检索结果-内蒙古大学图书馆

2023 International Conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Hanji, Bhagyashri R. Shree, K Deepa Nawdhar, Vinayak Kulkarni, Varun Sanjay, Shreyank Sukhi, M. Dayananda Sagar Academy of Technology and Management Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350315455

The Disaster Management Web Application is a comprehensive solution designed to facilitate efficient communication and coordination during disaster situations. This application aims to provide a platform for seamless communication among disaster management teams, authorities, and affected individuals. One of its unique features is the ability to function without an internet connection by leveraging server-based technology. It is a software tool designed to assist in the management and response to disasters. It makes use of artificial intelligence and other technologies to give emergency responders, impacted communities' real-time information, coordination, and support. Features like resource allocation and tracking, mapping and visualization of impacted areas, real-time monitoring of disaster situations, communication and collaboration tools, and access to pertinent guidelines and information can all be found within the application. © 2023 IEEE.

关键词： geographic information system Natural disaster technology Transfer web application

来源：评论

学校读者我要写书评

暂无评论

Improved top-down attention phasmatodea population spiking neural network based multi crop recommendation framework

引用

Multimedia Tools and Applications 2025年第10期84卷 8071-8105页

作者： R, Chetan Ashoka, D.V. B, Ajay Prakash Department of Computer Science and Engineering JSS Academy of Technical Education Visvesvaraya Technological University Karnataka India Department of Information Science JSS Academy of Technical Education Visvesvaraya Technological University Karnataka India Department of Information Science and Engineering JSS Academy of Technical Education Visvesvaraya Technological University Karnataka India Department of Artificial Intelligence and Machine Learning Dr. Ambedkar Institute of Technology Visvesvaraya Technological University Karnataka India

Modern agriculture refers to the contemporary practices, technologies and methods used in food production to meet the growing global demand for agricultural products. With increasing concerns about environmental degradation, soil health and resource depletion, there is an insistent need for agricultural practices that are both productive and sustainable. Multicropping mitigate the negative impacts of monoculture and reduce the reliance on synthetic inputs. This research introduces an innovative approach for multi-crop recommendation through the utilization of an integrated framework that combines advanced optimization techniques and neural networks like Enhanced top-down attention Spiking Neural Network (ETSNN). The proposed framework involves two main phases: the first phase focuses on classifying soils suitable for specific agro-ecological zones using an enhanced top-down attention spiking neural network. The second phase predicts multi-crop yields across different districts based on various environmental parameters using an Improved Phasmatodea population Evolutionary Algorithm (IPEA). Before classifying the crops feature selection takes place for the dataset by Enhanced Sea horse Optimization (ESO) method. The outputs from both phases are harmonized using a stacking-based fusion method. The developed user interface accepts real-time input for location-specific soil properties and provides crop recommendations that take into account both the input data and climate parameters. The proposed method attains 99.7% accuracy, 99.2% precision, 99% recall and 99.9% F1-score respectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Hashing and Analysis of Collision Resolution Techniques

Comparative Study of Hashing and Analysis of Collision Resol...

引用

2023 International Conference on IoT, Communication and Automation technology, ICICAT 2023

作者： Gowda, Aviksha Nayana Anshumali, M. Guruprasad, N. Global Academy of Technology Department of Computer Science and Engineering Karnataka Bengaluru India

ISBN: (纸本)9798350302820

Most data structures use hash tables. A key method in computer science for effectively storing, accessing, and searching for data is hashing. It involves converting a key into a hash value and using this value to access the corresponding data in a table. Hash table utilization involves trade-offs, just like many other aspects of computer science. The implementation of hash-based containers has two key problems: the collision resolution mechanism and the hash function. However, collisions may occur when two keys are mapped to the same hash value. In this paper, the study is focused on the concept of collision in hashing along with how collision is resolved by comparing the performance of these collision resolution techniques in terms of their time and space complexities. Our findings indicate that each technique has its advantages and disadvantages, and that the best technique to use, relies on the particular application's needs. Therefore, this paper can serve as a guide for developers and researchers to choose the most suitable collision resolution technique for their specific use case. © 2023 IEEE.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

KSRR: Knowledge Centric Semantically Driven Recipe Recommendation Framework Encompassing Collective Intelligence 15th

KSRR: Knowledge Centric Semantically Driven Recipe Recommend...

