检索结果-内蒙古大学图书馆

2024 International Conference on Decision Aid sciences and Applications, DASA 2024

作者： Hussein, Molla Rashied Shaikat, Abu Salman Tasnim, Rumana Zonayed, Md Amin, Abdullah Al Rahman, Shahed Jhara, Sayma Sultana University of Asia Pacific Dept. of Computer Science & Engineering Dhaka Bangladesh Laurentian University Bharti School of Engineering and Computer Science Canada World University of Bangladesh Dept. of Mechatronics Engineering Dhaka Bangladesh Anglia Ruskin University Dept of Mechanical Engineering Essex United Kingdom

ISBN: (纸本)9798350369106

Smart home technologies have significantly enhanced comfort and convenience in our daily lives by facilitating several domestic tasks. Household robots utilized in smart homes are designed to maintain clean floor spaces. The manually operated floor cleaning machines are exceedingly labor-intensive and time-consuming. Furthermore, fuel-operated machinery is prohibitively expensive as well as detrimental to the environment. This paper presents the design and development of an automated floor cleaning robot that eliminates previous limitations, thereby conserving both time and financial resources by reducing human labor costs. Recently, several household robots, particularly floor-cleaning robots, have been developed. Nonetheless, only a limited number of advanced robots were dedicated to the wet cleaning of floors. This study presents an efficient automated vacuum cleaning robot that can perform both vacuuming and wet cleaning of floor surfaces while navigating the area. This eliminates the labor and necessity of designating separate time for cleaning the premises. The automated robot was initially designed, followed by the construction of an effective chassis. Subsequently, IR sensors, an Arduino Nano, motor drivers, and a motor shield were incorporated into the system. The economical and user-friendly robot is designed for autonomous cleaning of various surfaces in both household and industrial settings. © 2024 IEEE.

关键词： Wages

来源：评论

学校读者我要写书评

暂无评论

A Multigrain-Multilabel (MGML) Dataset for Smartphone-Based Human Activity Recognition

引用

SN computer science 2024年第7期5卷 859页

作者： Thakur, Tushti Saha, Anindita Mallik, Manjarini Chowdhury, Chandreyee Department of Mechanical Engineering Jadavpur University Kolkata India Department of Information Technology Techno Main Saltlake Kolkata India Department of Computer Science and Engineering Jadavpur University Kolkata India

The efficacy of machine learning-based Human Activity Recognition (HAR) heavily relies on the datasets. Existing benchmark HAR datasets on smartphone accelerometer sensors provide mostly single-labeled, fine-grained activities like walking, sitting, etc. collected in lab set-up. In real life, users hardly perform an activity in isolation. Rather, the activities are often performed in sequence with non-uniform transition duration. So, for faster transitions, fine-grained data annotation is difficult and error-prone. A few existing benchmark datasets report coarse-grained activities like working, cooking, etc. that do not indicate enough information about the constituent fine-grained activities performed. HAR performance in these cases cannot satisfy real-life purposes like physical fitness prediction, or rehabilitation after surgery. To address this challenge, a Multigrain-multilabel (MGML) dataset has been designed by collecting smartphone accelerometer sensor readings from four users. Here, the coarse-grained activities are multi-labeled, and both fine-grained and coarse grained activities are covered. That means one can get information regarding the physical movements of the user from labelling information. The MGML dataset has been evaluated with four machine learning classifiers. We report a baseline classification accuracy of 95.40% for the classifiers considered. Experimentation has been conducted on the entire filtered and feature-engineered data. The effectiveness of feature engineering has also been shown. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Feature engineering Human Activity Recognition Machine learning Multi-labeled dataset Smartphone sensing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Data Privacy in IoT Cloud Environments with Trust Management 5

Enhancing Data Privacy in IoT Cloud Environments with Trust ...

