检索结果-内蒙古大学图书馆

Electronics and Sustainable communication systems (ICESC), 2020 International Conference on

作者： G. Revathy P. Uma Maheswari S. Madhavi Vijay Anand P R. Vajubunnisa Begum H. Jasmin Department of Computer Science and Engineering Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai India Department of Computer science and Business systems K. Ramakrishnan college of Engineering Trichy India Department of Information Technology Vel tech Multi tech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai India Department of Artificial Intelligence and Data Science CMR Institute of Technology Bengaluru India Department of Electronics and Communication Science Justice Basheer Ahmed Sayeed College for Women Affiliated by University of Madras Chennai India

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

Ovarian cancer is the fifth most common cause of death from cancer in women. This is mainly because it is often diagnosed at a late stage, as the earliest symptoms are unclear and inconsistent. Existing diagnostic techniques, such as biomarkers, biopsies, and imaging tests, have notable drawbacks such as reliance on subjective interpretation, inconsistency across different observers, and time-consuming testing procedures. This research study introduces an innovative deep learning framework that employs a convolutional neural network (CNN) algorithm to accurately predict and diagnose ovarian cancer, thereby overcoming the existing constraints. The CNN was trained using a dataset of histopathology images. The dataset was partitioned into test and training subsets to enhance the model's performance. The algorithm demonstrated an impressive accuracy rate of 96%, successfully detecting 97.12% of malignant instances and precisely categorizing 95.02% of healthy cells. This method effectively mitigates the challenges related to human expert evaluation, including elevated rates of misclassification and variability across different observers, while also reducing the time required for analysis. The results underscore the capability of this CNN-based technique to offer a more precise, effective, and dependable strategy for forecasting and detecting ovarian cancer. Subsequent investigations will prioritize the integration of new breakthroughs in deep learning to further amplify the efficacy of the suggested approach.

关键词： Deep learning Training Accuracy Histopathology Transfer learning Observers Prediction algorithms Partitioning algorithms Convolutional neural networks Ovarian cancer

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Voice-Recognition Wheelchair System for Disabled Persons

An Intelligent Voice-Recognition Wheelchair System for Disab...

引用

Sustainable Computing and Smart systems (ICSCSS), International Conference on

作者： A.V. Kalpana V. Venkataramanan G. Charulatha G Geetha Department of Data Science and Business Systems SRM Institute of Science and Technology Chennai Tamil Nadu India Department of Electronics and Communication Engineering D.J Sanghvi College of Engineering Mumbai Maharashtra India Department of Electronics and Communication Engineering Peri Institute of Technology Chennai Tamil Nadu India Department of Computer Science Engineering B V Raju Institute of Technology Hyderabad Telangana India

This study illustrates the creation of an intelligent voice-recognition wheelchair for disabled persons who cannot manually man-oeuvre their wheelchairs. Using voice recognition, the patient operates the wheelchair, and a GPS device included in the wheelchair can track the patient’s position and communicate the data to a Smartphone. To carry out the people’s orders, the voice module V3 records and can recognize the patient’s voice. This module converts the voice commands into letters, subsequently transmitted to the Wi-Fi module to operate the wheelchair. The Wi-Fi module sends commands to the motor drive for the wheels. In addition, three levels of motor speed adjustment are available: low, medium, and high. This device also utilizes an Infrared sensor to automatically identify obstacles, allowing the patient’s family members to know exactly where they are. Disabled People can be used this device, which simultaneously provides a voice-controlled wheelchair, obstacle detection, motor speed control, and patient GPS tracking via mobile phone; it will be a successful solution for disabled people across the world.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cloud-based Decentralized Smart Healthcare for Patient Monitoring on Deep Learning 2

Cloud-based Decentralized Smart Healthcare for Patient Monit...

引用

2nd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2023

作者： Arunachalam, Sripriya Shanthi, H.J. Sivagurunathan, G. Das, Shyamali Anand, D. Raj M, Thanga School of Computing Sciences Vels Institute of Science Technology & Advanced Studies - Vistas Computer Applications- Pg India Amet University Ecr Kanathur India St. Joseph's College of Engineering Omr Department of Electronics and Communication Engineering Chennai600119 India Cmr Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India Koneru Lakshmaiah Education Foundation Department of Cse AP Vaddeswaram India Persistent Systems Limited Pune India

