检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Mullick, Ankan Bose, Sombit Saha, Rounak Bhowmick, Ayan Kumar Goyal, Pawan Ganguly, Niloy Dey, Prasenjit Kokku, Ravi Computer Science and Engineering Department IIT Kharagpur India Emergence AI

In an ever-expanding world of domain-specific knowledge, the increasing complexity of consuming, and storing information necessitates the generation of summaries from large information repositories. However, every persona of a domain has different requirements of information and hence their summarization. For example, in the healthcare domain, a persona-based (such as Doctor, Nurse, Patient etc.) approach is imperative to deliver targeted medical information efficiently. Persona-based summarization of domain-specific information by humans is a high cognitive load task and is generally not preferred. The summaries generated by two different humans have high variability and do not scale in cost and subject matter expertise as domains and personas grow. Further, ai-generated summaries using generic Large Language Models (LLMs) may not necessarily offer satisfactory accuracy for different domains unless they have been specifically trained on domain-specific data and can also be very expensive to use in day-to-day operations. Our contribution in this paper is two-fold: 1) We present an approach to efficiently fine-tune a domain-specific small foundation LLM using a healthcare corpus and also show that we can effectively evaluate the summarization quality using ai-based critiquing. 2) We further show that ai-based critiquing has good concordance with Human-based critiquing of the summaries. Hence, such ai-based pipelines to generate domain-specific persona-based summaries can be easily scaled to other domains such as legal, enterprise documents, education etc. in a very efficient and cost-effective manner. © 2024, CC0.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Cash Flow Forecasting Based on Wavelet Transform and Neural Networks 8

Cash Flow Forecasting Based on Wavelet Transform and Neural ...

引用

8th International Conference on computer science and engineering, UBMK 2023

作者： Soylen, Zumra Mammadova, Farida Fasounaki, Mandana Ozmen, Ayse Irem Ince, Gokhan Istanbul Technical University Department of Computer Engineering İstanbul Turkey Mdp Group R&d Department İstanbul Turkey Istanbul Technical University Department of Computer Engineering & Ai and Data Science Application and Research Center İstanbul Turkey

ISBN: (纸本)9798350340815

Cash flow forecasting is a critical task for businesses and financial institutions to ensure effective financial planning and decision-making. However, limited data availability poses a significant challenge when developing accurate and robust cash flow prediction models. In this paper, we investigate the performance of various forecasting methods and propose an approach based on wavelet transform for improving the forecasting accuracy. We demonstrate the effectiveness of the proposed approach with the best combination of wavelet functions and methods for forecasting future values in a univariate time series. We investigate the impact of wavelet transform on forecasting techniques based on open-source datasets. Our methodology includes data collection, preprocessing, feature engineering, model selection, and experimentation using different performance evaluation metrics. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Leveraging the Power of LLMs: A Fine-Tuning Approach for High-Quality Aspect-Based Summarization

arXiv

引用

arXiv 2024年

作者： Mullick, Ankan Bose, Sombit Saha, Rounak Bhowmick, Ayan Kumar Vempaty, Aditya Goyal, Pawan Ganguly, Niloy Dey, Prasenjit Kokku, Ravi Computer Science and Engineering Department IIT Kharagpur India Emergence AI

The ever-increasing volume of digital information necessitates efficient methods for users to extract key insights from lengthy documents. Aspect-based summarization offers a targeted approach, generating summaries focused on specific aspects within a document. Despite advancements in aspect-based summarization research, there is a continuous quest for improved model performance. Given that large language models (LLMs) have demonstrated the potential to revolutionize diverse tasks within natural language processing, particularly in the problem of summarization, this paper explores the potential of fine-tuning LLMs for the aspect-based summarization task. We evaluate the impact of fine-tuning open-source foundation LLMs, including Llama2, Mistral, Gemma and Aya, on a publicly available domain-specific aspect based summary dataset. We hypothesize that this approach will enable these models to effectively identify and extract aspect-related information, leading to superior quality aspect-based summaries compared to the state-of-the-art. We establish a comprehensive evaluation framework to compare the performance of fine-tuned LLMs against competing aspect-based summarization methods and vanilla counterparts of the fine-tuned LLMs. Our work contributes to the field of aspect-based summarization by demonstrating the efficacy of fine-tuning LLMs for generating high-quality aspect-based summaries. Furthermore, it opens doors for further exploration of using LLMs for targeted information extraction tasks across various NLP domains. © 2024, CC0.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Production of Fabric from the Organic Extract

A Comprehensive Survey on Production of Fabric from the Orga...

