检索结果-内蒙古大学图书馆

International Conference on computing and Networking Technology (ICCNT)

作者： Samrudhi S. Kamble M. Yagnasri Priya Swetha Sridhar Sanjivani P. Shendre D.K Niranjan Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bangalore India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Poor air quality due to industrialization and urbanization causes respiratory problems and health concerns. Nearly 6.67 million people had died due to air pollution globally. To reduce we need to bring a new regulations as well as device for air pollutant purification. The proposed system has the stability of purification. Continuous monitoring and filtering are essential. This system integrates sensors and filters to provide real-time air quality data, using machine learning for accuracy. SMS alerts provide early warnings for timely action, increasing personal health awareness and regulatory compliance. Overall, it promotes better settings by reducing the negative effects of air pollution on public health and the environment.

关键词： Purification Urban areas Machine learning Air pollution Real-time systems Stability analysis Sensor systems Regulation Public healthcare Monitoring

来源：评论

学校读者我要写书评

暂无评论

Pceve: Part Contribution Evaluation Based Model Explanation for Human Figure Drawing Assessment and Beyond

SSRN

引用

SSRN 2024年

作者： Lee, Jongseo Ahn, Geo Kim, Seong Tae Choi, Jinwoo School of Computing Kyung Hee University Yongin Korea Republic of Department of Computer Science and Engineering

For automatic human figure drawing (HFD) assessment tasks, such as diagnosing autism spectrum disorder (ASD) using HFD images, the clarity and explainability of model decision is crucial. Existing pixel-level attribution-based explainable AI (XAI) approaches demand considerable effort from users to interpret the semantic information of a region in an image, which can be often time-consuming and impractical. To overcome this challenge, we propose a part contribution evaluation based model explanation (PCEvE) framework. On top of the part detection, we measure the Shapley Value of each individual part to evaluate the contribution to a model decision. Unlike existing attribution-based XAI approaches, the PCEvE provides a straightforward explanation of a model decision, i.e., a part contribution histogram. Furthermore, the PCEvE expands the scope of explanations beyond the conventional sample-level to include class-level and task-level insights, offering a richer, more comprehensive understanding of model behavior. We rigorously validate the PCEvE via extensive experiments on multiple HFD assessment datasets. Also, we sanity- check the proposed method with a set of controlled experiments. Additionally, we demonstrate the versatility and applicability of our method to other domains by applying it to a photo-realistic dataset, the Stanford Cars. © 2024, The Authors. All rights reserved.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Personalized Travel Itinerary Recommender System using Tkinter and SQLite

Personalized Travel Itinerary Recommender System using Tkint...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Advik Narendran Anantha Hothri Manyam Yashaswini Srinidhi Sundaram K. Aiswariya Milan Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bangalore India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

In the ever-evolving landscape of travel planning, the ‘Trip Planner” application is highly recommended. Using Python, Tkinter, and SQLite managed through pandas, this tool enhances user interaction with technology, offering a user-friendly platform for selecting hotels, generating itineraries, and preserving travel plans. Its design emphasizes simplicity and efficiency, making it ideal for users looking to redefine their travel organization. The application integrates advanced technological features, positioning it as a top choice for those interested in an effective travel planning tool. This recommendation suits anyone seeking to improve their travel planning processes with innovative software solutions, enhancing the overall experience and convenience of organizing travel adventures.

关键词： Databases Memory Authentication Organizations User experience Software Real-time systems Planning Recommender systems Python

来源：评论

学校读者我要写书评

暂无评论

Interpretable Predictive Modeling for Smoking and Drinking Behavior using SHAP and LIME

Interpretable Predictive Modeling for Smoking and Drinking B...

引用

IEEE International Conference on Current Trends in Advanced computing (ICCTAC)

作者： Arnav Thakur Arunbalaji C G Anish Maddi B Uma Maheswari Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350395808

ISBN: (纸本)9798350395815

Smoking and excessive alcohol consumption remain pressing public health issues. This research aimed to develop Machine Learning (ML) models leveraging sensor and biomarker data to predict smoking and drinking behaviors for targeted interventions. The Smoking and Drinking dataset (sourced from Kaggle) created from wearable sensor readings, blood tests, and lifestyle self-reports is used to train the 10 Machine Learning (ML) algorithms and validated for smoking and drinking prediction. The Random Forest model outperformed others, reaching an accuracy of 79.65% in predicting smoking, while the XGBoost model achieved a notable 73.96% accuracy in predicting drinking status. Overall, the ML models demonstrate strong capabilities for real-time smoking and drinking prediction using biological data. Such predictive analytics hold promise for early risk detection, personalized care, and nuanced interventions by healthcare systems. This research investigated ML algorithms to uncover and analyze patterns in lifestyle behaviors and associated health outcomes. Additionally, this work unlocks the Blackbox nature of ML models using Explainable AI tools “SHAP (SHapley Additive exPlanations)” and “LIME (Local interpretable model-agnostic explanations)”.