ISBN: (纸本)9781665456302

Over the past few years, there has been a meteoric surge in the quantity of digital information available online for instantaneous sharing, persistent archiving, and inquiring. It has expanded the possibilities for using digital data that is both decentralised and ad hoc in order to make decisions quickly. At present, e-Healthcare is among the most sought-after sectors for EHR and telemedicine communication. Securing electronic health records (EHR) has become a topic of intense interest in recent years, with previous works employing a wide range of methods to better ensure the confidentiality and security of EHR at a reasonable price. There are a number of serious problems with the current research, including computational complexity, increased process time, information leakage, vulnerability to various assaults, scalability difficulty, etc. Clinical data analysis presents several difficulties, but disease prediction is one of the most significant ones. The suggested study aims to apply deep learning (DL) classification algorithms for disease prediction. A technique that utilises cloud computing, fog computing, and IoMT more recently has been presented for diagnosing illness. Fast DL classification analysis is performed in the fog layer. When compared to the alternative proposed model Bi-CNN, the healthcare model's efficiency in the Bi-LSTM simulation yields significantly better results: 97.31% of accuracy, 97.58% of recall, 96.90% of precision, 94.90% of F1-measure, 97.25% of specificity, and 94.80% of G-mean. © 2023 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Personal Radiation Exposure from Wireless Signals in Indoor and Outdoor Environments

引用

IEEE Access 2025年 13卷 106489-106510页

作者： Ruijie, Pan Sali, Aduwati Li, Lu Mohyedin, Muhammad Zamir Qahtan, Sangin Universiti Putra Malaysia (UPM) WiPNET Research Centre Department of Computer and Communication Systems Engineering Faculty of Engineering Selangor Serdang 43400 Malaysia Universiti Putra Malaysia (UPM) Institute for Mathematical Research (INSPEM) Selangor Serdang 43400 Malaysia Anhui University of Technology School of Microelectronics and Data Science Maanshan 243002 China

With the development of wireless technology, the public is exposed to electromagnetic fields (EMF), which has led to concerns about the potential health effects of EMF exposures. This paper aims to evaluate personal EMF exposures from wireless signals in indoor and outdoor micro-environments in Malaysia. According to the influencing factors, four different types of micro-environments are selected. A radiation exposure meter called ExpoM-RF 4 is used to measure the electric field strength across these micro-environments. From the measurement campaigns, three machine learning (ML) techniques are simulated to model the Electric Field Strength in each micro-environment. The ML techniques are Fully connected neural network (FCNN), eXtreme Gradient Boosting (XG Boost), and Linear Regression (LR) to predict the RMS and Maximum radiation exposure. From the ML models, Total Emission Ratio (TER), Root Mean Square Error (RMSE) and Coefficient of Determination (R2) are evaluated to measure the performance of ML. By comparison, it is found that LR performs well with single and simple data set, while XG Boost and FCNN demonstrate superior capabilities in handling multiple types of data sets. The FCNN model provides the most accurate predictions, particularly in urban and suburban areas where extreme values are observed. Finally, the measured data and the predicted radiation exposure levels are compared against public exposure limit by International Commission on Non-Ionizing Radiation Protection (ICNIRP), Malaysian communications and Multimedia Commission (MCMC) and Federal communications Commission (FCC). The results demonstrate that typically personal radiation exposure is lower than the exposure limit (61.4 V/m), which is similar to the most research results. However, in areas with dense population and numerous base stations, the maximum exposure can approach 56.7365 V/m (measured data), which is close to the exposure limit. © 2013 IEEE.

关键词： Electromagnetic Fields (EMF) ExpoM-RF 4 Exposure Limit Indoor and Outdoor Environment Machine Learning (ML) Micro-Environments Personal Radiation Exposure

来源：评论

学校读者我要写书评

暂无评论

Toward Trustworthy and Responsible Autonomous Drones in Future Smart Cities

TechRxiv

引用

TechRxiv 2022年

作者： Ottun, Abdul-Rasheed Yin, Zhigang Liyanage, Mohan Boerger, Michell Asadi, Mehrdad Hui, Pan Tarkoma, Sasu Tcholtchev, Nikolay Nurmi, Petteri Flores, Huber Institute of Computer Science University of Tartu Tartu Estonia Fraunhofer Institute for Open Communication Systems Berlin Germany Department of Chemistry University of Helsinki Helsinki Finland Department of Computer Science University of Helsinki Helsinki Finland

Autonomous drones are reaching a level of maturity when they can be deployed in cities to support tasks ranging from medicine or food delivery to environmental monitoring. These operations rely on powerful AI models integrated into the drones. Ensuring these models are robust is essential for operating in cities as any errors in the decisions of the autonomous drones can cause damage to the citizens or the urban infrastructure. We contribute a research vision for trustworthy city-scale deployments of autonomous drones. We highlight current key requirements and challenges that have to be fulfilled for achieving city-scale autonomous drone deployments. In addition, we also analyze the complexity of using XAI methods to monitor drone behavior. We demonstrate this by inducing changes in AI model behavior using data poisoning attacks. Our results demonstrate that XAI methods are sensitive enough to detect the possibility of a data attack, but a combination of multiple XAI methods is better to improve the robustness of the estimation. Our results also suggest that currently, the reaction time to counter an attack in city-scale deployment is large due to the complexity of the XAI analysis. © 2022, CC BY.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Cooperative Agent System for Quantifying Link Robustness in Tactical Networks

Cooperative Agent System for Quantifying Link Robustness in ...