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Shah, Haiya Deepak, Gerard Santhanavijayan, A. Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering National Institute of Technology Tiruchirappalli Tiruchirappalli India

ISBN: (纸本)9783031889912

In the era of Web 3.0, there is a pressing need for a knowledge-centric model to recommend recipes, as the current structure of the worldwide Web lacks specialized recommendation frameworks for recipe recommendations, even though standard search engines offer some level of recipe recommendation. This paper aims to address this gap by proposing a dedicated recommendation channel. The model utilizes user historical activity on food apps as one of the criteria for personalization, leveraging the SimRank algorithm and Grey Wolf optimization to generate a comprehensive termset. Additionally, the model incorporates semantic similarity-based reasoning, employing techniques such as SimRank, Morisita overlap index, and normalized information distance. The Grey Wolf optimization framework further refines the solution set. The topic network comprises recipe ebooks, food blogs, and crawl labels from food blogs, with the inclusion of scientific ebooks to enrich the knowledge base. A restriction classifier is employed to control the features of the data center, ensuring computational feasibility and reducing complexity. Furthermore, a lightweight decision tree classifier demonstrates strong classification performance, characterized by high precision, a lower false discovery rate (FDR), and notable expressive percentage values. Extensive evaluations reveal that the proposed framework outperforms baseline models, establishing it as the leading model for recipe recommendations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

An efficient ACO-inspired multi-path routing for source location privacy with dynamic phantom node selection scheme in IoT environments

引用

Soft Computing 2024年第23期28卷 13149-13166页

作者： Arpitha, T. Chouhan, Dharamendra Shreyas, J. Department of Computer Science and Engineering University Visvesvaraya College of Engineering Bangalore University Karnataka Bengaluru560001 India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Karnataka Manipal India

The rapid growth in the smart era of Internet of Things (IoT) relies on the various applications that lead to the design wide range of routing protocols utilizing Machine learning techniques. Third party interference in the open network to perform malicious activities by using location information of the node is high. Many researchers have designed a wide range of protocols to improve security and energy efficiency but the dynamic nature of the Internet of Things suppressed the performance of those algorithms. This may lead to data drop, node death, delay, less network lifetime, and increased third party malicious activities. In this paper, a novel routing mechanism is developed to preserve source location privacy and prevent adversaries from doing backtracking attacks and traffic analysis for energy preservation. The proposed model consists of two key functions Node/Network Condition based Dynamic Phantom Node selection (NCDPNS) and Ant colony optimization Algorithm Aided Multi-Path based Routing (ACOMPR). Here, NCDPNS selects the phantom node based on the node/network conditions like node availability, link availability, node energy level, distance from other nodes in the network, and number of neighboring hops to preserve the location privacy. ACOMPR selects the path based on the ant colony optimization algorithm to choose more than one path for data transmission with very less common resources shared among multiple paths between the source and destination for energy efficient data transmission. The proposed mechanism is achieving the source location privacy at the first stage and energy efficient routing at the second stage. The proposed mechanism is implemented using a Network Simulator-2 (NS2) simulator with predefined network parameters. The results depict that it achieves high throughput, less delay, increased network lifetime, and low energy dissipation for data transmission by preserving the location of the node. The dynamic nature of the IoT is considered

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Dual-Mode Resonant Sectorial Monopole Antenna with Stable Backfire Gain

引用

Chinese Journal of Electronics 2024年第6期33卷 1478-1486页

作者： Feiyan JI Heng ZHANG Xiuqiong XING Wenjun LU Lei ZHU Jiangsu Key Laboratory of Wireless Communications Nanjing University of Posts and Telecommunications Key Laboratory of Wireless Sensor Network & Communication Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau

A novel design approach to wideband, dual-mode resonant monopole antenna with stable, enhanced backfire gain is advanced. The sectorial monopole evolves from a linear, 0.75-wavelength electric prototype monopole under wideband dual-mode resonant operation. As theoretically predicted by the two resonant modes TE3/5,1and TE9/5,1within a 150° radiator, the operation principle is revealed at first. As have been numerically demonstrated and experimentally validated at 2.4-GHz band, the designed antenna exhibits a wide impedance bandwidth over 90.1%（i.e., 2.06–5.44 GHz）, in which the stable gain bandwidth in the backfire,-x-direction（θ = 90°, φ = 180°） with peak value of 3.2 dBi and fluctuation less than 3 dB is up to 45.3%（i.e., 3.74–5.44 GHz）. It is concluded that the stable wideband backfire gain frequency response should be owing to the high-order resonant mode in the unique sectorial monopole antennas.

关键词： Fluctuations Azimuth Prototypes Metals Resonance Frequency measurement Broadband antennas Impedance Gain Wideband

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Renewable Sources of Energy using IoT: Impact and Challenges

Revolutionizing Renewable Sources of Energy using IoT: Impac...

引用

2023 International Conference on IoT, Communication and Automation technology, ICICAT 2023

作者： Kanchan, Pratik Singh, Avishkar Kumar Guruprasad, N. Global Academy of Technology Department of Computer Science and Engineering Karnataka Bengaluru India

ISBN: (纸本)9798350302820

The use of Internet of Things (IoT) technology in renewable energy is examined in this study. The efficiency and productivity of renewable power plants must be increased to meet the rising demand for renewable energy. By enabling real-time monitoring of numerous parameters like dust collection, temperature, weather, and so forth, IoT offers a solution to this issue. The production of energy can be improved using these statistics. The paper also addresses the many IoT sensors that can be used to construct such a system and the difficulties that must be overcome for its adoption. The study's findings show how the Internet of Things (IoT) has the power to revolutionise renewable energy sources and open the door to greater effectiveness, financial success, and environmental sustainability. © 2023 IEEE.

