During the years spent developing the GraphBLAS Template Library and then the C API Specification (in that order), I spent time developing algorithms using the interfaces to try and develop a better understanding (thr...
详细信息
ISBN:
(纸本)9781538655559
During the years spent developing the GraphBLAS Template Library and then the C API Specification (in that order), I spent time developing algorithms using the interfaces to try and develop a better understanding (through this experimentation) of what could be achieved with the primitives. In this talk I will give a summary of what has been implemented, some lessons learned, and some patterns that have repeated in a number of instances.
Floating point arithmetic, as specified in the IEEE standard, is used extensively in programs for science and engineering. This use is expanding rapidly into other domains, for example with the growing application of ...
详细信息
ISBN:
(纸本)9781538643686
Floating point arithmetic, as specified in the IEEE standard, is used extensively in programs for science and engineering. This use is expanding rapidly into other domains, for example with the growing application of machine learning everywhere. While floating point arithmetic often appears to be arithmetic using real numbers, or at least numbers in scientific notation, it actually has a wide range of gotchas. Compiler and hardware implementations of floating point inject additional surprises. This complexity is only increasing as different levels of precision are becoming more common and there are even proposals to automatically reduce program precision (reducing power/energy and increasing performance) when results are deemed "good enough." Are software developers who depend on floating point aware of these issues? Do they understand how floating point can bite them? To find out, we conducted an anonymous study of different groups from academia, national labs, and industry. The participants in our sample did only slightly better than chance in correctly identifying key unusual behaviors of the floating point standard, and poorly understood which compiler and architectural optimizations were nonstandard. These surprising results and others strongly suggest caution in the face of the expanding complexity and use of floating point arithmetic.
Biological design principles can potentially change the way we study, engineer, maintain, and develop large dynamic softwaresystems. For example, computer programmers like to think of software as the product of intel...
ISBN:
(纸本)9781450357852
Biological design principles can potentially change the way we study, engineer, maintain, and develop large dynamic softwaresystems. For example, computer programmers like to think of software as the product of intelligent design, carefully crafted to meet well-specified goals. In reality, large softwaresystems evolve inadvertently through the actions of many individual programmers, often leading to unanticipated consequences. Because software is subject to constraints similar to those faced by evolving biological systems, we have much to gain by viewing software through the lens of biology. The talk will highlight how abstractions of biological processes can lead to new computational algorithms and engineering principles. Specifically, it will show how the biological concepts of Darwinian evolution and immunology can be applied to problems such as repairing software bugs and cybersecurity.
With the emergence of cloud computing and big data, migrating legacy systems to a cloud platform has become a trend. To make full use of the parallel advantage of cloud computing, it is necessary to refactor the legac...
详细信息
ISBN:
(纸本)9781728111414
With the emergence of cloud computing and big data, migrating legacy systems to a cloud platform has become a trend. To make full use of the parallel advantage of cloud computing, it is necessary to refactor the legacy code according to the programming model of cloud computing. Before that, the parallelizability analysis is the first thing to do. In this paper, an approach is proposed for the distributedparallelizability analysis of legacy code, which is based on the analysis of dependency between loop iterations. According to the categories of the traditional dependency, the dependency between loop iterations is divided into three types, and the judgment rules of the dependency between loop iterations are proposed. Then a distributedparallelizability Analysis Tool (DPAT) based on Abstract Syntax Tree (AST) was developed to identify and annotate the parallelizable loops. Experimental results show that the approach can effectively identify the parallelizable code fragments, which will be the target objects of refactoring. In contrast to the existing approaches, our method can identify parallelizability between loop iterations and not limit the type of the loop.
Intrusion detection is an effective measure to prevent host and network attacks. The use of an intrusion detection system makes up for the shortcomings of traditional firewall technology, signature authentication tech...
详细信息
ISBN:
(纸本)9781728152103
Intrusion detection is an effective measure to prevent host and network attacks. The use of an intrusion detection system makes up for the shortcomings of traditional firewall technology, signature authentication technology, and access control technology in security protection. However, due to the imbalance of the distribution of intrusion detection data samples, the mutual redundancy between sample features seriously affects the accuracy and efficiency of specific attack detection. In this paper, a proposal was forward, the appropriate feature subsets are selected respectively based on mutual information and the firefly algorithm, and then proposed a feature selection strategy combining two feature subsets. Experiment outcomes show that the accuracy and efficiency of detection are improved by using the best feature set, compared to the use of all features.
This paper designs and develops an Environmental Data News Generation (EDNG) system of Internet of things data acquisition and generation that can automatically collect data such as environmental temperature, humidity...
This paper designs and develops an Environmental Data News Generation (EDNG) system of Internet of things data acquisition and generation that can automatically collect data such as environmental temperature, humidity and light intensity in a region and automate broadcast by data news for healthcare. The system is based on digital data collection, Internet of things, embedded development and other technologies. Through designing hardware and software such as the design of networking data acquisition devices, the establishment of cloud forwarding servers, the development of terminal WeChat mini-programs and data news acquisition systems, the problem of automatic data collection, fusion generation and accurate and efficient reporting of regional environmental data news is solved. At the same time, through the research of regional environmental data news gathering and generation technology, the functions of automation of environmental data collection and real evolution of news broadcast were realized. The accuracy of data acquisition and the speed of news reporting are improved, and an effective strategy is provided for the automatic generation of other data news.