引用

International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)

作者： Hunar Sajjan Agrawal Mokara Praneetha Anshika Singh Abha Kiran Rajpoot Department of Computer Science and Engineering Sharda University Greater Noida India Department of CSE (AI & ML) KIET Group of Institutions Ghaziabad India

The application of varied/various fabric types is constantly on the rise over time, the process of the fabric making involves a lot of fabric offcuts. The textile industry domain consists of transformation of fiber to yarn, yarn to fabric and fabric to finished garments. During these processes, the waste is generated in a large quantity and evidences from past justify the fact that fashion industry is lacking in sustainability measures. The textile industries create environmental harm at all stages of production from raw material cultivation to disposal of finished goods. Large amount of chemical loads, high amount of water usage, high energy consumption, air emission, solid waste are major environmental challenges in textile industries. This review paper will provide a comprehensive and up-to-date overview of sustainable fabrics, offering insights into their environmental, social and economic benefits. By understanding the potential of these alternatives, we can collectively contribute to a more sustainable and responsible fashion industry, fostering a healthier planet for future generations. An comprehensive range of fabric has been explored, each renowned by unique set of qualities. Sustainable fabrics such as bamboo, banana, coffee, hemp are examined that have beneficial outcomes unlike synthetic/polyster fabrics. The transition to such sustainable fabrics is a necessity. The sustainable fabrics are decent and renewable, these can unlock a new opportunity towards a eco-friendlier alternative. Dyeing also causes negative impacts which can be resolved by using sustainable dye that provide natural color and environmental benefits. In concordant, these sustainable methods and alternatives should be employed to foster better and sustainable world.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mental Health and Suicide Risk among College Students: A Detailed Exploration of Contributing Factors 15

Mental Health and Suicide Risk among College Students: A Det...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Meena, R. Gunasundari, B. Omana, J. Sripriya, N. Yamini, G. Revathi, K.P. Easwari Engineering College Department of AI&DS Chennai India Prathyusha Engineering College Department of CSE Chennai India VIT University School of Computer Science and Engineering Chennai India Veltech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Department of English Chennai India

ISBN: (纸本)9798350370249

This study aims to identify critical predictors of suicide and inform targeted interventions using data from 27,014 college students. It examines a comprehensive range of mental health indicators, including psychiatric symptoms, suicidal intentions, impulsivity, sleep disturbances, internet addiction, aggression, self-injury behaviors, and eating problems, alongside demographic and socioeconomic variables. Analytical techniques, including exploratory data analysis, cross-tabulation, and correlation analysis, uncover the complex interplay between these factors and suicide risk. The study evaluates several machine learning algorithms. The weighted Random Forest uses feature weighting based on point-biserial correlation coefficients to enhance prediction accuracy and prioritize relevant features. The findings reveal significant associations between higher scores in mental health indicators and increased suicidal behavior, emphasizing the need for comprehensive mental health support systems. By identifying key risk factors through machine learning models, the study provides actionable insights for developing targeted interventions aimed at reducing suicide risk among college students. © 2024 IEEE.

关键词： Feature weighting Fuzzy evaluation method Machine learning models Point-biserial correlation coefficients

来源：评论

学校读者我要写书评

暂无评论

Fault Tolerant Quality of Service Provisioning in Internet of Things using One Class Support Vector Machine

Fault Tolerant Quality of Service Provisioning in Internet o...

引用

Intelligent Systems and Computational Networks (ICISCN), International Conference on

作者： Mohhamied Husaein Fallaah T. Shanthi S. Balakrishna Reddy Rajavadhani K K. Sandhya Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Electronics and Communication Engineering Sona College of Technology Salem India Department of Computer Science and Engineering (DS) CVR College of Engineering Hyderabad India Department of Computer Science and Engineering Dhanalakshmi Srinivasan College of Engineering and Technology Mamallapuram India Department of Computer Science and Engineering (AI&ML) Mohan Babu University Tirupati India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

In recent years, the rapid development of the Internet of Things (IoT) has made fault tolerance is important for maintaining service quality and system availability. Fault tolerance Quality of Service (QoS) provisioning ensures IoT systems operate continuously, even in presence of failures or malfunctions. Traditional approaches for QoS provisioning had face several challenges which include data security risks, inconsistent updates. Therefore, this research proposes One Class Support Vector Machine (OCSVM) for fault tolerant QoS provisioning in IoT systems. Initially, data is collected from Message Queuing Telemetry Transport-IoT-Intrusion Detection System (MQTT-IoT-IDS 2020) and preprocessed by using Expectation Maximization (EM) which reduces noise in data and handles missing data. Finally, provisioning and fault detection is done by using proposed OCSVM which detected faults and communication errors. The proposed OCSVM achieved better results in Execution time (220.61), Execution Cost (793.02) and Energy Consumption (22J) when compared with existing Fault-Tolerant and Data-Oriented Scientific Workflow Management and Scheduling System (FD-SWMS).

关键词： Support vector machines Fault tolerance Costs Fault detection Computational modeling Fault tolerant systems Noise Quality of service Feature extraction Internet of Things

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Multilingual Reasoning Distillation for Question Answering

An Empirical Study of Multilingual Reasoning Distillation fo...