关键词： Renewable energy resources

来源：评论

学校读者我要写书评

暂无评论

Sentiment and Context-Aware Recurrent Convolutional Neural Network for Sentiment Analysis 3

Sentiment and Context-Aware Recurrent Convolutional Neural N...

引用

3rd IEEE Asian Conference on Innovation in technology, ASIANCON 2023

作者： Mariappan, Umasree Balakrishnan, D. Subhashini, S.J. Kumar, Narla Venkata Anand Sai Rao, Saila Lakshmi Sai Malleswara Alagusundar, Nanditha Sri Vidya College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Virudhunagar626001 India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamil Nadu Krishnankoil626126 India Srm Madurai College for Engineering and Technology Department of Information Technology Tamil Nadu Madurai630612 India

ISBN: (纸本)9798350302288

Sentiment analysis is a Natural Language Processing (NLP) task that involves using machine learning techniques, particularly deep learning, to determine the sentiment or emotion expressed in a piece of text. The goal of sentiment analysis is to understand whether the text expresses a positive, negative, or neutral sentiment towards a particular subject, product, service, or topic. A deep learning technique called Sentiment and Context-Aware Hybrid Deep Neural Network (SCA-HDNN) was proposed for sentiment analysis. In SCA-HDNN, Convolutional Neural Network (CNN) was used for sentiment classification. However, CNNs require fixed-sized inputs, which can be a limitation when dealing with sequences of different lengths. So in this paper, Recurrent CNN (RCNN) is introduced for sentiment classification. The incorporation of recurrent connections in each convolutional layer of RCNN enables handling variable-length sequences. RCNNs can be more computationally efficient than CNN. The combination of CNNs and RNNs allows for parallelization and shared computations across time steps, which can speed up training and inference for sentiment analysis. This method is named as SCA-RCNN. The results from the experiment demonstrate that the suggested SCA-RCNN method achieves high levels of accuracy, precision, and recall in sentiment analysis. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

DRCS: Document Recommendation Framework for Cultural Studies as a Prospective Domain 15th

DRCS: Document Recommendation Framework for Cultural Studies...

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Deepak, Gerard Hariharan, Nitin Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering Alagappa Chettiar Government College of Engineering and Technology Karaikudi India

ISBN: (纸本)9783031889912

The need for extensions of documents for highly special sensitive domains like cultural studies which involves countries, and which involves cultural relationships and political scenarios between cultures and across countries. As the worldwide web continues to evolve, it is transitioning into a densely populated semantic web, which is considered the standard for the next generation of the web, commonly known as web 3.0. This paper suggests a framework for Document Recommendation framework for Cultural Studies (DRCS) that utilizes methods like term frequency - inverse document frequency (TF-IDF) and LDA (Latent Dirichlet Allocation) to analyze the term data set. Metadata generation is used to collect and arrange the information, employing transformers for classification. The XGBoost classifier, which is feature-controlled, is used for data set classification. To measure semantic relevance, strong similarity measures like APMI (Adaptive Pointwise Mutual Information) and Pianka Index, Ren-Konen Index, Sim Rank are used. The model incorporates LDA for topic modelling and utilizes resources like the Google Knowledge Graph API to access community-verified knowledge. To optimize the solutions, the UnderCricket Algorithm optimization algorithm is employed. The proposed model achieves high percentages of precision, recall, accuracy, and F-measure, specifically 94.75%, 96.74%, 95.745%, and 95.7346598% respectively. Additionally, the model achieves a low value of FDR (False Discovery Rate) at 0.06% is achieved. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Optimized Deep Learning Classification Model for Intelligent Edge devices

引用

Journal of engineering science and technology Review 2024年第3期17卷 88-94页

作者： Naveen, Soumyalatha Kounte, Manjunath R Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Karnataka Manipal India School of Electronics and Communication Engineering REVA University Karnataka Bangalore560064 India

Deep learning models enable state-of-the-art accuracy in computer vision applications. However, the deeper, computationally expensive, and densely connected architecture of deep neural networks (DNN) have limitations for deploying the model on resource-constraint embedded IoT devices. We propose an efficient neural network compression framework that performs filter pruning, fine-tuning and 8-bit quantization to reduce computational complexity, inference time, and memory footprint. Furthermore, reducing the bit widths of activation and weights helps design a compact deployment model on resource-limited IoT devices such as smartphones. The proposed system is evaluated extensively on the CIFAR-10 dataset for Resnet34 and VGG16 models. In addition, we examine the efficacy of a larger model. The result shows that pruning followed by quantization compresses the neural network and compared to the baseline model, achieved an accuracy of 78.01% for Resnet34 and 82.34% for Vgg16 after pruning and quantization which is © 2024 School of science, DUTH. All rights reserved.

关键词： Object recognition

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：