Recent surveys about autonomous vehicles show that the public is concerned about the safety consequences of system or equipment failures and the vehicles' reactions to unexpected situations. We believe that inform...
详细信息
ISBN:
(纸本)9781728152103
Recent surveys about autonomous vehicles show that the public is concerned about the safety consequences of system or equipment failures and the vehicles' reactions to unexpected situations. We believe that informing about the technology and quality, e.g., safety and reliability, of autonomous vehicles is paramount to improving public expectations, perception and acceptance. In this paper, we report on the design of an interactive exhibit to illustrate (1) basic technologies employed in autonomous vehicles, i.e., sensors and object classification; and (2) basic principles for ensuring their quality, i.e., employing software testing and simulations. We subsequently report on a public engagement event involving this exhibit at the Royal Society Summer Science Exhibition 2019 in the exhibit titled "Trusted Autonomous Vehicles". We describe the process of designing and developing the artefacts used in our exhibit, the theoretical background associated to them, the design of our stand, and the lessons learned. The activities and findings of this study can be used by other educators and researchers interested in promoting trust in autonomous vehicles among the general public.
Due to the rapid increase in the use of and advancement of social media platforms, the amount of data available on the internet is increasing. The available information on the internet can be used to gain insights abo...
详细信息
ISBN:
(纸本)9781728152103
Due to the rapid increase in the use of and advancement of social media platforms, the amount of data available on the internet is increasing. The available information on the internet can be used to gain insights about searching trends and public interests. The advancements in machine learning and deep learning techniques drastically improved data analytics and processing solutions for social media and infotainment industry. It is no doubt that the majority of regular commuter encounters traffic congestion daily. There is a growing number of population in Metropolitans. This leads to higher population density rates and traditional methods for collecting traffic information using physical sensors are expensive, however, by using social media tools information regarding traffic jam, road and traffic congestion can be improved. In this paper, we analyze traffic congestion using Twitter data (tweets) in real-time. The proposed model extracts traffic-related tweets from Twitter and classifies the extracted information for traffic commute estimation road. In this study, tweets from Los Angeles, USA are taken into consideration as an analysis example. A machine learning classifier and a deep learning classier are used to classify traffic information. The model was trained to collect tweets containing the word 'traffic' in a real-time environment.
parallel and distributed computing have enabled development of much more scalable software. However, developing concurrent software requires the programmer to be aware of non-determinism, data races, and deadlocks. MP...
详细信息
ISBN:
(纸本)9781538609415
parallel and distributed computing have enabled development of much more scalable software. However, developing concurrent software requires the programmer to be aware of non-determinism, data races, and deadlocks. MPI (message passing interface) is a popular standard for writing message-oriented distributed applications. Some messages in MPI systems can be processed by one of the many machines and in many possible orders. This non-determinism can affect the result of an MPI application. The alternate results may or may not be correct. To verify MPI applications, we need to check all these possible orderings and use an application specific oracle to decide if these orderings give correct output. MPJ Express is an open source Java implementation of the MPI standard. Model checking of MPI Java programs is a challenging task due to their parallel nature. We developed a Java based model of MPJ Express, where processes are modeled as threads, and which can run unmodified MPI Java programs on a single system. This model enabled us to adapt the Java PathFinder explicit state software model checker (JPF) using a custom listener to verify our model running real MPI Java programs. The evaluation of our approach shows that model checking reveals incorrect system behavior that results in very intricate message orderings.
To the present day, a multitude of studies aims to understand how the Central Nervous System (CNS) translates neural pulses to muscle motor tasks, through the analysis of surface EMG (sEMG) recordings. One of the most...
详细信息
ISBN:
(纸本)9780769561493
To the present day, a multitude of studies aims to understand how the Central Nervous System (CNS) translates neural pulses to muscle motor tasks, through the analysis of surface EMG (sEMG) recordings. One of the most considerable methods applies the Non-Negative Matrix Factorization (NMF) to data recorded from sEMG electrodes, to extract coordinated motor patterns, the so-called muscle synergies, which hypothesize a modular control of the muscles by the CNS. The application of NMF could lead to novel applications in muscular rehabilitation or advanced prosthesis motor control. However, its application is still restricted to research laboratories, because the complexity of the NMF algorithm does not allow an efficient implementation on embedded systems, such as portable or wearable devices. This paper presents a FPGA-based hardware acceleration of a NMF algorithm, the Projected Gradient Alternating Least Square (ALS-PG), on a Xilinx Zynq7000 System-on-Chip (SoC) development board. In particular, we propose a case study for the pre-processing of sEMG in a hand prosthesis control system, where the NMF is subject to realtime processing constraints. Preliminary hardware optimizations produced a overall speed-up of 2.92x of the algorithm (23.9x considering only the accelerated sections) compared to the software implementation executed on the board ARM core. The real-time constraint could not be met because the entire process is slower than a standard CPU implementation (6.14x worse), nevertheless, the overall system shown a promising increase in the power efficiency of 1.65x.
暂无评论