Статті в журналах: "MAP REDUCE ARCHITECTURE"

1

Rathore, Neeraj. "Map Reduce Architecture for Grid." i-manager's Journal on Software Engineering 10, no. 1 (September 15, 2015): 21–30. http://dx.doi.org/10.26634/jse.10.1.3629.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

2

Osero, Benard O., Elisha Abade, and Stephen Mburu. "Mobile Agent Based Distributed Network Architecture with Map Reduce Programming Model." Computer Science and Information Technology 7, no. 5 (November 2019): 129–61. http://dx.doi.org/10.13189/csit.2019.070501.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

3

Moharrer, Armin, and Stratis Ioannidis. "Distributing Frank–Wolfe via map-reduce." Knowledge and Information Systems 60, no. 2 (December 18, 2018): 665–90. http://dx.doi.org/10.1007/s10115-018-1294-7.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

4

K N, Manjunatha, and Vaibhav A Meshram. "Energy Efficient VLSI Architecture for Variable Iterative 4G LTE Turbo Decoder." International Journal of Engineering & Technology 7, no. 3 (July 16, 2018): 1535. http://dx.doi.org/10.14419/ijet.v7i3.12652.

Повний текст джерела

Анотація:

The Long Term Evolution (LTE) networks main objective is to support the next generation wireless communication systems. But most of the LTE approaches are suffer from decoding latency. Hence results in drop of data rate and this is not supported by the 4G LTE standards. To overcome this few parallel architectures has been introduced with the cost of power and silicon chip area. One promising decoding algorithm to overcome the decoding latency is Maximum a Posteriori (MAP) algorithm. The MAP has two computationally challenging α and β units. These two units have critical path and are to be reduced. A novel architecture for Add-Compare-Select (ACS) is proposed with clock gating techniques to reduce the unnecessary power dissipation across the recursive computational units. The proposed technique is applied with max-log MAP algorithm to precise the approximation. The overall design in implemented in a 45nm CMOS technology and results in 179.2mW of power dissipation which results in 34.6% less power compared to reported design while monitoring the moderate or same throughput level.

Стилі APA, Harvard, Vancouver, ISO та ін.

5

THABTAH, FADI, and SUHEL HAMMOUD. "MR-ARM: A MAP-REDUCE ASSOCIATION RULE MINING FRAMEWORK." Parallel Processing Letters 23, no. 03 (September 2013): 1350012. http://dx.doi.org/10.1142/s0129626413500126.

Повний текст джерела

Анотація:

Association rule is one of the primary tasks in data mining that discovers correlations among items in a transactional database. The majority of vertical and horizontal association rule mining algorithms have been developed to improve the frequent items discovery step which necessitates high demands on training time and memory usage particularly when the input database is very large. In this paper, we overcome the problem of mining very large data by proposing a new parallel Map-Reduce (MR) association rule mining technique called MR-ARM that uses a hybrid data transformation format to quickly finding frequent items and generating rules. The MR programming paradigm is becoming popular for large scale data intensive distributed applications due to its efficiency, simplicity and ease of use, and therefore the proposed algorithm develops a fast parallel distributed batch set intersection method for finding frequent items. Two implementations (Weka, Hadoop) of the proposed MR association rule algorithm have been developed and a number of experiments against small, medium and large data collections have been conducted. The ground bases of the comparisons are time required by the algorithm for: data initialisation, frequent items discovery, rule generation, etc. The results show that MR-ARM is very useful tool for mining association rules from large datasets in a distributed environment.

Стилі APA, Harvard, Vancouver, ISO та ін.

6

Malekimajd, Marzieh, Danilo Ardagna, Michele Ciavotta, Alessandro Maria Rizzi, and Mauro Passacantando. "Optimal Map Reduce Job Capacity Allocation in Cloud Systems." ACM SIGMETRICS Performance Evaluation Review 42, no. 4 (June 2, 2015): 51–61. http://dx.doi.org/10.1145/2788402.2788410.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

7

Khakimov, A., A. Suminov, and A. Muthanna. "DEVELOPMENT OF EDGE COMPUTING DISTRIBUTION METHOD IN VANET." Telecom IT 7, no. 2 (December 2019): 46–54. http://dx.doi.org/10.31854/2307-1303-2019-7-2-46-54.

Повний текст джерела

Анотація:

Research subject. Devoted the VANET network architecture, based on SDN / MEC (software-defined networks / mobile edge computing) systems that can reduce network load and traffic density. Method. The developed algorithm is considered. A testbed experiment based on a model network was done. Core results. The article examined the possibility of temporarily placing an application in RSU to reduce the load on the transit network. The condition for temporary placement of an application is based on data on congestion of road sections from Google Map & Yandex monitoring systems and current statistics on Internet traffic. Practical relevance. The proposed architecture allows to optimal use of RSU/MEC resources and significantly reduces the delay and load on data transmission.

Стилі APA, Harvard, Vancouver, ISO та ін.

8

Shafighi, Nesa, and Babak Shirazi. "Ontological Map of Service Oriented Architecture Based on Zachman." Research in Economics and Management 2, no. 4 (July 18, 2017): 33. http://dx.doi.org/10.22158/rem.v2n4p33.

Повний текст джерела

Анотація:

Service orientation is an approach in the field of enterprise architecture, business information systems and software application that its main element is the service. Shared services is an organization model of sharing, across an organization. It enables collaboration among the functions/departments. Main motivations for shared services are sharing, promote efficiency, reduce cost, and support scalability. Despite of the widespread use of these two approaches in information technology, there is no tool to optimize the management of them. The aim of this study is Ontological map of service oriented architecture based on zachman framework to adapt it in the reference enterprise architecture framework through implementation ontology views on system architect software and as well as equivalent ontology component with UML diagrams. After the implementation of the suggested model, the results showed that ontology is a formal description and explicit display of objects, concepts and other entities in the relationship between them. In other words, there is a model that describe all that is in fact in to understandable language for the system. Thus the proposed establishes have association between all aspects of zachman framework, also to create a clear description of business concepts in the management of shared services and is effective to provide a unified platform for enterprise modeling.

Стилі APA, Harvard, Vancouver, ISO та ін.

9

Khamaru, Ananda, and Tryambak Hiwarkar. "A Dynamics of Machine Learning on Map-Reduce Architecture for Enhancing Big Data Analysis Performance." International Journal of Computer Science and Mobile Computing 11, no. 11 (November 30, 2022): 109–30. http://dx.doi.org/10.47760/ijcsmc.2022.v11i11.009.