引用

5th IEEE International Conference on Recent Trends in computer science and Technology, ICRTCST 2024

作者： Goyal, Himanshu Rai Vanitha, A. Karthikeyan, T. Adhikary, Priyabrata Saranya, R. Kiran Kumar, S. Graphic Era Deemed to be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Saveetha Engineering College Department of Management Studies Chennai India Sona College of Technology Biomedical Engineering Tamilnadu Salem India New Horizon College of Engineering Department of Mechanical Engineering Bangalore India V. S. B. Engineering College Department of Computer Science and Engineering Karur India St. Martins Engineering College Department of Computer Science and Engineering Telangana Secunderabad India

ISBN: (纸本)9798350351378

A new era of connectedness, convenience, and efficiency has arrived with the introduction of the Internet of Things (IoT), which has revolutionized the way we engage with the world around us. Data privacy in IoT cloud settings is an urgent problem, yet this shift is inevitable. The goal of this research is to improve data privacy by using trust management systems, and a technique to do so has been presented. Our method includes building a trust model to quantify the reliability of IoT devices and cloud service providers, and a privacy model to evaluate the potential dangers of data sharing. To find a happy medium between data value and data privacy, these trust and privacy evaluations lead to the idea of privacy-preserving data sharing. Our findings show that our method is useful, providing information on reliability, privacy risk, and the opportunity for businesses to make educated choices about data sharing. Our approach has far-reaching ramifications for many groups of people, including the IoT sector, businesses, regulators, and the general public. With the goal of improving and extending data privacy solutions in the ever-changing IoT world, future research paths include personalization, real-time adaption, scalability, user-centric controls, and ethical concerns. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

CanSat: Design, Development, and Deployment of Open-Source Weather Monitoring Nano-Satellite 4

CanSat: Design, Development, and Deployment of Open-Source W...

引用

4th International Conference on Digital Futures and Transformative Technologies, ICoDT2 2024

作者： Alam, Talha Javed, Mazhar Qureshi, Abdur Rahman Anik, Abdullah All Mamun University of Engineering and Technology Peshawar Electronic Engineering Abbottabad Pakistan Ghulam Ishaq Khan Institute of Engineering Science and Technology Faculty of Electrical Engineering Topi Pakistan The University of Haripur Computer science Haripur Pakistan University of Huddersfield Mechanical Engineering Queensgate United Kingdom

ISBN: (纸本)9798350391862

Environmental monitoring and educational accessibility face significant challenges due to the complexity and high cost of traditional satellite systems. Addressing these issues requires a cost-effective solution that enables comprehensive study and intervention to improve environmental conditions. In this paper, we introduce CanSat, a compact satellite designed for educational and research purposes, utilizing off-the-shelf components and a 3D-printed frame to streamline operations and focus on critical processes such as modeling and communication. Equipped with a microcontroller (Esp32) and an RF communication (LoRa Module). CanSat efficiently processes and transmits data, including real-time video, temp, and %RH (% Relative humidity), to ground stations. The CanSat's performance was observed through successful data transmission and global accessibility of data visualization and analysis. The results indicated reliable operation, with data visualization and analysis accessible worldwide through customized web pages and real-time tracking capabilities, demonstrating CanSat's potential as a user-friendly and cost-effective platform for near-space exploration © 2024 IEEE.

关键词： Space research

来源：评论

学校读者我要写书评

暂无评论

Design and fabrication of a mobile robot for weed removal applications in agricultural fields 3

Design and fabrication of a mobile robot for weed removal ap...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Natesan, Nandan Arunkumar, V. Sathiyavathi, S. Kalaiarassan, G. Vellore Institute of Technology School of Computer Science and Engineering Chennai India Kongu Engineering College Perundurai Department of Mechatronics Engineering Erode India Vellore Institute of Technology School of Mechanical Engineering Vellore India

ISBN: (纸本)9798350372120

Agriculture is one of the most important aspects across the globe which is also a primary task for any country to lead their economic growth and to be a healthy country. The objective of agriculture is to produce various food materials, vegetables and fruits as an outcome of the process. But to provide the outcome from agriculture is not as simple as it looks, Farmers face many issues while making the outcome and they need to work separately to overcome this problem. One of the issues faced by the farmer is the weed management. Weed Management is that the method of dominant that the expansion and removal of the weeds in timely manner. The weeds present in the fields have a major impact on the farmers in terms of their reduction in yield and loss in the capital income. In all recent surveys, it is stated that Weeds present in the field causes almost 60 to 75 percentage loss in agriculture. In order to solve this problem and to give a tentative visioned solution, this project focuses on the development of a mobile robot which can identify the weeds in the field while traversing the field and also capable of differentiating the weeds with crops and other small plants and after the identification, weeds are removed by the weed remover. Apart from removing the weeds this project can also give the small summary of the traversed agricultural land. © 2024 IEEE.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

Optimizing Resource Allocation for Secure Communication in IoT Ecosystems

Optimizing Resource Allocation for Secure Communication in I...

