检索结果-内蒙古大学图书馆

Brazilian Symposium on Computing System Engineering (SBESC)

作者： Derek N. A. Alves André dos Santos Bruno G. Ferreira Tiago F. Vieira Edge Innovation Center Maceió Brazil Vertex Institute of Innovation and Technology Maceió Brazil Postgraduate Program in Informatics (PPGI-UFAL) UFAL - Federal University of Alagoas Maceió Brazil FEUP - Faculty of Engineering of the University of Porto Porto Portugal

ISBN: (数字)9798331509002

ISBN: (纸本)9798331532857

To improve safety and efficiency of land vehicles, such as cars and trucks, frequent tire inspections are necessary. Regular checks of tire tread depths help prevent accidents and enhance fuel efficiency. However, traditional methods for estimating tread depth, like depth gauges, can be both time-consuming and imprecise, especially for vehicles with multiple tires. In this paper, we propose a novel portable embedded Digital Processing System (DPS) device that utilizes linear image sensors (CCDs) and active illumination to estimate the depths of all tire treads at once. The device features a microcontroller that configures the linear sensor's parameters and collects its readings. The microcontroller communicates with an Android device via a serial connection to transfer the data for processing. Additionally, the Android application offers visual feedback to the user, enabling them to conduct tire inspections on vehicles. Both the Printed Circuit Board (PCB) and the device case are designed in our laboratory, with the case being 3D printed. The proposed device achieves an error of 0.115 millimeters in tread depth estimation and consumes only 22.15% of the time required by the traditional depth gauge to estimate all the tread depths of a tire. The integration of the proposed device into tire manufacturing companies can significantly enhance the efficiency of tread inspection processes. This innovation not only improves overall quality control and productivity in tire inspection but also offers substantial benefits in both scientific and economic contexts.

关键词： Performance evaluation Charge coupled devices Microcontrollers Printed circuits Lighting Inspection Tires Sensor systems Real-time systems Safety

来源：评论

学校读者我要写书评

暂无评论

ConvNeXt Model for Breast Cancer Image Classification

ConvNeXt Model for Breast Cancer Image Classification

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Devin Setiawan Andrea Stevens Karnyoto Indo Intan Bens Pardamean Department of Electrical Engineering and Computer Science University of Kansas Lawrence United States Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Department of Informatics Engineering Universitas Dipa Makassar Makassar Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331539603

ISBN: (纸本)9798331539610

Breast cancer is an occurrence of cancer that attacks breast tissue and is the most common cancer among women worldwide, affecting one in eight women. In this modern world, breast cancer image classification simplifies the process of analyzing, providing objective and accurate results. By leveraging machine learning algorithms and computer vision techniques, we developed breast cancer detection. The dataset is histopathology dataset from BreakHis and UNHAS Hospital. We chose the ConvNeXt-Tiny model then modified the classifier head as the proposed method. Before the dataset is processed by the model, we augment the images by applying random horizontal and vertical flips, adjustments to brightness, contrast, saturation, and hue using color jitter. The augmentation process simulates real-world variance and enhances the model's ability to generalize to unseen data. Our proposed model gained better performance (accuracy, F1-Score) results compared two other techniques to VGG16 and SVM. According to our experiments, the F1-Score for the ConvNeXt-Tiny model with classifier head modification is higher at 0.9516, than the gain for VGG16 at 0.9292, and the gain for the SVM at 0.83.

关键词： Support vector machines Accuracy Head Computational modeling Transfer learning Breast cancer Magnetic heads Data models Reliability Image classification

来源：评论

学校读者我要写书评

暂无评论

Event log analytics to correlate the academic achievements of students using low-cost high-utility sequential pattern algorithm

引用

AIP Conference Proceedings 2024年第1期2867卷

作者： Ridho Gunawan Informatics Study Program Sanata Dharma University Yogyakarta Indonesia

