检索结果-内蒙古大学图书馆

International Seminar on Application for Technology of Information and Communication (ISemantic)

作者： Catur Supriyanto Abu Salam Junta Zeniarja Adi Wijaya Bachelor Program in Informatics Engineering Faculty of Computer Science Universitas Dian Nuswantoro Semarang Indonesia Department of Health Information Management Universitas Indonesia Maju Jakarta Indonesia

The field of dermatology faces considerable challenges when it comes to early detection of skin cancer. Our study focused on using different datasets, including original data, augmented data, and SMOTE oversampled data, to identify skin cancer. Our dataset consisted of images of skin lesions from the MNIST Skin Cancer dataset (HAM 10000), including samples of both cancerous and benign cases in the dataset. We employed data augmentation to expand the dataset’s size and increase the diversity of skin lesion features. Furthermore, to tackle class imbalance in the dataset, we applied the SMOTE oversampling technique to generate synthetic samples for the under-represented group. With the original, augmented, and SMOTE oversampled datasets, we trained a Convolutional Neural Network (CNN) model. The performance of the model was evaluated using accuracy, recall, precision, and F1-score. The comparison between the results obtained from the original data, augmented data, and SMOTE oversampling data clearly revealed distinctions in performance. Our findings clearly demonstrate that employing data augmentation and SMOTE oversampling can significantly enhance the efficacy of skin cancer detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Experimentation of Integrating Roadmapping and Sci-Fi Prototyping Methods

Experimentation of Integrating Roadmapping and Sci-Fi Protot...

引用

2024 Portland International Conference on Management of Engineering and Technology, PICMET 2024

作者： Nishinaka, Miwa Shirahada, Kunio Kishita, Yusuke Miyamoto, Dohjin Osawa, Hirotaka Kiyokawa, Sachiko Takeda, Hideaki The Graduate School of Management Kagawa University Kagawa Takamatsu Japan Ishikawa Nomi Japan The University of Tokyo Department of Precision Engineering Tokyo Japan Communication in Science and Technology Education and Research Program Hokkaido University Sapporo Japan Keio University Faculty of Science and Technology Kanagawa Yokohama Japan Graduate School of Education The University of Tokyo Tokyo Japan National Institute of Informatics Tokyo Japan

ISBN: (纸本)9781890843458

In 2023, we proposed a hypothetical knowledge management framework that incorporates science fiction prototyping (SFP) into the traditional roadmapping (RM) method to make RM more innovative and create a future beyond what we can currently imagine. Our main objective is to create a new organizational knowledge co-creation method for generating innovative ideas by incorporating humanistic factors utilizing SFP into RM. In the current article, we present the exploratory study we conducted to examine the hypothetical framework. Experimental workshops were held in November 2023 to compare the integrated method, in which SFP is applied to RM, with the original RM method. We followed a crossover design in the workshops and analyzed the results qualitatively and quantitatively following the perspectives proposed in the hypothetical framework. The qualitative analysis revealed successful integration regarding diverse and broader perspectives. The quantitative analysis utilizing Wilcoxon signed rank tests showed that the scores of the integrated method were significantly higher than those of RM for variables evaluating the effectiveness of the integration, while not for variables related to participants' feelings and satisfaction with the workshops, and sustainability. These findings indicate that the integration was successful in terms of its effectiveness as a method, while participants' subjective feelings toward the workshops were not different in both methods. As for sustainability, which requires a long-term perspective, no apparent differences were observed in these short-term workshops. © 2024 PICMET.

关键词：

来源：评论

学校读者我要写书评

暂无评论

‘Do I Belong Here, There, or Elsewhere?’: The Materiality and Intangible Benefits of Technology in Digital Nomads' Place-Belongingness

‘Do I Belong Here, There, or Elsewhere?’: The Materiality ...

引用

International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)

作者： Hesam Mohseni Marcos Antonio de Almeida Daniel Schneider António Correia Faculty of Information Technology University of Jyväskylä Jyväskylä Finland Systems Engineering and Computer Science Program (PESC) Federal University of Rio de Janeiro Rio de Janeiro Brazil Postgraduate Program in Informatics (PPGI) Federal University of Rio de Janeiro Rio de Janeiro Brazil

ISBN: (数字)9798350354423

ISBN: (纸本)9798350354430

The advent of digital technology has contributed to experiencing liquid lifestyles and flexible work arrangements with different mobility routes and targets. Escaping the exhausting routine of commuting to and from work has been a key driver of digital nomadism, a phenomenon that has become increasingly widespread across the globe and is often centered around cross-border travel and expatriate settlement. Due to their frequent mobility, digital nomads face unique challenges in fostering a sense of place-belongingness compared to most other types of workers. Despite the popularity of digital nomadic work/life in the current public discourse, there is no standardized guidebook for understanding how digital technology already supports or could potentially support the sense of place-belongingness among these voluntary migrants. Motivated by this line of research, in our paper, we propose an initial guide with practical methodological considerations on how to investigate this phenomenon using qualitative and quantitative materials. Such studies can assist strategists and organizations in attracting new talent and fostering more inclusive environments.