引用

MILCOM, Military communications Conference

作者： Johannes F. Loevenich Philipp Zißner Paulo H. L. Rettore Jonas Bode Tobias Hürten Thorsten Lampe Roberto Rigolin F. Lopes Secure Communications & Information (SIX) Thales Deutschland Ditzingen Germany Department of Mathematics/Computer Science University of Osnabrück Osnabrück Germany Communication Systems (KOM) Fraunhofer FKIE Bonn Germany

This paper presents a cooperative agent system employing Reinforcement Learning (RL) to quantify path robustness in tactical networks. We implement an environment builder agent generating network graphs with dynamic topologies, constrained by tactical network characteristics and conditions derived from experimental results using real military radios (VHF). Subsequently, the RL agent interacts with this environment, learning to quantify the robustness of feasible transmission paths by solving an optimal control problem. Furthermore, we propose an adversary to evaluate the RL agent’s robustness against adversarial perturbations. Experiments across a large set of network graphs reveal that policy optimization algorithms (PPO and TRPO) outperform others (ARS, DQN and A2C), demonstrating high rewards (∼105) in the absence of adversaries. However, when assessing performance in scenarios with adversarial noise injection, experimental results indicate that iterative, and momentum boosting attack techniques can substantially degrade the RL model’s performance by up to 300% lower rewards.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Binocular Disparity Unveils the Mechanisms of Stereo Feature Selectivity: Orientation and Motion

Binocular Disparity Unveils the Mechanisms of Stereo Feature...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Bin Li Yuki Todo Zheng Tang Cheng Tang Division of Electrical Engineering and Computer Science Kanazawa University Kanazawa Japan Division of Electrical Information and Communication Engineering Kanazawa University Kanazawa Japan Department of Intelligence Information Systems University of Toyama Toyama Japan Faculty of Information Science and Electrical Engineering Kyushu University Fukuoka Japan

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Binocular vision serves as the foundation for stereo vision, providing humans with the ability to perceive the three-dimensional information of their surroundings. However, although some cortical neurons are reported with 3D information selectivity, the interconnections between binocular input and cortical neuron firing have yet to be fully established, impeding progress in our understanding of stereo information perception. In this work, we aim to address this issue by examining the causality between retinal input and selective neuron firing. We propose a general mechanism of stereo orientation and motion direction detection based solely on binocular disparity input, which is the difference in visual information between the two eyes. Our results suggest that this disparity-based mechanism is robust and can effectively complete stereo orientation and motion direction detection. Our proposed general perceiving mechanism has the potential to contribute to the resolution of the complex problem of binocular information processing and computation. Further research into this area may help to deepen our understanding of stereo vision and provide insights into the underlying neural mechanisms.

关键词： Visualization Three-dimensional displays Firing Neurons Noise Reliability theory Retina

来源：评论

学校读者我要写书评

暂无评论

Development of an Artificial Intelligence-Based Prediction System for Short-Term Solar Power Generation

Development of an Artificial Intelligence-Based Prediction S...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Minseok Kang Suhyeon Choi Woohyun Kim Jaehyeon Kim Seokheon Cho Department of Computer Science Yonsei University Seoul Republic of Korea Department of Management Information Systems Kyonggi University Suwon Republic of Korea Department of Information and Communication Chosun University Gwangju Republic of Korea Department of Business Chosun University Gwangju Republic of Korea Qualcomm Institute University of California San Diego La Jolla USA

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

The increased occurrence of extreme weather events is closely related to global warming caused by excessive fossil fuel consumption. This has resulted in significant global interest in renewable energy sources, especially solar power, which is showing rapid growth worldwide. However, the excessive and disorganized utilization of solar power systems can cause instability of the existing power system because of a continuous time varying output of solar power systems. Hence, it is crucial to accurately predict the solar power generation for a stable energy supply to the traditional electricity system. This study aims to provide a short-term solar power generation prediction model based on various Artificial Intelligence algorithms and improve its performance. The Multiple Linear Regression, Random Forest Regression, Multi-Layer Perceptron and Long Short-Term Memory algorithms were utilized for a solar power generation prediction model. Also, solar power-related data measured every 15 minutes and hourly meteorological data were used to train and evaluate our proposed prediction models. Several datasets generated by the feature selection process and the addition of the historical solar power-related data as well as the historical weather data were used to enhance a short-term solar power generation prediction model. The comparison of performance results showed that the Multi-Layer Perceptron algorithm-based prediction model using the solar power-related data and the weather data as well as their past data outperforms by achieving the highest value of R-squared $(\mathrm{R}^{2})$ but the lowest value of the Root Mean Squared Error. An architecture of an Artificial Intelligence-based solar power prediction system embedded with this optimal short-term solar power prediction model is proposed.

