Sports racing is attracting billions of audiences each year. It is powered and transformed by the latest data analysis technologies, from race car design, driving skill improvements to audience engagement on social me...
详细信息
ISBN:
(纸本)9781728127057
Sports racing is attracting billions of audiences each year. It is powered and transformed by the latest data analysis technologies, from race car design, driving skill improvements to audience engagement on social media. However, most of the data processing are off-line and retrospective analysis. The emerging real-time data analysis from the Internet of Things (IoT) result in fast data streams generated from distributed sensors. Applying advanced Machine Learning/Artificial Intelligence over such data streams to discover new information, predict future insights and make control decision is a crucial process. In this paper, we start by articulating racing car big data characteristics and present time-critical anomaly detection of the racing cars with the real-time sensors of cars and the tracks from actual racing events. We build a scalable system infrastructure based on neuro-morphic Hierarchical Temporal Memory Algorithm (HTM) algorithm and Storm stream processing engine. By courtesy of historical Indy500 racing logs, evaluation experiments on this prototype system demonstrate good performance in terms of anomaly detection accuracy and service level objective (SLO) of latency for a real-world streaming application.
distributed data-parallel algorithms aim to accelerate the training of deep neural networks by parallelizing the computation of large mini-batch gradient updates across multiple nodes. Approaches that synchronize node...
详细信息
ISBN:
(纸本)9781510886988
distributed data-parallel algorithms aim to accelerate the training of deep neural networks by parallelizing the computation of large mini-batch gradient updates across multiple nodes. Approaches that synchronize nodes using exact distributed averaging (e.g., via ALLREDUCE) are sensitive to stragglers and communication delays. The PUSH-SUM gossip algorithm is robust to these issues, but only performs approximate distributed averaging. This paper studies Stochastic Gradient Push (SGP), which combines Pus HS um with stochastic gradient updates. We prove that SGP converges to a stationary point of smooth, nonconvex objectives at the same sub-linear rate as SGD, and that all nodes achieve consensus. We empirically validate the performance of SGP on image classification (ResNet-50, ImageNet) and machine translation (Transformer, WMT'16 En-De) workloads.
The main aim of this article is the description of specialized software RoboSim for off-line programming and simulation of robotic systems developed at the University of Zilina during the last decade. It contains basi...
详细信息
ISBN:
(纸本)9783319974903;9783319974897
The main aim of this article is the description of specialized software RoboSim for off-line programming and simulation of robotic systems developed at the University of Zilina during the last decade. It contains basic information about the development process of this universal software for simulation of automated workplaces equipped with one or more robots with up to 6 degrees of freedom (DOFs). The latest version can be used as a universal platform for simulation of mechanisms with serial, parallel as well as hybrid kinematic structure. This flexibility can be considered as the main advantage of the RoboSim software. Its specific feature is that there are two different methods used for calculation of inverse kinematics: heuristic and vector method as well. The versatility, openness and access to the source code create the predisposition for its deployment under laboratory conditions for controlling robotic devices developed in authors' workplace within the last fifteen years.
Cloud computing is a spirited topic in this epoch where IOT introducing the modern lifestyle. These embrace cost-effectiveness, time savings and the actual arrangement of computing properties. Conversely, in Cloud Com...
详细信息
This paper investigates parallel random sampling from a potentially-unending data stream whose elements are revealed in a series of element sequences (minibatches). While sampling from a stream was extensively studied...
详细信息
ISBN:
(纸本)9783030294007;9783030293994
This paper investigates parallel random sampling from a potentially-unending data stream whose elements are revealed in a series of element sequences (minibatches). While sampling from a stream was extensively studied sequentially, not much has been explored in the parallel context, with prior parallel random-sampling algorithms focusing on the static batch model. We present parallel algorithms for minibatch-stream sampling in two settings: (1) sliding window, which draws samples from a prespecified number of most-recently observed elements, and (2) infinite window, which draws samples from all the elements received. Our algorithms are computationally and memory efficient: their work matches the fastest sequential counterpart, their parallel depth is small (polylogarithmic), and their memory usage matches the best known.
With the ongoing advances in the area of cloud computing, Internet of Things, Industry 4.0, and the increasing prevalence of cyber-physical systems and devices equipped with sensors, the amount of data generated every...
详细信息
ISBN:
(数字)9781728110998
ISBN:
(纸本)9781728111001
With the ongoing advances in the area of cloud computing, Internet of Things, Industry 4.0, and the increasing prevalence of cyber-physical systems and devices equipped with sensors, the amount of data generated every second is rising steadily. Thereby, the gathering of data and the creation of added value from this data is getting easier and easier. However, the increasing volume of data stored in the cloud leads to new challenges. Analytics software and scalable platforms are required to evaluate the data distributed all over the internet. But with distributed applications and large data sets to be handled, the network becomes a bottleneck. Therefore, in this work, we present an approach to automatically improve the deployment of such applications regarding the placement of data processing components dependent on the data flow of the application. To show the practical feasibility of our approach, we implemented a prototype based on the open-source ecosystem OpenTOSCA. Moreover, we evaluated our prototype using various scenarios.
The role of the Internet has significantly changed due to the development in communication technologies. Nowadays, billions of people and physical devices are connected via Internet. In near future, storage and comput...
详细信息
ISBN:
(数字)9781728144528
ISBN:
(纸本)9781728144535
The role of the Internet has significantly changed due to the development in communication technologies. Nowadays, billions of people and physical devices are connected via Internet. In near future, storage and computational services will be more pervasive and distributed. Even in recent times, we can see that people, machines, objects, and platforms are connected with wireless or wired sensors. Considering such an internet setting with billions of connected devices, in this paper, we present a study on the background, state-of-the-art, growth, key players, applications, challenges, and future opportunities in the area of Internet of Things (IoT). The Kingdom of Saudi Arabia's IoT and M2M (Machine to Machine) communication market is estimated to grow to $16.01 billion by 2019 from $4.88 billion in 2014[26]. We also discuss general aspects and issues of IoT and explore the implication of all these in a developing country's setting taking the case of Saudi Arabia.
Computerized Decision Support Systems (CDSSs) can be a vital component in a medical setting to foster the use of evidence based medicine and minimize malpractice. Surprisingly, the adoption rate of CDSSs has remained ...
详细信息
ISBN:
(数字)9783030110512
ISBN:
(纸本)9783030110512;9783030110505
Computerized Decision Support Systems (CDSSs) can be a vital component in a medical setting to foster the use of evidence based medicine and minimize malpractice. Surprisingly, the adoption rate of CDSSs has remained far below expectations and there has been little impact of CDSSs on measurable health outcomes. We outline the components of clinical work environments in order to elaborate on the driving forces for technology acceptance. The components address issues such as high involvement work systems and distributed intelligence. The reflection of these characteristics leads us to the conclusion that the perceived usefulness of a technology and its ease of use is a necessary but not a sufficient condition. Technological acceptance primarily depends on the perceived mindfulness of individual intelligence in workplace design.
In the last two decades deep learning has attracted a lot of attention internationally, solving problems in different application domains and achieving results beyond expectations. For example it has been applied in b...
详细信息
A grid is an infrastructure to meet the ongoing demands of science and engineering (Foster et al. in Int J High Perform Comput Appl 13(3):200–222, 2001) [1]. In the midst of the 1980s and the 1990s, researchers obser...
详细信息
暂无评论