检索结果-内蒙古大学图书馆

3rd International Conference on Novel and Intelligent Digital Systems, NiDS 2023

作者： Chytas, Konstantinos Tsolakidis, Anastasios Triperina, Evangelia Karanikolas, Nikitas N. Skourlas, Christos University of West Attica department of Informatics and Computer Engineering Athens12243 Greece

ISBN: (纸本)9783031441455

Currently, universities not only offer technologically enhanced education and automated processes, but also provide a wide spectrum of online services, especially after COVID19. We propose e-EDURES, an integrated platform for educational and research management in tertiary education to further benefit the stakeholders by relying on the data of university online services to enable strategic planning and decision making. More specifically, in this paper, we focus on the presentation of an interactive system that utilizes the data derived by university’s synchronous and asynchronous e-learning services to gain insights about the educational performance of the students. It employs Educational Data Mining techniques to ultimately boost the educational process, by assessing the previous performance, monitoring the provided services and predicting future performance of the students, in order to avoid potential pitfalls. The proposed solution merges the current advances in smart education and educational data mining to offer an advanced and updated version of online services provided by universities that respond better to the current needs in academia. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Stunting Program Classification in East Java, Indonesia from Internet News Using Location-Based and SVM 25

Stunting Program Classification in East Java, Indonesia from...

引用

25th International Electronics Symposium, IES 2023

作者： Ananta, Caesar Jalu Fariza, Arna Asmara, Rengga Politeknik Elektronika Negeri Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350314731

Stunting is a serious health problem for toddlers in Indonesia, especially in East Java, which makes the Indonesian government seriously try to overcome it to achieve the Golden Generation of Indonesia. To reduce the prevalence of stunting, programs related to stunting are held regularly. This research aims to compile and classify information regarding stunting programs in East Java from internet news. The solution is to create a website that visualizes the prevalence of stunting and stunting programs in East Java, Indonesia, in the form of a map that is divided into several districts in East Java. Stunting prevalence data is taken from SSGI data that has been collected by the Indonesian Ministry of Health, while information about the stunting program is taken from mined internet news, filtered using the SVM machine learning algorithm, and classified based on the location of the stunting program reported. The SVM filtering model created can classify and filter news with an accuracy rate of up to 87%. With this website, it is hoped that the public can easily get information about stunting programs in their location and that the government can conduct an interactive analysis of stunting data in East Java. © 2023 IEEE.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Mobile Application for Early Screening of Skin Cancer Using Dermoscopy Image Data Based on Convolutional Neural Network 25

Mobile Application for Early Screening of Skin Cancer Using ...

引用

25th International Electronics Symposium, IES 2023

作者： Fariza, Arna Muliawati, Tri Hadiah Wibowo, Mohamad Akbar Fadlika Setiowati, Yuliana Politeknik Elektronika Negeri Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350314731

The dermoscopy image produced by the dermatoscope represents the skin surface structure in more detail than clinical images because the imaging technique uses optical magnification and liquid immersion lighting or cross-polarization. Detection of skin cancer is a challenge for several reasons. Doctors find it difficult to detect the presence of cancer on the skin only with dermoscopy images. Sometimes further tests are needed to confirm the results of the diagnosis, such as a biopsy or pathology examination, that is relatively time-consuming. Mobile skin screening technology can be used as an early screening tool for the early detection of melanoma, allowing patients to share images of their lesions with their skin specialists quickly. In this study, a novel method for early skin cancer detection based on dermoscopy pictures and the convolution neural network (CNN) algorithm is proposed. Three convolution layers, two average pooling layers, and a batch normalization layer make up the five feature extraction layers of CNN's proprietary design. The ISIC Archive, which has a collection of skin lesion photos, was the dataset utilized to create the model. Four thousand dermoscopy images in JPG format are used in this study and are divided into two classes: benign and malignant. The dataset is divided randomly into 80% training data and 20% test data. The experiments found that the model with the best performance resulted in a training data accuracy of 99.3% and a test data accuracy of 97.63%. It concludes that the model with batch normalization can distinguish the benign and malignant well. The model requires a small enough space to be easily accessible through mobile devices. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

The combination of the NDBI and machine learning algorithms to classification the development of urban areas in Surabaya uses Landsat 8 Imagery. 25

The combination of the NDBI and machine learning algorithms ...