关键词： Accuracy Biological system modeling Computational modeling Predictive models Prediction algorithms Data models Real-time systems

来源：评论

学校读者我要写书评

暂无评论

SafeComm: An IOT-based System for enhancing rural child safety using LoRa Technology

SafeComm: An IOT-based System for enhancing rural child safe...

引用

Communications and Information Technologies (GCCIT), Global Conference on

作者： Thangam S Rohan Gamidi Thotapalli Sri Surya Sneha Saragadam J Jesy Janet Kumari Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

The safety of kids who play outside while travelling in rural areas is a big concern. Safecomm’s new technical fix combines LoRa, NFC, as well as UVC cam systems. Thereby, the gadget has been engineered by merging LoRa modules, NFC tags, GSM module and ESP cams for real-time tracking of where their children are and instant alerting their parents or schools. Besides, when there is an emergency, the wearer can choose to press the emergency button for the SOS family contacts and the emergency services organisations to be alerted in case the battery level is still good. If required, images can also be captured and saved on the cloud storage. This IoT product leverages LoRa, NFC, and an UVC cam to cater for safety issues relating to modes of transport for rural schools. Every day when children mobile around, this machine secures them. The attendance is made easy and quick response in cases of emergency is also possible through this technology so the risks are averted. This device ensures that children are safe when they move about every day. These technologies make keeping track of attendance easier and being able to quickly respond during emergencies so that dangers are mitigated, therefore parents as well as teachers can be less worried. This undertaking is seen as one important stride toward using internet of things (IoT) technology for ensuring children from outside urban areas are safe and boosting safety inside schools or while commuting using linked transportation means.

关键词： GSM Visualization Tracking Surveillance Urban areas LoRa Transportation Safety Internet of Things Testing

来源：评论

学校读者我要写书评

暂无评论

Automatic Braking System and Driver Safety Using Arduino Uno Atmega 328p

Automatic Braking System and Driver Safety Using Arduino Uno...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： M Sunil Thippaluru Tharun Sai Thokali Sanjay Uppalapati Dhanush H.N. Vishwas Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

This project addresses one of the primary causes of vehicle accidents: the sudden appearance of obstacles while driving. Drivers’ varying response times often lead to accidents due to delayed braking or inability to stop in time. To mitigate this, an Autonomous Braking system is proposed, leveraging intelligent mechatronic technology. The system employs an Ultrasonic wave emitter at the front of the vehicle to emit Ultrasonic waves, coupled with a corresponding Ultrasonic receiver that detects reflected signals. By analyzing these signals, the system calculates the distance between the vehicle and any obstacles, enabling the microprocessor to adjust the vehicle’s speed accordingly. In emergencies, the microcontroller activates the braking system to apply brakes swiftly and decisively, enhancing safety. A significant upgrade to the system is the integration of a Python-based application using Flask, which dynamically determines the incident’s location and communicates with the nearest emergency services based on real-time geographical data. This is facilitated through GSM technology, which transmits alarm signals and the vehicle’s GPS location to the appropriate authorities, ensuring prompt response and assistance. Additionally, the system’s potential expansion includes inter-vehicle communication capabilities, allowing cars to share information about their locations and speeds, thus enhancing road cooperation and awareness. This not only leads to fewer collisions but also smoother traffic flow. The models used in this project, including the ultrasonic sensor and GPS modules, have demonstrated an accuracy rate of over $\mathbf{9 0 \%}$ in obstacle detection and emergency alert transmission. Overall, the Autonomous Braking system aims to enhance road safety by reducing response times and stopping distances, thereby preventing accidents and significantly improving emergency response capabilities.

关键词： Microcontrollers Receivers Emergency services Acoustics Road safety Real-time systems Time factors Accidents Global Positioning System Vehicles

来源：评论

学校读者我要写书评

暂无评论

Forecasting and Analysis of Transient Voltage with Random Forest Regressor

Forecasting and Analysis of Transient Voltage with Random Fo...

