can automate the classification of death-related data, allowing for early interventions and informed policy decisions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Development of the Decision Systems for Cloud Security Based on AI and ML 12th

Development of the Decision Systems for Cloud Security Based...

引用

12th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2024

作者： Maral, Vikas Balasaheb Tambakhe, Manoj D. Dhage, Prashant Shukla, Jyoti Khalaf, Osamah Ibrahim Pise, Ganesh Shivaji Vishwakarma Institute of Information Technology Maharashtra Pune India Department of Information Technology Sipna College of Engineering and Technology Amravati Maharashtra Amravati India Pune India Department of Computer Science and Engineering Arya College of Engineering Jaipur India Department of Solar Al-Nahrain Research Center for Renewable Energy Al-Nahrain University Jadriya Baghdad Iraq Department of Information Technology PICT Maharashtra Pune India

ISBN: (纸本)9789819601387

One of the most important and crucial factors often considered in keeping a network secure is the adoption of an intrusion detection system. This process is commonly called as an IDS stage which is required to keep the network protected from certain attacks in real time. Due to the wide usage of cloud on a daily purpose, the platform is constantly evolving and becoming more advanced. This has helped the developers comprehend the necessity of advancing the process of IDS. However, there are certain obstacles and issues that might arise with its acceptance. One such factor is the problem of overhead. This problem of overhead occurs when the cloud server is overloaded with existing services and thereby cannot transit other services on urgency. In such a scenario, the working concept of an IDS comes into picture wherein this adaptive design helps the developers to overcome such issues and provide a conventional flow of services to the allocate resource. The primary purpose of the presented research paper is to adapt such a concept and therefore maximize the overall potential of the system. The author of the research paper also tends to enhance and increase the overall capacity required to identify the occurrence of such threats in an online manner which are expected to occur. A CICIDS2017 dataset is used to fulfill the purpose of the same and a recurring infrastructure is therefore built in order to understand the working nature of an intrusion detection system. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

LegalAI Across Languages: A Comprehensive Survey on Tasks, Methodologies and Challenges

LegalAI Across Languages: A Comprehensive Survey on Tasks, M...

引用

AIML-Applications for engineering & Technology (ICAET), International Conference on

作者： Anjali Deshpande Pratiksha Deshmukh Dept. of Computer Science and Engineering COEP Technological University Pune Dept. of AI & DS PICT Pune Dept. of Computer Science and Engineering School of Computational Sciences COEP Technological University Pune

ISBN: (数字)9798350355611

ISBN: (纸本)9798350355628

关键词： Surveys Law Reviews Semantics Focusing Named entity recognition Linguistics Natural language processing Labeling Global communication

来源：评论

学校读者我要写书评

暂无评论

Collating Random Forest Classifier and Artificial Neural Networks for the Risk Detection of Maternal Health

Collating Random Forest Classifier and Artificial Neural Net...

引用

Computational, Communication and Information Technology (ICCCIT), International Conference on

作者： Sneha Nahatkar Adityaraj Sanjay Belhe Vedant Vinay Ganthade Prathamesh Suhas Uravane Tareek Pattewar Electronics & Comp Engg Department PICT Pune Pune India AIDS Department Vishwakarma University Pune Pune India Computer Engineering Department Vishwakarma University Pune Pune India

ISBN: (数字)9798331512965

ISBN: (纸本)9798331512972

关键词： Heart rate Accuracy Artificial neural networks Medical services Predictive models Data models Information and communication technology Risk management Reliability Random forests

来源：评论

学校读者我要写书评

暂无评论

Energy-aware VM migration using dragonfly–crow optimization and support vector regression model in Cloud

引用

International Journal of Modeling, Simulation, and Scientific Computing 2018年第6期9卷 19-42页

作者： Nitin S.More Rajesh B.Ingle Department of Computer Engineering Pune Institute of Computer Technology(PICT)SPPU Pune 411043MaharashtraIndia

Nowadays,virtual machine migration(VMM)is a trending research since it helps in balancing the load of the Cloud *** VMM-based strategies defined in the literature have considered various metrics,such as load,energy,and migration cost for balancing the load of the *** paper introduces a novel VMM strategy by considering the load of the Cloud *** important aspects of the proposed scheme are the load prediction through the support vector regression(SVR)and the optimal VM placement through the proposed dragonfly-based crow(D-Crow)optimization *** proposed D-Crow optimization algorithm is developed by incorporating crow search algorithm(CSA)into dragonfly algorithm(DA).Also,the proposed VMM strategy defines a load balancing model based on the energy consumption,load,and the migration cost to achieve the energy-aware *** simulation of the proposed VMM strategy is done based on the metrics such as load,energy consumption,and the migration *** the results,it can be shown that the proposed VMM strategy surpassed other comparative models by achieving the minimum values of 7.3719%,10.0368%,and 11.0639%for the load,energy consumption,and migration cost,respectively.