关键词： Liquids Standards organizations Organizations Mediation Faces

来源：评论

学校读者我要写书评

暂无评论

Dynamic Healthcare Embeddings for Improving Patient Care 14

Dynamic Healthcare Embeddings for Improving Patient Care

引用

14th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2022

作者： Jang, Hankyu Lee, Sulyun Hasibul Hasan, D.M. Polgreen, Philip M. Pemmaraju, Sriram V. Adhikari, Bijaya University of Iowa Department of Computer Science Iowa CityIA United States University of Iowa Interdisciplinary Graduate Program in Informatics Iowa CityIA United States University of Iowa Department of Internal Medicine Iowa CityIA United States

ISBN: (纸本)9781665456616

As hospitals move towards automating and integrating their computing systems, more fine-grained hospital operations data are becoming available. These data include hospital architectural drawings, logs of interactions between patients and healthcare professionals, prescription data, procedures data, and data on patient admission, discharge, and transfers. This has opened up many fascinating avenues for healthcare-related prediction tasks for improving patient care. However, in order to leverage off-the-shelf machine learning software for these tasks, one needs to learn structured representations of entities involved from heterogeneous, dynamic data streams. Here, we propose DECENT, an auto-encoding heterogeneous co-evolving dynamic neural network, for learning heterogeneous dynamic embeddings of patients, doctors, rooms, and medications from diverse data streams. These embeddings capture similarities among doctors, rooms, patients, and medications based on static attributes and dynamic interactions. DECENT enables several applications in healthcare prediction, such as predicting mortality risk and case severity of patients, adverse events (e.g., transfer back into an intensive care unit), and future healthcare-associated infections. The results of using the learned patient embeddings in predictive modeling show that DECENT has a gain of up to 48.1% on the mortality risk prediction task, 12.6% on the case severity prediction task, 6.4% on the medical intensive care unit transfer task, and 3.8% on the Clostridioides difficile (***) Infection (CDI) prediction task over the state-of-the-art baselines. In addition, case studies on the learned doctor, medication, and room embeddings show that our approach learns meaningful and interpretable embeddings. © 2022 IEEE.

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

Trajectory Analysis of Inter-Island Logistics Transportation for Aggregate Material Using Web-Based Information 2

Trajectory Analysis of Inter-Island Logistics Transportation...

引用

2nd International Conference on Technology Innovation and Its Applications, ICTIIA 2024

作者： Suraji, Aji Ishak, Syarifuddin Prabowo, Prabowo Fatkhurrozi, Muhammad Alawy, Gholiqul Amrodh Putra, Rangga Pahlevi University of Widyagama Malang Dept. of Civil Engineering Malang City Indonesia Malang State University Study Program of D4 Eng. Tech and Civil Building Maintenance Malang City Indonesia Institut Teknologi Sumatera Dept. of Ocean Engineering Lampung Selatan Regency Indonesia University of Widyagama Malang Dept. of Informatics Engineering Malang City Indonesia

ISBN: (纸本)9798350351613

Transportation of material aggregates over long distances and between islands requires a long time by changing modes of transportation. Therefore, determining a material aggregate travel trajectory model using a web database is something that can help in logistics movement analysis. This study aims to create a web-based material aggregate transportation trajectory model. The data collection method involves extracting data with Google Maps which shows distance and time indications. Next, validation is carried out in the field with a direct survey at the location. The analytical method uses statistical methods to create modeling using a linear regression model approach and statistical tests using anova. The results of the study show that the linear regression model is simple with an independent variable coefficient of 0.0306 and an R-square of 0.8649. Meanwhile, using the ANOVA test, it was stated that the modeling results were quite significant and the model could be used to make predictions. © 2024 IEEE.

