检索结果-内蒙古大学图书馆

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Ahmad, Zoheb Quasim, Danish Garg, Shreeya Kumar, Vinod Delhi Technological University Dept. of Software Engineering New Delhi India Delhi Technological University Dept. of Computer Engineering New Delhi India Iiit Delhi Dept. of Computer Engineering and Bioscience New Delhi India

ISBN: (纸本)9789380544472

YouTube's recommendation system is famous for its success in maintaining high retention rates. The cause of its success is its ability to learn and predict an individual user's preferences appropriately. An unintended consequence, however, is that users get stuck in what is known as their own 'echo chambers' when dealing with and feeding users back their preferences. These echo chambers can cause increasing perspective bias within users, making it difficult for users to understand differing opinions. This work aims to prepare a model that counteracts YouTube's recommendation system by forcefully exposing users to content from varying viewpoints. The SSKA pipeline (Suno Sabki, Karo Apni) is a complementary deep learning model that involves Natural Language Processing (NLP) and K-Means clustering. It utilizes modern software libraries such as the YouTube API (Application Programming Interface) for data collection and was trained and tested on a varied set of users. The results prove that the model is successful in decreasing the bias recommendation by exposing users to the content of varying opinions and helping them break away from their echo chambers. The proposed methodology of explicitly exposing users to the content of varying opinions can positively impact local societies and the global community. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Personal Finance Management and Prediction using ML Algorithms 8

Personal Finance Management and Prediction using ML Algorith...

引用

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

作者： Kaushik, Sujay G. Kashyap, Sumukha S. Surabhi, B.V. Chaitra, M. Reddy, Santhosh Anitha, N. Bnm Institute of Technology Affiliated to Vtu Dept. of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798331505462

Effective personal finance management is essential for achieving financial stability and long-term financial health. This paper presents a comprehensive approach to summarizing, analyzing, and show monthly expenses using machine learning models. By collecting user inputs such as age, place of stay, number of dependents, monthly expenses on transport, education, subscriptions, savings, medical expenses, and more, the system uses linear regression, decision trees and random forest algorithms to predict financial values. The system provides detailed information of expenses, savings, and overall financial health, along with personal health analysis based on dietary habits. Users have access to a wide range of financial and lifestyle information, allowing the system to provide personalized recommendations to increase financial security and achieve financial goals. The model also evaluates the impact of recurring expenses and notable investments, helping users understand their spending patterns and make informed financial decisions. The results demonstrate the system's capability to deliver accurate predictions and actionable advice, enable users to better manage their finances. This approach has led to significant advances in personal financial management by integrating machine learning techniques to provide insight into people's financial health. © 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

IoT-based Automatic Pan Evaporimeter Monitoring and Irrigation Control System for Crops 8

IoT-based Automatic Pan Evaporimeter Monitoring and Irrigati...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Kabir, Md Shahriar Niloy, Khalid Mahmud Hossen, Md Imon Afrose, Sumaiya Mofazzol, Md. Ismail Hossain American International University-Bangladesh Dept. of Electrical & Electronics Engineering Dhaka Bangladesh Uttara University Dept. of Computer Science Engineering Dhaka Bangladesh

ISBN: (纸本)9798350376425

This research study intends to automate the manual pan evaporimeter system and scheduling irrigation by considering soil water content and crop evapotranspiration. Automating the pan evaporimeter means performing tasks without human intervention, such as measuring the daily water evaporation amount, calculating and storing data, and refilling the pan with water. A waterproof ultrasonic sensor was used to measure the water evaporation amount. The ultrasonic sensor was installed on an innovatively designed structure facing the pan's water surface. The sensor measured the distance between the water surface and the sensor. The surface level decreased as the water evaporated over time, which caused an increment in the distance between the ultrasonic and water surfaces. By this, the sensor calculated the daily evaporation amount. The pan needed to be refilled when all water evaporated;a submersible pump was used to refill the pan automatically. A relay switch controlled the pump, and a microcontroller turned on the switch based on sensor value. The entire setup was IoT-enabled to monitor and control the system remotely on a mobile device. The entire system was backed up by solar energy to run on clean energy. A solenoid valve was used to control the flow of irrigation water. Pan evaporation estimated the amount of water that could be lost owing to evaporation and transpiration. Soil moisture sensors provided a direct measurement of the amount of water present in the soil. The two combined generated a dynamic and responsive irrigation plan that maximized water use and promoted the healthy development of crops. That approach was used. The ultrasonic sensor accurately measured water evaporation, but the installation process was complex. So, a need arises to develop a simple system or scale-type sensors to overcome the complexity. © 2024 IEEE.

