检索结果-内蒙古大学图书馆

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

作者： Tripathi, Deeksha Biswas, Saroj K. Das, Akhil Kr. Bhattacharya, Arijit Purkayastha, Biswajit Department of Computer Science and Engineering National Institute of Technology Silchar India Department of Computer Science Gour Mahavidyalaya West Bengal India

ISBN: (纸本)9798350370249

Crop Yield Prediction (CYP) plays a vital role in mitigating emerging food security challenges, particularly when the rapid shifts in global climate patterns occur. Machine Learning (ML) is crucial for CYP because it can estimate the crop production based on different characteristics such as environmental characteristics, soil fertilizers, and crop management. Researchers have used lots of ML techniques with distinct kinds of data analytics techniques. Thus, this study proposes an ensemble model, named Voting-based Ensemble Expert System for Crop Yield Prediction (VEESCYP) to predict the best crop yield for the Assam state of India. This study tries to present the strength of a voting classifier with Ensemble Learning (EL) approaches. The proposed VEESCYP model has performed some data preprocessing tasks before classification, such as the Multiple Imputation by Chained Equation (MICE) to treat the missing values, Isolation Forest (IF) for outlier detection, Genetic Algorithm (GA) for feature selection and Robust Scaling (RS) for data normalization. To show the strength of EL techniques in voting classifier, the proposed VEESCYP model compares with some standard ML algorithms, a Voting-based EL technique using standard ML algorithms and some existing models presented in the literature. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Innovative Design of a Solar-Powered Wireless Soil Moisture Sensor for Maximizing the Efficiency of IoT-Based Systems 4th

Innovative Design of a Solar-Powered Wireless Soil Moisture ...

引用

4th International Conference on Recent Trends in Machine Learning, IoT, Smart Cities, and Applications, ICMISC 2023

作者： Gangone, Anjali Bharat Kumar, G.J. Gangone, Swapna Department of Computer Science and Engineering CMR Institute of Technology Telangana Hyderabad India Department of Computer Science Mattu University Mattu Ethiopia

ISBN: (纸本)9789819994410

This paper presents a comprehensive design and implementation of a Sunward Solar-Powered Wireless Soil Moisture Sensor, which combines cutting-edge technology to enable energy-efficient soil moisture measurement and wireless data transmission. The proposed sensor system employs capacitance-based soil moisture measurement principles and incorporates innovative design elements to reduce costs and simplify installation. It also integrates solar power technology to ensure autonomous and sustainable operation. The core components of the system include a microcontroller (MSP430F149), a Wireless Transceiver Unit (nRF905), a Soil Moisture Sensor Unit with annular and conical electrodes, and a servo motor-based solar panel module for optimal solar energy capture. The sensor's power consumption is meticulously analyzed, and its energy requirements are met by a combination of solar panels and rechargeable batteries. The design of the Sunward Solar Panel Module, featuring a spherical servo motor, is a highlight of this system. The servo motor ensures precise tracking of the sun's position, optimizing solar panel orientation for maximum energy generation. Four Light-Dependent Resistors (LDRs) strategically placed on the solar panel aid in this tracking process. Through this innovative system, real-time soil moisture data can be collected and wirelessly transmitted over long distances, making it a valuable tool for applications in agriculture and environmental monitoring. The paper also discusses the dimensions and efficiency of the solar panel, ensuring that it meets the energy needs of the sensor. It achieves the main objective of this research, that is, not only in day time when sun is with more intensity but also in the low-intensity times like morning and evenings, the proposed design exhibits better results. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

Prediction of Liver Disease Using Machine Learning Approaches Based on KNN Model 1

引用

International Conference on Modeling, Simulation and Optimization, CoMSO 2022

作者： Dutta, Souptik Mondal, Subhash Nag, Amitava Department of Computer Science and Engineering Central Institute of Technology Kokrajhar Assam Kokrajhar783370 India Department of Computer Science and Engineering Meghnad Saha Institute of Technology West Bengal Kolkata700150 India

