scholarly journals Distributed Machine Learning Using Data Parallelism on Mobile Platform

2020 ◽  
Author(s):  
Máté Szabó
Keyword(s):  
Machine Learning ◽  
Mobile Devices ◽  
Large Datasets ◽  
Software Implementation ◽  
Data Parallelism ◽  
Client Server ◽  
Distributed Training ◽  
Using Data ◽  
Server Architecture ◽  
Distributed Machine Learning

Machine learning has many challenges, and one of them is to deal with large datasets, because the size of them grows continuously year by year. One solution to this problem is data parallelism. This paper investigates the expansion of data parallelism to mobile, which became the most popular platform. Special client-server architecture was created for this purpose. The software implementation of this problem measures the mobile devices training capabilities and the efficiency of the whole system. The results show that doing distributed training on mobile cluster is possible and safe, but its performance depends on the algorithm’s implementation.

scholarly journals Web-Based Android Malicious Software Detection and Classification System

2018 ◽  
Vol 8 (9) ◽  
pp. 1622 ◽  
Author(s):  
İbrahim Doğru ◽  
Ömer KİRAZ
Keyword(s):  
Mobile Devices ◽  
Classification System ◽  
Detection System ◽  
Third Party ◽  
Web Based ◽  
Malicious Software ◽  
Client Server ◽  
Service Support ◽  
Server Architecture ◽  
Client Server Architecture

Android is the most used operating system (OS) by mobile devices. Since applications uploaded to Google Play and other stores are not analyzed comprehensively, it is not known whether the applications are malicious software or not. Therefore, there is an urgent need to analyze these applications regarding malicious software. Moreover, mobile devices have limited resources to analyze the applications. In this study, a malicious detection system named “Web-Based Android Malicious Software Detection and Classification System” was developed. The system is based on client-server architecture, static analysis and web-scraping methods. The proposed system overcomes the resource restriction issue, as well as providing third-party service support by means of client-server architecture. Based on the performance evaluation conducted in this research, the developed system’s success rate is 97.62% on benign and malicious datasets.

scholarly journals Design and Development of an Android App Based on Firebase in the Study of Unsportsmanlike Behaviors in Grassroots Tennis Competitions

2021 ◽  
Author(s):  
José García ◽  
V. De Lera ◽  
D. Lacambra ◽  
F. Gimeno ◽  
Álvaro Alesanco
Keyword(s):  
Mobile Devices ◽  
Psychological Aspects ◽  
Psychological Wellbeing ◽  
Android Application ◽  
Design Development ◽  
Client Server ◽  
Android App ◽  
High Level ◽  
Common Situation ◽  
Server Architecture

This paper presents the design, development and evaluation of an android application based on the Google Firebase platform aimed to facilitate the creation of questionnaires and collection of data for the management of sports and unsportsmanlike behaviors in grassroots tennis competitions. Although sportsmanship among players is the most common situation, in low categories sometimes aggressive or violent situations may occur and not always with the presence of referees. In recent years, the use of conventional questionnaires has been the most widespread tool to obtain information on sports and unsportsmanlike behaviors in sports competitions. The developed system allows tennis tournament organizers to easily create forms linked to the players in order to evaluate different psychological aspects during the competition. Players are notified and they answer the proposed questions on their mobile devices at the end of the matches. By using the application it is easy to collect the responses of the competitors and process and evaluate them. The developed system is based on a client-server architecture where the Firebase platform acts as system server and the application is the client that communicates with it. The application was validated by a tournament administrator showing a high level of usability. Afterwards it has been tested in a real tournament with 20 players (in a total of 34 matches) answering a form consisting of 13 questions to evaluate sports and unsportsmanlike behaviors. The results in this pilot tournament showed the perception of sportsmanship of the players as very good, but also showed that parents or companions interfere in children’s matches and two potential cases of unsportsmanlike conduct were detected. This system may become a versatile and useful tool for improvement of players’ psychological wellbeing during grassroots tennis competitions.

scholarly journals Country of Origin Effects on the Average Annual Values of NHL Player Contracts

2019 ◽  
Vol 7 (2) ◽  
pp. 24
Author(s):  
Aju J. Fenn ◽  
Lucas Gerdes ◽  
Samuel Rothstein
Keyword(s):  
Quantile Regression ◽  
Fixed Effects ◽  
Country Of Origin ◽  
Large Datasets ◽  
National Hockey League ◽  
Dummy Variables ◽  
Country Of Origin Effects ◽  
Performance Statistics ◽  
Career Performance ◽  
Using Data