关键词： aggregate material logistics trajectory transportation web-based information

来源：评论

学校读者我要写书评

暂无评论

Deep STI: Deep Stochastic Time-series Imputation on Electronic Health Records 46

Deep STI: Deep Stochastic Time-series Imputation on Electron...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Cheng, Ming-Che Hsieh, Yi-Hsien Hsu, Te-Cheng Su, Tung-Hung Lin, Che Institute of Communications Engineering National Tsing Hua University Hsinchu30013 Taiwan Taipei10617 Taiwan Division of Gastroenterolgy and Hepatology Dept. of Internal Medicine National Taiwan University Hospital Taipei10048 Taiwan Department of Electrical Engineering Ntu Taipei Taiwan Center for Advanced Computing and Imaging in Biomedicine Ntu Taipei Taiwan Smart Medicine and Health Informatics Program Ntu Taipei Taiwan

ISBN: (纸本)9798350371499

Electronic Health Records (EHRs) are a cornerstone of modern healthcare analytics, offering rich datasets for various disease analyses through advanced deep learning algorithms. However, the pervasive issue of missing values in EHRs significantly hampers the development and performance of these models. Addressing this challenge is crucial for enhancing clinical decision-making and patient care. Existing methods for handling missing data, ranging from simple imputation to more sophisticated approaches, often fall short of capturing the temporal dynamics inherent in EHRs. To bridge this gap, we introduce the Deep Stochastic Time-series Imputation (Deep STI) algorithm, an innovative end-to-end deep learning model that seamlessly integrates a sequence-to-sequence generative network with a prediction network. Deep STI is designed to leverage the observed time-series data in EHRs, learning to infer missing values from the temporal context with high accuracy. We evaluated Deep STI on the liver cancer data from the National Taiwan University Hospital (NTUH), Taiwan. Our results showed that Deep STI achieved better 5-year hepatocellular carcinoma predictions (19.21% in the area under the precision-recall curve) than extreme gradient boosting (18.15%) and Transformer (18.09%). The ablation study also illustrates the efficacy of our generative architecture design compared to regular imputations. This approach not only promises to improve the reliability of disease analysis in the presence of incomplete data but also sets a new standard for utilizing EHRs in predictive healthcare. Our work aims to advance the field of healthcare analytics and open new avenues for research in deep learning applications to EHRs. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Alternative Reference Samples to Improve Coding Efficiency for Parallel Intra Prediction Solutions

Alternative Reference Samples to Improve Coding Efficiency f...

引用

IEEE Latin American Symposium on Circuits and Systems (LASCAS)

作者： Iago Storch Nuno Roma Daniel Palomino Sergio Bampi Graduate Program in Computing Institute of Informatics Federal University of Rio Grande do Sul Porto Alegre Brazil INESC-ID Instituto Superior Técnico Universidade de Lisboa Lisboa Portugal Video Technology Research Group Graduate Program in Computing Federal University of Pelotas Pelotas Brazil

Exploring massive parallelism is a common strategy to mitigate the processing time of modern video encoding standards. Nonetheless, the existing data dependencies in some encoding tools pose difficult challenges to exploit such parallelism, especially during intra prediction, where the reconstructed adjacent blocks are used as references. Although some works made use of different reference samples to allow block-level parallelism in intra prediction, their proposals do not consider the variations caused by different bitrates, leading to some degradation in the output sequence. To deal with multiple bitrates more properly, this work proposes the application of image smoothing techniques to generate alternative reference samples that better represent the nuances of different bitrates. Experimental validations demonstrate that these improved references provide coding efficiency gains while still offering an equivalent parallelization opportunity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Influence of Overcharging and Over-Discharging on the Capacity Degradation of Lithium-Ion Batteries

The Influence of Overcharging and Over-Discharging on the Ca...

引用

IEEE Conference on Vehicle Power and Propulsion (VPPC)

作者： Joelton Deonei Gotz Marco Antonio Simões Teixeira Fernanda Cristina Corrêa Emilson Ribeiro Viana Alceu André Badin Milton Borsato Graduate Program in Electrical and Computer Engineering Federal Technological University of Paraná (UTFPR-CT) Curitiba Brazil Graduate Program in Informatics (PPGIa) Pontifical Catholic University of Paraná (PUC-PR) Curitiba Brazil Graduate Program in Electrical Engineering Federal Technological University of Paraná (UTFPR-PG) Ponta Grossa Brazil Physics Department Graduate Program in Physics and Astronomy Federal Technological University of Paraná (UTFPR-CT) Curitiba Brazil Graduate Program in Mechanical Engineering Federal Technological University of Paraná (UTFPR-CT) Curitiba Brazil