ISBN: (数字)9789819968664

ISBN: (纸本)9789819968657

The liver, the most crucial interior organ of the human body, performs functions of metabolism control and food digestion. Liver disorders can sometimes prove fatal, and appropriate treatment at the right time will save many lives. Research has been conducted to predict and diagnose liver diseases for quite a while, and Machine Learning (ML) tools have proven very effective. We have considered eight ML models for this study while working on the Liver Patient Dataset, which contains more than 30k instances, for accurately predicting liver diseases. This study includes some boosting algorithms as well. For the proper judgment of the performance of the proposed models, commonly used performance metrics such as accuracy, RoC-AuC, F1 score, precision, and recall have been used. We have inferred that the k-Nearest Neighbor (KNN) produced the most accurate results at 92.345%. Since the models are not overfitted, they are k-fold cross-validated, and hence, the standard deviation of each model is lower. Therefore, the standard deviation of KNN is 0.815, and the False Negative (FN) rate comes out to be 3.7%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Driven Sentiment Analysis in Textual Data 5

Deep Learning-Driven Sentiment Analysis in Textual Data

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Kathiravan, M. Saravanan, S. Jagadeesh, M. Lakshmi, I. Durga, V. Sathya Raja, N. Bharathi Computer Science and Engineering Chennai India Computer Science and Engineering Saveetha School of Engineering Chennai Thandalam India Computer Science and Engineering Rajalakshmi Engineering College Chennai India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798350383522

Emotional recognition from text is essential in natural language processing with far-reaching consequences in areas such as Artificial Intelligence, Human-computer Interaction, and others. Emotions are felt, thought-out physical responses to events. Analyzing these feelings independently of vocal and facial cues is critical to interpreting emotions. Despite these challenges, it is crucial to understand human emotions, especially as people become more comfortable expressing themselves through hate speech on sites like Facebook, Twitter, etc. This paper discusses how to classify many tweets based on their tone. Here, we use deep learning algorithms to determine whether an expression means a happy or sad emotion. There are four distinct negative states of mind: rage, indifference, loneliness, disdain, sadness, and despair. The subset of positive emotions includes zeal, joy, happiness, love, calm, pleasure, and wonder. Using three datasets, we validated and assessed the method's use of long short-term memory and recurrent neural networks to obtain high accuracy in emotion categorization. With an 85.07% predictability for positive and negative classification and an 87.23% and 86.3% accuracy for positive and negative subclasses, respectively, a detailed examination reveals that the system improves emotion prediction using the LSTM model. © 2024 IEEE.

关键词： Deep Learning techniques Emotion Classification Long Short-term memory Recurrent Neural Networks

来源：评论

学校读者我要写书评

暂无评论

ElementaryCQT: A New Dataset and its Deep Learning Analysis for 2D Geometric Shape Recognition

引用

SN computer science 2025年第1期6卷 1-14页

作者： Boob, Archana Radke, Mansi Computer Science and Engineering Visvesvaraya National Institute of Technology South Ambazari Road Maharashtra Nagpur 440010 India

Geometry problems at the elementary school level typically include a figure and input text, which requires interpreting both and finding a solution. Figures may include shape, side values, angles, perpendicular symbols, and other information that may or may not be mentioned in the question text. The initial step in tackling such challenges is identifying the geometric shape. Typical shapes include circles, triangles, squares, rectangles, parallelograms, trapeziums, rhombus, etc. The existing 2-dimensional (2D) shape dataset consists of plain shapes, i.e. shapes without geometrical properties. This paper presents a comprehensive dataset, ElementaryCQT (CQT stands for Circle, Quadrilateral, Triangle), of geometric 2D shapes with and without geometric properties like diagonals, perpendiculars, chords, tangents, etc. This dataset is a benchmark for machine learning and deep learning shape identification models for geometry problems. It is trained and tested with sequential CNN, VGG16, ResNet50, Inception-v3, and Inception-ResNet-v2 pre-trained deep learning models to prove their efficacy. Each network is fine-tuned on the dataset and evaluated using 10-fold cross-validation. The ResNet50 model has the best F1 score of 81.86% and accuracy of 81.97%. We performed three ensembling strategies namely, average, weighted average, and majority voting which give an F1 score of 84.07%, 84.3%, and 83.8% respectively. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： 2D geometric shapes dataset Classification Deep learning Ensemble Geometry problems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Public Safety through Real-time Weapon Detection: A Deep Learning Approach 3