Using data from 2005 to 2016, this paper examines if players in the National Hockey League (NHL) are being paid a positive differential for their services due to the competition from the Kontinental Hockey League (KHL) and the Swedish Hockey League (SHL). In order to control for performance, we use two different large datasets, (N = 4046) and (N = 1717). In keeping with the existing literature, we use lagged performance statistics and dummy variables to control for the type of NHL contract. The first dataset contains lagged career performance statistics, while the performance statistics are based on the statistics generated during the years under the player’s previous contract. Fixed effects least squares (FELS) and quantile regression results suggest that player production statistics, contract status, and country of origin are significant determinants of NHL player salaries.

scholarly journals Using Machine Learning Methods to Identify Particle Types from Doppler Lidar Measurements in Iceland

2021 ◽  
Vol 13 (13) ◽  
pp. 2433
Author(s):  
Shu Yang ◽  
Fengchao Peng ◽  
Sibylle von Löwis ◽  
Guðrún Nína Petersen ◽  
David Christian Finger
Keyword(s):  
Machine Learning ◽  
Weather Conditions ◽  
Dust Storms ◽  
Machine Learning Algorithms ◽  
Lidar Data ◽  
Data Sets ◽  
Doppler Lidar ◽  
Lidar Measurements ◽  
Using Data ◽  
Filter Noise

Doppler lidars are used worldwide for wind monitoring and recently also for the detection of aerosols. Automatic algorithms that classify the lidar signals retrieved from lidar measurements are very useful for the users. In this study, we explore the value of machine learning to classify backscattered signals from Doppler lidars using data from Iceland. We combined supervised and unsupervised machine learning algorithms with conventional lidar data processing methods and trained two models to filter noise signals and classify Doppler lidar observations into different classes, including clouds, aerosols and rain. The results reveal a high accuracy for noise identification and aerosols and clouds classification. However, precipitation detection is underestimated. The method was tested on data sets from two instruments during different weather conditions, including three dust storms during the summer of 2019. Our results reveal that this method can provide an efficient, accurate and real-time classification of lidar measurements. Accordingly, we conclude that machine learning can open new opportunities for lidar data end-users, such as aviation safety operators, to monitor dust in the vicinity of airports.

scholarly journals Predicting and interpreting oxide glass properties by machine learning using large datasets

2021 ◽  
Author(s):  
Daniel R. Cassar ◽  
Saulo Martiello Mastelini ◽  
Tiago Botari ◽  
Edesio Alcobaça ◽  
André C.P. L.F. de Carvalho ◽  
...  
Keyword(s):  
Machine Learning ◽  
Large Datasets ◽  
Oxide Glass ◽  
Glass Properties

PODC 2020 Review

2021 ◽  
Vol 51 (4) ◽  
pp. 75-81
Author(s):  
Ahad Mirza Baig ◽  
Alkida Balliu ◽  
Peter Davies ◽  
Michal Dory
Keyword(s):  
Machine Learning ◽  
Distributed Computing ◽  
Keynote Speaker ◽  
Lively Discussion ◽  
Theoretical Understanding ◽  
New Directions ◽  
New Ideas ◽  
New Challenges ◽  
The Impact ◽  
Distributed Machine Learning

Rachid Guerraoui was the rst keynote speaker, and he got things o to a great start by discussing the broad relevance of the research done in our community relative to both industry and academia. He rst argued that, in some sense, the fact that distributed computing is so pervasive nowadays could end up sti ing progress in our community by inducing people to work on marginal problems, and becoming isolated. His rst suggestion was to try to understand and incorporate new ideas coming from applied elds into our research, and argued that this has been historically very successful. He illustrated this point via the distributed payment problem, which appears in the context of blockchains, in particular Bitcoin, but then turned out to be very theoretically interesting; furthermore, the theoretical understanding of the problem inspired new practical protocols. He then went further to discuss new directions in distributed computing, such as the COVID tracing problem, and new challenges in Byzantine-resilient distributed machine learning. Another source of innovation Rachid suggested was hardware innovations, which he illustrated with work studying the impact of RDMA-based primitives on fundamental problems in distributed computing. The talk concluded with a very lively discussion.

Sign in / Sign up

Export Citation Format

Share Document