ISBN: (数字)9798331541606

ISBN: (纸本)9798331541613

Lithium-ion batteries (LIB) are the best technology for supplying and storing energy for electric mobility systems. Despite that, this technology is sensitive to abuses that can compromise its lifetime and cause fire and explosion risks. In this context, if LIB is not correctly controlled, some abuses, such as overcharging (OC) and over-discharging (OD), can be observed and provoke a loss of capacity. Therefore, this work presented the application of several experiments in cells, of the NMC type, under OC and the combination of OC and OD. The results indicated that cells charged until 4.4 and 4.5 V and discharged until 3.0 V do not lose capacity for twenty-five cycles, but more cycles should be done to understand the impact over time. On the other side, the cell charged until 4.6 and 4.8 V had its security protection romped in the fourth charging cycle, and the cell charged until 5.0 V had its safety compromised in the first charging cycle. Conversely, cells with a combination of OC and OD were more compromised. In this context, while a cell is submitted only with OC and does not lose capacity, a cell under OC and then under OD had its protection romped in the third charging cycle. Cells under 4.6 V and 4.8 V lost capacity during the second charging cycle. In conclusion, OC provokes a high level of degradation in the cell, but the combination of OC and OD causes even more degradation.

关键词： Degradation Lithium-ion batteries Battery management systems Propulsion Security Reliability Protection Stress Monitoring Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Identifying university students’ online academic help-seeking patterns and their role in Internet self-efficacy

引用

Internet and Higher Education 2023年 56卷

作者： Fan, Yang-Hsin Lin, Tzung-Jin School of Learning Informatics Graduate Institute of Information and Computer Education National Taiwan Normal University Taiwan School of Learning Informatics Program of Learning Sciences National Taiwan Normal University Taiwan Institute for Research Excellence in Learning Sciences National Taiwan Normal University Taiwan

The main purposes of this study were, first, to identify Taiwanese university students’ online academic help-seeking (OAHS) patterns and further to compare their Internet self-efficacy (ISE) among the identified patterns. A total of 366 Taiwanese university students were invited to fill out two questionnaires to understand their OAHS and ISE, respectively. The results revealed that three OAHS patterns, adaptive, self-reliant, and socially-affiliated, were characterized based on the cluster analysis. The differences in the students’ various ISE dimensions among the three patterns were then compared. The adaptive students, who commonly adopted all types of OAHS behaviors, tended to be the most efficacious in the seven measured ISE dimensions. The self-reliant students, highlighting that they mainly sought help by searching for relevant information online, showed higher confidence in the ISE dimensions of "Usage," "Application," and "Learning" than did the socially-affiliated students (i.e., those who tended to use formal and informal queries to seek academic help online). The socially-affiliated students only showed higher confidence in sharing online information than the self-reliant students. However, in the "Communication," "Verifying," and "Metacognition" ISE dimensions, there were no significant differences between the socially-affiliated and self-reliant students. © 2022 Elsevier Inc.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Utilizing Battery Energy Storage Systems to Enhance the Integration of Photovoltaic Systems for Damping Oscillations

Utilizing Battery Energy Storage Systems to Enhance the Inte...

引用

IEEE Southeastcon

作者： Ilham Akbar Ariesa Budi Zakaria Mayur Basu Eduard Muliadi Suwarno Nanang Hariyanto Graduate Program PLN-ITB PLN Corporate University Auburn USA Electrical and Computer Engineering Auburn University Auburn USA School of Electrical Engineering and Informatics Institut Teknologi Bandung (ITB) Bandung Indonesia

As the integration of Variable Renewable Energy (VRE) generators into power systems increases, there is a potential decrease in overall system reliability, particularly in terms of stability. This research suggests the integration of a Battery Energy Storage System (BESS) into a power system with Variable Renewable Energy sources, such as a utility-scale Photovoltaic (PV) plant, to accelerate the damping of post-fault oscillations following a short-circuit disturbance. The objective is for a Power Oscillation Damping (POD) within the PV plant to address post-fault oscillations within a specific timeframe. The POD in the PV plant is designed to supply additional active and reactive power, responding to the system's demands after a disturbance. The addition of BESS to the system is anticipated to enhance the time required for the system to achieve a stable state, resulting in quicker system stabilization. Simulations conducted through PSCAD software can effectively depict the post-fault conditions of short-circuit disturbances, considering the impact of the integrated BESS.

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：