关键词： Renewable energy sources Predictive models Power system stability Prediction algorithms Data models Solar power generation Random forests Long short term memory Meteorology Load modeling Climate change

来源：评论

学校读者我要写书评

暂无评论

Thick Film Interdigitated Electrode Graphite and Carbon Nanotube on Flexible Substrate for Hydrogen Gas Detection

Thick Film Interdigitated Electrode Graphite and Carbon Nano...

引用

2023 IEEE International Conference on Sensors and Nanotechnology, SENNANO 2023

作者： Abu Bakar, Azlinda Nizar Hamidon, Mohd Yaacob, Mohd Hanif Paiman, Suriati Jaafar, Haslina Wan Jusoh, Wan Nursheila Universiti Putra Malaysia Funtional Device Laboratory Institute of Nanoscience and Nanotechnology Selangor Serdang Malaysia Universiti Putra Malaysia Faculty of Engineering Department of Computer and Communication Systems Selangor Serdang Malaysia Universiti Putra Malaysia Faculty of Science Department of Physics Selangor Serdang Malaysia Universiti Putra Malaysia Faculty of Engineering Department of Electrical and Electronic Selangor Serdang Malaysia Universiti Kuala Lumpur Section of Aerospace Malaysians Institute of Aviation Technology Selangor Dengkil Malaysia

ISBN: (纸本)9798350333312

The comparison on the performance of interdigitated electrode (IDE) graphite and carbon nanotube (CNT) using titanium dioxide-multiwall carbon nanotube (TiO2-MWCNT) composite as sensing materials to detect hydrogen gas is presented in this research work. Screen printing technique has been selected to deposited IDE graphite and CNT conductive pastes as the electrode thick film on a flexible substrate, which is continued by firing at 120°C each. TiO2-MWCNT paste was printed as a sensing layer on top of IDE, followed by firing at 350°C. FESEM was used to characterize the morphological analysis of the IDE film. The operating temperature was varied at 27°C, 50°C and 100°C and concentration varied from 100-1000 ppm for gas hydrogen. The gas sensor demonstrated as n-type gas characteristics where the response of the gas sensor produced increased current from the results. The results purpose when the sensor was exposed to hydrogen gas. Therefore, the ability of IDE graphite and CNT as an electrode to harvest the electron from sensing materials were successfully proven. The IDE CNT showed better response compare to IDE graphite, but both electrodes were able to sense 100 - 1000 ppm at the operating temperature of 27°C, 50°C and 100°C. The optimal of operating temperature for IDE graphite is 50°C and IDE CNT is at room temperature for the hydrogen gas detections in this research work. © 2023 IEEE.

关键词： Thick films

来源：评论

学校读者我要写书评

暂无评论

Estimating the AGV load and a battery lifetime based on the current measurement and random forest application

Estimating the AGV load and a battery lifetime based on the ...

引用

IEEE International Conference on Big Data

作者： Krzysztof Hanzel Damian Grzechca Adam Ziebinski Lukas Chruszczyk Artur Janus Department of Telecommunications and Teleinformatics Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Department of Electronics Electrical Engineering and Microelectronics Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Department of Distributed Systems and Informatics Devices Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Student of Electrical Engineering Faculty of Electrical Engineering Silesian University of Technology Gliwice Poland

The paper describes the energy consumption from the battery based on the current measurements for various cases, i.e., speed (PWL adjustment) and loads. The main purpose of the research is to have additional and reliable information about power consumption and battery life estimation for autonomous guided vehicles (AGV). The authors propose a two-step algorithm. In the first step, a linear classifier was proposed. Then, the KNN classifier was tested; however, it did not give satisfactory results, so it was finally decided to use the random forest to estimate the load and PWL. The time domain current measurement is evaluated, and the beforementioned algorithms process the selected statistical measures. It has been proven that a two-step algorithm allows for achieving high accuracy. Based on the current observation, the paper is a good starting point for further investigation of the AGV because it is usually implemented in the AGV – so it does not require additional hardware. Moreover, it can lead to better energy management and increase battery lifetime.

关键词：

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：