检索结果-内蒙古大学图书馆

4th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2023

作者： Ullas, S. Maheswari, B. Uma Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9789819965854

As the global population grows and water resources become scarce, the only way to effectively conserve and utilise them is by adequately treating and reusing them. In Sewage Treatment Plants, ensuring a safe gaseous environment for the worker’s health is essential. Exposure to toxic gases for a long duration may cause health issues for workers. It is essential to understand these factors and take necessary precautions to prevent further deterioration of their health. In this work, we aim to develop a sensor-based system that measures the intensity levels of toxic gases like Methane, Ammonia, Carbon dioxide, and Hydrogen Sulphide emitted from the plant and spread to its environment and to alert at the right time to safeguard the humans around. We compared these gas levels with data captured in good air to demonstrate the high density of the toxic gases in the plant. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Ammonia

来源：评论

学校读者我要写书评

暂无评论

Bidirectional English-Nepali Machine Translation System for the Legal Domain 3

Bidirectional English-Nepali Machine Translation System for ...

引用

3rd Annual Meeting of the ELRA-ISCA Special Interest Group on Under-Resourced Languages, SIGUL 2024

作者： Poudel, Shabdapurush Bal, Bal Krishna Acharya, Praveen Department of Computer Science and Engineering Kathmandu University Nepal School of Computing Dublin City University Ireland

ISBN: (纸本)9782493814296

Nepali, a low-resource language belonging to the Indo-Aryan language family and spoken in Nepal, India, Sikkim, and Burma has comparatively very little digital content and resources, more particularly in the legal domain. However, the need to translate legal documents is ever-increasing in the context of growing volumes of legal cases and a large population seeking to go abroad for higher education or employment. This underscores the need for developing an English-Nepali Machine Translation for the legal domain. We attempt to address this problem by utilizing a Neural Machine Translation (NMT) System with an encoder-decoder architecture, specifically designed for legal Nepali-English translation. Leveraging a custom-built legal corpus of 125,000 parallel sentences, our system achieves encouraging BLEU scores of 7.98 in (Nepali → English) and 6.63 (English → Nepali) direction. © 2024 ELRA Language Resource Association.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Coarse models for bird migrations using clustering and non-stationary markov chains 29

Coarse models for bird migrations using clustering and non-s...

引用

29th AAAI Conference on Artificial Intelligence, AAAI 2015

作者： Jain, Nitin Dilkina, Bistra Georgia Institute of Technology School of Computational Science and Engineering College of Computing AtlantaGA United States

ISBN: (纸本)9781577357179

While great strides have been made in collecting presence data and developing accurate species distribution models, much less is known about the migratory process that guides the spatio-temporal changes in distributions for migrating species, especially birds. In this work, we address a challenging inference task, where given only aggregate and noisy data of the volume of birds for each spatial pixel and time window, we predict the likely transition links with their associated probabil-ities. We propose a framework to build such migration networks for different bird species and present a real world example of constructing a network using our approach. © Copyright 2015, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Entity-centered Cross-document Relation Extraction

Entity-centered Cross-document Relation Extraction

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Wang, Fengqi Li, Fei Fei, Hao Li, Jingye Wu, Shengqiong Su, Fangfang Shi, Wenxuan Ji, Donghong Cai, Bo Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University China School of Computing National University of Singapore Singapore

Relation Extraction (RE) is a fundamental task of information extraction, which has attracted a large amount of research attention. Previous studies focus on extracting the relations within a sentence or document, while currently researchers begin to explore cross-document RE. However, current cross-document RE methods directly utilize text snippets surrounding the target entities in multiple given documents, which brings considerable noisy and non-relevant sentences. Moreover, they utilize all the text paths in a document bag in a coarse-grained way, without considering the connections between these text paths. In this paper, we aim to address both of these shortages and push the state-of-the-art for cross-document RE. First, we focus on input construction for our RE model and propose an entity-based document-context filter to retain useful information in the given documents by using the bridge entities in the text paths. Second, we propose a cross-document RE model based on cross-path entity relation attention, which allows the entity relations across text paths to interact with each other. We compare our cross-document RE method with the state-of-the-art methods in the dataset CodRED. Our method outperforms them by at least 10% in F1, thus demonstrating its effectiveness. © 2022 Association for Computational Linguistics.

关键词： Information use

来源：评论

学校读者我要写书评

暂无评论

Classification of Cotton Leaf Disease Using Multi-Support Vector Machine

Classification of Cotton Leaf Disease Using Multi-Support Ve...

