The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Explosive naval mines pose a threat to ocean and sea faring vessels, both military and civilian. This work applies deep neural network (DNN) methods to the problem of detecting minelike objects (MLO) on the seafloor in side-scan sonar imagery. We explored how the DNN depth, memory requirements, calculation requirements, and training data distribution affect detection efficacy. A visualization technique...
Stochastic gradient descent (SGD) is one of the most popular numerical algorithms used in machine learning and other domains. Since this is likely to continue for the foreseeable future, it is important to study techniques that can make it run fast on parallel hardware. In this paper, we provide the first analysis of a technique called BUCKWILD! that uses both asynchronous execution and low-precision...
The limitation of bandwidth resource in a wireless network has driven a large amount of work in resource scheduling to better utilize the available bandwidth. Most of these work aim to maximize the throughput by considering a uniform user distribution across the cellular network. In reality, users may be distributed non-uniformly. This work studies the effects of nonuniform user distribution on throughput...
Traffic engineering at network edges is challenging given the latency-sensitive nature of all applications that need to be supported. End-to-end delay estimation and forecasts were essential traffic engineering tools even before the mobile edge computing paradigm pushed the cloud closer to the end user. In this paper, we model the path selection problem for edge traffic engineering using a risk minimization...
Here we study the shape, size, and merging pattern of the area following the toll barrier, from the five aspects including the accident prevention, throughput, cost, service time and passing capacity. We build the corresponding model of the new single-in and double_out toll station to measure the optimal solution of the toll plaza on the basis of a series of methods such as the factor analysis, principal...
A key challenge in software systems that are exposed to runtime variabilities, such as workload fluctuations and service degradation, is to continuously meet performance requirements. In this paper we present an approach that allows performance self-adaptation using a system model based on queuing networks (QNs), a well-assessed formalism for software performance engineering. Software engineers can...
General queueing modeling method, Stochastic Timed Automation, is employed to model the Semiconductor Wafer Fabrication System because of its flexibility and fidelity. The machine allocation is formulated as a stochastic integer programming problem with the objective to optimize the throughput of the Semiconductor Wafer Fabrication System. And we propose an Optimal Computing Budget Allocation-based...
Volume Diagnosis is a proven methodology to significantly improve the yield enhancement rates. One of the key factors of success to this methodology is being able to perform diagnosis on hundreds to thousands of failing dies using a limited amount of computational resource in a tractable time. This paper presents a new Multiple Device Diagnosis (MDD) system to significantly improve the throughput...
As the US Department of Energy (DOE) invests in exascale computing, scalable performance modeling of physics codes on CPUs remains a hard challenge in computational codesign due to advanced design features of processors such as the memory hierarchy, instruction pipelining, and speculative execution. Reuse distance is a powerful (but unscalable) characteristic that helps to predict cache hit-rates...
Recent research interest in cellular communication systems focuses on the design of the radio access networks (RAN) considering Transmission Control Protocol (TCP) behavior. However, less attention has been paid to the specific transmission method of TCP ACK. The authors have been studying methods including TCP ACK filtering that can well work with the link layer protocols in LTE-Advanced Pro (LTE-A...
Memory price will continue dropping in the next few years according to Gartner. Such trend renders it affordable for in-memory key-value stores (IMKVs) to maintain redundant memory-resident copies of each key-value pair to provision enhanced reliability and high availability services. Though contemporary IMKVs have reached unprecedented performance, delivering single-digit microsecond-scale latency...
Cloud-based services are increasingly popular for big data analytics due to the flexibility, scalability, and cost-effectiveness of provisioning elastic resources on-demand. However, data analytics-as-a-service suffers from the overheads of data movement between compute and storage clusters, due to their decoupled architecture in existing cloud infrastructure. In this work, we propose a novel approach...
HPC (high-performance computing) applications usually show bursty I/O behaviors. In order to expedite the applications, permanent storage systems are usually provisioned to serve such I/O bursts. Approaching the era of exascale computing, non-volatile RAM is introduced as burst buffers, to absorb the bursty bulk data and relax the I/O provisioning requirement of the permanent storage systems. However,...
Increasingly, the application providers are using a separate fault management system that offers out-of-the-box monitoring and alarms support for application instances. A fault management system is usually distributed in nature and consists of a set of management components that does both fault detection and can trigger actions, for example, automatic restart of monitored components. Such a distributed...
In this paper we study how to estimate the back-off rates in an idealized CSMA network consisting of n links to achieve a given throughput vector using free energy approximations. More specifically, we introduce the class of region-based free energy approximations with clique belief and present a closed form expression for the back-off rates based on the zero gradient points of the free energy approximation...
Throughput performance, an important metric for interconnection networks, is often quantified by the aggregate throughput for a set of representative traffic patterns. A number of models have been developed to estimate the aggregate throughput for a given traffic pattern on an interconnection network. Since all of the models predict the same property of interconnection networks, ideally, they should...
This work aims at understanding and evaluating the impact of using different path loss models in the optimization trade-off of small cell (SC) networks. In LTE-A, the more realistic propagation models are the more efficient the radio and network optimization becomes. In this work we compare four urban path loss models: the urban/vehicular and pedestrian test environment from the ITU-R M. 1255 Report...
In cognitive radio (CR), changing the primary user's status diminishes the achievable throughput for secondary user. Traffic of primary user is inversely proportional to throughput of secondary user. Increasing sensing time increases the primary user protection, but has a negative effect on the throughput of secondary user. Solving the dilemma of sensing-throughput tradeoff is to find the optimal...
Satellite can provide remote sensing data for disaster monitoring, and various sensors are generating huge volumes of remote sensing data for disaster management. It is urgent to store and process massive data acquired by satellite as fast as possible. A flexible and rapid service platform can realize integrated services from data acquisition, data production and product visualization. This article...
Pattern matching is an important class of problemsrelated to graphs. It is a fundamental problem for manyapplications and has been extensively studied in literature. Withthe advent of huge graphs, the challenges in this domain haveincreased manifold. Consequently a lot of recent research has ledto new architectures and approaches for optimized solutions tothe pattern matching problem. A vast majority...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.