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Naga, Suresh Bysani Venkata Kotiyal, Arnav Singh, Suruchi Brahma Rao, K.B.V. Mitra, Abhijit Natrayan, L. Eightfold.ai Ex - Cohesity CA United States Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Uiet Chhatrapati Shahu Ji Maharaj University Department of Computer Science and Engineering Kanpur India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering India Pune India Simats Saveetha School of Engineering Department of Mechanical Engineering India

ISBN: (纸本)9798350375442

The proliferation of social media has made sites like Twitter a treasure trove of information for diagnosing mental health problems like depression. By examining trends in user-generated material, this research presents a machine learning system with the goal of identifying Twitter profiles exhibiting symptoms of sadness. We made sure to include tweets from a wide range of demographics in our dataset by collecting them from both people who reported having depression and a control group. Text, facial expressions, and interaction patterns were all subjected to feature extraction analysis. We used sentiment analysis and natural language processing (NLP) techniques to identify depressive symptoms in language and emotions. A number of ML models were trained and assessed for accuracy, precision, and recall;these models included Neural Networks, Random Forests, and Support Vector Machines (SVMs). Our approach outperforms baseline algorithms in identifying depressed symptoms, according to the data. Providing a scalable method for early diagnosis of depression, this research adds to the continuing efforts in digital psychiatry. It could aid in prompt intervention and support for affected patients. Responsible use of technology in mental health monitoring requires further discussion of privacy implications and ethical considerations when implementing such models. Several indicators were used to objectively analyze the performance of the machine learning models. With 89% accuracy, 86% precision, and 88% recall, the Neural Network model was the top performer. Additionally, the Random Forest model performed admirably, achieving 85% accuracy, 83% precision, and 84% recall. A recall of 81%, precision of 80%, and accuracy of 82% were all rather respectable for the SVM model. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Using a Hybrid-Domain Attention Mechanism with YOLOv8 for Victim Detection in Disasters 7

Using a Hybrid-Domain Attention Mechanism with YOLOv8 for Vi...

引用

7th International Conference on computer Information science and Application Technology, CISAT 2024

作者： Ahmed, Ali Wang, Huan Almadwami, Hashem Kaf, Amira Abo Al-Soswa, Mohammed Wuhan University of Technology School of Mechanical and Electronic Engineering Wuhan China Chang'an University School of Information Engineering Shaanxi Xi'an China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350375107

The disaster response and management domain constitute a formidable challenge to resilience and technological innovation. Prompt identification and localization of victims are paramount for search and rescue teams during emergencies. However, the intricacy of disaster scenes, often obscured by haze and cluttered backgrounds, exacerbates the difficulty in distinguishing victims. This paper introduces an algorithm to detect and locate victims within affected areas. Leveraging the acclaimed YOLOv8 model, renowned for its exceptional speed and accuracy, this study advances the one-stage detector, subsequently termed DSP-YOLOv8, through enhancements tailored to bolster detection precision. By integrating DCNv2, SE, and SPDConv modules into YOLOv8, optimizing feature capture for complex shapes and establishing adaptive spatial and channel dependencies, thus enhancing detection across various scales and occlusion levels. The model was trained and tested on a dataset comprising 5100 images of victims. The efficacy of the developed model was assessed by comparative evaluations Faster R-CNN, SSD, YOLOv5, YOLOv6 and YOLOv8. The resultant model achieved a high accuracy rate of 95.11 percent. Performance evaluation during training and testing phases was conducted based on established metrics, including mean Average Precision (mAP), precision (P), recall (R), and Precision-Recall (PR) curves. The findings from our testing regimen underscore the proposed catastrophe victim identification technique's efficacy, particularly in highly cluttered scenarios. © 2024 IEEE.

关键词： Disasters

来源：评论

学校读者我要写书评

暂无评论

Impact of different voltage source models on antenna current and input impedance within the boundary element method formalism 24

Impact of different voltage source models on antenna current...

