检索结果-内蒙古大学图书馆

Neural Networks and Explainable Artificial Intelligence for Breast Cancer Prediction and Classification

Procedia Computer Science 2025年 256卷 1159-1166页

作者： Erika Yahata Pablo Deoclecia dos Santos Maria Marlene de Souza Pires Ricardo Suyama Priscyla Waleska Simoes Graduate Program in Information Engineering Federal University of ABC Santo André SP Brazil Graduate Program in Biomedical Engineering Federal University of ABC São Bernardo do Campo SP Brazil Pediatrics Department Federal University of Santa Catarina Florianópolis Santa Catarina Brazil

Solutions based on Artificial Intelligence techniques have been proposed in the healthcare sector, however the lack of understanding of the results has been a cause for concern and one of the main barriers to their effective use. To fill the gap in understanding these models considered black boxes, the Explainable Artificial Intelligence was proposed to explain the relationship between input data and the prediction results made by the Artificial Intelligence models. In this study, we present the use of explainability techniques for a black box machine learning model in breast cancer classification. Breast cancer is the type of cancer that causes the most deaths among women in the world and early diagnosis is essential to increase the chances of survival. The study evaluated the explainability of breast tumor predictions based on the Multilayer Perceptron artificial neural networks algorithm, considering a sample that contained data from 164 female patients undergoing Core Biopsy in the southern region of Brazil. The SHAP, LIME, PDP and ICE methods were used for the global and local explainability of the predictions. The results showed that in the global assessment, the BI-RADS® 5 ultrasound and mammography attributes were considered the most important for predicting the malignant tumor. Nodule size greater than 2 cm, presence of a family history and palpable nodule were also considered important for the prediction. In the local evaluation, it was found that the model correctly classified the tumors considering different characteristics of the patients. Through the results presented, the methods of explicability show evidence that the predictive model for breast cancer can be interpreted and understood, overcoming the barrier of lack understanding of the results of a black box model.

关键词： Explainable Artificial Intelligence Predictive Model Explainability Machine Learning Breast Cancer

来源：评论

学校读者我要写书评

暂无评论

Localization and Perception for Control of a Low Speed Autonomous Shuttle in a Campus Pilot Deployment

arXiv

引用

arXiv 2024年

作者： Wen, Bowen Graduate Program in Electrical and Computer Engineering The Ohio State University United States

Future SAE Level 4 and Level 5 autonomous vehicles will require novel applications of localization, perception, control and artificial intelligence technology in order to offer innovative and disruptive solutions to current mobility problems. Accurate localization is essential for self driving vehicle navigation in GPS inaccessible environments. This thesis concentrates on low speed autonomous shuttles that are mainly utilized for university campus intelligent transportation systems and presents initial results of ongoing work on developing solutions to the localization and perception challenges of a university planned pilot deployment orientated application. The paper treats autonomous driving with real time kinematics GPS (Global Positioning Systems) with an inertial measurement unit (IMU), combined with simultaneous localization and mapping (SLAM) with three-dimensional light detection and ranging (LIDAR) sensor, which provides solutions to scenarios where GPS is not available or a lower cost and hence lower accuracy GPS is desirable. The in-house automated low speed electric vehicle from the Automated Driving Lab is used in experimental evaluation and verification. An improved version of Hector SLAM was implemented on ROS and compared with high resolution GPS aided localization framework in the same hardware architecture. The overall configuration that combines ROS with DSpace controller can be easily transplantable prototype in other hardware architectures for future similar research. Real-world experiments that are reported here have been conducted in a small test area close to the Ohio State University AV pilot test route. are used for demonstrating the feasibility and robustness of this approach to developing and evaluating low speed autonomous shuttle localization and perception algorithms for control and decision making. © 2024, CC BY.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Model reference adaptive voltage control of photovoltaic boost converter

Model reference adaptive voltage control of photovoltaic boo...

