Tae Hyun Kim, Won Seok Jang, S. Heo, MinDong Sung, Y. Park
{"title":"Personalized Progressive Federated Learning with Leveraging Client-Specific Vertical Features","authors":"Tae Hyun Kim, Won Seok Jang, S. Heo, MinDong Sung, Y. Park","doi":"10.5121/csit.2023.130106","DOIUrl":"https://doi.org/10.5121/csit.2023.130106","url":null,"abstract":"Federated learning (FL) has been used for model building across distributed clients. However, FL cannot leverage vertically partitioned features to increase the model complexity. In this study, we proposed a personalized progressive federated learning (PPFL) model, which is a multimodel PFL approach that allows the leveraging of vertically partitioned client-specific features. The performance of PPFL was evaluated using the Physionet Challenges 2012 dataset. We compared the performance of in-hospital mortality and length of stay prediction between our model and the FedAvg, FedProx, and local models. The PPFL showed an accuracy of 0.849 and AUROC of 0.790 in average in hospital mor-tality prediction, which are the highest scores compared to client-specific algorithm. For length-of-stay prediction, PPFL also showed an AUROC of 0.808 in average which was the highest among all comparators.","PeriodicalId":366692,"journal":{"name":"Computer Science and Machine Learning Trends 2023","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124399692","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}
{"title":"Accelerating Experience Replay for Deep Q-Networks with Reduced Target Computation","authors":"Bob Zigon, Fengguang Song","doi":"10.5121/csit.2023.130101","DOIUrl":"https://doi.org/10.5121/csit.2023.130101","url":null,"abstract":"Mnih’s seminal deep reinforcement learning paper that applied a Deep Q-network to Atari video games demonstrated the importance of a replay buffer and a target network. Though the pair were required for convergence, the use of the replay buffer came at a significant computational cost. With each new sample generated by the system, the targets in the mini batch buffer were continually recomputed. We propose an alternative that eliminates the target recomputation called TAO-DQN (Target Accelerated Optimization-DQN). Our approach focuses on a new replay buffer algorithm that lowers the computational burden. We implemented this new approach on three experiments involving environments from the OpenAI gym. This resulted in convergence to better policies in fewer episodes and less time. Furthermore, we offer a mathematical justification for our improved convergence rate.","PeriodicalId":366692,"journal":{"name":"Computer Science and Machine Learning Trends 2023","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121845645","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}
{"title":"Predicting the Dissolution of Tablets based on Raman Maps using a Linear Regression Model","authors":"Gábor Knyihár, K. Csorba, H. Charaf","doi":"10.5121/csit.2023.130107","DOIUrl":"https://doi.org/10.5121/csit.2023.130107","url":null,"abstract":"Investigation of the dissolution of tablets is an important area of pharmaceutical research. Such research aims to predict the dissolution process as accurately as possible without destroying the tablets. Several methods have been published that can estimate dissolution with approximate accuracy, but they are mostly complex and time-consuming. This article seeks to answer whether these complex models are necessary or whether a similar result can be achieved with the help of more straightforward methods. Therefore, during this work, a simpler linear regression model was created and analysed its effectiveness in estimating the dissolution curves. The investigation concluded that the results are not as accurate as in the case of more complex methods, but they are not far behind. Thus, even similar results may be achieved by fine-tuning and possibly developing these methods.","PeriodicalId":366692,"journal":{"name":"Computer Science and Machine Learning Trends 2023","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131590480","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}
{"title":"An Empirical Evaluation of Writing Style Features in Cross-Topic and Cross-Genre Documents in Authorship Identification","authors":"Simisani Ndaba, E. Thuma, G. Mosweunyane","doi":"10.5121/csit.2023.130104","DOIUrl":"https://doi.org/10.5121/csit.2023.130104","url":null,"abstract":"In this paper, an investigation was done to identify writing style features that can be used for cross-topic and cross-genre documents in the Authorship Identification task from 2003 to 2015. Different writing style features were empirically evaluated that were previously used in single topic and single genre documents for Authorship Identification to determine whether they can be used effectively for cross-topic and crossgenre Authorship Identification using an ablation process. The dataset used was taken from the 2015 PAN CLEF Forum English collection consisting of 100 sets. Furthermore, it was investigated whether combining some of these feature sets can help improve the authorship identification task. Three different classifiers were used: Naïve Bayes, Support Vector Machine, and Random Forest. The results suggest that a combination of a lexical, syntactical, structural, and content feature set can be used effectively for cross topic and cross genre authorship identification, as it achieved an AUC result of 0.837.","PeriodicalId":366692,"journal":{"name":"Computer Science and Machine Learning Trends 2023","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128105253","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}