Повний текст джерела

Анотація:

Big data is a fantastic resource for disseminating system-generated insights to external stakeholders. However, automation is required to manage such a large body of information, and this has spurred the development of data processing and machine learning tools. Just as in other fields of study and business, the ICT industry is serving and developing platforms and solutions to help professionals treat their knowledge and learn automatically. Large companies like Google and Microsoft, as well as the Apache Foundation's incubator, are the primary providers of these platforms. Spark is an open-source platform for handling Big Data insights that have been tainted by contamination. This unified framework provides a variety of methods for dealing with unstructured or structured text data, graph data, and real-time streaming data. Spark relies on MLlib to create customised ML algorithms. To parallelize a huge cluster of machines for data analytics, these methods require less memory, less processing time, and, to a large extent, hand tuned specialized architecture. Data sets are analysed with machine learning methods including Linear Regression, Decision Tree, Random Forest, and Gradient Boosting Tree. In order to comprehend the data sets with the help of machine learning algorithms and to determine the best forecast value from the comparative study, the prediction model provided in this research is used. One key goal of this study is to use the proposed model to make the most accurate forecast possible utilising machine learning methods. The suggested model utilizes the Apache Spark framework to perform a comparative analysis of the various existing approaches that have implemented the supervised and unsupervised techniques utilizing the MapReduce approach. By comparing the temporal complexity of each method, this method calculates the best prediction from the model. This dissertation emphasizes the characteristics of datasets that are most useful for examining the most effective prediction using machine learning algorithms.

Стилі APA, Harvard, Vancouver, ISO та ін.

10

AlZubi, Ahmad Ali. "Big data analytic diabetics using map reduce and classification techniques." Journal of Supercomputing 76, no. 6 (April 16, 2018): 4328–37. http://dx.doi.org/10.1007/s11227-018-2362-1.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

11

Su, Yen-Liang, Po-Cheng Chen, Jyh-Biau Chang, and Ce-Kuen Shieh. "Variable-sized map and locality-aware reduce on public-resource grids." Future Generation Computer Systems 27, no. 6 (June 2011): 843–49. http://dx.doi.org/10.1016/j.future.2010.09.001.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

12

Fan, Yu-Cheng, Yi-Cheng Liu, and Chiao-An Chu. "Efficient CORDIC Iteration Design of LiDAR Sensors’ Point-Cloud Map Reconstruction Technology." Sensors 19, no. 24 (December 9, 2019): 5412. http://dx.doi.org/10.3390/s19245412.

Повний текст джерела

Анотація:

In this paper, we propose an efficient COordinate Rotation DIgital Computer (CORDIC) iteration circuit design for Light Detection and Ranging (LiDAR) sensors. A novel CORDIC architecture that achieves the goal of pre-selecting angles and reduces the number of iterations is presented for LiDAR sensors. The value of the trigonometric functions can be found in seven rotations regardless of the number of input N digits. The number of iterations are reduced by more than half. The experimental results show the similarity value to be all 1 and prove that the LiDAR decoded packet results are exactly the same as the ground truth. The total chip area is 1.93 mm × 1.93 mm and the core area is 1.32 mm × 1.32 mm, separately. The number of logic gates is 129,688. The designed chip only takes 0.012 ms and 0.912 ms to decode a packet and a 3D frame of LiDAR sensors, respectively. The throughput of the chip is 8.2105 × 10 8 bits/sec. The average power consumption is 237.34 mW at a maximum operating frequency of 100 MHz. This design can not only reduce the number of iterations and the computing time but also reduce the chip area. This paper provides an efficient CORDIC iteration design and solution for LiDAR sensors to reconstruct the point-cloud map for autonomous vehicles.

Стилі APA, Harvard, Vancouver, ISO та ін.

13

ШИБАЕВ, Д. С., В. В. ВЫЧУЖАНИН, and Н. О. ШИБАЕВА. "ANALYSIS OF A LARGE VOLUME OF DATA ON THE STATE OF HIGH-TECH EQUIPMENT." Transport development, no. 1(1) (September 27, 2017): 90–95. http://dx.doi.org/10.33082/td.2017.1-1.09.

Повний текст джерела

Анотація:

The ideological basis of the study is to analyze the data obtained in the result of a large number of high-tech equipment. The data is distributed in databases, depending on various characteristics. The complexity of the sub-sequent processing depends on the amount of information you need to perform, as well as architectural type of data storage. The use of data mining technology allows to significantly improve the analysis of information and subsequent short-term search value. The use of this technology will improve the efficiency of the archives of marine indicators for all time of operation of the vessel. The technology of data analysis is not tho-rough and requires permanent modification to increase their own efficiency. The addition of modern architecture through data in the databases, will allow to increase efficiency of data analysis, consisting of a large number of indicators of the condition of the vessel and its equipment. One of these architectures is Map-Reduce.

Стилі APA, Harvard, Vancouver, ISO та ін.

14

Tong, Minglei, Lyuyuan Fan, Hao Nan, and Yan Zhao. "Smart Camera Aware Crowd Counting via Multiple Task Fractional Stride Deep Learning." Sensors 19, no. 6 (March 18, 2019): 1346. http://dx.doi.org/10.3390/s19061346.

Повний текст джерела

Анотація:

Estimating the number of people in highly clustered crowd scenes is an extremely challenging task on account of serious occlusion and non-uniformity distribution in one crowd image. Traditional works on crowd counting take advantage of different CNN like networks to regress crowd density map, and further predict the count. In contrast, we investigate a simple but valid deep learning model that concentrates on accurately predicting the density map and simultaneously training a density level classifier to relax parameters of the network to prevent dangerous stampede with a smart camera. First, a combination of atrous and fractional stride convolutional neural network (CAFN) is proposed to deliver larger receptive fields and reduce the loss of details during down-sampling by using dilated kernels. Second, the expanded architecture is offered to not only precisely regress the density map, but also classify the density level of the crowd in the meantime (MTCAFN, multiple tasks CAFN for both regression and classification). Third, experimental results demonstrated on four datasets (Shanghai Tech A (MAE = 88.1) and B (MAE = 18.8), WorldExpo’10(average MAE = 8.2), NS UCF_CC_50(MAE = 303.2) prove our proposed method can deliver effective performance.

Стилі APA, Harvard, Vancouver, ISO та ін.

15

Cui, Liyuan, Guoqiang Zhong, Xiang Liu, and Hongwei Xu. "A Compact Object Detection Architecture with Transformer Enhancing." Journal of Physics: Conference Series 2278, no. 1 (May 1, 2022): 012034. http://dx.doi.org/10.1088/1742-6596/2278/1/012034.

Повний текст джерела

Анотація:

Abstract With the advancements in rising computer vision processing, Transformer has attracted increasing interesting in this field. However, it is limited because of its unprecedented storage, heavy reliance on data size and intolerable computational power consumption. While lightweight network is in other extreme, pursuing the compact architectures accompanied by performance loss. In this paper, we enhance an architecture as the backbone of object detection networks through combining right-size Transformer, i.e. Vision Transformer module. Specifically, based on GhostNet, a well-known lightweight neural network structure moreover, embed this Vision Transformer module at the end of GhostNet, and use the input data with slicing design to reduce the computational burden of the neural networks. Vision Transformer is taken to enhance the architecture as the backbone of object detection networks, and the well-known YOLOv5 as the baseline. We conduct multi-metric comparison experiments on two medium-scale object detection datasets with large, medium and small scale networks. Results show that without relying on ultra-large dataset and pre-trained models, the proposed Transformer module enhanced architecture achieves comparable or even higher mAP metrics with only half of the model size and floating-point computation of the baseline.