During the Covid-19 pandemic, almost all learning is done online through learning management system. All activities carried out in the learning management system are recorded in the event log. Only looking for the sequence of activities carried out by the learner is not an enough analysis of the event log. It is also necessary to see whether the activities carried out are effective. Analysis of event logs can be used to improve the quality of the learning process. The method used to get an effective event log activity is to develop a sequential pattern method, which is to find a sequence of activities that is low-cost while getting high utility. Low cost means that students use as little time as possible to complete an activity, while high utility means that students get maximum value learning outcomes. Learning outcomes can be in the form of quizzes or assignments. Measurement of the effectiveness of the pattern obtained is in terms of looking at the correlation between cost and utility of the pattern formed. This method is applied to analyse the event log obtained from the Moodle learning management system for one course. The experimental results show learning patterns in which they show effective patterns and can obtain patterns that can improve learning optimization. Searching for low-cost high-utility patterns in the event log of the learning management system is one effective way to improve learning performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Twitter Data Sentiment Analysis of COVID-19 Vaccination using Machine Learning 5

Twitter Data Sentiment Analysis of COVID-19 Vaccination usin...

引用

5th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2022

作者： Maulana, Fairuz Iqbal Adi, Puput Dani Prasetyo Lestari, Dian Purnomo, Agung Prihatin, Sukeipah Yuli School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Telecommunication Research Center National Research and Innovation Agency Jakarta11480 Indonesia Airlangga University Faculty of Medicine Surabaya60132 Indonesia BINUS Business School Undergraduate Program Bina Nusantara University Entrepreneurship Department Jakarta11480 Indonesia Informatics Study Program Politeknik Kota Malang Malang Indonesia

ISBN: (纸本)9781665455121

The expansion of the web is accelerating, which helps encourage the creation of fresh ideas. In today's internet era, we must suggest techniques to filter out various information. Social media sentiment analysis based on Twitter data can monitor the real-Time monitoring of the COVID-19 vaccine. In this way, relevant organizations or governments can take proactive steps to address misinformation and inappropriate behaviour around the COVID-19 vaccine, which threatens the success of the national vaccination campaign. The purpose of this research is to determine if there is a link between how people feel about the COVID-19 vaccine on Twitter and how many people actually get vaccinated against it. This study uses the COVID-19 All Vaccines Tweet dataset sourced from Kaggle. This research Identifies public sentiment, emotion, word usage, and trend of all filtered tweets. The results show that there are 31% positive tweets, 10% negative tweets, and 58% neutral tweets. Tweets with neutral subjective valence tend to cluster in the middle of the polarity scale (between-1 and +1), whereas tweets with strong subjective valence are spread across the scale. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Imprecise Subtractors into Test Zone Search for VVC Encoding

Evaluation of Imprecise Subtractors into Test Zone Search fo...

引用

Symposium on Integrated Circuits and Systems Design (SBCCI)

作者： Rafael Ferreira Luciano Agostini Cláudio M. Diniz Bruno Zatt ViTech Group Graduate Program in Computing Federal University of Pelotas (UFPel) Pelotas Brazil PGMICRO Institute of Informatics Federal University of Rio Grande do Sul (UFRGS) Porto Alegre Brazil

The error-tolerant behavior of some video encoding algorithms has motivated researchers to exploit approximate computing in the seek for energy-efficient coding systems. If approximate adders have been widely evaluated, approximate subtractors did not receive much attention. Subtractors, however, are extensively used during the encoding process and optimizing them represents an opportunity for further improving energy efficiency. This study explores the adoption of approximate subtractors in Versatile Video Coding (VVC) encoders, with a specific focus on the distortion metric used in the Test Zone Search (TZS) algorithm for inter-picture prediction. The detailed analysis reveals the impact of imprecise subtractors on each stage of TZS, presenting unprecedented data about the number of calls and energy consumption per stage. The results show that the use of approximate subtractors leads to changes in the number of calls for each TZS stage, induces a minimal impact in terms of coding efficiency, and enables nearly 6% reduction in energy consumption. Therefore, this work provides substantial contributions to the understanding and to the optimization of video coding processes, energy-constrained scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Music Mood Classification with Dynamic Classifier Selection

Multi-Modal Music Mood Classification with Dynamic Classifie...

