The solid-phase extraction using Pd-Al2O3 as the stationary phase was employed to pre-separate the sulfur compounds in straight-run diesel. The isolating effect was evaluated quantitatively by gas chromatography with ...The solid-phase extraction using Pd-Al2O3 as the stationary phase was employed to pre-separate the sulfur compounds in straight-run diesel. The isolating effect was evaluated quantitatively by gas chromatography with a sulfur chemiluminescence detector to harvest a satisfactory result. The identification of the structure of sulfur compounds by comprehensive two-dimensional gas chromatography coupled with the time-of-flight mass spectrometry indicated that cyclo-sulfides, benzothiophenes, dibenzothiophenes, dihydro-benzothiophenes and tetrahydro-dibenzothiophenes were included in straightrun diesel obtained from the Arab medium crude(AM). A total of 259 individual compounds were detected and their molecular structures were identified. The analytical method was approved as an effective way to characterize the composition of sulfur compounds, which reduced the interference of other compounds, facilitated the data presentation and provided more detailed information about molecular composition of sulfur compounds.展开更多
Despite the rapid development of mobile and embedded hardware, directly executing computationexpensive and storage-intensive deep learning algorithms on these devices’ local side remains constrained for sensory data ...Despite the rapid development of mobile and embedded hardware, directly executing computationexpensive and storage-intensive deep learning algorithms on these devices’ local side remains constrained for sensory data analysis. In this paper, we first summarize the layer compression techniques for the state-of-theart deep learning model from three categories: weight factorization and pruning, convolution decomposition, and special layer architecture designing. For each category of layer compression techniques, we quantify their storage and computation tunable by layer compression techniques and discuss their practical challenges and possible improvements. Then, we implement Android projects using TensorFlow Mobile to test these 10 compression methods and compare their practical performances in terms of accuracy, parameter size, intermediate feature size,computation, processing latency, and energy consumption. To further discuss their advantages and bottlenecks,we test their performance over four standard recognition tasks on six resource-constrained Android smartphones.Finally, we survey two types of run-time Neural Network(NN) compression techniques which are orthogonal with the layer compression techniques, run-time resource management and cost optimization with special NN architecture,which are orthogonal with the layer compression techniques.展开更多
3-D Networks-on-Chip （NoC） emerge as a potent solution to address both the interconnection and design complexity problems facing future Multiprocessor System-on-Chips （MPSoCs）. Effective run-time mapping on such 3...3-D Networks-on-Chip （NoC） emerge as a potent solution to address both the interconnection and design complexity problems facing future Multiprocessor System-on-Chips （MPSoCs）. Effective run-time mapping on such 3-D NoC-based MPSoCs can be quite challenging, as the arrival order and task graphs of the target applications are typically not known a priori, which can be further complicated by stringent energy requirements for NoC systems. This paper thus presents an energy-aware run-time incremental mapping algorithm （ERIM） for 3-D NoC which can minimize the energy consumption due to the data communications among processor cores, while reducing the fragmentation effect on the incoming applications to be mapped, and simultaneously satisfying the thermal constraints imposed on each incoming application. Specifically, incoming applications are mapped to cuboid tile regions for lower energy consumption of communication and the minimal routing. Fragment tiles due to system fragmentation can be gleaned for better resource utilization. Extensive experiments have been conducted to evaluate the performance of the proposed algorithm ERIM, and the results are compared against the optimal mapping algorithm （branch-and-bound） and two heuristic algorithms （TB and TL）. The experiments show that ERIM outperforms TB and TL methods with significant energy saving （more than 10%）, much reduced average response time, and improved system utilization.展开更多
In large-scale distributed simulation, thousands of objects keep moving and interacting in a virtual environment, which produces a mass of messages. High level architecture （HLA） is the prevailing standard for model...In large-scale distributed simulation, thousands of objects keep moving and interacting in a virtual environment, which produces a mass of messages. High level architecture （HLA） is the prevailing standard for modeling and simulation. It specifies two publish-subscribe mechanisms for message filtering： class-based and value-based. However, the two mechanisms can only judge whether a message is relevant to a subscriber or not. Lacking of the ability to evaluate the relevance, all relevant messages are delivered with the same priority even when congestion occurs. It significantly limits the scalability and performance of distributed simulation. Aiming to solve the relevance evaluation problem, speed up message filtering, and filter more unnecessary messages, a new relevance evaluation mechanism Layer of Interest （Lol） was proposed by this paper. Lol defines a relevance classifier based on the impact of spatial distance on receiving attributes and attribute values. An adaptive publish-subscribe scheme was built on the basis of Loh This scheme can abandon most irrelevant messages directly. Run-time infrastructure （RTI） can also apply congestion control by reducing the frequency of sending or receiving object messages based on each objects＇ Loh The experiment results verify the efficiency of message filtering and RTI congestion control.展开更多
The run-time security guarantee is a hotspot in current cyberspace security research, especially on embedded terminals, such as smart hardware as well as wearable and mobile devices. Typically, these devices use unive...The run-time security guarantee is a hotspot in current cyberspace security research, especially on embedded terminals, such as smart hardware as well as wearable and mobile devices. Typically, these devices use universal hardware and software to connect with public networks via the Internet, and are probably open to security threats from Trojan viruses and other malware. As a result, the security of sensitive personal data is threatened and economic interests in the industry are compromised. To address the run-time security problems efficiently, first, a TrustEnclave-based secure architecture is proposed, and the trusted execution environment is constructed by hardware isolation technology. Then the prototype system is implemented on real TrustZone-enabled hardware devices. Finally, both analytical and experimental evaluations are provided. The experimental results demonstrate the effectiveness and feasibility of the proposed security scheme.展开更多
基金financially supported by the National Basic Research Program of China (973 Program) (2012CB224800)
文摘The solid-phase extraction using Pd-Al2O3 as the stationary phase was employed to pre-separate the sulfur compounds in straight-run diesel. The isolating effect was evaluated quantitatively by gas chromatography with a sulfur chemiluminescence detector to harvest a satisfactory result. The identification of the structure of sulfur compounds by comprehensive two-dimensional gas chromatography coupled with the time-of-flight mass spectrometry indicated that cyclo-sulfides, benzothiophenes, dibenzothiophenes, dihydro-benzothiophenes and tetrahydro-dibenzothiophenes were included in straightrun diesel obtained from the Arab medium crude(AM). A total of 259 individual compounds were detected and their molecular structures were identified. The analytical method was approved as an effective way to characterize the composition of sulfur compounds, which reduced the interference of other compounds, facilitated the data presentation and provided more detailed information about molecular composition of sulfur compounds.