Стилі APA, Harvard, Vancouver, ISO та ін.

16

Althebyan, Qutaibah, Omar AlQudah, Yaser Jararweh, and Qussai Yaseen. "A scalable Map Reduce tasks scheduling: a threading-based approach." International Journal of Computational Science and Engineering 14, no. 1 (2017): 44. http://dx.doi.org/10.1504/ijcse.2017.081175.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

17

Bao, Chun, Jie Cao, Qun Hao, Yang Cheng, Yaqian Ning, and Tianhua Zhao. "Dual-YOLO Architecture from Infrared and Visible Images for Object Detection." Sensors 23, no. 6 (March 8, 2023): 2934. http://dx.doi.org/10.3390/s23062934.

Повний текст джерела

Анотація:

With the development of infrared detection technology and the improvement of military remote sensing needs, infrared object detection networks with low false alarms and high detection accuracy have been a research focus. However, due to the lack of texture information, the false detection rate of infrared object detection is high, resulting in reduced object detection accuracy. To solve these problems, we propose an infrared object detection network named Dual-YOLO, which integrates visible image features. To ensure the speed of model detection, we choose the You Only Look Once v7 (YOLOv7) as the basic framework and design the infrared and visible images dual feature extraction channels. In addition, we develop attention fusion and fusion shuffle modules to reduce the detection error caused by redundant fusion feature information. Moreover, we introduce the Inception and SE modules to enhance the complementary characteristics of infrared and visible images. Furthermore, we design the fusion loss function to make the network converge fast during training. The experimental results show that the proposed Dual-YOLO network reaches 71.8% mean Average Precision (mAP) in the DroneVehicle remote sensing dataset and 73.2% mAP in the KAIST pedestrian dataset. The detection accuracy reaches 84.5% in the FLIR dataset. The proposed architecture is expected to be applied in the fields of military reconnaissance, unmanned driving, and public safety.

Стилі APA, Harvard, Vancouver, ISO та ін.

18

Zhang, Shaofang, Xianjun Li, and Yuechun Wang. "The Construction of High-Performance Optoelectronic Interconnection Network and the Realization of Cloud Computing for Traffic Data Recognition." Journal of Nanoelectronics and Optoelectronics 15, no. 7 (July 1, 2020): 894–903. http://dx.doi.org/10.1166/jno.2020.2807.

Повний текст джерела

Анотація:

Due to the problems of congestion, insufficient scalability, and high cost in the network core layer link, the network interconnection architecture needs to be optimized. The photoelectric interconnection technology has attracted the attention of many researchers with its high bandwidth, low latency, and low power consumption. In this study, after fully considering the requirements of optoelectronic switching on network node degree and processing delay and corresponding to different transmission characteristics of circuit switching and optical circuit switching, an optoelectronic interconnection architecture supporting heterogeneous network topology, namely THtop, is proposed. According to the optical circuit switching/circuit switching characteristics of the Internet, the corresponding topology structure is designed respectively in this architecture to enhance the system integration and reduce the cost. At the same time, in order to meet the requirements of wavelength and number of hops of optical circuit switching, distributed control is designed in THtop, and the design method of heterogeneous optical switching unit is introduced in the switching equipment, so that the optical switching node can further reduce the cost while playing its role. The use of high-speed optoelectronic networks will cause a large amount of traffic on the channel. In this study, the traffic identification is analyzed on the proposed THtop architecture. The Map Reduce framework in cloud computing is used as the identification model, and the K-means algorithm is taken as the identification algorithm. According to its characteristics, the W_K-means algorithm is proposed for the type identification of traffic. The results show that under the OpenNet Internet simulation environment, when the traffic is set to a certain level, more than 90% of the non-blocking network switching can be realized under the THtop architecture, and the completion time of the mouse flow and elephant flow can be significantly improved. Therefore, under the Map Reduce model, the proposed W_K -means algorithm can quickly identify different traffic types.

Стилі APA, Harvard, Vancouver, ISO та ін.

19

VeeraManickam, M. R. M., M. Mohanapriya, Bishwajeet K. Pandey, Sushma Akhade, S. A. Kale, Reshma Patil, and M. Vigneshwar. "Map-Reduce framework based cluster architecture for academic student’s performance prediction using cumulative dragonfly based neural network." Cluster Computing 22, S1 (February 7, 2018): 1259–75. http://dx.doi.org/10.1007/s10586-017-1553-5.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

20

Bagui, Sikha, Arup Kumar Mondal, and Subhash Bagui. "Improving the Performance of kNN in the MapReduce Framework Using Locality Sensitive Hashing." International Journal of Distributed Systems and Technologies 10, no. 4 (October 2019): 1–16. http://dx.doi.org/10.4018/ijdst.2019100101.

Повний текст джерела

Анотація:

In this work the authors present a parallel k nearest neighbor (kNN) algorithm using locality sensitive hashing to preprocess the data before it is classified using kNN in Hadoop's MapReduce framework. This is compared with the sequential (conventional) implementation. Using locality sensitive hashing's similarity measure with kNN, the iterative procedure to classify a data object is performed within a hash bucket rather than the whole data set, greatly reducing the computation time needed for classification. Several experiments were run that showed that the parallel implementation performed better than the sequential implementation on very large datasets. The study also experimented with a few map and reduce side optimization features for the parallel implementation and presented some optimum map and reduce side parameters. Among the map side parameters, the block size and input split size were varied, and among the reduce side parameters, the number of planes were varied, and their effects were studied.

Стилі APA, Harvard, Vancouver, ISO та ін.

21

Desai, Sharmishta Suhas, and S. T. Patil. "Big Data Classification Using Distributed Optimized Hoeffding Trees." Journal of Machine Intelligence 2, no. 1 (June 26, 2017): 14–20. http://dx.doi.org/10.21174/jomi.v2i1.101.

Повний текст джерела

Анотація:

Large usage of social media, online shopping or transactions gives birth to voluminous data. Visual representation and analysis of this large amount of data is one of the major research topics today. As this data is changing over the period of time, we need an approach which will take care of velocity of data as well as volume and variety. In this paper, author has proposed a distributed method which will handle three dimensions of data and gives good results as compared to other method. Traditional algorithms are based on global optima which are basically memory resident programs. Our approach which is based on optimized hoeffding bound uses local optima method and distributed map-reduce architecture. It does not require copying whole data set onto a memory. As the model build is frequently updated on multiple nodes concurrently, it is more suitable for time varying data. Hoeffding bound is basically suitable for real time data stream. We have proposed very efficient distributed map-reduce architecture to implement hoeffding tree efficiently. We have used deep learning at leaf level to optimize the hoeffding tree. Drift detection is taken care by the architecture itself no separate provision is required for this. In this paper, with experimental results it is proved that our method takes less learning time with more accuracy. Also distributed algorithm for hoeffding tree implementation is proposed.

Стилі APA, Harvard, Vancouver, ISO та ін.