Enhancing Public Safety through Real-time Weapon Detection: ...

引用

3rd International Conference for Advancement in technology, ICONAT 2024

作者： Dass, J. Maria Arockia Suresh, A. Swathi, K. Shalini, Paidimuddala Sinha, N A Yaswanth Kotholla Uday Kiran, U. Siddharth Institute of Engineering & Technology Department of Computer Science and Engineering Andhra Pradesh Chittoor India

ISBN: (纸本)9798350354171

Date In response to the imperative need for mitigating criminal activities and ensuring public safety, this research proposes a novel approach leveraging deep learning techniques for real-time weapon detection. In contemporary society, criminal acts pose significant threats to both individuals and the broader community, necessitating proactive measures to counter such offenses swiftly. By harnessing advanced technologies, particularly deep learning algorithms like YOLOv7-tiny, this study intend to create a robust system capable of identifying weapons in surveillance footage captured by CCTV cameras. The project begins with the meticulous collection of datasets from reputable research sources, ensuring diverse and comprehensive samples for training the deep learning model. Subsequently, these datasets undergo rigorous pre-processing steps to optimize them for training, including resizing images to the required format. To facilitate accurate annotation and labelling of the dataset, advanced tools like Robo flow software are employed, streamlining the process and enhancing efficiency. Upon completion of the pre-processing phase, the YOLOv7-tiny algorithm is deployed for training the model on the annotated datasets. Through iterative training and validation processes, the model is fine-tuned to achieve optimal performance in weapon detection tasks. Once trained, the model is capable of swiftly and accurately identifying weapons in real-time surveillance footage. This project presents an effective solution for real-time weapon detection in public spaces, leveraging deep learning algorithms and advanced software tools. © 2024 IEEE.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Product Review Understanding: Text Summarization with BART Large XSum 1st

Enhancing Product Review Understanding: Text Summarization w...

引用

1st International Research Conference on Computing Technologies for Sustainable Development, IRCCTSD 2024

作者： Gopika, S. Balaji, Mayuri Mahimaa Vishwanath, M. Karthikayani, K. Department of Computer Science and Engineering SRM Institute of Science and Technology Chennai Vadapalani India

ISBN: (纸本)9783031823824

Online shopping has revolutionized the way consumers make purchasing decisions. Customer reviews play a crucial role in this process, providing valuable insights into product quality and satisfaction. However, sifting through numerous reviews can be time-consuming for customers. This research aims to address this issue by proposing a novel method to generate a single summary for the overall reviews of each product across different years. The proposed approach utilizes the BART large xsum model to streamline the summarization process. Initially, the dataset is preprocessed to remove irrelevant reviews, such as those lacking product IDs or years. Subsequently, the dataset is divided into batches, each containing 1024 tokens, to facilitate efficient processing. Summaries are generated for each batch, and the output is then used as input for the next stage. Finally, a concise summary is produced for each product across different years. Experimental evaluations are conducted using the Amazon baby product reviews dataset, with the performance of the BART large xsum model assessed using confidence scores. The results demonstrate that the proposed method effectively generates concise summaries for the overall reviews of each product across different years, saving customers valuable time in decision-making. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Crop Recommendation with BiLSTM-MERNN Algorithm for Precision Agriculture 1

Crop Recommendation with BiLSTM-MERNN Algorithm for Precisio...