引用

Emerging Technology (INCET), International Conference for

作者： Arnav Thakur Arunbalaji C G Peeta Basa Pati Department of Computer Science & Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

This research addresses the critical challenge of predicting transient voltage events in electrical appliances. Transient voltages are temporary deviations from normal voltage levels that can damage electrical appliances and cause power interruptions if not addressed preemptively. Currently, limitations exist in detecting and forecasting these events across various electrical systems. This study investigates the value of predictive strategies to minimize transient voltage risks. Utilizing simulated data from RLC circuits, we train multiple machine learning regressor models to estimate transient onset times and predict voltage at specific timestamps using time series analysis and lag-based forecasting. Our approach demonstrates promising accuracy and lower error rate as measured by key performance metrics, opening doors for preventive measure of appliances. These findings provide essential insights into data-driven forecasting of transient voltages, paving the way for the development of a more resilient and reliable electrical infrastru cture.

关键词： Fluctuations Time series analysis Measurement uncertainty RLC circuits Predictive models Transient analysis Forecasting

来源：评论

学校读者我要写书评

暂无评论

FER-Net: Leveraging Attention Mechanisms in EfficintNetB5 model for Enhanced Emotion Recognition in Augmented Images

FER-Net: Leveraging Attention Mechanisms in EfficintNetB5 mo...

引用

Global Conference for Advancement in Technology (GCAT)

作者： Balla Charishma Sulochana Bhavya Sri Pragada Gaddam Anvith Reddy Rimjhim Padam Singh Suja Palaniswamy Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

Facial emotion recognition is a critical component in the development of advanced human-computer interaction systems, with applications spanning security, healthcare, and social robotics. This study explores the efficacy of advanced deep learning models, specifically EfficientNetB5 model in identifying emotions from facial images. Leveraging with augmented data, our approach integrates attention mechanisms, batch normalization, convolutional layers, global average pooling layers, and dropout techniques to enhance model performance. The proposed model demonstrated significant performance accuracy of 87.5%, highlighting the importance of emphasizing relevant image regions for better emotion detection. Additionally, we conducted a comparative analysis with other prominent deep learning architectures, including AlexNet, XceptionNet, ResNet, MobileNet and EfficientNetV2M and proved the superiority of the proposed model against them.

关键词： Human computer interaction Emotion recognition Attention mechanisms Image recognition Face recognition Medical services Data models Security Robots Batch normalization

来源：评论

学校读者我要写书评

暂无评论

Suraksha: Advanced SOS Android App with Intelligent Spam Alert Management and Collaborative Decision-Making

Suraksha: Advanced SOS Android App with Intelligent Spam Ale...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： A Padmavathi V Shashini J Collin Ryan Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Safety is first and foremost in the current busy life, and smartphones give a helping hand in protecting. This paper has presented an Android app, Suraksha, which enhances personal safety during emergencies. This app ensures that assistance is sought immediately, whereas traditional ways require one to call a person or send the person a message or even unlock the phone, which may not happen when in distress. The nature of shrugs allows the app to differentiate a safe situation and a red alert. Through distress shrugs, the app sends the user’s location and the user’s defined message to the pre-registered ones. Suraksha app depends on humans to judge the alerts and all the information involved, which creates a bundle of evidence that will be sufficient. It is designed with a Machine Learning model, which studies the user’s learned things and the emergency type to understand its effectiveness.

关键词： Surveys Technological innovation Machine learning algorithms Machine learning Reliability engineering Real-time systems Safety Security Smart phones Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Hyperparameter Tuning in Deep Learning Models using Bayesian Optimization and XAI

A Comparative Study of Hyperparameter Tuning in Deep Learnin...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： N. Jai Vardhan Daggupati Chandana R Dheepak Raaj Sudireddy Shanmukhi Anisha Radhakrishnan Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Plant disease detection is a crucial step in improving the quantity and quality of farm products since many plant diseases that arise in rice crops reduce the production of agriculture and cause financial loss. The manual evaluation of plant health is tiring and time consuming. Combining optimization algorithms with deep learning architectures can lead to more effective and efficient plant disease detection, with improved accuracy and generalization capabilities. This paper presents a comparison study on hyperparameter tuning of deep learning architectures for early detection of rice plant diseases. The hyperparameter tuning was performed by incorporating Bayesian Optimization algorithm on CNN, ResNet, MobileNet, InceptionNet and RegNet. The experimental study is conducted on dataset containing 1007 images of rice seed crop that contains 501 images of healthy samples and 506 unhealthy samples. Performance evaluation metrics such as accuracy, precision and inference time are employed to compare models. Additionally, a comparative analysis using explainable Artificial Intelligence (XAI) is conducted to visualize the interpretability of hyperparameter combinations and their impact on disease detection.

关键词： Deep learning Plant diseases Visualization Accuracy Explainable AI Computational modeling Predictive models Bayes methods Tuning Optimization

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：