22

Li, Jianjiang, Yajun Liu, Jian Pan, Peng Zhang, Wei Chen, and Lizhe Wang. "Map-Balance-Reduce: An improved parallel programming model for load balancing of MapReduce." Future Generation Computer Systems 105 (April 2020): 993–1001. http://dx.doi.org/10.1016/j.future.2017.03.013.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

23

Vaddi, Subrahmanyam, Dongyoun Kim, Chandan Kumar, Shafqat Shad, and Ali Jannesari. "Efficient Object Detection Model for Real-time UAV Application." Computer and Information Science 14, no. 1 (January 22, 2021): 45. http://dx.doi.org/10.5539/cis.v14n1p45.

Повний текст джерела

Анотація:

Unmanned Aerial Vehicles (UAVs) equipped with vision capabilities have become popular in recent years. Many applications have especially been employed object detection techniques extracted from the information captured by an onboard camera. However, object detection on UAVs requires high performance, which has a negative effect on the result. In this article, we propose a deep feature pyramid architecture with a modified focal loss function, which enables it to reduce the class imbalance. Moreover, the proposed method employed an end to end object detection model running on the UAV platform for real-time application. To evaluate the proposed architecture, we combined our model with Resnet and MobileNet as a backend network, and we compared it with RetinaNet and HAL-RetinaNet. Our model produced a performance of 30.6 mAP with an inference time of 14 fps. This result shows that our proposed model outperformed RetinaNet by 6.2 mAP.

Стилі APA, Harvard, Vancouver, ISO та ін.

24

DEREJE TEKILU, Aseffa, and Chin-Hsien WU. "A Virtualization-Based Hybrid Storage System for a Map-Reduce Framework." IEICE Transactions on Information and Systems E99.D, no. 9 (2016): 2248–58. http://dx.doi.org/10.1587/transinf.2015edp7365.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

25

Hayat, Ahatsham, and Fernando Morgado-Dias. "Deep Learning-Based Automatic Safety Helmet Detection System for Construction Safety." Applied Sciences 12, no. 16 (August 18, 2022): 8268. http://dx.doi.org/10.3390/app12168268.

Повний текст джерела

Анотація:

Worker safety at construction sites is a growing concern for many construction industries. Wearing safety helmets can reduce injuries to workers at construction sites, but due to various reasons, safety helmets are not always worn properly. Hence, a computer vision-based automatic safety helmet detection system is extremely important. Many researchers have developed machine and deep learning-based helmet detection systems, but few have focused on helmet detection at construction sites. This paper presents a You Only Look Once (YOLO)-based real-time computer vision-based automatic safety helmet detection system at a construction site. YOLO architecture is high-speed and can process 45 frames per second, making YOLO-based architectures feasible to use in real-time safety helmet detection. A benchmark dataset containing 5000 images of hard hats was used in this study, which was further divided in a ratio of 60:20:20 (%) for training, testing, and validation, respectively. The experimental results showed that the YOLOv5x architecture achieved the best mean average precision (mAP) of 92.44%, thereby showing excellent results in detecting safety helmets even in low-light conditions.

Стилі APA, Harvard, Vancouver, ISO та ін.

26

Struharik, Rastislav, and Vuk Vranjković. "Striping input feature map cache for reducing off-chip memory traffic in CNN accelerators." Telfor Journal 12, no. 2 (2020): 116–21. http://dx.doi.org/10.5937/telfor2002116s.

Повний текст джерела

Анотація:

Data movement between the Convolutional Neural Network (CNN) accelerators and off-chip memory is critical concerning the overall power consumption. Minimizing power consumption is particularly important for low power embedded applications. Specific CNN computes patterns offer a possibility of significant data reuse, leading to the idea of using specialized on-chip cache memories which enable a significant improvement in power consumption. However, due to the unique caching pattern present within CNNs, standard cache memories would not be efficient. In this paper, a novel on-chip cache memory architecture, based on the idea of input feature map striping, is proposed, which requires significantly less on-chip memory resources compared to previously proposed solutions. Experiment results show that the proposed cache architecture can reduce on-chip memory size by a factor of 16 or more, while increasing power consumption no more than 15%, compared to some of the previously proposed solutions.

Стилі APA, Harvard, Vancouver, ISO та ін.

27

Gazis, Alexandros, and Eleftheria Katsiri. "IoT Cloud Computing Middleware for Crowd Monitoring and Evacuation." International Journal of Circuits, Systems and Signal Processing 15 (December 23, 2021): 1790–802. http://dx.doi.org/10.46300/9106.2021.15.193.

Повний текст джерела

Анотація:

Map-Reduce is a programming model and an associated implementation for processing and generating large data sets. This model has a single point of failure: the master, who coordinates the work in a cluster. On the contrary, wireless sensor networks (WSNs) are distributed systems that scale and feature large numbers of small, computationally limited, low-power, unreliable nodes. In this article, we provide a top-down approach explaining the architecture, implementation and rationale of a distributed fault-tolerant IoT middleware. Specifically, this middleware consists of multiple mini-computing devices (Raspberry Pi) connected in a WSN which implement the Map-Reduce algorithm. First, we explain the tools used to develop this system. Second, we focus on the Map-Reduce algorithm implemented to overcome common network connectivity issues, as well as to enhance operation availability and reliability. Lastly, we provide benchmarks for our middleware as a crowd tracking application for a preserved building in Greece (i.e., M. Hatzidakis’ residence). The results of this study show that IoT middleware with low-power and low-cost components are viable solutions for medium-sized cloud computing distributed and parallel computing centres. Potential uses of this middleware apply for monitoring buildings and indoor structures, in addition to crowd tracking to prevent the spread of COVID-19.

Стилі APA, Harvard, Vancouver, ISO та ін.

28

Xiao, Yun, Wei Zeng, and Huang Zhang. "FPGA Delay-Oriented Process Mapping Algorithm of Xiangxi Minority Based on LUT." Mathematical Problems in Engineering 2022 (February 7, 2022): 1–13. http://dx.doi.org/10.1155/2022/4994923.

Повний текст джерела

Анотація:

At present, FPGA (field-programmable gate array) architecture has made great progress in the requirements of hardware volume, which can meet common needs. However, for the increasing number of resources, it is difficult to significantly reduce the delay of process mapping. Therefore, this paper proposes FDMAP (fit descending map) algorithm from the perspective of the LUT number to reduce the delay. This paper proposes a method of FPGA mapping and debugging for heterogeneous multicore high-performance processors based on isomorphic symmetric FPGA architecture, which effectively utilizes the architectural features of heterogeneous multicore processors and the symmetric features of isomorphic FPGA, divides FPGA functions from top to bottom in a hierarchical way, and constructs FPGA architecture from bottom to top. Using differential bridge and adaptive delay adjustment sampling technology, combined with the embedded virtual logic analyzer debugging tool, FPGA architecture can be lightened and deployed quickly. Multicore complementary core-to-core replacement simulation mapping methods such as debug shells can be used to effectively complete the mapping of the target’s high-performance heterogeneous multicore processor to the entire SOC (system on-ship) chip system-level FPGA. In the aspect of algorithm, the fdmap algorithm is mainly implemented, and the low latency mapping of resources is realized with FPGA architecture. In order to verify the effectiveness of mapping the fdmap algorithm, this paper compares the fdmap algorithm with the vector VM algorithm. The research shows that when the wavelength resolution is 7 pm and the temperature error is less than 1°C, the shell is debugged, and 10 mapping examples are simulated with the fdmap algorithm. In the experiment, the LUT with the most critical 20% is selected, and the closed value of the LUT search type is set to 0.86. Compared with the original data, the number of LUTs increased by 15.2%, and the criticality decreased by 35.21%. Compared with the vector VM algorithm with the biggest gap, the number of LUTs decreased by 14.25%, the criticality improved by 14.21%, and the overall delay decreased by 65%. Therefore, the isomorphic symmetric FPGA architecture proposed in this paper can improve the structural criticality and significantly reduce the latency while reducing the number of LUTs.

