Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference最新文献_第3页

Augmenting Image Aesthetic Assessment with Diverse Deep Features 基于不同深度特征的增强图像审美评价

Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference Pub Date : 2021-12-17 DOI: 10.1145/3508259.3508264

Rui Lin

引用次数: 0

Literature Review Profiles of Specialization in Education and Profession as the basis for the development of Artificial Intelligence Website 教育专业化与职业专业化作为人工智能网站发展基础的文献综述

Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference Pub Date : 2021-12-17 DOI: 10.1145/3508259.3508296

Y. Indrianti, Sasmoko, S. R. Manalu, Queensy Lovenia Kerrin Waromi

{"title":"Literature Review Profiles of Specialization in Education and Profession as the basis for the development of Artificial Intelligence Website","authors":"Y. Indrianti, Sasmoko, S. R. Manalu, Queensy Lovenia Kerrin Waromi","doi":"10.1145/3508259.3508296","DOIUrl":"https://doi.org/10.1145/3508259.3508296","url":null,"abstract":"Profiles of specialization in education and profession are currently heavily influenced by the development of industry 4.0. The era of disruption is marked by massive changes due to innovations that change business systems and arrangements to newer levels. In various studies, there will be many professions that are extinct but there will also be many new professions that will be born. This study aims to conduct a literature review of profiles of specialization in education and profession that are relevant to industry 4.0 trends which will then be developed in a measurement through an artificial intelligence-based website. The research method used is a bibliometric approach through scientific studies of various library sources using VOSViewer with cartographic overlay techniques and density visualization maps, to represent sequences and their relationships. While the method used to develop website profiles of specialization in education and profession based on artificial intelligence is to use the waterfall method. The results of the literature review found 10 words with a high level of bibliometric correlation as the basis for developing artificial intelligence-based websites.","PeriodicalId":259099,"journal":{"name":"Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131896521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

A Hybrid Recommender System based on DeepCF and Wide Linear Model for K12 Online Education 基于深度cf和宽线性模型的K12在线教育混合推荐系统

Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference Pub Date : 2021-12-17 DOI: 10.1145/3508259.3508279

Tuanji Gong, Xuan-xia Yao, Kate N. Sirota

{"title":"A Hybrid Recommender System based on DeepCF and Wide Linear Model for K12 Online Education","authors":"Tuanji Gong, Xuan-xia Yao, Kate N. Sirota","doi":"10.1145/3508259.3508279","DOIUrl":"https://doi.org/10.1145/3508259.3508279","url":null,"abstract":"Compared to traditional classroom education, online education has the advantage of personalized teaching and is able to significantly improve learning efficiency and outcomes. K12 online education refers to online education serving students across 12 grade levels, from primary school to high school. As there are a plethora of courses offered on online education platforms, how to recommend proper courses for students is a serious challenge. In order to resolve this problem, this study proposes a hybrid recommendation model that combines the deep collaborative filtering (DeepCF) model and the wide linear model. Together, in the hybrid model, these models can integrate course features, student features, and side information. The DeepCF model learns low-dimension latent representations for both courses and students and integrates them into matrix factorization to predict ratings. The wide linear model uses a factorization machine to design and select features automatically. The hybrid model can achieve good performance and alleviate the problem of sparse features and cold start. Experimental results demonstrate that compared with the collaborative filter model, the hybrid model achieved a significant improvement with a 12.7% relative increase in AUC metric.","PeriodicalId":259099,"journal":{"name":"Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124844593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

LINEN ASSESSMENT APPS: Artificial Intelligence Integration to develop Android-based applications that measure the "literacy, numeracy, entrepreneurial mindset" capacity of students in Indonesia 亚麻评估应用程序:人工智能集成，开发基于android的应用程序，测量印度尼西亚学生的“读写、计算、创业思维”能力

Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference Pub Date : 2021-12-17 DOI: 10.1145/3508259.3508295