引用

2019 IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing, INCOS 2019

作者： Jenifa, A. Ramalakshmi, R. Ramachandran, V. School of Computing Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Virudhunagar Tamilnadu India

ISBN: (纸本)9781538695425

Management of crops along with its production plays a vital role in order to cope-up with the increasing population eventually reduce the possibility of illness to the human power. With an aid of precision agriculture along with the emerging technology, we could ensure the crops get optimum nutrition fixing the cons of traditional procedure. in this paper, Multi-Support Vector Machine based classification for cotton leaf disease is proposed. The proposed algorithm uses automatic snaps of the crops at every stage, process them at very early stages to determine their flaws, so that the farmer's loss both in terms of money and goods to be hence avoided. The above said Multi-SVM algorithm are models that are either supervised by human or robot which, when fed with the essential data makes segmentation and classification of the types of illness. The Image processing is been implemented to get the capture of leaves at significant stages. This Multi-SVM when compared over the Convolutional Neural Networks has several advantages. While the Multi-SVM is global and unique, the Convolutional neural network suffers from multiple local minima. The complexity of computation of Multi-SVM does not depend on the dimensions of the input space while the Convolutional Neural Networks does. The reason why Multi-SVM outperform Convolutional Neural Network is Multi-SVMs are less prone to over fits. © 2019 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Analytic solutions and multi-stable chaotic dynamics in perturbed and unperturbed nonlinear electromagnetic wave systems for engineering applications

Results in Engineering

引用

Results in engineering 2025年 26卷

作者： Muhammad Zahid Zia Ur Rehman Sultan Shoaib Devi Prasanth Bolla Muhammad Muddassar Riqza Khattak Yasar Amin University of Engineering and Technology Department of Telecommunication Engineering Taxila 47050 Punjab Pakistan Gulf University for Science and Technology Computer Engineering Department Hawally 32093 Kuwait University of Engineering and Technology Department of Mathematical Sciences Taxila 47050 Punjab Pakistan Lamar University Phillip M. Drayer Department of Electrical Engineering Beaumont 77705 TX USA Wrexham University School of Applied Science Computing and Engineering Wrexham LL11 2AW Wales UK

This paper undertakes a theoretical analytic study of a (3+1)-dimensional NLHSM, thereby generalizing the (2+1)-dimensional NLHSM to three spatial dimensions with a view of capturing rich features in the NL electromagnetic wave systems. From the solutions gained by the IGREM method, a variety of dynamical behaviors, including bifurcation, multi-stable chaos, period, and quasi-period wave structures, are given. Both the cases of perturbation and no perturbation are considered to study the effect of interactions in the various wave phenomena. The complexity of stability and sensitivity of these systems is described through bifurcation analysis, which shows how the system proceeds from stable periodic oscillations to quasi-periodic and chaotic oscillations. The new ideas on the excitation and stabilization of electromagnetic waves in strongly nonlinear media can be useful in engineering, for example, for accurately modeling modern telecommunication systems and controlling waves in plasma physics. The analytic solutions offer a starting point to investigate wave behaviors in higher dimensions, which aids in the creation of new approaches to the management of waves in engineering. Users can gain physical wave behavior access to both simulations and their practical implementation through the generalized model for enhancing electromagnetic wave-based engineering systems.

关键词： Mathematical model Visualization Sensitivity analysis Bifurcation Lyapunov exponent

来源：评论

学校读者我要写书评

暂无评论

Enhanced Visual Clarity in Noise-Reduced Image Environment

Enhanced Visual Clarity in Noise-Reduced Image Environment

引用

2023 International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2023

作者： Reddy, Nalagatla Mohaneesh Reddy, Thellapally Jagadishwar Kiran, M Udaya Adharsh, Veldi Vivek Natarajan, B. Bhuvaneswari, R. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai601103 India

ISBN: (纸本)9798350300857

This research introduces an advanced deep learning approach aimed at restoring highly degraded aging photographs. While conventional restoration tasks in supervised learning are effective, real-world image degradation is intricate, making it challenging for the network to generalize due to the disparity between artificial images and genuine aged photographs. The proposed research pioneers a distinctive triplet domain translation network, leveraging a comprehensive dataset containing both artificial image pairs and genuine snapshots to address these complexities. The approach involves training two variational autoencoders (VAEs) to encode clean images and aged photos into distinct latent spaces, facilitating translation between these latent representations. The existence of a discernible gap in the latent space enables the proposed translation strategy to effectively generalize to real photos, overcoming real-world degradation challenges. Moreover, this research incorporates a global branch integrated with a partial nonlocal block to tackle structural defects and multiple mixed deteriorations within a single aged image. Additionally, an extra branch is introduced to handle unstructured defects such as noise, blurriness, scratches, and dust spots. The fusion of these branches in the latent space translation significantly enhances the capability to address a wide array of defects commonly found in antique photos. Furthermore, a specialized face refinement network is employed to extract intricate facial details from the old photos, resulting in enhanced perceptual quality of the restored images. The effectiveness of the proposed method is demonstrated through extensive evaluations, showcasing its superior performance in terms of visual quality for restoring ancient images compared to both current state-of-the-art techniques and existing commercial technologies. © 2023 IEEE.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of Machine Learning Algorithms in Forecasting AQI

Effectiveness of Machine Learning Algorithms in Forecasting ...