引用

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

作者： Payoungkhamdee, Patomporn Limkonchotiwat, Peerat Baek, Jinheon Manakul, Potsawee Udomcharoenchaikit, Can Chuangsuwanich, Ekapol Nutanong, Sarana School of Information Science and Technology VISTEC Thailand AI Singapore Singapore KAIST Korea Republic of SCB 10X Thailand Department of Computer Engineering Chulalongkorn University Thailand

ISBN: (纸本)9798891761643

Reasoning is one crucial capability in Large Language Models (LLMs), allowing them to perform complex tasks such as solving math problems and multi-step planning. While reasoning capability can emerge in larger models, smaller ones usually have to rely on distillation to transfer this capability from a larger model. However, recent efforts to distill reasoning capabilities have focused mainly on English, leaving multilingual distillation underexplored. To address this gap, this paper examines existing English reasoning distillation methods that utilize a variety of positive rationales in multilingual settings and proposes d-CoT-nR, which incorporates incorrect rationales as additional guidance. Empirical results from multilingual high-school examinations show that d-CoT-nR significantly surpasses the baseline, improving accuracy and the correctness of step-by-step reasoning. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach for Multiclass Orange Disease Classification

A Deep Learning Approach for Multiclass Orange Disease Class...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Sandeep Kumar Abhay Kumar Pandey Daksh Raghav Gaurav Gupta Varsha Srivastava Department Of Computer Science & Engineering (AI) ABES Institute of Technology Ghaziabad

This research investigates “Machine Learning (ml)” models for the multiclass classification of orange diseases, examining “K-Nearest Neighbors (KNN)”, “Convolutional Neural Network (CNN)” with MobileNetV2 architecture, “Random Forest (RF)” and “Support Vector Machine (SVM)”. The study assesses their performance across Blackspot, Canker, Fresh, and Greening disease classes —using metrics and highlighting the models' strengths. Notably, the CNN model utilizing MobileNetV2 exhibits exceptional accuracy, achieving an impressive 98.22% across all disease categories. The findings emphasize the remarkable accuracy and robustness of CNN in precisely identifying and classifying diverse orange diseases. This suggests its pivotal role in revolutionizing agricultural disease detection systems, underscoring the importance of leveraging advanced deep learning architectures for precise crop health management. The study's outcomes highlight the potential impact of employing sophisticated models in the agriculture sector for effective disease monitoring and crop preservation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging Effective Language and Speaker Conditioning In Indic TTS for Limmits 2024 Challenge

Leveraging Effective Language and Speaker Conditioning In In...

引用

Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE International Conference on

作者： Yejin Jeon Young Jae Kim Gary Geunbae Lee Graduate School of AI POSTECH Department of Computer Science and Engineering POSTECH

ISBN: (数字)9798350374513

ISBN: (纸本)9798350374520

In this paper, we explain the model that was developed by the NLP_POSTECH team for the LIMMITS 2024 Grand Challenge. Among the three tracks, we focus on Track 1, which necessitates the creation of a few-shot text-to-speech (TTS) system that generates natural speech across diverse languages. Towards this end, to realize multi-lingual capability, we incorporate a learnable language embedding. In addition, for precise imitation of target speaker voices, we leverage an inductive speaker bias conditioning methodology. Despite the simplicity of our strategy, our model is able to demonstrate remarkable efficacy in the generation of natural speech and preservation of high speaker fidelity for both mono and cross-lingual settings.

关键词： Target tracking Conferences Natural languages Signal processing Data models Acoustics Text to speech

来源：评论

学校读者我要写书评

暂无评论

A Smart Governance Architecture for Integrating Heterogeneous IoT Solutions within the Framework of Smart Cities

A Smart Governance Architecture for Integrating Heterogeneou...

引用

2023 International Conference on Data science and Network Security, ICDSNS 2023

作者： Madhurya, J.A. Padhi, Manoj Kumar Kondala Rao, P. Awasthy, Mohan Pareek, Piyush Kumar Gitam School of Technology Gitam University Department of Cse Bengaluru India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaadeswaram India Hyderabad Institute of Technology and Management Department of Ece Hyderabad India Bharati Vidyapeeth Peeth Deemed to Be University Department of Engineering and Technology Navi Mumbai India Nitte Meenakshi Institute of Technology Department of Ai and Ml Bengaluru India

ISBN: (纸本)9798350301595

The Internet of Things (IoT) is a network of networked devices that links commonplace things to the Internet. The present IT infrastructure for managing IoT technologies lacks the necessary enterprise networking approach, which necessitates municipal collaboration. This is due to the compartmentalization of smart city app functionality. To integrate heterogeneous Internet of Things solutions within the framework of smart cities, we offer a smart governance architecture that integrates power needs, security constraints, and scalability components. This will promote cross-sector contacts at all levels and contribute to the accessibility of smart cities. This research proposal suggests a multi-level governance model for the distributed administration of IoT subsystems as a possible way to solve the problem of IoT systems in smart city applications that don't work together. As an important part of smart governance, the proposed architecture includes things like a one-of-a-kind model, open-source software, and digital objects. The goal of this research is to run a proof-of-concept simulation to test the suggested infrastructure. A lot of thought will be put into the solution for multi-level governance, as well as security and the resolution of digital objects with security constraints. The proposed infrastructure is meant to make it possible for different Internet of Things technologies and agents to work well together by providing security, repeatability, scalability, and interoperability. © 2023 IEEE.

关键词： Smart city

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：