Given Name Sasmoko, Y. Indrianti, Davy Ronald Hermanus

{"title":"LINEN ASSESSMENT APPS: Artificial Intelligence Integration to develop Android-based applications that measure the \"literacy, numeracy, entrepreneurial mindset\" capacity of students in Indonesia","authors":"Given Name Sasmoko, Y. Indrianti, Davy Ronald Hermanus","doi":"10.1145/3508259.3508295","DOIUrl":"https://doi.org/10.1145/3508259.3508295","url":null,"abstract":"The LINEN Assessment application is an application developed to measure the capacity of students in Indonesia in terms of literacy, numeracy and entrepreneurial mindset. To be able to get an automatic profiling picture and be able to provide more accurate predictions, the application was developed based on artificial intelligence. This study aims to provide an overview of the integration of artificial intelligence that is carried out to be applied in the process of developing the LINEN Assessment application. The research method used is the Neuroresearch research method. Through the three stages in this method, namely exploratory, explanatory and confirmatory research, the research process is carried out to produce a research construct as the basis for compiling a standard and valid LINEN Assessment instrument. The application development stage itself uses the waterfall method, specifically through the agile development method. The results of the study are illustrated by the presence of several diagrams showing the integration process carried out. The description of the LINEN Assessment application also shows that the LINEN Assessment Apps were developed with the concept of self-assessment and diagnostic-assessment to equip students with fundamental skills and competencies that are important for their future. One of these important foundations is when students have basic skills, namely literacy, numeracy and skills that refer to innovative creative power, namely entrepreneurial mindset skills. Students can independently use smartphones to explore their own profiles and explore learning experiences through the LINEN Assessment application.","PeriodicalId":259099,"journal":{"name":"Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125566491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

COVID-19 Diagnosis Using Chest X-ray Images via Classification and Object Detection 基于分类和目标检测的胸部x线图像诊断COVID-19

Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference Pub Date : 2021-12-17 DOI: 10.1145/3508259.3508268

Kenji Yoshitsugu, Y. Nakamoto

引用次数: 2

Reconfigurable Hybrid Model Convolutional Stage – Infinity Laplacian Applied to Depth Completion 可重构混合模型卷积阶段-无穷拉普拉斯在深度补全中的应用

Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference Pub Date : 2021-12-17 DOI: 10.1145/3508259.3508275

V. Lazcano, F. Calderero

{"title":"Reconfigurable Hybrid Model Convolutional Stage – Infinity Laplacian Applied to Depth Completion","authors":"V. Lazcano, F. Calderero","doi":"10.1145/3508259.3508275","DOIUrl":"https://doi.org/10.1145/3508259.3508275","url":null,"abstract":"Convolutional networks are the current approach that presents the best performance in many applications. The principal critic of classical models is that they are hand-crafted by the designer. Still, the proposed architecture of a convolutional network is also hand-crafted, for example, the number of layers. Depth map completion is crucial for computer vision due to its applications in different fields such as video games or autonomous vehicles. Depth maps are acquired by a sensor or obtained by a stereo algorithm and present a lack of information due to occlusions or sensor misinterpretation. In this paper, we offer a reconfigurable hybrid model to interpolate depth maps. This model consists of a convolutional stage (SC1) pipeline, interpolation model, and convolutional stage (SC2). The convolutional stage input is a color reference image of the scene, creating a color features map as input for the next step. The interpolation model is the infinity Laplacian. We interpolated the incomplete depth map solving the Infinity Laplacian in a Manifold. Then, the completed depth map is processed again by the last convolutional stage. In this pipeline, we used a fixed number of convolutional filters, but we can interchange convolutional steps, i.e., interchange SC1 by SC2, reconfiguring the computing sequence. We estimated the parameters of the convolutional filter and the Infinity Laplacian using Particle Swarm Optimization (PSO). Our proposal obtained MSE=1.315 in the KITTI depth completion suite outperforming some contemporaneous methods.","PeriodicalId":259099,"journal":{"name":"Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132156414","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

DECA: DoD Enterprise Cloud Architecture Concept for Cloud-Based Cross Domain Solutions DECA:基于云的跨域解决方案的国防部企业云架构概念

Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference Pub Date : 2021-12-17 DOI: 10.1145/3508259.3508283