引用

25th International Electronics Symposium, IES 2023

作者： Wibowo, Prasetyo Fariza, Arna Saputra, Ferry Astika Politeknik Elektronika Negeri Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350314731

Development is a transformation that occurs in order to better people's lives. In this instance, efforts are required to monitor development progress swiftly and efficiently so that outcomes that support the government's new policies are obtained. With a population of 2,848,583 people, Surabaya is the largest metropolitan city in Eastern Indonesia. An increase in population can impact Surabaya's development and generate potential issues with urban planning development. Through these issues, remote sensing technology can efficiently and swiftly detect advances in Surabaya. This research study employs Landsat 8 image data with a combination of Normalized Build-Up Index (NDBI) as pre-processed pixels to segment into urban areas. It employs machine learning to classify urban areas to separate class types in depth. The findings show that the method successfully classified subclasses in residential and industrial areas. Random Forest (RF) outputs have an overall accuracy of 85%, whereas Decision Tree (DT) outputs have an overall accuracy of 84%. This study's findings also indicate the possibility for practical applicability to various case studies, such as conducting detections in forests, plantations, mining, and coastal environments. © 2023 IEEE.

关键词： Landsat

来源：评论

学校读者我要写书评

暂无评论

Obstacle Detection and Tracking System for Robot Soccer ERSOW based on Centroid Tracking Method 25

Obstacle Detection and Tracking System for Robot Soccer ERSO...

引用

25th International Electronics Symposium, IES 2023

作者： Wardhana, Vega Kurnia Garindra Wibowo, Iwan Kurnianto Bachtiar, Mochamad Mobed Politeknik Elektronika Negeri Surabaya Departement of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350314731

EEPIS Robot Soccer on Wheeled (ERSOW) is a wheeled soccer robot developed by Politeknik Elektronika Negeri Surabaya and participated in the national robot competition, Indonesian Robot Contest in KRSBI Wheeled division. ERSOW team has striker robot, striker robot was used in attack strategy for scoring goals. The ability to tracking the obstacle is one of main abilities that striker robot must has. Obstacle tracking plays a crucial role in robot soccer on wheels due to the dynamic and unpredictable nature of the game. As robots navigate the field, they encounter various obstacles such as opponents, teammates, and static objects (obstacle). Accurate and real-time tracking of these obstacles enables robots to make informed decisions, adapt their strategies, and effectively interact with the environment. Obstacle tracking enhances situational awareness. By continuously monitoring the positions and movements of obstacles, robots gain valuable information about the current game state. Tracking system on this research works with centroid tracking algorithm. The fundamental concept of the centroid tracking algorithm revolves around assigning a distinct identification (ID) to every tracked object by taking their centroids, this algorithm takes the center of obstacle bounding box as an input, to generated bounding box this system used thresholding detection method based on HSV color space. The center of bounding box (in pixel coordinate) converted into world coordinate by using Ab-exponential regression and Linear regression. The testing results of tracking system could estimate obstacle from 50cm-250cm from the robot with 0,967 cm error average, the system also could track the obstacle with 86% accuracy when the robot moved 330 cm ahead. © 2023 IEEE.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Cloud Computing Using the NDLC Method Combined with Tunnel Link Split

Design and Implementation of Cloud Computing Using the NDLC ...