引用

Power Electronics and Control (SEPOC), Seminar on

作者： Andrei Da Cunha Lima Lucas Vizzotto Bellinaso Leandro Michels Graduate Program in Electrical Engineering (PPGEE)) Federal University Of Santa Maria (UFSM)

ISBN: (数字)9798350379419

ISBN: (纸本)9798350379426

This article aims to present a methodology for adaptive control of a boost converter through two loops based on a Model Reference. This methodology makes it possible to reduce the input capacitance of the boost converter, increasing the response speed and consequently the efficiency of tracking the maximum power point. In the introduction section, the problem involving the reduction of input capacitance in boost converters is presented. In the next sections, mathematical modeling of the converter is carried out, and a model for voltage transfer function related to inductor’s current was obtained, and finaly a model for current transfer funcion related to duty-cycle. The last section presents simulation results, demonstrating the stability of controller under several parametrics variations. Finnaly, a comparison among an adaptive controller and a classical controller was presented.

关键词： Seminars Adaptation models Simulation Transfer functions Capacitance Mathematical models Stability analysis Power electronics Adaptive control Voltage control

来源：评论

学校读者我要写书评

暂无评论

Location Analysis Probing Rockets in Ground with Telemetry Data

Location Analysis Probing Rockets in Ground with Telemetry D...

引用

International Symposium on Instrumentation Systems, Circuits and Transducers (INSCIT)

作者： Nilton Rodrigues Cantanhede Ewaldo Eder Carvalho Santana Paulo Fernandes da Silva Júnior Raimundo Carlos Silvério Freire Tiago Pereira Santana Lúcio Flávio de Albuquerque Campos Gabrielle Muniz Fernandes Maria Tereza Cunha de Albuquerque Sophia Viana Macedo Graduate Program in Electrical Engineering Federal University of Maranhão São Luís Brazil Graduate Program in Computer and System Engineering State University of Maranhão São Luís Brazil Graduate Program in Electrical Engineering Federal University of Campina Grande Campina Grande Brazil Graduate Program in Computational Engineering and Systems State University of Maranhão São Luís Brazil Undergraduate Program in Computational Engineering State University of Maranhão São Luís Brazil Graduate Program in Electrical Engineering Federal University of Paraiba João Pessoa Brazil

ISBN: (数字)9798350350869

ISBN: (纸本)9798350350876

Rocket launch centers are crucial in technological development across various fields, including meteorology, long-distance real-time communications, geoprocessing, and satellite operations. However, one of the challenges in tracking probing rockets is accurately identifying their position from the moment of launch until the initial seconds, due to ground noise that interferes with traditional radar location systems. In this study is proposed an innovative method to precisely determine the distance between the rocket and the ground telemetry station. We utilize onboard telemetry signals processed by the Acquisition and Processing Data Trajectory (APDtraj) system, developed by Delsis Aerospace for the Launch Center. This system enables the identification of the rocket's position both on the ground and during the early stages of flight, using telemetry data processed by APDtraj. This monitoring equipment alone calculated the distance between the Telemetry Station and the rocket just moments before launch lift-off with an error of only 16.844 meters from the actual position of origin. Based on our studies, we were able to measure the radial distance and location between the rocket and the telemetry station just four seconds after launch, even without reliable radar information, which is often disrupted by ground noise. This technological advancement not only enhances the efficiency of rocket launch operations but also expands overall tracking capabilities.

关键词： Rockets Transducers Satellites Radar measurements Spaceborne radar Noise Radar tracking Real-time systems Trajectory Telemetry

来源：评论

学校读者我要写书评

暂无评论

Exploring Approximate Adders for an Energy-Efficient Pre-Processing Pan-Tompkins Algorithm VLSI Design

Exploring Approximate Adders for an Energy-Efficient Pre-Pro...

引用

Symposium on Integrated Circuits and Systems Design (SBCCI)

作者： Léo Ribeiro Morgana M. A. Rosa Rafael Soares Eduardo Costa Graduate Program on Computing Federal University of Pelotas (UFPel) Pelotas Brazil Graduate Program on Electronic Engineering and Computing Catholic University of Pelotas (UCPel) Pelotas Brazil

ISBN: (数字)9798350391695

ISBN: (纸本)9798350391701

This work explores a set of approximate adders (COPY adder, error-tolerant adder - ETA, lower-part OR adder - LOA, truncation - Trunc, and approximate parallel prefix adder - AxPPA) to enhance a VLSI design for ECG signal preprocessing based on Pan-Tompkins algorithm (AxPTA) to improve energy efficiency and QRS complex detection. Validation with the MIT-BIH database confirms that the AxPTA design maintains excellent sensitivity and positive predictivity with reduced energy consumption and circuit area. The AxPTA with AxPPA achieves a 10.22% reduction in circuit size and saves 85.06% energy, with an acceptable 1.32% precision deviation. These results suggest that the AxPPA significantly boosts energy efficiency in the AxPTA design for ECG analysis, supporting the development of portable devices for continuous heart monitoring and cardiovascular disease prevention.