引用

International Conference on Systems, Signals and Image Processing, IWSSIP

作者： João G. Bracaioli Vitório Alceu S. Britto Junior Costa Yandre M. G. Carlos N. Silla Graduate Program in Computer Science (PPGIA) Pontifícia Universidade Católica do Paraná (PUCPR) Curitiba Brazil Department of Informatics State University of Maringá (UEL) Maringá – Paraná Brazil

In this paper we investigate the suitability of different types of Dynamic Classifier Selection approaches for the task of multimodal music mood classification. The dynamic selection methods evaluated were: KNORA-UNION, KNORAELIMINATE, Dynamic Ensemble Selection Performance, Overall Local Accuracy, Local Class Accuracy, Multiple Classifier Behaviour, A Priori and A Posteriori. The experiments were performed using the Brazilian Music Mood Database, which is a multimodal database, containing the audio signal itself, beyond their visual representation (i.e. spectrogram) and the lyrics. The obtained results have shown that the use of dynamic classifier selection methods can improve the classification results for the task at hand.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Tire Tread Depth Estimation with ESP32CAM and U-Net Based Segmentation

Efficient Tire Tread Depth Estimation with ESP32CAM and U-Ne...

引用

Brazilian Symposium on Computing System Engineering (SBESC)

作者： Andre dos Santos Derek N.A. Alves Bruno G. Ferreira Tiago F. Vieira Edge Innovation Center Maceio Brazil Vertex Institute of Innovation and Technology Maceio Brazil Postgraduate Program in Informatics (PPGI-UFAL) UFAL - Federal University of Alagoas Maceio Brazil FEUP - Faculty of Engineering of the University of Porto Porto Portugal

ISBN: (数字)9798331509002

ISBN: (纸本)9798331532857

Tire inspection is essential for ensuring the safety and efficiency of land vehicles, such as cars and trucks. Reg-ularly checking tire tread depth helps prevent accidents like aquaplaning and reduced braking performance, and also lowers fuel consumption. Traditional estimation methods, like depth gauges, are time-consuming, especially for vehicles with multiple tires, and often imprecise due to the rounded shape of some tire treads. To address these challenges, a portable device is proposed, consisting of cameras, microcontrollers and lasers, capable of quickly capture the tire tread shape. The proposed device connects to an Android application via WiFi, offering the user a graphical interface to conduct tire tread inspections on vehicles. The device retrieves the images from the cameras and uses an artificial intelligence model to estimate the tire treads shape, which are highlighted by lasers. At the end, the device provides the tire tread depth estimation in millimeters, allowing the user to determine if the tire is still functional or not. The proposed device significantly reduces the inspection time per tire by 69.46% compared to traditional depth gauges, with a tread depth estimation error of 0.112 millimeters. The proposed device can be integrated into tire management and maintenance companies to enhance the efficiency of tread inspection processes. This innovation offers significant benefits in both scientific and economic contexts, improving overall quality control and productivity in tire inspection process.

关键词： Millimeter wave devices Shape Microcontrollers Computational modeling Inspection Laser modes Tires Safety Maintenance Load modeling

来源：评论

学校读者我要写书评

暂无评论

Enhancing Explainable AI: Leveraging SHAP for Transparent Decision-Making in Machine Learning

Enhancing Explainable AI: Leveraging SHAP for Transparent De...

引用

International Conference on informatics and Computing (ICIC)

作者： Marsani Asfi Budi Warsito Adi Wibowo Doctoral Program Of Information System School of Postgraduate Studies Diponegoro University Semarang Indonesia Department Of Statistics Faculty of Science and Mathematics Diponegoro University Semarang Indonesia Departement Of Informatics Faculty Of Science and Mathematics Diponegoro University Semarang Indonesia

ISBN: (数字)9798331517601

ISBN: (纸本)9798331517618

In recent years, the swift progress in Artificial Intelligence (AI) has resulted in to impressive performance across various domains, but the opacity of complex models, often referred to as “black-box” models, has raised concerns regarding trust and interpretability. This paper addresses these challenges through Explainable Artificial Intelligence (XAI), focusing on Shapley Additive Explanations (SHAP) to interpret a predictive model built on an online retail dataset. The research employs Gradient Boosting Machines (GBM) to predict customer repeat purchases and uses SHAP to provide clear insights into the model’s decision-making process. SHAP effectively identifies key features such as TotalPrice, UnitPrice, and Quantity as the most significant factors driving the model’s predictions. TotalPrice was found to be the most influential feature, demonstrating its strong association with repeat purchases. The analysis reveals that the total price of items purchased is the most significant predictor of repeat purchases, with a SHAP value of 0.45, indicating a strong positive correlation. Additionally, unit price and quantity also play important roles, contributing SHAP values of 0.32 and 0.20, respectively The model achieved an accuracy of 85%, with a precision of 0.78 and a recall of 0.80. These results indicate a robust performance in predicting repeat purchases. Furthermore, the research highlights that consumers from certain countries demonstrate distinct purchasing patterns, influencing overall sales performance. These insights empower retail managers to identify critical variables and adapt marketing strategies accordingly. The analysis not only enhances model transparency but also ensures that the predictions align with business expectations, allowing stakeholders to trust and act on the model’s insights.

