检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Kabir, Md Rysul Mochizuki-Freeman, James Tiganj, Zoran Department of Computer Science Luddy School of Informatics Computing and Engineering Indiana University Bloomington United States

ISBN: (纸本)157735897X

The ability to estimate temporal relationships is critical for both animals and artificial agents. Cognitive science and neuroscience provide remarkable insights into behavioral and neural aspects of temporal credit assignment. In particular, scale invariance of learning dynamics, observed in behavior and supported by neural data, is one of the key principles that governs animal perception: proportional rescaling of temporal relationships does not alter the overall learning efficiency. Here we integrate a computational neuroscience model of scale invariant memory into deep reinforcement learning (RL) agents. We first provide a theoretical analysis and then demonstrate through experiments that such agents can learn robustly across a wide range of temporal scales, unlike agents built with commonly used recurrent memory architectures such as LSTM. This result illustrates that incorporating computational principles from neuroscience and cognitive science into deep neural networks can enhance adaptability to complex temporal dynamics, mirroring some of the core properties of human learning. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Indian legal text summarization using large language model 6

Indian legal text summarization using large language model

引用

6th International Conference on Futuristic Trends in Networks and computing Technologies, FTNCT 2024

作者： Omanakuttan, Vishnu Kesav Rohith, A. Uthara, R. Geetha, M. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Kollam690546 India

This research introduces a novel framework for summarizing legal judgments by integrating two state-of-the-art pretrained models-Google T5-small and Facebook BART-with rhetorical labels to enhance both accuracy and relevance. Each model is fine-tuned to pro-cess distinct rhetorical components, such as facts, arguments, and conclusions, while LoRA adapters ensure efficient fine-tuning with minimal computational over-head. The incorporation of rhetorical labels allows the models to differentiate between various legal roles, ensuring the generated summaries preserve the logical structure and critical reasoning embedded in the text. Our experiments demonstrate that this multi-model, label-guided approach not only outperforms traditional summa-rization methods but also delivers coherent, context aware summaries tailored to the needs of legal practitioners, improving both usability and decision-making efficiency. © 2025 The Author(s). Published by Elsevier B.V.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Optimizing Urban Waste Collection Routes: Comparative Study of Shortest Path Algorithms

Optimizing Urban Waste Collection Routes: Comparative Study ...

引用

2025 International Conference on computing for Sustainability and Intelligent Future, COMP-SIF 2025

作者： Begum, Chimakurthy Mounika Reddy, Kamalapuram Vigneswara Neeraja Bhaskaran, Sreebha Amrita School of Computing Amrita Vishwa Vidyapeetham Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331538538

Collection of waste is one of the important goals of Waste Management Unit (WMU), where collecting waste decreases the amount of time, expenses, and the impact of waste collectors on the environment. The work is to create a set of routes for waste collection that will take minimal time to get through several collection centers given the capabilities of the collection vehicles, and road systems and traffic conditions. For waste collection points, ten major stations in Bengaluru were selected along with the disposal point. For this purpose, several algorithms such as Dijkstra's Algorithm, Bellman-Ford Algorithm, Floyd-Warshall Algorithm, Johnson's Algorithm, Nearest Neighbour Algorithm, and Ant Colony Optimization (ACO) were designed and evaluated. Algorithms were measured based on parameters such as the time taken, the fuel consumed, the CO2 produced, the effectiveness of the trip that was made. The theoretical and applied objectives of the project correlate with the goals of the integration of improved optimization possibilities with operational issues with the purpose of defining such effective methods in relation to the containment of fuel consumption, the decrease in emissions and the waste management optimization in the urban environment. © 2025 IEEE.

关键词： Wastewater disposal

来源：评论

学校读者我要写书评

暂无评论

A data-centric approach to terminal unit’s fault categorization and optimal positioning in building HVAC systems using ensemble learning

引用

Discover Data 2025年第1期3卷 1-20页

作者： Dey, Maitreyee Patel, Preeti Rana, Soumya Prakash GENESIS Research Lab Computer Science and Applied Computing London Metropolitan University London UK School of Engineering University of Greenwich Chatham UK