Стилі APA, Harvard, Vancouver, ISO та ін.

29

Zeng, Feng Sheng. "Research and Improvement of Database Storage Method." Applied Mechanics and Materials 608-609 (October 2014): 641–45. http://dx.doi.org/10.4028/www.scientific.net/amm.608-609.641.

Повний текст джерела

Анотація:

This paper presents a massive data storage and parallel processing method based on MPP architecture, and put forward full persistent data storage way from the client to request, and the integration the idea of Map/Reduce, the system will be distributed to each data node, the data has high scalability, high availability, high concurrency. And the simulation test and verifies the feasibility of mass data storage mode by building a distributed data node.

Стилі APA, Harvard, Vancouver, ISO та ін.

30

Alvarez-Gonzalez, Ruben, and Andres Mendez-Vazquez. "Deep Learning Architecture Reduction for fMRI Data." Brain Sciences 12, no. 2 (February 8, 2022): 235. http://dx.doi.org/10.3390/brainsci12020235.

Повний текст джерела

Анотація:

In recent years, deep learning models have demonstrated an inherently better ability to tackle non-linear classification tasks, due to advances in deep learning architectures. However, much remains to be achieved, especially in designing deep convolutional neural network (CNN) configurations. The number of hyper-parameters that need to be optimized to achieve accuracy in classification problems increases with every layer used, and the selection of kernels in each CNN layer has an impact on the overall CNN performance in the training stage, as well as in the classification process. When a popular classifier fails to perform acceptably in practical applications, it may be due to deficiencies in the algorithm and data processing. Thus, understanding the feature extraction process provides insights to help optimize pre-trained architectures, better generalize the models, and obtain the context of each layer’s features. In this work, we aim to improve feature extraction through the use of a texture amortization map (TAM). An algorithm was developed to obtain characteristics from the filters amortizing the filter’s effect depending on the texture of the neighboring pixels. From the initial algorithm, a novel geometric classification score (GCS) was developed, in order to obtain a measure that indicates the effect of one class on another in a classification problem, in terms of the complexity of the learnability in every layer of the deep learning architecture. For this, we assume that all the data transformations in the inner layers still belong to a Euclidean space. In this scenario, we can evaluate which layers provide the best transformations in a CNN, allowing us to reduce the weights of the deep learning architecture using the geometric hypothesis.

Стилі APA, Harvard, Vancouver, ISO та ін.

31

Ibrahem, Hatem, Ahmed Salem, and Hyun-Soo Kang. "DTS-Depth: Real-Time Single-Image Depth Estimation Using Depth-to-Space Image Construction." Sensors 22, no. 5 (March 1, 2022): 1914. http://dx.doi.org/10.3390/s22051914.

Повний текст джерела

Анотація:

As most of the recent high-resolution depth-estimation algorithms are computationally so expensive that they cannot work in real time, the common solution is using a low-resolution input image to reduce the computational complexity. We propose a different approach, an efficient and real-time convolutional neural network-based depth-estimation algorithm using a single high-resolution image as the input. The proposed method efficiently constructs a high-resolution depth map using a small encoding architecture and eliminates the need for a decoder, which is typically used in the encoder–decoder architectures employed for depth estimation. The proposed algorithm adopts a modified MobileNetV2 architecture, which is a lightweight architecture, to estimate the depth information through the depth-to-space image construction, which is generally employed in image super-resolution. As a result, it realizes fast frame processing and can predict a high-accuracy depth in real time. We train and test our method on the challenging KITTI, Cityscapes, and NYUV2 depth datasets. The proposed method achieves low relative absolute error (0.028 for KITTI, 0.167 for CITYSCAPES, and 0.069 for NYUV2) while working at speed reaching 48 frames per second on a GPU and 20 frames per second on a CPU for high-resolution test images. We compare our method with the state-of-the-art methods on depth estimation, showing that our method outperforms those methods. However, the architecture is less complex and works in real time.

Стилі APA, Harvard, Vancouver, ISO та ін.

32

Jiang, Wei, Zicheng Gong, Jinyu Zhan, Zhiyuan He, and Weijia Pan. "A Low-Cost Image Encryption Method to Prevent Model Stealing of Deep Neural Network." Journal of Circuits, Systems and Computers 29, no. 16 (May 28, 2020): 2050252. http://dx.doi.org/10.1142/s0218126620502527.

Повний текст джерела

Анотація:

Model stealing attack may happen by stealing useful data transmitted from embedded end to server end for an artificial intelligent systems. In this paper, we are interested in preventing model stealing of neural network for resource-constrained systems. We propose an Image Encryption based on Class Activation Map (IECAM) to encrypt information before transmitting in embedded end. According to class activation map, IECAM chooses certain key areas of the image to be encrypted with the purpose of reducing the model stealing risk of neural network. With partly encrypted information, IECAM can greatly reduce the time overheads of encryption/decryption in both embedded and server ends, especially for big size images. The experimental results demonstrate that our method can significantly reduce time overheads of encryption/decryption and the risk of model stealing compared with traditional methods.

Стилі APA, Harvard, Vancouver, ISO та ін.

33

Kim, Jungseok, Jeongmin Moon, and Changjoo Moon. "Lane-Level Map Generation and Management Framework Using Connected Car Data." Electronics 12, no. 18 (September 5, 2023): 3738. http://dx.doi.org/10.3390/electronics12183738.

Повний текст джерела

Анотація:

This study proposes a lane-level map generation and management framework using connected sensor data to reduce the manpower and time required for producing and updating high-definition (HD) maps. Unlike previous studies that relied on the onboard processing capabilities of vehicles to collect map-constructing elements, this study offloads computing for map generation to the cloud, assigning vehicles solely the role of transmitting sensor data. For efficient data collection, we divide the space into a grid format to define it as a partial map and establish the state of each map and its transition conditions. Lastly, tailored to the characteristics of the road elements composing the map, we propose an automated map generation technique and method for selectively collecting data. The map generation method was tested using data collected from actual vehicles. By transmitting images with an average size of 350 KB, implementation was feasible even with the current 5G upload bandwidth. By utilizing 12,545 elements, we were able to achieve a position accuracy and regression RMSE of less than 0.25 m, obtaining 651 map elements to construct the map. We anticipate that this study will help reduce the manpower and time needed for deploying and updating HD maps.

