s2p: Provenance Research for Stream Processing System

The main purpose of our provenance research for DSP (distributed stream processing) systems is to analyze abnormal results. Provenance for these systems is not nontrivial because of the ephemerality of stream data and instant data processing mode in modern DSP systems. Challenges include but are not limited to an optimization solution for avoiding excessive runtime overhead, reducing provenance-related data storage, and providing it in an easy-to-use fashion. Without any prior knowledge about which kinds of data may finally lead to the abnormal, we have to track all transformations in detail, which potentially causes hard system burden. This paper proposes s2p (Stream Process Provenance), which mainly consists of online provenance and offline provenance, to provide fine- and coarse-grained provenance in different precision. We base our design of s2p on the fact that, for a mature online DSP system, the abnormal results are rare, and the results that require a detailed analysis are even rarer. We also consider state transition in our provenance explanation. We implement s2p on Apache Flink named as s2p-flink and conduct three experiments to evaluate its scalability, efficiency, and overhead from end-to-end cost, throughput, and space overhead. Our evaluation shows that s2p-flink incurs a 13% to 32% cost overhead, 11% to 24% decline in throughput, and few additional space costs in the online provenance phase. Experiments also demonstrates the s2p-flink can scale well. A case study is presented to demonstrate the feasibility of the whole s2p solution.

УСКОРЕНИЕ ОБРАБОТКИ СИГНАЛОВ В SIMULINK С ИСПОЛЬЗОВАНИЕМ ПОТОКА ДАННЫХ

Статья посвящена DSP System Toolbox, которые предоставляет алгоритмы, приложения и дисплеи для проектирования, симуляции и анализа систем обработки сигналов в MATLAB и Simulink, типам параллелизма.

Excess mortality in Wuhan city and other parts of China during the three months of the covid-19 outbreak: findings from nationwide mortality registries

Objective To assess excess all cause and cause specific mortality during the three months (1 January to 31 March 2020) of the coronavirus disease 2019 (covid-19) outbreak in Wuhan city and other parts of China. Design Nationwide mortality registries. Setting 605 urban districts and rural counties in China’s nationally representative Disease Surveillance Point (DSP) system. Participants More than 300 million people of all ages. Main outcome measures Observed overall and weekly mortality rates from all cause and cause specific diseases for three months (1 January to 31 March 2020) of the covid-19 outbreak compared with the predicted (or mean rates for 2015-19) in different areas to yield rate ratio. Results The DSP system recorded 580 819 deaths from January to March 2020. In Wuhan DSP districts (n=3), the observed total mortality rate was 56% (rate ratio 1.56, 95% confidence interval 1.33 to 1.87) higher than the predicted rate (1147 v 735 per 100 000), chiefly as a result of an eightfold increase in deaths from pneumonia (n=1682; 275 v 33 per 100 000; 8.32, 5.19 to 17.02), mainly covid-19 related, but a more modest increase in deaths from certain other diseases, including cardiovascular disease (n=2347; 408 v 316 per 100 000; 1.29, 1.05 to 1.65) and diabetes (n=262; 46 v 25 per 100 000; 1.83, 1.08 to 4.37). In Wuhan city (n=13 districts), 5954 additional (4573 pneumonia) deaths occurred in 2020 compared with 2019, with excess risks greater in central than in suburban districts (50% v 15%). In other parts of Hubei province (n=19 DSP areas), the observed mortality rates from pneumonia and chronic respiratory diseases were non-significantly 28% and 23% lower than the predicted rates, despite excess deaths from covid-19 related pneumonia. Outside Hubei (n=583 DSP areas), the observed total mortality rate was non-significantly lower than the predicted rate (675 v 715 per 100 000), with significantly lower death rates from pneumonia (0.53, 0.46 to 0.63), chronic respiratory diseases (0.82, 0.71 to 0.96), and road traffic incidents (0.77, 0.68 to 0.88). Conclusions Except in Wuhan, no increase in overall mortality was found during the three months of the covid-19 outbreak in other parts of China. The lower death rates from certain non-covid-19 related diseases might be attributable to the associated behaviour changes during lockdown.

An Efficient Fixed-Point Multiplier Based on CORDIC Algorithm

Fixed-point multiplication is an important operation that is frequently used in many digital signal processing (DSP) applications. The operation is computationally intense and very often the performance of multiplier determines the overall performance of DSP system. Evidently, a wide range of approaches have been proposed for efficient implementation of fixed-point multipliers on different hardware platforms. In this paper, we use Coordinate Rotation DIgital Computer (CORDIC) algorithm to perform fixed-point multiplication operation. The motivation for our approach is based on the fact that CORDIC is a hardware-efficient algorithm, wherein accuracy can be traded-off for performance. Our implementation targets field programmable gate arrays (FPGAs) and focuses on exploiting the underlying general and specialized fabric to the fullest. Performance comparisons against various traditional and recent approaches show that a substantial improvement is achievable by using CORDIC-based multipliers. We have also implemented a recently proposed convolution architecture using CORDIC-based multipliers. The results show that a proper choice of CORDIC architecture can result in an improvement of performance parameters like resource utilization, throughput and dynamic power. This, however, is achieved in lieu of a small cost in accuracy. Our analysis of an 8-stage CORDIC multiplier reports a mean absolute percentage error (MAPE) of 6.032 — a factor that reduces exponentially with increasing number of stages.