引用

1st IEEE International Conference on Networking and Communications, ICNWC 2023

作者： Sreemathy, J. Prasath, N. Sri Eshwar College of Engineering Department of Computer Science and Engineering Tamilnadu Coimbatore India SRM Institute of Science and Technology Department of Networking and Communications School of Computing Tamilnadu Chennai India

ISBN: (纸本)9798350336009

The term 'precision agriculture' (PA) refers to the application of high-tech sensors and analysis tools to increase agricultural output and assist with management decisions. Deep learning, also referred as DL, has lately emerged as a potential remedy for information assertions and CPU vision difficulties. It offers a lot of promise and can be applied to agriculture just like it does to other industries. With this goal in mind, this study makes a case for establishing a crop recommendation system dependent on DL. This location is responsible for collecting a great amount of historical data on agricultural productivity, climatic conditions, and the preprocessing of said data. After that, crop recommendations are generated using an algorithm known as the Bidirectional LSTM-Modified Elman Recurrent Neural Network (BiLSTM-MERNN). A crop dataset is used to test how well the proposed method performs compared to other methods already in use, demonstrating the method's applicability. © 2023 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Ultra-Gain Two-Input Two-Output DC–DC Converter for Electric Vehicle Application 1

引用

2nd International Conference on Sustainable technology and Advanced Computing in Electrical engineering, ICSTACE 2023

作者： Ramanathan, G. Bharatiraja, C. Department of Electrical and Electronics Engineering SRM Institute of Science and Technology Tamil Nadu Kattankulathur Chennai603 203 India

ISBN: (数字)9789819992355

ISBN: (纸本)9789819992348

Electric vehicles are popular due to savings in fuel cost, environment, and climatic changes. In this paper, a two-stage ultra-gain converter is proposed to achieve high-output voltage in two different ports with inductor–capacitor 2-diodes (LC2D) configuration. The inductor and capacitor in LC2D configuration are used to improve the current and voltage, respectively, while the diode protects the reverse flow of current. The switches are worked at different duty ratios to attain high gain voltage. This converter is designed for the continuous mode of operation, which generates 250 W and 1 kW outputs at two ports and achieves 94.2% efficiency. The presentation of the suggested converter is consumed through simulation and implemented in the experimental platform. The output waveforms are presented under static conditions for the proposed converter. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Simulation platform

来源：评论

学校读者我要写书评

暂无评论

Centrality of Any Node in Social Network Analysis 2024

Centrality of Any Node in Social Network Analysis

引用

16th International Conference on Contemporary Computing, IC3 2024

作者： Srivastava, Milli Manju, Manju Department of Computer Science & Engineering and Information Technology Jaypee Institute of Information Technology Noida India

ISBN: (纸本)9798400709722

In the contemporary landscape of advanced mobile technology, social media platforms have emerged as prominent arenas for expression, fostering vast volumes of communication ripe for research and analysis. Social network analysis (SNA) stands as a pivotal tool in identifying influential individuals within microblogging platforms, notably Twitter, which serves as a catalyst for online dialogues, trends, and content virality. The applications of discerning influential users on Twitter are multifaceted, ranging from viral marketing and brand analysis to news dissemination, health awareness campaigns, political activism, and governance empowerment. In this study, we introduce a sustainable method, termed Weighted Correlated Influence (WCI), designed to capture the relative impact of both activity on a timeline and characteristics of online users that are trend-specific. Weighted Correlated Influence in social network analysis evaluates the significance of nodes by combining their connectivity and influence, considering both the weight and correlation of their relationships. This metric helps identify key influencers and the overall structure of the network, highlighting nodes with high influence and strong, correlated connections. Our methodology integrates profile activity with underlying network topology to assign influence scores to users, synthesizing their combined effect. To evaluate the efficacy of our proposed methodology, we focus on the Twitter trend #Coronavirus Pandemic and validate the results against another social media trend. Experimental findings demonstrate the superior performance of WCI over existing methods. © 2024 Copyright held by the owner/author(s).

关键词： Tweets

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：