Стилі APA, Harvard, Vancouver, ISO та ін.

34

Mao, Jiachen, Qing Yang, Ang Li, Kent W. Nixon, Hai Li, and Yiran Chen. "Toward Efficient and Adaptive Design of Video Detection System with Deep Neural Networks." ACM Transactions on Embedded Computing Systems 21, no. 3 (May 31, 2022): 1–21. http://dx.doi.org/10.1145/3484946.

Повний текст джерела

Анотація:

In the past decade, Deep Neural Networks (DNNs), e.g., Convolutional Neural Networks, achieved human-level performance in vision tasks such as object classification and detection. However, DNNs are known to be computationally expensive and thus hard to be deployed in real-time and edge applications. Many previous works have focused on DNN model compression to obtain smaller parameter sizes and consequently, less computational cost. Such methods, however, often introduce noticeable accuracy degradation. In this work, we optimize a state-of-the-art DNN-based video detection framework—Deep Feature Flow (DFF) from the cloud end using three proposed ideas. First, we propose Asynchronous DFF (ADFF) to asynchronously execute the neural networks. Second, we propose a Video-based Dynamic Scheduling (VDS) method that decides the detection frequency based on the magnitude of movement between video frames. Last, we propose Spatial Sparsity Inference, which only performs the inference on part of the video frame and thus reduces the computation cost. According to our experimental results, ADFF can reduce the bottleneck latency from 89 to 19 ms. VDS increases the detection accuracy by 0.6% mAP without increasing computation cost. And SSI further saves 0.2 ms with a 0.6% mAP degradation of detection accuracy.

Стилі APA, Harvard, Vancouver, ISO та ін.

35

Chen, Li, Zhen Zhang, Jianjun Wu, Xiang Wei, and Wenyuan Bai. "Dynamic Retrieval Model of Quantitative Data of Power Grid Resources Based on 3D Geographic Information Systems (GIS)." Journal of Nanoelectronics and Optoelectronics 17, no. 2 (February 1, 2022): 344–50. http://dx.doi.org/10.1166/jno.2022.3204.

Повний текст джерела

Анотація:

In order to improve the efficiency of the quantitative data retrieval of power grid resources, a dynamic retrieval model of the quantitative data of power grid resources based on a three-dimensional GIS system is designed. First, the retrieval model architecture is designed based on the 3D GIS system, which is mainly composed of application architecture, technical architecture, data architecture and physical architecture. The technical architecture includes core technologies such as 3D GIS engine, index storage and retrieval applications. Secondly, the real-time daemon mode in the distributed computing method is used to establish a two-level dynamic index and store all kinds of data. Based on the dynamic index, a dynamic retrieval model is constructed by combining the parallel computing unit and the distributed coordination service unit. Finally, the Cirl-Skyline retrieval algorithm under the Map-Reduce parallel framework is used to realize the dynamic retrieval of the quantitative data of power grid resources. The performance test results show that the designed model can effectively improve retrieval efficiency on the basis of ensuring high-precision retrieval results, and can meet the needs of dynamic retrieval of massive quantitative data.

Стилі APA, Harvard, Vancouver, ISO та ін.

36

Zvonkov, Ivan, Gabriel Tseng, Catherine Nakalembe, and Hannah Kerner. "OpenMapFlow: A Library for Rapid Map Creation with Machine Learning and Remote Sensing Data." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 12 (June 26, 2023): 14655–63. http://dx.doi.org/10.1609/aaai.v37i12.26713.

Повний текст джерела

Анотація:

The desired output for most real-world tasks using machine learning (ML) and remote sensing data is a set of dense predictions that form a predicted map for a geographic region. However, most prior work involving ML and remote sensing follows the traditional practice of reporting metrics on a set of independent, geographically-sparse samples and does not perform dense predictions. To reduce the labor of producing dense prediction maps, we present OpenMapFlow---an open-source python library for rapid map creation with ML and remote sensing data. OpenMapFlow provides 1) a data processing pipeline for users to create labeled datasets for any region, 2) code to train state-of-the-art deep learning models on custom or existing datasets, and 3) a cloud-based architecture to deploy models for efficient map prediction. We demonstrate the benefits of OpenMapFlow through experiments on three binary classification tasks: cropland, crop type (maize), and building mapping. We show that OpenMapFlow drastically reduces the time required for dense prediction compared to traditional workflows. We hope this library will stimulate novel research in areas such as domain shift, unsupervised learning, and societally-relevant applications and lessen the barrier to adopting research methods for real-world tasks.

Стилі APA, Harvard, Vancouver, ISO та ін.

37

Tauer, Gregory, and Rakesh Nagi. "A map-reduce lagrangian heuristic for multidimensional assignment problems with decomposable costs." Parallel Computing 39, no. 11 (November 2013): 653–68. http://dx.doi.org/10.1016/j.parco.2013.08.012.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

38

Ragaventhiran, J., and M. K. Kavithadevi. "Map-optimize-reduce: CAN tree assisted FP-growth algorithm for clusters based FP mining on Hadoop." Future Generation Computer Systems 103 (February 2020): 111–22. http://dx.doi.org/10.1016/j.future.2019.09.041.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

39

Ren, Qiong. "Massive Collaborative Wireless Sensor Network Structure Based on Cloud Computing." International Journal of Online Engineering (iJOE) 14, no. 11 (November 10, 2018): 4. http://dx.doi.org/10.3991/ijoe.v14i11.9499.

Повний текст джерела

Анотація:

To explore the wireless sensor network (WSN) structure, the cooperative WSN architecture of mass data processing based on cloud computing is studied. The technology of WSN and cloud computing is deeply discussed. The system and node structure of WSN are studied by theoretical analysis method, and the performance of the WSN is studied by using the numerical simulation method. The mass data processing technology based on Map Reduce and its application in WSN are discussed. The numerical simulation method is used to experiment on the architecture of SVC4WSN and MD4LWSN. The relationship between the optimal network number and the node communication radius at different node density is verified. Moreover, the energy and time delay Reduce path is compared with three protocols of LEACH, PEGASIS and PEDAP. The results show that the two Reduce paths have better performance in both network survival time and the total time slot of data acquisition.

Стилі APA, Harvard, Vancouver, ISO та ін.

40

Cheng, Qimin, Deqiao Gan, Peng Fu, Haiyan Huang, and Yuzhuo Zhou. "A Novel Ensemble Architecture of Residual Attention-Based Deep Metric Learning for Remote Sensing Image Retrieval." Remote Sensing 13, no. 17 (August 30, 2021): 3445. http://dx.doi.org/10.3390/rs13173445.