Laser-based Thickness Control in a Double-Side Polishing System for Silicon Wafers

Thickness control is a critical process of automated polishing of large and thin Si wafers in the semiconductor industry. In this paper, an elaborate double-side polishing (DSP) system is demonstrated, which has a polishing unit with feedback control of wafer thickness based on the scan data of a laser probe. Firstly, the mechanical structure, as well as the signal transmission and control of the DSP system, are discussed, in which the thickness feedback control is emphasized. Then, the precise positioning of the laser probe is explored to obtain the continuous and valid scan data of the wafer thickness. After that, a B-spline model is applied for the characterization of the wafer thickness function to provide the thickness control system with credible thickness deviation information. Finally, experiments of wafer-thickness evaluation and control are conducted on the presented DSP system. With the advisable number of control points in B-spline fitting, the thickness variation can be effectively controlled in wafer polishing with the DSP system, according to the experimental results of curve fitting and the statistical analysis of the experimental data.

X-ray study of the double source plane gravitational lens system Eye of Horus observed with XMM–Newton

ABSTRACT A double source plane (DSP) system is a precious probe for the density profile of distant galaxies and cosmological parameters. However, these measurements could be affected by the surrounding environment of the lens galaxy. Thus, it is important to evaluate the cluster-scale mass for detailed mass modelling. We observed the Eye of Horus, a DSP system discovered by the Hyper Suprime-Cam Subaru Strategic Survey (HSC–SSP), with XMM–Newton. We detected two X-ray extended emissions, originating from two clusters, one centred at the Eye of Horus, and the other located ∼100 arcsec north-east to the Eye of Horus. We determined the dynamical mass assuming hydrostatic equilibrium, and evaluated their contributions to the lens mass interior of the Einstein radius. The contribution of the former cluster is $1.1^{+1.2}_{-0.5}\times 10^{12}\, \mathrm{M}_{\odot }$, which is $21\!-\!76{{\ \rm per\ cent}}$ of the total mass within the Einstein radius. The discrepancy is likely due to the complex gravitational structure along the line of sight. On the other hand, the contribution of the latter cluster is only $\sim 2{{\ \rm per\ cent}}$ on the Eye of Horus. Therefore, the influence associated with this cluster can be ignored.

Implementation of Audio CODEC with a Novel Design Methodology

Currently in the real-time audio applications fixed point CODEC is being used. But the major disadvantage of such CODEC is the speed and accuracy. Because , as the DSP systems cannot be operated with real-time signal ‘t’, but they can be operated with the discrete time ‘n’ , the real-time analog signal x(t) is to be converted into discrete time signal x(n) by the analog to digital convert (ADC). The most widely used ADC in the signal processing environment is sigma-delta ADC. But, it can operate with the maximum speed of 1MHz. The DSP processor can give several times more speed than sigma-delta ADC. Hence, the speed of DSP system is being limited by sigma-delta ADC, even though the DSP system has the capability to operate with great speed. Similarly, the accuracy is being missed because the floating point samples are converted into fixed point to get the compatibility with fixed point DSP processor. To eliminate these two bottlenecks the novel design methodology has been proposed in which the ADC and DAC have been eliminated and the system is developed by the 16 bit floating point.

Binary Template Matching for Morphological Dilation Enhancement in Navigation Radar Imaging

Radar imaging system is strongly influenced by other supporting systems. There is a motor system that provides angular information to the display system, and Digital Signal Processing (DSP) system that provides the main information for radar imaging. The new approach, we substitute a DC servo motor with a DC stepper motor as radar antenna rotator in our navigation radar system development. Different from the use of servo motors that can provide angle movements smoothly, the new motor system provides angle information of 0.56 degrees in every step, results in empty pixel gaps in every 0.56 degrees in radar Plan Position Indicator (PPI) image. The width of the empty pixel gaps becomes wider when the cell array of raw data is increasing regarding the image plotting process. In this paper, we proposed a new morphological dilation method to the radar raw data based on binary template matching to accommodate the various width of empty pixel gaps before the radar raw data are plotted into the radar PPI image. By this method, the morphological dilation will only be applied to the raw data that meet the same criteria as the binary template. Otherwise, the raw data will be left as they are. The result shows that there is 150.52% pixel data addition in the empty pixel gaps from the original image, and 48.44% increase of the morphological dilation without binary template matching method.