关键词： Solenoid valves

来源：评论

学校读者我要写书评

暂无评论

Experimental Thermal Model-Based SOC Estimation Algorithm for Lithium-Ion Phosphate Batteries Considering Internal Temperature

引用

Transactions of the Korean Institute of Electrical Engineers 2024年第12期73卷 2289-2296页

作者： Kim, Dong Hwan Ko, Jeong Soo Kim, Do Hyeon Lim, Jong-Hun Lim, Je Yeong Lee, Jaein Lee, Byoung Kuk Dept. of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of Advanced Defense Science & Technology Research Institute Agency for Defense Development Korea Republic of

This paper proposes a method for estimating the State of Charge (SOC) of lithium iron phosphate (LFP) batteries based on an experimental thermal model that considers internal battery temperatures. The proposed algorithm involves selecting a thermal model and suggesting methods for extracting parameters from the chosen model. Using the proposed thermal model, the algorithm compensates for temperature differences in cold and hot environments, thereby correcting the internal temperature to estimate SOC accurately. The effectiveness of the proposed algorithm is verified by estimating the SOC of electric vehicle LFP batteries and comparing the accuracy before and after correction. Copyright © The Korean Institute of Electrical Engineers.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

Modular Deep Reinforcement Learning: Enhancing Flexibility through Agent Splitting

Modular Deep Reinforcement Learning: Enhancing Flexibility t...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Tian, Chong Rawat, Danda B. Howard University Dept. of Electrical Engineering & Computer Science WashingtonDC United States

ISBN: (纸本)9798350362480

Deep reinforcement learning (DRL) has shown remarkable success in tackling complex tasks by learning representations directly from raw data. However, as DRL agents become increasingly sophisticated, they often face challenges in adapting to new tasks or environments due to their monolithic structure. In this paper, we prove that by decomposing the agent into modular components, we enable more efficient adaptation as well as more efficient than that of the singular DRL agent on tackling complex tasks. Overall, our work contributes to advancing the field of DRL by introducing a flexible and scalable framework for agent decomposition. By enabling the creation of modular agents, we empower DRL systems to efficiently adapt to changing environments, learn new tasks with minimal intervention, and achieve higher levels of performance and versatility. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Heart Disease Prediction Model using Merged XGBoost-SVM Classifier and Particle Swarm Optimization 5

A Heart Disease Prediction Model using Merged XGBoost-SVM Cl...

引用

5th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2024

作者： Majumder, Annwesha Banerjee Gupta, Somsubhra Majumder, Sourav Singh, Dharmpal JIS College of Engineering Dept. of Information Technology Kalyani India Swami Vivekananda University Dept. of Comouter Science Kolkata India Capgemini Kolkata India JIS College of Engineering Dept. of Computer Science and Engineering Kalyani India

ISBN: (纸本)9798350395235

This study aims to develop an advanced heart disease prediction model using machine learning techniques to address the global health challenge of early identification and accurate diagnosis, especially considering the projected deficits in healthcare by 2030. The proposed model integrates two powerful algorithms, XGBoost and Support Vector Machine Classifier, leveraging their complementary strengths to achieve effective classification. To enhance the model's performance, feature selection has been conducted using the LASSO method, which identifies the most relevant features, while outlier removal based on the Z score ensures data quality. StandardScaler has been utilized to standardize the data, mitigating any biases caused by differing scales. Furthermore, Particle Swarm Optimization has been employed to optimize the model's performance by fine-tuning its parameters. The reported accuracy of 91.8% underscores the model's potential to accurately predict heart disease, offering valuable support in prevention efforts. These findings highlight the significance of technological advancements in healthcare, particularly in addressing the growing demand for accurate and timely diagnoses. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Adaptive Traffic Signal Timing: Leveraging YOLOv10 and computer Vision for Real-Time Optimization 8

Adaptive Traffic Signal Timing: Leveraging YOLOv10 and Compu...

引用

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

作者： Papanashi, Suhas Chadaga, Manya Kshithi, R. Huddar, Santosh S. Sreelakshmi, K. Ramakanth Kumar, P. Rv College of Engineering Dept. of Electronics and Telecomm Bengaluru India Rv College of Engineering Dept. of Computer Science & Eng. Bengaluru India

ISBN: (纸本)9798331505462

Traffic congestion poses a significant challenge in modern urban environments, particularly in densely populated cities. Traditional traffic signals, which operate on fixed timings, often require manual adjustments to respond to varying traffic densities, leading to inefficient traffic flow. This issue arises because fixed intervals do not account for the dynamic nature of traffic patterns throughout the day. While developing intelligent systems that adjust signal durations dynamically offers a potential solution, such systems involve substantial financial investment and extended implementation timelines. This paper proposes a method to optimize green light durations by analyzing footage collected from a traffic junction in Bengaluru. This analysis can be performed using existing CCTV footage or manually gathered data. Even limited sample sizes can provide valuable insights for preliminary adjustments. The approach utilizes YOLOv10, a state-of-the-art computer vision algorithm, to extract relevant traffic data. The data is processed by an algorithm designed to reallocate green light durations, which are then compared with the original timings. An experimental setup involved recording one-minute videos over three days at the selected junction and applying the proposed algorithm to assess and refine signal durations. The results demonstrate the feasibility of using such algorithms to improve traffic signal management effectively. © 2024 IEEE.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