Leonardo Aguilera, D. Jacobson

{"title":"DECA: DoD Enterprise Cloud Architecture Concept for Cloud-Based Cross Domain Solutions","authors":"Leonardo Aguilera, D. Jacobson","doi":"10.1145/3508259.3508283","DOIUrl":"https://doi.org/10.1145/3508259.3508283","url":null,"abstract":"The Department of Defense (DoD) battlefield exists both in cyber and the physical world. Information sharing is a top priority for the DoD in support of our warfighters and allies. To maintain military technological advantage and superiority, access to information and the capacity to process it are critical components for empowering the warfighter for mission success. The volume of information shared has increased exponentially, necessitating the development of a DoD enterprise cloud capable of sustaining, and supporting strategic worldwide DoD missions through effective information sharing. However, the existing U.S. Government cloud design does not support enterprise use, and legacy software and hardware applications such as a Cross Domain Solution (CDS) will need to be re-architected, certified, accredited, and authorized for future enterprise cloud use. A CDS is a requirement for information sharing in both unclassified and classified systems and information transmission from one system to another, but there must also be a DoD enterprise cloud structure to leverage the CDS in the U.S. Government cloud. The purpose of this research is to explore the future possibilities of using an enterprise cloud CDS and to present a conceptual design for a DoD enterprise cloud architecture that will save the DoD time and money in the certification process while also allowing efficient information sharing across multiple DoD Command and Control (C2) systems. To have this architecture design approved and accredited by the DoD for future use, we adhere to the Federal Risk and Authorization Management Program (FedRAMP), a process required for federal agency cloud deployments and the National Institute of Standards and Technology (NIST) standards. We use existing systems from across the DoD and allies found in the open literature as a baseline.","PeriodicalId":259099,"journal":{"name":"Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122175968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Colorizing Black and White Videos with Damping Factor and Pixel Tolerance: Reducing Flickering Effect 利用阻尼系数和像素公差对黑白视频进行着色:减少闪烁效果

Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference Pub Date : 2021-12-17 DOI: 10.1145/3508259.3508274

Sahith Kurapati, Om Shreenidhi BN, Saksham Gupta, Kalp Abhinn Aghada, Jayashree Rangareddy

引用次数: 0

Deep-Learning-Based Diagnosis of Cassava Leaf Diseases Using Vision Transformer 基于视觉转换器的木薯叶病深度学习诊断

Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference Pub Date : 2021-12-17 DOI: 10.1145/3508259.3508270

Li Zhuang

{"title":"Deep-Learning-Based Diagnosis of Cassava Leaf Diseases Using Vision Transformer","authors":"Li Zhuang","doi":"10.1145/3508259.3508270","DOIUrl":"https://doi.org/10.1145/3508259.3508270","url":null,"abstract":"Viral diseases are major causes leading to the poor yields of cassava, which is the second-largest source of food carbohydrates in Africa. As symptoms of these diseases can usually be identified by inspecting cassava leafs, visual diagnosis of cassava leaf diseases is of significant importance in food security and agriculture development. Considering the shortage of qualified agricultural experts, automatic approaches for the image-based detection of cassava leaf diseases are in great demand. In this paper, on the basis of Vision Transformer, we propose a deep learning method to identify the type of viral disease in a cassava leaf image. The image dataset of cassava leaves is provided by the Makerere Artificial Intelligence Lab in a Kaggle competition, consisting of 4 subtypes of diseases and healthy cassava leaves. Our results show that Vision-Transformer-based model can effectively achieve an excellent performance regarding the classification of cassava leaf diseases. After applying the K-Fold cross validation technique, our model reaches a categorization accuracy 0.9002 on the private test set. This score ranks top 3% in the leaderboard, and can get a silver medal prize in the Kaggle competition. Our method can be applied for the identification of diseased plants, and potentially prevent the irreparable damage of crops.","PeriodicalId":259099,"journal":{"name":"Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126677408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Combined Spatial Features Recognition Method for Similar Video Action Automatic Classification 相似视频动作自动分类的组合空间特征识别方法

Proceedings of the 2021 4th Artificial Intelligence and Cloud Computing Conference Pub Date : 2021-12-17 DOI: 10.1145/3508259.3508260

Ling Wang, Yuanhao Mei, Shiru Gao, T. Zhou

引用次数: 0