基金supported by the National Key Research and Development Program of China (No. 2018YFB1003605)Foundations of CARCH (No. CARCH201704)+3 种基金the National Natural Science Foundation of China (No. 61472312)Foundations of Shaanxi Province and Xi’an ScienceTechnology Plan (Nos. B018230008 and BD34017020001)the Foundations of Xidian University (No. JBZ171002)
文摘Despite the rapid development of mobile and embedded hardware, directly executing computationexpensive and storage-intensive deep learning algorithms on these devices’ local side remains constrained for sensory data analysis. In this paper, we first summarize the layer compression techniques for the state-of-theart deep learning model from three categories: weight factorization and pruning, convolution decomposition, and special layer architecture designing. For each category of layer compression techniques, we quantify their storage and computation tunable by layer compression techniques and discuss their practical challenges and possible improvements. Then, we implement Android projects using TensorFlow Mobile to test these 10 compression methods and compare their practical performances in terms of accuracy, parameter size, intermediate feature size,computation, processing latency, and energy consumption. To further discuss their advantages and bottlenecks,we test their performance over four standard recognition tasks on six resource-constrained Android smartphones.Finally, we survey two types of run-time Neural Network(NN) compression techniques which are orthogonal with the layer compression techniques, run-time resource management and cost optimization with special NN architecture,which are orthogonal with the layer compression techniques.
基金This work is supported by the National Natural Science Foundation of China under Grant Nos. 60873112 and 61028004, the National Natural Science Foundation of USA under Grant No. CNS-1126688.
文摘3-D Networks-on-Chip （NoC） emerge as a potent solution to address both the interconnection and design complexity problems facing future Multiprocessor System-on-Chips （MPSoCs）. Effective run-time mapping on such 3-D NoC-based MPSoCs can be quite challenging, as the arrival order and task graphs of the target applications are typically not known a priori, which can be further complicated by stringent energy requirements for NoC systems. This paper thus presents an energy-aware run-time incremental mapping algorithm （ERIM） for 3-D NoC which can minimize the energy consumption due to the data communications among processor cores, while reducing the fragmentation effect on the incoming applications to be mapped, and simultaneously satisfying the thermal constraints imposed on each incoming application. Specifically, incoming applications are mapped to cuboid tile regions for lower energy consumption of communication and the minimal routing. Fragment tiles due to system fragmentation can be gleaned for better resource utilization. Extensive experiments have been conducted to evaluate the performance of the proposed algorithm ERIM, and the results are compared against the optimal mapping algorithm （branch-and-bound） and two heuristic algorithms （TB and TL）. The experiments show that ERIM outperforms TB and TL methods with significant energy saving （more than 10%）, much reduced average response time, and improved system utilization.
基金Supported by the National Basic Research Program of China (Grant No. 2009CB320805)the National Natural Science Foundation of China(Grant No. 60603084)the National High-Tech Research & Development Program of China (Grant No. 2006AA01Z331)
文摘In large-scale distributed simulation, thousands of objects keep moving and interacting in a virtual environment, which produces a mass of messages. High level architecture （HLA） is the prevailing standard for modeling and simulation. It specifies two publish-subscribe mechanisms for message filtering： class-based and value-based. However, the two mechanisms can only judge whether a message is relevant to a subscriber or not. Lacking of the ability to evaluate the relevance, all relevant messages are delivered with the same priority even when congestion occurs. It significantly limits the scalability and performance of distributed simulation. Aiming to solve the relevance evaluation problem, speed up message filtering, and filter more unnecessary messages, a new relevance evaluation mechanism Layer of Interest （Lol） was proposed by this paper. Lol defines a relevance classifier based on the impact of spatial distance on receiving attributes and attribute values. An adaptive publish-subscribe scheme was built on the basis of Loh This scheme can abandon most irrelevant messages directly. Run-time infrastructure （RTI） can also apply congestion control by reducing the frequency of sending or receiving object messages based on each objects＇ Loh The experiment results verify the efficiency of message filtering and RTI congestion control.
基金supported by the National Natural Science Foundation of China (Nos.61572516 and 61503213)
文摘The run-time security guarantee is a hotspot in current cyberspace security research, especially on embedded terminals, such as smart hardware as well as wearable and mobile devices. Typically, these devices use universal hardware and software to connect with public networks via the Internet, and are probably open to security threats from Trojan viruses and other malware. As a result, the security of sensitive personal data is threatened and economic interests in the industry are compromised. To address the run-time security problems efficiently, first, a TrustEnclave-based secure architecture is proposed, and the trusted execution environment is constructed by hardware isolation technology. Then the prototype system is implemented on real TrustZone-enabled hardware devices. Finally, both analytical and experimental evaluations are provided. The experimental results demonstrate the effectiveness and feasibility of the proposed security scheme.