From Ranch to Worldwide:Observing Soil Welbeing Patterns

From Ranch to Worldwide:Observing Soil Welbeing Patterns

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Divakar, K.M. Ankith Gowrishankar Esturi, R. Anil, P.S. Namith, D. Chethan, A. S J C Institute of Technology Dept. of Computer Science Engineering Chikkaballapur India

ISBN: (纸本)9798350359688

Declining soil wellbeing represents a huge danger to worldwide food security and rural maintainability. Precisely checking soil wellbeing patterns and anticipating future land appropriateness at nearby and worldwide scales are essential for illuminating feasible administration practices and strategy intercessions. This paper proposes a clever structure that use the force of large information investigation to address this test. We expect to overcome any issues between ranch level checking and worldwide experiences, engaging partners at each level to come to informed conclusions about land use and management. Our structure depends on the mix of assorted information sources. High-goal remote detecting information, including satellite symbolism and aeronautical photography, will give basic experiences into soil properties, crop conditions, and land the board rehearses. We will additionally improve the examination by consolidating promptly accessible open-access datasets on environment, soil overviews, and financial data. This exhaustive information combination approach permits us to catch the diverse idea of soil wellbeing and land reasonableness dynamics. Extracting significant experiences from these tremendous datasets requires clever examination devices. We will use a setup of AI procedures, including regulated and solo learning calculations, to reveal stowed away examples and connections inside the information. Directed learning will empower us to foster prescient models for soil wellbeing appraisal and land appropriateness planning, while solo learning will assist with recognizing remarkable attributes and likely peculiarities in various farming *** system will create constant soil wellbeing maps, featuring areas of corruption, supplement lacks, and potential improvement open doors. This enables ranchers to come to informed conclusions about manure application, water the board, and harvest choice, advancing their activities for expanded yield and long ha

关键词： Fertilizers

来源：评论

学校读者我要写书评

暂无评论

HAR-CLET: A Novel Conv-LSTM with Extra Tree Classifier for Human Activity Recognition

HAR-CLET: A Novel Conv-LSTM with Extra Tree Classifier for H...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Choudhury, Nurul Amin Soni, Badal National Institute of Technology Silchar Dept. of Computer Science and Engineering Assam Silchar India

ISBN: (纸本)9798350350821

In this paper, we propose a novel ensemble of Convolutional Neural Network-Long Short-Term Memory with an Extra Tree Classifier for automatic feature engineering in the spatiotemporal domain and classification of different human activities collected using inbuilt smartphone sensors. Prominent sensor-based HAR systems are trained and validated in extracted features of datasets collected in a controlled and simulated environment, which can adversely impact the reliability in real-world scenarios. Our approach utilizes unsimulated data from diverse users collected using inbuilt smartphone sensors in real world environment. Also, the proposed model was effectively trained and tested with multiple standard public datasets for validation and benchmarking with diverse evaluation metrics. With effective parameter tuning and lightweight feature extraction architecture, the proposed model achieved an average performance accuracy of 99 % with their own generated dataset, mHealth and MotionSense dataset, in comparatively optimized computational time compared to the benchmark models. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

NutriSpy: Investigate Your Food's Health Quotient 3

NutriSpy: Investigate Your Food's Health Quotient

引用

3rd IEEE North Karnataka Subsection Flagship International Conference, NKCon 2024

作者： Thanay Kumar, Y.R. Joshi, Sudhanva S Sujan, A.T. Ujwal Karanth, K.V. Asha Rani, K.P. Gowrishankar, S. Dr. Ambedkar Institute of Technology Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350364569

NutriSpy is a comprehensive web and mobile application designed to enhance users' health and wellbeing through personalized food and exercise recommendations. At its core, NutriSpy integrates three powerful features: a tailored workout recommendation system, an advanced food identification tool, and a robust diet advisory service. By leveraging state-of-the-art machine learning algorithms, NutriSpy accurately identifies food items, assesses their nutritional and caloric content, and generates customized dietary guidance. The food identification system employs image recognition and natural language processing to provide precise nutritional information from photographs or descriptions of meals. This is combined with a diet advice system that considers individual health profiles, dietary restrictions, and fitness goals to offer personalized nutrition plans. Additionally, NutriSpy's workout recommendation system aligns exercise routines with users' dietary needs and fitness aspirations, creating a harmonious balance between food intake and physical activity. NutriSpy's sophisticated technology facilitates real-time adjustments and recommendations, making it a dynamic tool for promoting healthier lifestyles. By analyzing user data and integrating current health trends, NutriSpy not only aids in immediate dietary and fitness decisions but also contributes to long-term health improvements. This study explores the development and functionality of NutriSpy, detailing its components, underlying technologies, and potential impact on fostering healthier living habits. © 2024 IEEE.

关键词： Diet Recommendation system Exercise Recommendation System Food Recognition System

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：