{"title":"Models4Artist: An Intelligent Pose-based Image Search Engine to Assist Artist Creation using Artificial Intelligence and Post Estimate","authors":"Huibin Xie, Yu Sun","doi":"10.5121/csit.2023.130103","DOIUrl":"https://doi.org/10.5121/csit.2023.130103","url":null,"abstract":"Since some years ago, the popularity of drawing has been increasing. There are a lot of existing tools to help people to improve their drawing [5]. Some tools provide human body images, so people can practice their human body drawing [6]. However, users cannot find the desirable pose images since these tools provide only a list of images but it cannot be sorted by pose. Thus, we proposed a tool in which users can move the joints of a stick figure to obtain the matching human pose image. In our experiments, the result shows that the engine matches 87% of the human images and the stick figure. Also, we performed data analysis with feedback from 10 high school students. The result shows that 5 out of 10 students were satisfied with our tool.","PeriodicalId":366692,"journal":{"name":"Computer Science and Machine Learning Trends 2023","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125231679","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}
{"title":"A Mobile Application to Mark Attendance using a Combined Backend of the Firestore Database and Amazon AWS Services","authors":"Andy Jiang, Yu Sun","doi":"10.5121/csit.2023.130108","DOIUrl":"https://doi.org/10.5121/csit.2023.130108","url":null,"abstract":"Since the beginning of the COVID-19 pandemic, education largely shifted away from the physical classroom and towards more digitally oriented platforms. This simplified classroom attendance problems greatly, as newly created programming scripts could easily track the students in a meeting room via their names. However, with the recent growing return to in person education, it has become apparent that the problem of attendance within the context of a non-virtual classroom environment has yet to be solved in an efficacious automated fashion. In larger classrooms, the severity of this problem becomes exacerbated even further, as teachers are forced to allocate valuable time for the purpose of marking attendance. The flourishing world of machine-learning based algorithms were the first solutions that we considered, and within the context of the premise, we concluded that facial recognition would likely be the most feasible and effective approach that we could use. This paper develops a mobile application to apply real time face recognition for the purpose of the above stated problem, using a combined backend of the Firestore database and Amazon AWS services. Applying our application to in person classrooms, the results show that our solutions are immensely effective in both saving time and reducing error.","PeriodicalId":366692,"journal":{"name":"Computer Science and Machine Learning Trends 2023","volume":"2000 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132400656","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}
{"title":"Newly Discovered Route Takeover and DNS Hijacking Attacks in Openshift","authors":"Luiza Nacshon, Martin Ukrop","doi":"10.5121/csit.2023.130105","DOIUrl":"https://doi.org/10.5121/csit.2023.130105","url":null,"abstract":"OpenShift uses Route objects to expose web applications to the outside world through HAproxy. One of the challenges of managing web application routing in containerized environments such as OpenShift is securely transferring information and allowing access to the applications running in those environments. This paper will examine two possible attacks discovered during security research on OpenShift networking: Route takeover and DNS hijacking. While writing this paper, we didn’t find related works discussing the attacks in containerized environments like Openshift. The novelty of the discovered attacks is the way those attacks are implemented and leveraged in the Openshift environment. The techniques used to gain route takeover and DNS hijacking can work only on Openshift clusters. Next, in the paper, we will briefly present and explain how users can prevent those possible attacks by following specific security practices.","PeriodicalId":366692,"journal":{"name":"Computer Science and Machine Learning Trends 2023","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128105052","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}