In FPGA chips, interconnects occupy a large part of the timing and area consumption. Previous work on timemultiplexed FPGAs inspires us to apply the time-multiplexing technique to FPGA interconnects. To support this n...
详细信息
ISBN:
(数字)9781728134277
ISBN:
(纸本)9781728134277
In FPGA chips, interconnects occupy a large part of the timing and area consumption. Previous work on timemultiplexed FPGAs inspires us to apply the time-multiplexing technique to FPGA interconnects. To support this new architecture with time- multiplexed interconnects, we propose a routing algorithm that is time-multiplexing aware. This algorithm is similar to the VPR 5 routing algorithm, but this algorithm can also identify nets that can be scheduled to reuse. We validate the algorithm experimentally by implementing it as a multiplexing aware router and using this router to implement benchmark circuits to FPGAs with time-multiplexed interconnects. The results show that compared with an existing router targeting a conventional island-style architecture, 20% smaller minimum channel width and 10% smaller circuit critical path delay can be achieved.
In this paper, a new parallel Montgomery binary exponentiation algorithm was proposed. This algorithm is based on the Montgomery modular reduction technique, binary method, common-multiplicand-multiplication (CMM) alg...
详细信息
ISBN:
(纸本)9783642030949
In this paper, a new parallel Montgomery binary exponentiation algorithm was proposed. This algorithm is based on the Montgomery modular reduction technique, binary method, common-multiplicand-multiplication (CMM) algorithm, and the canonical-signed-digit recoding (CSD) technique. By using the CMM algorithm of computing the common part from two modular multiplications, the same common part in two modular multiplications can be computed once rather twice, we can thus improve the efficiency of the binary exponentiation algorithm by decreasing the number of modular multiplications. Furthermore, by using the proposed parallel CMM-CSD Montgomery binary exponentiation algorithm, the total number of single-precision multiplications can be reduced by about 66.7% and 30% as compared with the original Montgomery algorithm and the Ha-Moon's improved Montgomery algorithm, respectively.
The availability of reasonably priced, increasingly powerful, mobile devices is driving the growth of new video content services. One likely solution for video content delivery is based on the Peer-to-Peer (P2P) archi...
详细信息
ISBN:
(纸本)9781424495375
The availability of reasonably priced, increasingly powerful, mobile devices is driving the growth of new video content services. One likely solution for video content delivery is based on the Peer-to-Peer (P2P) architecture. Network congestion can have a significantly negative impact on the performance of P2P distribution. This paper focuses on enabling effective P2P content distribution over radio access networks. We developed a IEEE802.11k assisted mechanism to perform load balancing of peer associations across available networks. Load balancing can reduce congestion and increase throughput. Simulation results show significant throughput increase following a handover.
Posture correction of college students' English reading mobile learning habits based on smart phone camera image-assisted distance measurement algorithm is discussed in the paper. Based on the related study, the s...
详细信息
ISBN:
(数字)9781665408370
ISBN:
(纸本)9781665408387;9781665408370
Posture correction of college students' English reading mobile learning habits based on smart phone camera image-assisted distance measurement algorithm is discussed in the paper. Based on the related study, the speed of video image acquisition and the resolution of the collected image will directly affect the industrial production efficiency. Hence, this study considers the camera image-assisted distance measurement algorithm to improve the information transmission efficiency. Considering that the line synchronization signal of the video stream is aligned with the output data, this module will operate the line synchronization timing sequence, and the purpose is to synchronize the line synchronization signal with the output data during the working time of the camera. Furthermore, the posture correction of college students' English reading mobile learning habits is combined as the application testing. The experimental analysis is conducted to verify the performance.
Deep learning (DL) is one of the most emerging types of contemporary machine learning techniques that mimic the cognitive patterns of animal visual cortex to learn the new abstract features automatically by deep and h...