引用

2023 International Conference on Information Technology and Computing, ICITCOM 2023

作者： Wibowo, Iqbal Tri Kurniawan, Asep Noviandri Sulaiman, Nur Fauzi Oktivasari, Prihatin Politeknik Negeri Jakarta Dept. of Informatics and Computer Engineering Depok Indonesia

ISBN: (纸本)9798350359633

Today's education system increasingly incorporates information technology, such as the use of computers, the internet, and mobile devices. Utilization of this information technology can facilitate the teaching and learning process and increase the effectiveness, efficiency and productivity of users, both teachers, students and school administrators. However, given the growing number of users and the amount of data processed, school infrastructure often cannot meet these needs. The system development method will use the NDLC (Network Development Life Cycle) method which will be combined with the Tunnel Link Split to become a system that can be used remotely (remoting). The results of this research are that the results of designing and implementing cloud computing with the NDLC method combined with tunneling can be successful and used. Implementation is also carried out with additional monitoring using observium software and for access to the cloud using additional software, namely owncloud by obtaining an extended processor observium value of 99.90% (idle), detailed observium memory 69% (% of ram), swap storage observium 218.48kb/ s, observium ping response 86.4m/s, and observium traffic port wlo15.63m. © 2023 IEEE.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

EXPLORING INFLUENTIAL FACTORS IN KNOWLEDGE SHARING WITHIN INDONESIAN PRISONS 22

EXPLORING INFLUENTIAL FACTORS IN KNOWLEDGE SHARING WITHIN IN...

引用

22nd International Conference on e-Society 2024, ES 2024 and 20th International Conference on Mobile Learning 2024, ML 2024

作者： Imandeka, Ejo Hidayanto, Achmad Nizar Suhartanto, Heru Pidanic, Jan Department of Computer Science Faculty of Computer Science University of Indonesia Depok Indonesia Department of Electrical Engineering Faculty of Electrical Engineering and Informatics Pardubice University Pardubice Czech Republic

The exchange of knowledge is widely recognized as a crucial aspect of effective knowledge management. When it comes to sharing knowledge within Prison settings, things get complicated due to various challenges such as limited resources, social stigma, isolation, communication barriers, and security concerns. Additionally, there's a scarcity of resources dedicated to promoting knowledge sharing in secure environments. This study aims to dig deep into the key factors that influence how knowledge is shared in Indonesian prisons. To navigate this intricate terrain, the study uses questionnaires distributed among Prison officers to understand the complex relationship between the identified critical factors and knowledge sharing in Prison. Leadership support, organizational culture, organizational structure, incentives, and individual beliefs emerge as pivotal elements in knowledge sharing. It's also noted that the connection between these critical factors and the intention to share knowledge is significantly influenced by organizational structure. Recognizing and addressing critical factors in knowledge sharing within prisons not only improves rehabilitation within prison walls but also transforms the broader criminal justice system. This approach fosters evidence-based practices, better communication, and a comprehensive understanding of factors leading to successful rehabilitation and reduced recidivism, ultimately creating a more just and effective system. © 2024 International Conferences e-Society 2024 and Mobile Learning 2024. All rights reserved.

关键词： Critical Factors Indonesia Knowledge Knowledge Sharing Prison

来源：评论

学校读者我要写书评

暂无评论

Evaluation and Prediction of Resource Usage for multi-parametric Deep Learning training and inference 27

Evaluation and Prediction of Resource Usage for multi-parame...

引用

27th Pan-Hellenic Conference on Progress in Computing and informatics with International Participation, PCI 2023

作者： Tsalera, Eleni Stratogiannis, Dimitrios Papadakis, Andreas Voyiatzis, Ioannis Samarakou, Maria Department of Informatics and Computer Engineering University of West Attica Greece Athens Greece

ISBN: (纸本)9798400716263

Deep learning is increasingly used in diverse application fields with results typically surpassing those of traditional machine learning techniques. The portfolio of available neural networks is wide, consisting of the full range in terms of complexity, from compact networks to large ones with multiple layers and parameters. This heterogeneity in the model topology is reflected, not necessarily linearly, on the required computational resources for training and inference. Similarly, the environments where the neural networks are trained and executed are transformed from fully-fledged centralized nodes to distributed architectures with constrained resources. In this view, computational resource requirements can be one of the criteria for resource usage management and neural network selection. In this work we measure the training times for a set of five convolutional neural networks of varying complexity and age (GoogleNet, ShuffleNet, VGGish, YAMNet) under different training configurations, considering the batch size, the number of epochs and the learning rate. These measurements are used to create a CPU-time-training dataset of more than 500 values. This dataset is used to train and evaluate models, based on neural networks, for estimating and predicting training times depending on the models employed and the training parameters. Five regression models have been trained and evaluated in terms of correlation coefficient and root mean square error. In addition, we measure the CPU times needed for inference for a subset of the trained models, which prove to be uncorrelated with the corresponding training times. © 2023 Owner/Author.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Analysis of *** Email Domain Security Status Using DMARC (Domain-Based Message Authentication, Reporting, and Conformance) 6

Analysis of *** Email Domain Security Status Using DMARC (Do...