Повний текст джерела

Анотація:

Recently, deep metric learning (DML) has received widespread attention in the field of remote sensing image retrieval (RSIR), owing to its ability to extract discriminative features to represent images and then to measure the similarity between images via learning a distance function among feature vectors. However, the distinguishability of features extracted by the most current DML-based methods for RSIR is still not sufficient, and the retrieval efficiency needs to be further improved. To this end, we propose a novel ensemble architecture of residual attention-based deep metric learning (EARA) for RSIR. In our proposed architecture, residual attention is introduced and ameliorated to increase feature discriminability, maintain global features, and concatenate feature vectors of different weights. Then, descriptor ensemble rather than embedding ensemble is chosen to further boost the performance of RSIR with reduced time cost and memory consumption. Furthermore, our proposed architecture can be flexibly extended with different types of deep neural networks, loss functions, and feature descriptors. To evaluate the performance and efficiency of our architecture, we conduct exhaustive experiments on three benchmark remote sensing datasets, including UCMD, SIRI-WHU, and AID. The experimental results demonstrate that the proposed architecture outperforms the four state-of-the-art methods, including BIER, A-BIER, DCES, and ABE, by 15.45%, 13.04%, 10.31%, and 6.62% in the mean Average Precision (mAP), respectively. As for the retrieval execution complexity, the retrieval time and floating point of operations (FLOPs), needed by the proposed architecture on AID, reduce by 92% and 80% compared to those needed by ABE, albeit with the same Recall@1 between the two methods.

Стилі APA, Harvard, Vancouver, ISO та ін.

41

Shim, Hye-jin, Jee-weon Jung, Ju-ho Kim, and Ha-jin Yu. "Capturing Discriminative Information Using a Deep Architecture in Acoustic Scene Classification." Applied Sciences 11, no. 18 (September 9, 2021): 8361. http://dx.doi.org/10.3390/app11188361.

Повний текст джерела

Анотація:

Acoustic scene classification contains frequently misclassified pairs of classes that share many common acoustic properties. Specific details can provide vital clues for distinguishing such pairs of classes. However, these details are generally not noticeable and are hard to generalize for different data distributions. In this study, we investigate various methods for capturing discriminative information and simultaneously improve the generalization ability. We adopt a max feature map method that replaces conventional non-linear activation functions in deep neural networks; therefore, we apply an element-wise comparison between the different filters of a convolution layer’s output. Two data augmentation methods and two deep architecture modules are further explored to reduce overfitting and sustain the system’s discriminative power. Various experiments are conducted using the “detection and classification of acoustic scenes and events 2020 task1-a” dataset to validate the proposed methods. Our results show that the proposed system consistently outperforms the baseline, where the proposed system demonstrates an accuracy of 70.4% compared to the baseline at 65.1%.

Стилі APA, Harvard, Vancouver, ISO та ін.

42

Jun, Sung-Bae, Chan-Ho Kim, JuKyung Cha, Jin Hwan Lee, Yong-Jae Kim, and Sang-Yong Jung. "A Novel Method for Establishing an Efficiency Map of IPMSMs for EV Propulsion Based on the Finite-Element Method and a Neural Network." Electronics 10, no. 9 (April 29, 2021): 1049. http://dx.doi.org/10.3390/electronics10091049.

Повний текст джерела

Анотація:

In this paper, we introduce a novel method for establishing an efficiency map of interior permanent-magnet synchronous motors that are used for electric vehicle propulsion, by employing the finite-element method (FEM) and a neural network (NN) to reduce the analysis time. The electro-magnetic analysis of motors using the FEM, particularly iron loss analysis, is significantly time-consuming owing to the nonlinearity and the post-processing. Moreover, to obtain an efficiency map, a data map of the d-q flux linkages based on the d-q currents should be established. At this stage, we compute the flux densities in all the elements, and they are learned by the NN to obtain a function of the d-q currents. Subsequently, the iron losses at all operating points are calculated using the learned data via the harmonic loss method. The results of the proposed method indicate that the time required to obtain the efficiency map is reduced; furthermore, the results are validated via a comparison with the FEM results.

Стилі APA, Harvard, Vancouver, ISO та ін.

43

Abed, Qusay Abdullah. "An Analytical Approach to Big Data Issues in the Health Care Sector Using R Model & Hadoop." Webology 19, no. 1 (January 20, 2022): 2196–203. http://dx.doi.org/10.14704/web/v19i1/web19149.

Повний текст джерела

Анотація:

Big data is a term used to depict the availability and exponential growth of data. The data may be structured or unstructured. It is an all-encompassing expression for any assortment of dataset so complex and large that makes it hard to process by use of traditional data processing applications or on-hand data management tools. Despite of the role of Big Data in healthcare adaptation service there is a concerning of how to analysis this data in efficient and significant way. This problem has negatively affected the healthcare management system from the end user level that represented by patient registration to the clink records. To overcome these issues, we have adopted Hadoop to remedy this current situation, and then we add R model for Map Reduce and adopt R Map Reduce for analytical health care records, and raw data at clink. Additionally, a description of other capabilities has been given to facilitate practical application of Big Data services in the healthcare. This article also reports about the designing of Big Data Healthcare Service architecture, which enhances the management of data analysis operations capabilities, regulatory compliance and constructive Healthcare usages.

Стилі APA, Harvard, Vancouver, ISO та ін.

44

Sarrazin, E., M. Cournet, L. Dumas, V. Defonte, Q. Fardet, Y. Steux, N. Jimenez Diaz, E. Dubois, D. Youssefi, and F. Buffe. "AMBIGUITY CONCEPT IN STEREO MATCHING PIPELINE." International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLIII-B2-2021 (June 28, 2021): 383–90. http://dx.doi.org/10.5194/isprs-archives-xliii-b2-2021-383-2021.

Повний текст джерела

Анотація:

Abstract. In a 3D reconstruction pipeline, stereo matching step aims at computing a disparity map representing the depth between image pair. The evaluation of the disparity map can be done through the estimation of a confidence metric. In this article, we propose a new confidence metric, named ambiguity integral metric, to assess the quality of the produced disparity map. This metric is derived from the concept of ambiguity, which characterizes the property of the cost curve profile. It aims to quantify the difficulty in identifying the correct disparity to select. The quality of ambiguity integral metric is evaluated through the ROC curve methodology and compared with other confidence measures. In regards to other measures, the ambiguity integral measure shows a good potential. We also integrate this measure through various steps of the stereo matching pipeline in order to improve the performance estimation of the disparity map. First, we include ambiguity integral measure during the Semi Global Matching optimization step. The objective is to weight, by ambiguity integral measure, the influence of points in the SGM regularization to reduce the impact of ambiguous points. Secondly, we use ambiguity as an input of a disparity refinement deep learning architecture in order to easily locate noisy area and preserve details.

Стилі APA, Harvard, Vancouver, ISO та ін.

45

Liu, Yan. "Rural Financial Mobile Service Management System Based on Big Data." Mobile Information Systems 2022 (March 20, 2022): 1–11. http://dx.doi.org/10.1155/2022/3316460.