关键词： Energy consumption Sensitivity Databases Energy conservation Electrocardiography Very large scale integration Approximation algorithms Energy efficiency Adders System analysis and design

来源：评论

学校读者我要写书评

暂无评论

An Indoor Localization Technique Based on Visible Light Communication 1

An Indoor Localization Technique Based on Visible Light Comm...

引用

1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022

作者： Nascimento, Mateus Rabelo Fonseca Do Coutinho, Olange Guerson Goncalves Olivi, Leonardo Rocha Soares, Guilherme Marcio Electrical Engineering Postgraduate Program Juiz de Fora Brazil Electrical Engineering Graduate Program Juiz de Fora Brazil Department of Electric Power Juiz de Fora Brazil

ISBN: (纸本)9798350398069

This paper proposes a technique for indoor localization based on a visible light positioning approach. The strategy relies on using lighting luminaires that modulate the luminous flux at different frequencies. A light sensor is then used to gather the illuminance signal used as input for a previously trained Artificial Neural Network (ANN) to estimate the position of the sensor. The work's main contribution is using an illuminance estimator based on the lighting distribution of the luminaires to perform the training procedure of the ANN. The lighting distribution is obtained through *** file provided by the manufacturer, i.e., the same file used for lighting designs. Therefore, by using characteristics of the environment and *** file, the proposed system can provide data to train accurately the ANN used in the positioning method. The results attested to the satisfactory performance of the proposed localization technique as it produced mean distance errors of 1.51cm and 0.79cm considering 0% and 70% walls' reflectance levels, respectively. © 2022 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

A Power-Efficient VLSI Multiplier Design Employing Radix-2m Squarer Unit and Adder Compressor

A Power-Efficient VLSI Multiplier Design Employing Radix-2m ...

引用

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Leonardo Antonietti Morgana Da Rosa Rodrigo Lopes Eduardo Da Costa Rafael Soares Graduate Program on Computing - Federal University of Pelotas (UFPel) Pelotas Brazil Graduate Program on Electronic Engineering and Computing - Catholic University of Pelotas (UCPel) Pelotas Brazil

ISBN: (数字)9798350377200

ISBN: (纸本)9798350377217

Multipliers are pivotal in numerous applications, including digital signal processing, image processing, and video processing. Nonetheless, their operation substantially increases power consumption for these applications. Therefore, applying strategies that can reduce power in this arithmetic operator is paramount. This paper presents a novel approach to optimize arithmetic units, focusing on multiplier units, through the integration of the Radix- $2^{m}$ squarer unit (RSU) and 4–2 adder/subtractor compressor (AC). Compared to the state-of-the-art, the proposed multiplier unit, termed MRSU (multiplier unit RSU-based), offers significant area-and energy-savings. The synthesis results show remarkable improvements in the MRSU Dadda 4–2 architecture, which achieves 14.35× more energy-savings for 8 bits, 4.87× for 16 bits, and 2.22× for 32 bits compared to the multiplier unit automatically selected by the logic-synthesis tool. Furthermore, compared to the Booth multiplier with the Dadda compression tree, MRSU Dadda 4–2 exhibits 1.67× more energy-savings for 8 bits, 1.93× for 16 bits, and 1.95× for 32 bits.

关键词： Image coding Power demand Focusing Digital signal processing Computer architecture Very large scale integration Energy efficiency Electronic circuits Adders Arithmetic

来源：评论

学校读者我要写书评

暂无评论

Energy Performance Indicators for Energy Management Systems in Net Zero Energy Buildings

Energy Performance Indicators for Energy Management Systems ...