引用

2021 International Conference on Technological Advancements and Innovations, ICTAI 2021

作者： Pal, Sudhanshu Pramanik, Debanshi Jain, Ena Dit University Computer Science Engineering Dehradun India Dit University School of Computing Dehradun India

ISBN: (纸本)9781665420877

Air pollution has become major cause of global concern in recent times. Global warming, climate changes and many major hazardous diseases are all reasons of air pollution. Rapid industrialization, urbanization, deforestation have all accelerated the air pollution level. Air is getting polluted due to release of poisonous gases by industrialization, vehicular emissions, unplanned construction activities. Everyone is at an alarming risk whether they are children or elder. Among metro cities of the world Delhi is known as one polluted metro cities in the world and we have used AQI data of Delhi city as our testbed. This work proposes a model in which Machine Learning algorithms are applied to measure the future AQI data from the current and past available AQI data. We have used various algorithms like Linear Regression, Lasso Regression, Random Forest and Decision Tree to predict the future AQI with past AQI and found that Decision Tree algorithm gives best prediction with limited number of data entries and Random Forest gives best result with larger dataset. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Deadlock Detection Methodology Using Tarjan's Algorithm 8

An Enhanced Deadlock Detection Methodology Using Tarjan's Al...

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Neeraja, Adhi Begum, Chimakurthy Mounika Reddy, Kamalapuram Vigneswara Koushal, Rebbavarapu Henry Divya, K.V. Amrita School of Computing Amrita Vishwa Vidyapeetham Dept. of Computer Science Engineering Bengaluru India

ISBN: (纸本)9798331505462

The reliability and performance of concurrency are severely affected by deadlocks in concurrent systems. An efficient deadlock detection algorithm is needed to ensure that any deadlock cases can be pre-empted. The paper introduces a novel algorithm based on Tarjan's method for detecting deadlocks. The algorithm identifies strongly connected components in a directed graph and accurately tracks dependencies among processes using a wait-for graph, enabling precise deadlock detection in concurrent systems. It's implementation is described hereby and its performance is evaluated through extensive experiments on various scenarios. Therefore, this re- search has shown how important it is to detect deadlocks in these concurrent systems which improves their stability as well as reliability. The results demonstrates that the proposed deadlock detection algorithm performs its task efficiently, which is crucial for enhancing the consistency and stability of concurrent systems. This work makes a significant contribution to the development of deadlock detection techniques and offers valuable insights into their application. It is aimed at preventing deadlocks in real-world scenarios. © 2024 IEEE.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

A Large Scale IoT Botnet Attack Detection Using Ensemble Learning 14th

A Large Scale IoT Botnet Attack Detection Using Ensemble Lea...

引用

12th International Advanced computing Conference, IACC 2022

作者： Jwalin, B. Saravanan, S. Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham Banglore India

ISBN: (纸本)9783031356438

The escalation of the newer technology called Internet of Things (IoT), introduced numerous benefits to people. However, it has also raised the risk of cybercriminal attacks. For instance, it has allowed criminals to access confidential information and launch Distributed Denial of Service (DDoS) attacks. Most frequent type of attacks that are carried out is botnets, which are designed to take over a device’s memory and computation. The shortfall of security platform for these devices, can make them vulnerable to exploitation. As connected devices and huge network traffic data rocket in number, it has become more challenging for companies to concentrate on safeguards. In this paper, we propose to implement ensemble algorithms specifically Random Forest and Gradient Boosted Decision Tree (GBDT) that can identify botnet attacks. The research is conducted on a complete N_BaIoT dataset as more data leads to better decisions. We deployed an Apache Spark, a big data technology platform, five nodes cluster to process the complete N_BaIoT dataset. Through the experiments, both the GBDT and Random Forest can produce impressive results. With respect to accuracy, GBDT and Random Forest resulted in 99.24% and 99.8% respectively. However, in terms of time elapsed, GBDT can outperform Random Forest by 12 s. Overall, the GBDT model proved effective in finding malicious data from diverse IoT devices with astounding accuracy and a noteworthy time. © 2023, Springer Nature Switzerland AG.

关键词： Botnet

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：