关键词： Analytical models Adaptation models Ethics Explainable AI Decision making Focusing Predictive models Boosting Stakeholders informatics

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Brazilian Climate Data Influence on Soybean Pricing by Using Long Short-Term Memory Models

SSRN

引用

SSRN 2024年

作者： Oliva, Jefferson Tales Martelli, Otávio Pigozzo de Castro Barbosa, Marco Antônio Dal Molin, Viviane Casanova, Dalcimar Teixeira, Marcelo Graduate Program in Electrical and Computer Engineering Federal University of Technology-Paraná PR Pato Branco85503-390 Brazil Department of Academic Informatics Federal University of Technology-Paraná PR Pato Branco85503-390 Brazil Graduate Program in Production and Systems Engineering Federal University of Technology-Paraná PR Pato Branco85503-390 Brazil

This work uses machine learning to verify whether the Brazilian climate influences international soybean price prediction. For this, climatic data, dollar quotes, inflation, and annual soybean production were collected from different data sources. Then, the collected data were pre-processed and grouped by Brazilian state. Afterward, data from the five most productive Brazilian states are chosen, such as Mato Grosso (MT), Mato Grosso do Sul (MS), Goiás (GO), Paraná (PR), and Rio Grande do Sul (RS). Afterward, predictive models are built using the long short-term memory (LSTM) method, which is applied in each chosen state dataset considering two different settings: with and without climatic data. Thus, two models were built for each Brazilian state, totaling ten predictors. In the experimental evaluation, when trained with climatic data, the PR model achieved the lowest values of root mean squared error (RMSE) and mean absolute error (MAE). Regarding predictors trained without climate data, the RS and PR obtained the lowest values of RMSE and MAE, respectively. After conducting statistical hypothesis tests, no significant difference was found among models, stating, with 95% certainty, that, in this study, the Brazilian climatic data did not influence the model performance for predicting soybean prices. On the other hand, one of the main contributions of work is conducting an unprecedented study about soybean price prediction using Brazilian climatic data. © 2024, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Wound Reconstruction using Point Descriptors: A Comparative Study

Three-Dimensional Wound Reconstruction using Point Descripto...

引用

Annual IEEE Symposium on Computer-Based Medical Systems

作者： José R. A. Souto Fellipe M. C. Barbosa Bruno M. Carvalho Graduate Program in Systems and Computing Federal University of Rio Grande do Norte Natal Brazil Department of Informatics and Applied Mathematics Federal University of Rio Grande do Norte Natal Brazil

Precise measurements of chronic wound areas are very important for measuring the efficacy of different treatments, since it provides a clear picture of the chosen treatment evolution. The most used techniques still in use for measuring the wound areas involve manual measuring, paper scales and/or acetate tracing, with each health professional possibly measuring the wounds in slightly different ways, specially when dealing with the wound's depth. Thus, it is common to observe inconsistent wound area estimations by different health workers on the same wounds. Moreover, the measuring process requires direct contact with the wound, increasing the contamination and infection risks, besides possibly causing discomfort for the patient. An alternative that has already been proved successful is the use of Structure from Motion (SfM) to recover three-dimensional representations of a wound's surface and estimate that area. In this work, we analyze the effectiveness of several widely used point descriptors (BRIEF, DRINK, FREAK, ORB, SIFT and SURF) in the SfM wound reconstruction task when applied to real images of realistic synthetic wounds made of latex placed on different areas of the body. The results showed that SIFT, SURF and DRINK produced better area estimates. Since the execution time is a factor, we selected DRINK as the standard descriptor for our system, since it is approximately 9.3 and 4.9 times faster than SIFT and SURF, respectively.

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：