This paper focuses on the fault detection and diagnosis of terminal units (TUs) in a building located in London, utilizing real operational historical data to assess their performance and optimal placement across multiple floors. While precise locations of the TUs are unavailable, our method analyzes their operational behaviour for one month, applying popular machine learning models to detect and analyze faults effectively. By examining each TU individually and in the aggregate, we identify behavioural patterns that inform decisions regarding their positioning within the building. The dataset comprises over 2 million data points collected from 730 TUs, enabling a comprehensive analysis of their functionality and the impact of suboptimal thermostat placements. Our study employs three machine learning models-traditional multi-class Support Vector Machines and two ensemble methods: Random Forest (RF), and Adaptive Boosting (AdaBoost)-to classify TU behaviors into normal operation, heating faults, and cooling faults. Results indicate that RF outperforms the other models with an accuracy of 99.89%, while AdaBoost achieves an accuracy of 85% and SVM shows 47% accuracy. The findings underscore the potential of a data-driven approach to inform retrofitting decisions and enhance the reliability of HVAC systems. This research contributes valuable knowledge toward optimizing TU placement, ultimately leading to improved energy efficiency and indoor environmental quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IoT Device for Food Storage

IoT Device for Food Storage

引用

International Conference on Electronics, Materials engineering and Nano-Technology (IEMENTech)

作者： Lopa Mandal Guttapalem Reddy Vishnu Vardhan Bharani G S Jawad Ahmed Kavin K Nandi Sasidhar Reddy Department of Computer Science & Engineering Alliance School of Advanced Computing Alliance University Bengaluru Karnataka India

ISBN: (数字)9798331520762

ISBN: (纸本)9798331520779

The integration of IoT technology provides realtime, data-driven monitoring that reduces waste and maintains the quality of the food, changing the way food is preserved and managed. This research focuses on the development and implementation of an Arduino-based IoT device for monitoring freshness, temperature, and humidity in storage food environments. Equipped with an MQ-4 methane sensor and DHT11 sensor, the system detects spoilage indicators and environmental conditions and opens an exhaust fan if the moisture has been in excess. The BLYNK IoT app provides instant information to the user about storage conditions, thus ensuring efficient and proactive food management. This product finds answers to some of the main food-related storage challenges by offering scalable and effective solutions for enhanced freshness and reduced spoilage.

关键词： Temperature sensors Temperature measurement Methane Fans Temperature distribution Moisture Humidity Real-time systems Internet of Things Monitoring

来源：评论

学校读者我要写书评

暂无评论

Design and analysis of key scheduling algorithm for symmetric cipher security

引用

International Journal of Information Technology (Singapore) 2024年第6期16卷 3991-3997页

作者： Tiwari, Vikas Kameswari, U. Surya Singh, Ajeet Saxena, Ashutosh Acharya Nagarjuna University Andhra Pradesh Guntur 522510 India C.R. Rao Advanced Institute of Mathematics Statistics and Computer Science University of Hyderabad Campus Telangana Hyderabad 500046 India Dept of Computer Science and Engineering Acharya Nagarjuna University Andhra Pradesh Guntur 522510 India School of Computing Science and Engineering Vellore Institute of Technology VIT Bhopal University Bhopal-Indore Highway Madhya Pradesh Bhopal 466114 India CMR Technical Campus Telangana Hyderabad 501401 India

The success and safety of block cipher systems heavily depend on how efficient and secure their Key Schedule Algorithms (KSAs) are, especially when fighting against cryptanalytic attacks. This paper proposes a novel KSA architecture designed to strike an optimal balance between computational efficiency and cryptographic security. Through the utilization of advanced algorithmic constructs, the proposed KSA minimizes processing time and resource consumption, thus catering to the needs of both high-performance and resource-constrained environments. We conduct a comprehensive statistical analysis to ascertain the computational innovation of our design, employing entropy measures, autocorrelation tests, and non-linear complexity assessments. The empirical evaluation demonstrates the resilience of our KSA against a variety of cryptanalytic benchmarks, revealing significant improvements in key unpredictability and distribution. Additionally, extensive benchmarking against established cryptographic standards confirms the superior performance and security enhancements offered by our KSA. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Block cipher security Cryptographic design Encryption analysis Key schedule algorithm Secure communication

来源：评论

学校读者我要写书评

暂无评论

Securing Networks: Advanced Detection and Prevention of Address Resolution Protocol Cache Spoofing Attack

Securing Networks: Advanced Detection and Prevention of Addr...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Sriharsha VVS Viraj Kisan Daule Surya R Thangam S Dept. of Computer Science and Engineering Amrita Vishwa Vidyapeetham Amrita School of Computing Bengaluru India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

As the technology advances, an increase in the attacks to manipulate or extract data illegally has also risen. This also includes one such attack known as Address Resolution protocol cache spoofing attack. The Address Resolution protocol Spoofer conducts an in-depth exploration into one of the most significant security vulnerabilities identified in local networks, namely Address resolution protocol cache poisoning. The study implements a system which uses a Python based tool which is able to simulate Address Resolution protocol spoofing attacks on the network traffic of two hosts through a Python library known as the Scapy library. This tool allows the execution of Man In The Middle attacks by forging Address Resolution protocol replies and changing the stream of traffic without setting off any alarm by the user. The tool also has a detection mechanism that alerts the users as soon as it detects attempted spoofing; which hence identifies both the offender and the defensive capabilities in Address Resolution protocol spoofing. Additionally, another layer of security is added by user-defined encryption and decryption of the message being delivered. The study has resulted in a secure network, protecting the data from ARP spoofing.