引用

On-Line Conference (ONCON), Industrial Electronics Society Annual

作者： Elder Costa Rogério Silva Electrical Engineering Graduate Program UFERSA Mossoró Brazil

The present paper aims to evaluate the energy use, the variables that affect the electric energy consumption of a public building to develop energy performance indicators based on ISO 50001 and ISO 50006, in addition to simulating and evaluating proposals for Energy Efficiency Actions having as study case in point, the restaurant of the Federal University of the Semi-Arid Region (UFERSA), at Caraúbas, located in the northeast region of Brazil, with a semi-arid climate characterized by high temperatures and thermal sensation. The application of the methodology resulted in more than 50% of final energy use being concentrated in air conditioning and refrigeration, for environments or food. Relevant variables were established and verified graphically and statistically, as well as determining static factors that influence consumption, among them air temperature (°C) has the greatest effect on the building. Two Energy Performance Indicators (EnPI) were determined, the active energy consumed per square meter per year, 60.70 kWh/m 2 /year, and the active energy per user per year, 0.83 kWh/m 2 /year, when compared using reference values, it was determined that the building can be classified as energy efficient in terms of the first indicator. Energy efficiency actions was simulated, use of more efficient air conditioning units, application of thermal insulation on the roof and replacement of single-glazed windows with insulated glass were evaluated and compared, technically and economically, against the investment in a grid-connected photovoltaic system, for the same building and based on the Brazilian INI-C methodology, it was assessed whether this building would be classified as Nearly Zero Energy Buildings (NZEB) and Positive Energy Buildings (PEB).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Numerical Investigation Effect of the addition of palm fronds on the burning of coal-fired boilers tangentially

Numerical Investigation Effect of the addition of palm frond...

引用

2023 International Conference on Advanced Mechatronics, Intelligent Manufacture and Industrial Automation, ICAMIMIA 2023

作者： Ihsan, Sobar Prabowo Widodo, Wawan Aries Adi Saputra, I Nyoman Agus Institut Teknologi Sepuluh Nopember Graduate Program of Mechanical Engineering Department Surabaya Indonesia University of Islam Kalimantan Maab Indonesia Institut Teknologi Sepuluh Nopember Mechanical Engineering Department Surabaya Indonesia

ISBN: (纸本)9798350309225

Biomass co-firing is an appropriate and cheap solution for achieving renewable energy targets towards net zero emissions because it can reduce the potential environmental impacts associated with burning fossil fuels. CFD simulations were carried out by adding palm frond biomass with a ratio of 5% and 95% LRC coal, which was injected into the boiler combustion furnace. The boiler operational parameters used in this simulation are a coal flow rate of 151.75 tons/hour and an airflow rate of 1184.33 tons/hour on the research subject PLTU Pacitan with a capacity of 315 Mw. The results show that adding palm frond biomass to burning coal changes calorific value, affecting the combustion process's high temperature. However, it has a good impact from the operational side of burning coal particles. © 2023 IEEE.

关键词： Biomass

来源：评论

学校读者我要写书评

暂无评论

Development of Machine Learning Models to Predict Strip Breakage During the Aluminium Cold Rolling Process

Development of Machine Learning Models to Predict Strip Brea...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Tiago Ramos Abreu Alexandre Magno Andrade Maciel Graduate Program in Computer Engineering (PPGEC) University of Pernambuco (UPE) Recife Brazil

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

The aluminium processing industry relies on cold rolling as a crucial method for producing materials essential to everyday life. As a consequence of thickness reduction: Strip Breakage, which is one of the main degraders in the aluminum rolling process, arises. In more recent related studies, data were mainly chosen by experts, which can sometimes hide crucial causal factors. Therefore, this work develops Machine Learning models to predict strip breakage, by investigating the relationship between features and the breakage event, using attribute selection techniques to reduce the dimensionality of the problem, comparing classification methods based on trees, such as Decision Trees (DT), Random Forest (RF) and Extra Trees (ET). This work uses the following methodology: first, the models were evaluated for the complete set of data with default initial parameters, then a new evaluation of the models was carried out with the optimized parameters still with high data dimensions, and finally, an evaluation was carried out of the models with the best-selected attributes. The model that performed best was the DT with 21 attributes, with a recall or TPR (True Positive Rate) of 0.863 and an AUC (Compute Area Under of ROC Curve) of 0.926. The models also indicated that there is no unique cause that characterizes the breaks in the aluminium cold mill, but several others, such as the effect of the rolling mill, coil history domain, oil mill and lamination cylinders.

关键词： Industries Radio frequency Performance evaluation Strips Computational modeling Oils Aluminum Predictive models Data models Random forests

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：