引用

6th International Conference on computer and informatics engineering, IC2IE 2023

作者： Arnaldy, Defiana Theyser, Regina Patricia Politeknik Negeri Jakarta Dept. of Informatics and Computer Engineering Depok Indonesia

ISBN: (纸本)9798350345162

The rapid development of technology not only provides benefits that facilitate all human activities. However, it also encourages more security loopholes due to a person's lack of awareness in maintaining data security. Phishing emails are one of the fastest growing security crimes and harm both businesses and individuals. This research aims to implement DMARC (Domain-based Message Authentication, Reporting, and Conformance) as an email authentication method that can monitor the security status of all types of messages that enter *** email domains. This research uses email phishing and spoofing as penetration testing techniques to analyze how good that email security method is. DMARC is implemented in three types of scenarios (none, quarantine, and reject) which manage to get different delivery rates and the success rate of DMARC work performance reaches 90% in monitoring and managing all email messages that go to the *** email domain. In the situation without policy enforcement, the DMARC system effectively observed a 100.0% external delivery rate during the phishing email delivery test. In the scenario where a quarantine policy was implemented, the DMARC system successfully monitored the external sending of phishing emails at a rate of 88.5%. Similarly, in the case of the reject policy scenario, DMARC effectively oversaw incoming phishing emails with an external delivery rate of 97.7%. © 2023 IEEE.

关键词： Apilogy.id DMARC Email Security Phishing Spoofing

来源：评论

学校读者我要写书评

暂无评论

A classifier design for micro bubble generators based on deep learning technique

引用

Materials Today: Proceedings 2023年 80卷 2684-2696页

作者： Qaddoori, Ayman S. Saud, Jamila H. Hamad, F.A. Informatics Institute for Postgraduate Studies Iraqi Commission for Computer and Informatics Baghdad Iraq College of Science Mustansiriyah University Baghdad Iraq School of computing Engineering and Digital Technology Teesside University Middlesbrough United Kingdom

This paper aims to study the sizes of bubbles generated by the micro-bubble generator device (MBGs) in the water because of its impact on the dissolved oxygen percentage in the water and we find this in aquaculture where oxygen is important for marine life and in many applications. Where we have designed a classifier for micro-bubbles of different sizes and the effectiveness of the device has been proven in generating bubbles whose size ranges from 20 to 50 and calculating their numbers in the image by converting the image from (RGB) to (HSV), it has proven its effectiveness in maintaining lighting and neglecting color information Which is not important in identifying bubbles in the image, as well as increasing the processing speed, and then finding edges in the image, using canny edge detection, which has proven its great effectiveness in finding weak and strong edges. Where we then used the (Circular Hough Transform) algorithm to identify the tiny bubbles in the image, calculate their average diameter and numbers in the image, and find the overlapping bubbles between them by using (Two Thresholds) one for the edge and the other for the center of the bubble and then making (Segmentation) for these bubbles and inserting them on (Gaussian Normal Distribution) Do not neglect the dark bubbles, because in most cases they are unreal bubbles and may be distortions in the image or reflections in the lighting. And then make (zero paddings) for the extracted images to make them equal in size and avoid the distortion that will happen in the image if another method is used to make all bubbles of equal dimensions to prepare them for classification. And then we calculated the (mean square error) of the resulting bubble images to avoid repeating the same bubble in (datasets). The efficiency of the classifier was calculated by using deep learning technology. Where we built a (Convolution Neural Network) consisting of (15) layers and then we trained these layers on the images resul

关键词： Feature extraction

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：