关键词： Integrated circuits Protocols Unicast Prevention and mitigation Telecommunication traffic Libraries Vectors Encryption Security Data mining

来源：评论

学校读者我要写书评

暂无评论

Confidence-Guided Feature Alignment for Cloth-Changing Person Re-identification 27th

Confidence-Guided Feature Alignment for Cloth-Changing Pers...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Huang, Sirong Zheng, Huicheng School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China

ISBN: (纸本)9783031781094

Much progress has been made in the field of person re-identification, but changes in clothing have hindered the practical application of long-term person re-identification. Cloth-changing person re-identification (CC-ReID) aims to address this problem, with the main challenge being the extraction of discriminative features unrelated to clothing. Existing methods, which mainly focus on introducing clothing-irrelevant cues such as key points, contours, and 3D shapes, require additional modules for feature extraction, resulting in increased complexity and potential inaccuracies due to dependence on the performance of external models. Few studies directly use the original RGB images to make the model constantly focus on clothing-independent information. In this paper, we propose a Confidence-Guided Feature Alignment Network (CGFA) for CC-ReID. Specifically, we design a confidence module that automatically learns to make confidence adjustments to fine-grained information, prompting the model to mine clothing-independent discriminative features without introducing other modal cues. By transferring knowledge, we encourage the model to learn discriminative identity features that are independent of clothing bias. As a result, the confidence module can be removed during the inference phase. The proposed simple but efficient method uses only RGB modality without additional cues, and can serve as a powerful baseline for CC-ReID to drive future research. Extensive experiments on the CC-ReID datasets demonstrate the effectiveness of the proposed method, which achieves state-of-the-art performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Meta Learning for Complexity-Aware Optimal Sampling in Few-Shot Intent Classification

Meta Learning for Complexity-Aware Optimal Sampling in Few-S...

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： Krishnendu S Manju Venugopalan Dept. of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Intent classification plays a crucial role in applications such as virtual assistants and chatbots, enabling an accurate determination of the user's intention and providing relevant responses. Minimal supervision models that train from minimal labeled data have become important since they can train models using less amount of data as manually labeling data is time-consuming. To address this problem, the proposed model utilizes a few-shot learning mechanism approach using a metalearning architecture for intent classification. Model-Agnostic Meta Learning model is implemented to enhance generalization given the scenario of constrained labeled samples. Model Agnostic Meta Learning is tested using uniform and complexity aware optimal sampling based methods to assess the impact of data imbalance and robustness of the model. The experimental results on the Banking77 dataset show that the Meta Agnostic Meta Learning architectures in a complexity aware non-uniform sampling setting are able to achieve 100 % of the results achieved by full train models when integrated with ML models. DL models on the other hand did not report a considerable enhancement when migrated from a uniform to a non-uniform sampling setting.

关键词： Metalearning Training Hands Intent recognition Computational modeling Training data computer architecture Data models Complexity theory Few shot learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Drone Delivery Management: An Algorithmic Framework for Collision Detection and Avoidance with Resource Management 3

Optimizing Drone Delivery Management: An Algorithmic Framewo...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Sriharsha, Paramkusam Gowtham, Yelipe Chowdary, Geda Tejesh Bhaskaran, Sreebha Amrita School of Computing Amrita Vishwa Vidyapeetham Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331508456

The revolutionary impact of drones on delivery services encounters major challenges, such as collision with other obstacles and other drones when operating inside crowded areas. This research introduces a Collision Detection and Avoidance (CDA) algorithm which performs effective path identification together with altitude reservation to prevent mid-air collisions. The system improves operational safety together with generating effective delivery routes that deliver both operational safety and efficiency. The system optimizes resource allocation through its ability to arrange drones for the purpose of meeting delivery requirements without excessive congestion. Performance measurement facilitates continuous system improvement. The research implements Dijkstra, A∗ and Bellman Ford shortest path algorithms to the CDA system for evaluating their transport safety and productivity and resource utilization performance. The analysis checks appropriate drone usage in diverse drone applications. The system proves its capability in the incorporation of real-time data for improving drone operations that leads to effective resource use in challenging delivery settings. © 2025 IEEE.

关键词： Resource allocation

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：