引用

24th International Conference on Applied Electromagnetics and Communications, ICECOM 2023

作者： Susnjara, Anna Poljak, Dragan University of Split Faculty of Electrical Engineering Mechanical Engineering and Naval Architecture Department of Electronics and Computer Science Split Croatia

ISBN: (纸本)9798350313017

This paper investigates the differences in dipole current and input impedance due to different source models in the framework of boundary element formalism. The half-wavelength and full-wavelength dipole antennas are placed in free space and above a lossy medium. Antenna current and input impedance are obtained by numerically solving the Pocklington's integro-differential equation via Galerkin-Bubnov Indirect Boundary Element Method (GB-IBEM). Two different feeding structures are used as excitation sources, a delta gap source model usually used under GB-IBEM formalism and a magnetic frill source model. Different segment numbers are also used. The results indicate that the current magnitude in case of half-wavelength dipole antenna varies to a relatively great extent depending on the applied voltage generator model. Input impedance does not vary due to different source models, however, its value changes greatly with segment number. © 2023 IEEE.

关键词： Boundary element method

来源：评论

学校读者我要写书评

暂无评论

Impact of Al2O3, CaO, and Fe2O3 additives on spirulina biodiesel blends in a comparative compression ignition engine study

引用

International Journal of Hydrogen Energy 2025年 139卷 1159-1167页

作者： Ahamed, T.S. Almoallim, Hesham S. Chinnathambi, Arunachalam Josephin JS, Femilda Varuvel, Edwin Geo Department of Mechanical Engineering Noorul Islam University Kanyakumari India Department of Oral and Maxillofacial Surgery College of Dentistry King Saud University PO Box-60169 Riyadh11545 Saudi Arabia Department of Botany and Microbiology College of Science King Saud University PO Box -2455 Riyadh11451 Saudi Arabia Department of Computer Engineering Faculty of Engineering and Natural Sciences Istinye University Istanbul Turkey Department of Mechanical Engineering Faculty of Engineering and Natural Sciences Istinye University Istanbul Turkey Institute of Mechanical Science Vilnius Gediminas Technical University Plytinės Str. 25 Vilnius10105 Lithuania

The current study investigates the impact of three different nano-additives such as Al2O3, CaO, and Fe2O3 on the engine performance and emissions of biodiesel made from Spirulina microalgae blends. The nano-additives were mixed at a concentration of 100 ppm with a blend of 20 % Spirulina biodiesel and 80 % pure diesel to create A20 (with Al2O3), C20 (with CaO), and F20 (with Fe2O3). The Fe2O3 blend (F20) showed the greatest improvement, with brake thermal efficiency 11.8 % higher than neat diesel at maximum engine speed. The CaO (C20) and Al2O3 (A20) blends saw efficiency gains of 3.1 % and 4.2 % respectively under the same conditions. Fuel consumption was reduced for all blends across the range of engine speeds tested. In terms of emissions, the nano-additive blends also outperformed neat diesel, with the Al2O3 blend demonstrating the greatest reductions in CO and HC. These improvements in performance and emissions were due to the high oxygen content in biodiesel blends and large surface area-to-volume ratio of the nanoparticles. © 2025 Hydrogen Energy Publications LLC

关键词： Microalgae

来源：评论

学校读者我要写书评

暂无评论

Scenarios of AI in Smart Grid Systems

Scenarios of AI in Smart Grid Systems

引用

2024 International Conference on Sustainable Computing and Integrated Communication in Changing Landscape of AI, ICSCAI 2024

作者： Kumar, Sanjay Upadhyay, Rimpi Haripriya Department of Mechanical Engineering Noida Institute Of Engineering and Technology Uttar Pradesh Greater Noida India Department of Computer Science and Engineering Tula's Institute Dehradun India Bangalore India

ISBN: (纸本)9798350355338

The power system exhibits traits of openness, ambiguity, and complexity due to the implementation of electricity market reform and the utilization of renewable energy and power demand response in various circumstances. The development and implementation of intelligent power grid systems have emerged as a prevailing phenomenon. The utilization of artificial intelligence (AI) within the context of smart grid infrastructure offers robust technological assistance for the development of digital power networks. This research presents a novel approach that uses Long Short-Term Memory (LSTM) to forecast an institutional building's energy use. The suggested approach makes use of weather forecasts to estimate daily energy consumption ahead of time. The Meteorological Department provides weather forecasts, which allow the model to represent the complex link between energy usage and meteorological conditions. The performance of the LSTM model is compared with Support Vector Regression (SVR) and Gaussian Process Regression (GPR) in order to evaluate its efficacy. © 2024 IEEE.

关键词： AI infrastructure Artificial Intelligence energy generation Smart grid systems technology

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：