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.
In this work, we propose an efficient architecture for the hardware realization of deep neural networks on reconfigurable computing platforms like FPGA. The proposed neural network architecture employs only one single physical computing layer to perform the whole computational fabric of fully-connected feedforward deep neural networks with customizable number of layers, number of neurons per layer...
Nowadays, the amount of small devices performing any kind of Digital Signal Processing (DSP) has increased drastically. On the other hand, the limited energy available to such battery-powered devices is a real problem. In DSP applications, one of the most important operations is the Finite Impulse Response (FIR) filter computation. The main FIR filter characteristics are the linear phase and feed...
This paper proposes an improved KNN algorithm to overcome the class overlapping problem when the class distribution is skewed. Different from the conventional KNN algorithm, it not only finds out the k nearest neighbors of each sample (even the test object itself) in the training dataset, but also the neighbors of the unknown test object. Then the validity value of a data point is computed based on...
Analog-to-Digital Converters (ADCs) are becoming increasingly common to be involved in most systems in Integrated Circuits (ICs). Thanks to the rapid growth of modern semiconductor technology, the performance of the data converters becomes better and better. One of the difficulties being faced is to be able to accurately and cost-effectively test the continually better performance ADCs. The conventional...
Stencil computations represent a highly recurrent class of algorithms in various high performance computing scenarios. The Streaming Stencil Time-step (SST) architecture is a recent implementation of stencil computations on Field Programmable Gate Array (FPGA). In this paper, we propose an automated framework for SST-based architectures capable of achieving the maximum performance level for a given...
Emerging resistive non-volatile memory technology (RRAM) is fast gaining importance as a possible successor of Flash memory. Very few experimental studies exist on emerging RRAM that analyze the impact of soft-techniques or purely algorithm driven performance enhancement for such memory devices. In this paper, we study in detail four different soft techniques optimized for bit-flip minimization, mainly...
High performance computing applications are far more difficult to write, therefore, practitioners expect a well-tuned software to last long and provide optimized performance even when the hardware is upgraded. It may also be necessary to write software using sufficient abstraction over the hardware so that it is capable of running on heterogeneous architecture. Therefore, it is required to have a...
Parity declustering is widely deployed in erasure coded storage systems so as to provide fast recovery and high data availability. However, to perform scaling on such RAIDs, it is necessary to preserve the parity declustered data layout so as to guarantee the RAID performance after scaling. Unfortunately, existing scaling algorithms fail to achieve this goal so they can not be applied for scaling...
With the development of cloud computing, disk arrays tolerating triple disk failures (3DFTs) are receiving more attention nowadays because they can provide high data reliability with low monetary cost. However, a challenging issue in these arrays is how to efficiently reconstruct the lost data, especially for partial stripe errors (e.g., sector and chunk errors). It is one of the most significant...
Anomaly detection (outlier) using simulation helps us analyze the anomaly instances from big data source. As the hasty explosion of today's data stream, outlier detection technique will be an analytical tool to be employed for evaluating massive unstructured datasets. In order to speed-up the processing time to handle enormous datasets, this research will conduct experiments of advanced distant-based...
Target tracking is an important part of many applications in computer vision. With continuous researching and developing, more and more advanced tracking algorithms have been put forward. Therefore, a benchmark and dataset used to evaluate the most advanced tracking algorithms are needed. One of the most widely used benchmarks is Online Tracking Benchmark (OTB). This benchmark has a clear statement...
Electrocardiography (ECG) devices are considered essential medical tools for detecting and preventing cardiovascular diseases. These devices are used to obtain information about the structure and function of the human heart. Given the various medical uses of the information from ECG devices, it is essential that these devices provide accurate information about the heart in a precise manner. Although...
Since the introduction of finite control set model predictive control (FCS-MPC) in power electronics the algorithm has been missing an important aspect that would speed up its implementation in industry: a simple method to verify the algorithm performance. This paper proposes to use a statistical model checking (SMC) method for performance evaluation of the algorithm applied to power electronics converters...
Quantum cascade lasers (QCLs) are compact and powerful sources that cover a wide spectral range from infrared to terahertz (THz) radiation. The emission characteristics of QCLs depend on design parameters such as layer thickness, material composition and doping. Therefore, the material system has to be chosen accurately. Most commonly used material systems for THz QCLs are GaAs/AlGaAs and InGaAs/InAlAs...
In the data migration study, in order to make migration efficient, accurately measuring the value of data is useful. Aiming at the problem that the existing data value measure method can not describe the true value of data accurately, this paper presents a new evaluation method of data value. The algorithm not only considers the size of the data, access time, file content, data read and write frequency...
Various systems have natural groupings. For instance in large scale distributed system, we can have groups of virtual and/or physical devices. A system can also have groups of time series datasets collected at different time intervals. Such groups are usually characterized by multidimensional metrics (features) set. Clustering such groups using their multidimensional datasets has various applications,...
Motion estimation consumes the major part of time and power in both video compression standards — HEVC and H.264. This paper presents a Fast Motion Estimation algorithm, which targets Full Search quality even at HD resolution. It is an enhancement of existing Fast Motion Estimation algorithms with the main purpose of reducing cost and power consumption for devices performing Motion Estimation while...
Getting confidence regions for parameter estimates obtained from data collected by a wireless sensor network (WSN) is very important to assess the performance of the estimator. The sign perturbed sums (SPS) approach has been proposed recently to defined exact confidence regions in a centralized setting even if only few measurements are available. SPS may be distributed to get confidence regions at...
In this article known methods of design fieldbus network in distributed control system (DCS) are analyzed and the synthesis of new algorithm is presented. Building a network is made in the condition of strict restraints on cost, as well as probabilistic and temporal characteristics of the information exchange. The analysis is conducted for fieldbus networks, based on methods of random multiple nodes...
MPI collective operations are implemented using a variety of algorithms which define different communication patterns between the ranks involved in the operation. The performance of these algorithms in multi-core clusters highly depends on the mapping of the ranks to the system processors due to the uneven capabilities of shared memory and network channels. The hierarchical design of these algorithms...
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.