详细信息
ISBN:
(纸本)9789811033735;9789811033728
Deep learning (DL) is one of the most emerging types of contemporary machine learning techniques that mimic the cognitive patterns of animal visual cortex to learn the new abstract features automatically by deep and hierarchical layers. DL is believed to be a suitable tool so far for extracting insights from very huge volume of so-called big data. Nevertheless, one of the three "V" or big data is velocity that implies the learning has to be incremental as data are accumulating up rapidly. DL must be fast and accurate. By the technical design of DL, it is extended from feed-forward artificial neural network with many multi-hidden layers of neurons called deep neural network (DNN). In the training process of DNN, it has certain inefficiency due to very long training time required. Obtaining the most accurate DNN within a reasonable run-time is a challenge, given there are potentially many parameters in the DNN model configuration and high dimensionality of the feature space in the training dataset. Meta-heuristic has a history of optimizing machine learning models successfully. How well meta-heuristic could be used to optimize DL in the context of big data analytics is a thematic topic which we pondered on in this paper. As a position paper, we review the recent advances of applying meta-heuristics on DL, discuss about their pros and cons and point out some feasible research directions for bridging the gaps between meta-heuristics and DL.
With the rapid development of RFID technologies,RFID has been introduced into applications such as supply chain management,inventory control,sampling inspection,3-D positioning and object ***,the reader accesses all t...
详细信息
ISBN:
(纸本)9781509009107
With the rapid development of RFID technologies,RFID has been introduced into applications such as supply chain management,inventory control,sampling inspection,3-D positioning and object ***,the reader accesses all the tags in its interrogation region while some applications may only need to identify the tags in a specified area which is smaller than the reader's interrogation *** paper concerns the essential problem of estimating cardinality of tags in the specified *** key novelty of our solution builds on an estimation synopsis that can capture key counting information by moving the reader as well as a simple *** the help of this data structure,a BS can be obtained which only contains the target *** computing the number of 1 in the BS,we can easily get cardinality |E| of the tags in the specified *** conduct extensive experiments to examine this design and the results shows that our solution achieves high *** it not requires any modification of tags and can be implemented with only one reader and some passive RFID tags,the proposed method is easy to deploy in a practical system.
Nowadays an increasing number of papers appears in the subject of combinatorial optimization proposing a great variety of heuristics and metaheuristics, most of them apply special solution to fit the particular proble...
详细信息
ISBN:
(纸本)9781424414406
Nowadays an increasing number of papers appears in the subject of combinatorial optimization proposing a great variety of heuristics and metaheuristics, most of them apply special solution to fit the particular problem type. The analysis points out the importance of the generalization but the special intelligence in the algorithm design is still very important. Although the navigation in the solution space can be realized implicitly it has a decisive role in the performance. It is important to note that the success of sophisticated methods is often reduced by their relatively bad explorative capability. The well known algorithms are compared and also the latest most successful methods based on fast and simple heuristics- are discussed.
We introduce a new automaton on a word p, sequence of letters taken in an alphabet Sigma, that we call factor oracle. This automaton is acyclic, recognizes at least the factors of p, has m + 1 states and a linear numb...
详细信息
ISBN:
(纸本)354066694X
We introduce a new automaton on a word p, sequence of letters taken in an alphabet Sigma, that we call factor oracle. This automaton is acyclic, recognizes at least the factors of p, has m + 1 states and a linear number of transitions. We give an on-line construction to build it. We use this new structure in string matching algorithms that we conjecture optimal according to the experimental results. These algorithms are as efficient as the ones that already exist using less memory and being more easy to implement.
We investigate the relationship between algorithm construction and optimal decision processes. We provide a sufficient condition, a linear ordering over the experiment set, for when we can efficiently use an optimizat...
详细信息
Over the years, various path planning problems have been brought up and addressed. For example, shortest path first algorithm is usually adopted to search for the best route between a source and a destination for pack...
详细信息
ISBN:
(纸本)9781467382700
Over the years, various path planning problems have been brought up and addressed. For example, shortest path first algorithm is usually adopted to search for the best route between a source and a destination for packet transmission over a network. In that case, we add up the distance of every segment along each of the available routes and choose the one with the least value. Path planning problems of this sort often use evaluation functions that are commutative in nature. However, in case our objective is to plan a biking or driving route that is safe and / or fun, ordinary evaluation functions, especially commutative ones, usually fail to resolve the issue properly. Accordingly, in this paper, we propose an un-conventional non-commutative path planning strategy as well as algorithm to address the problem in a more efficient manner.
暂无评论