关键词： Virtual machine migration load balancing load prediction optimal VM placement energy awareness.

来源：评论

学校读者我要写书评

暂无评论

Vehicle Type Classification Using Deep Learning 2nd

Vehicle Type Classification Using Deep Learning

引用

2nd International Conference on Soft Computing and Signal Processing, ICSCSP 2019

作者： Bhujbal, Avinash Mane, D.T. Department of Computer Engineering PICT Pune India

ISBN: (纸本)9789811524745

As the rate of data generation is growing rapidly which can be from a number of sources. Information collected can be used for and processed for its commercial or business value. Here, one of the characteristics is the significance of data in terms of time. In time-dependent applications, the need for analysis and quick processing is a necessity. Using YOLO (you look only once) method, we have performed recognition of vehicle type in which for each of the objects the model is trained. Here, the dataset used is from cityscapes where 2659 input set images are taken for training purpose and the performance is calculated in terms of accuracy which is 87%. Using the approach detection for different vehicle categories, i.e., car, bus, truck, motorbike is performed. YOLO model works well and does not require any intrusive approach for detection also due to less to no dependency on any other system optimization and reliability is attained. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Hyaline: A Transparent Distribwuted Computing Framework for CUDA 5

Hyaline: A Transparent Distribwuted Computing Framework for ...

引用

5th IEEE International Conference for Convergence in Technolog, I2CT 2019

作者： Jain, Akshat Kazi, Owais Joshi, Raviraj Basantwani, Shraddha Bang, Yogita Khengare, Rahul PICT Computer Engineering Pune India IIT Computer Science Madras India

ISBN: (纸本)9781538680759

The GPU usually handles the homogenous data parallel work, by taking advantage of its massive number of cores. In most of the applications, we use CUDA programming for utilizing the power of GPU. In data intensive high computational applications like neural networks, utilizing the GPU on a single machine is time consuming. Instead if multiple GPUs are used in a network the amount of time required will be significantly reduced. Traditionally to enable a set of program to be run in a distributed environment, programmer has to accordingly design components to make his system dynamic and resilient to changes in number of systems in cluster, which is a daunting task. This work distribution can be a poor solution as it may underutilize the GPUsIn our approach, we developed a framework which transparently distributes data parallel kernels across multiple GPUs in a distributed network. The programmer is responsible for developing a single data parallel kernel in CUDA while the framework automatically distributes the workload across an arbitrary set of CUDA enabled GPUs. Depending on current workload on GPUs and the amount of data to be processed optimal distribution is done. The goal is to maximally utilize the available resources with minimal programming complexity. The systems not compatible with CUDA can also utilize our solution. We expect our framework to reduce the processing time along with simplifying the task of programmers. © 2019 IEEE.

关键词： Parallel programming

来源：评论

学校读者我要写书评

暂无评论

Decentralized Fundraising Application Using Blockchain 1

Decentralized Fundraising Application Using Blockchain

引用

1st IEEE International Conference on Blockchain and Distributed Systems Security, ICBDS 2022

作者： Dange, Rishi Sawant, Aditya Chavan, Aditya Bhardwaj, Prerna Bundele, Ashwini Pune Institute of Computer Technology Pict Department of Computer Engineering Pune India

ISBN: (数字)9781665428323

ISBN: (纸本)9781665428323

It is critical for a donor to understand where and how their money is being used. This will not only make them happy, but it will also encourage them to donate again and propose or publicise donations, resulting in a large donation amount for the needy. This paper proposes a decentralized application which utilizes blockchain and smart contracts which is built with the aim of helping the needy and underprivileged people by providing a platform that is secured, flawless, easy to use and transparent with the funds. Fundraising applications have come into existence to help people and communities alike. But these applications have been far from perfect. People have shown general distrust in a third-party to securely handle their funds before reaching the people donations were meant for. Some reports of misuse of collected funds have worsened the situation. The lack of transparency and involvement of third-party has hindered people from donating at times and have left many needy people without any help. To combat these issues, we have decided to build a fundraising website accessible to everyone whose working will be transparent. Registered users, once verified, can donate to various charity drives and funds and also ask for funds when in need. using Machine learning recommendations of similar fundraisers are made who like to donate to some particular charity drives. To acheive transparency, the blockchain technology is used to store records of donations made by the users. Decentralization of fundraising process also eliminates involvement of any third-party group. © 2022 IEEE.

关键词： Smart contract

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：