Повний текст джерела

Анотація:

Aiming at the problems of poor functionality, low resource utilization, and long response time in the currently designed rural financial mobile service management system, a rural financial mobile service management system based on big data is designed. This paper discusses the ideas and characteristics of big data, as well as the functional needs and development viability of rural financial mobile services. Based on Hadoop’s big data technology and Map Reduce and Spark, a big data analysis service management system architecture that is suitable for the field of rural finance is designed. Based on the overall system architecture, which is combined with linear discriminant analysis and data mining algorithms, the system software architecture is designed to realize system functions. Model the database in the system design process through power designer, and then realize the design of the rural financial mobile service management system based on big data. The experimental results show that the proposed method design system has better functionality, can effectively improve the utilization of system resources, and shorten the system response time.

Стилі APA, Harvard, Vancouver, ISO та ін.

46

Kao, Chi-Chou. "Design and Implementation of Stereoscopic Image Generation." Journal of Circuits, Systems and Computers 28, no. 08 (July 2019): 1950133. http://dx.doi.org/10.1142/s0218126619501330.

Повний текст джерела

Анотація:

In this paper, we proposed the design and implementation of a new stereoscopic image generation system. In the conventional system, the smoothness of depth map can reduce the incidence of image holes, but cause geometric distortions of the image depth. To solve the problems, the depth map is first refined to increase the accuracy of image depth and the quality of images. Next, we derive a hardware-oriented method for 3D warping and improve hole-filling procedures to enhance the performance of image. Finally, the circuit design is presented according to the proposed stereoscopic image generation system to achieve real-time applications. The experimental results demonstrate that the proposed system can improve by 10–27% when compared to existing methods.

Стилі APA, Harvard, Vancouver, ISO та ін.

47

Huang, Huasheng, Jizhong Deng, Yubin Lan, Aqing Yang, Xiaoling Deng, Sheng Wen, Huihui Zhang, and Yali Zhang. "Accurate Weed Mapping and Prescription Map Generation Based on Fully Convolutional Networks Using UAV Imagery." Sensors 18, no. 10 (October 1, 2018): 3299. http://dx.doi.org/10.3390/s18103299.

Повний текст джерела

Анотація:

Chemical control is necessary in order to control weed infestation and to ensure a rice yield. However, excessive use of herbicides has caused serious agronomic and environmental problems. Site specific weed management (SSWM) recommends an appropriate dose of herbicides according to the weed coverage, which may reduce the use of herbicides while enhancing their chemical effects. In the context of SSWM, the weed cover map and prescription map must be generated in order to carry out the accurate spraying. In this paper, high resolution unmanned aerial vehicle (UAV) imagery were captured over a rice field. Different workflows were evaluated to generate the weed cover map for the whole field. Fully convolutional networks (FCN) was applied for a pixel-level classification. Theoretical analysis and practical evaluation were carried out to seek for an architecture improvement and performance boost. A chessboard segmentation process was used to build the grid framework of the prescription map. The experimental results showed that the overall accuracy and mean intersection over union (mean IU) for weed mapping using FCN-4s were 0.9196 and 0.8473, and the total time (including the data collection and data processing) required to generate the weed cover map for the entire field (50 × 60 m) was less than half an hour. Different weed thresholds (0.00–0.25, with an interval of 0.05) were used for the prescription map generation. High accuracies (above 0.94) were observed for all of the threshold values, and the relevant herbicide saving ranged from 58.3% to 70.8%. All of the experimental results demonstrated that the method used in this work has the potential to produce an accurate weed cover map and prescription map in SSWM applications.

Стилі APA, Harvard, Vancouver, ISO та ін.

48

Ma, Li, Zhibin Guan, Xinguan Dai, Hangbiao Gao, and Yuanmeng Lu. "A Cross-Modality Person Re-Identification Method Based on Joint Middle Modality and Representation Learning." Electronics 12, no. 12 (June 15, 2023): 2687. http://dx.doi.org/10.3390/electronics12122687.

Повний текст джерела

Анотація:

Modality differences and intra-class differences have been hot research problems in the field of cross-modality person re-identification currently. In this paper, we propose a cross-modality person re-identification method based on joint middle modality and representation learning. To reduce the modality differences, a middle modal generator is used to map different modal images to a unified feature space to generate middle modality images. A two-stream network with parameter sharing is used to extract the combined features of the original image and the middle modality image. In addition, a multi-granularity pooling strategy combining global features and local features is used to improve the representation learning capability of the model and further reduce the modality differences. To reduce the intra-class differences, the model is further optimized by combining distribution consistency loss, label smoothing cross-entropy loss, and hetero-center triplet loss to reduce the intra-class distance and accelerate the model convergence. In this paper, we use the publicly available datasets RegDB and SYSU-MM01 for validation. The results show that the proposed approach in this paper reaches 68.11% mAP in All Search mode for the SYSU-MM01 dataset and 86.54% mAP in VtI mode for the RegDB dataset, with a performance improvement of 3.29% and 3.29%, respectively, which demonstrate the effectiveness of the proposed method.

Стилі APA, Harvard, Vancouver, ISO та ін.

49

Wang, Jingchuan, Ruochen Tai, and Jingwen Xu. "A Bi-Level Probabilistic Path Planning Algorithm for Multiple Robots with Motion Uncertainty." Complexity 2020 (June 5, 2020): 1–16. http://dx.doi.org/10.1155/2020/9207324.

Повний текст джерела

Анотація:

For improving the system efficiency when there are motion uncertainties among robots in the warehouse environment, this paper proposes a bi-level probabilistic path planning algorithm. In the proposed algorithm, the map is partitioned into multiple interconnected districts and the architecture of proposed algorithm is composed of topology level and route level generating from above map: in the topology level, the order of passing districts is planned combined with the district crowdedness to achieve the district equilibrium and reduce the influence of robots under motion uncertainty. And in the route level, a MDP method combined with probability of motion uncertainty is proposed to plan path for all robots in each district separately. At the same time, the number of steps for each planning is dependent on the probability to decrease the number of planning. The conflict avoidance is proved, and optimization is discussed for the proposed algorithm. Simulation results show that the proposed algorithm achieves improved system efficiency and also has acceptable real-time performance.

Стилі APA, Harvard, Vancouver, ISO та ін.

50

Li, Ming, Meng Yue Yuan, and Ying Cheng Xu. "The Construction of the Knowledge Management System in the Cloud Computing Environment." Applied Mechanics and Materials 713-715 (January 2015): 2366–69. http://dx.doi.org/10.4028/www.scientific.net/amm.713-715.2366.

Повний текст джерела

Анотація:

In order to make the implementation of the KMS more easily and handle the knowledge more efficiently, we propose the KMS in the cloud computing environment. Firstly, we proposed the document, where the explicate knowledge exists in, processing method based on the Map reduce. Then the explicate knowledge can be processed parallel and faster. Afterwards we give the architecture of the KBS in the environments. The organization can rent the different kinds of services according to their requirements. Since the infrastructure is provided by the cloud computing providers, the organization can focus more on the functions of the KMS. It makes the implementation of the KMS more easily with lower costs.

Стилі APA, Harvard, Vancouver, ISO та ін.

Статті в журналах з теми "MAP REDUCE ARCHITECTURE"

Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями