As a key technology in modern society, face detection has become an active subject in the field of pattern recognition and computer vision. In this paper, we propose some applications of analyzing crowd attention based on face detection technology and realize a crowd attention detection system using Haar-like features and Adaboost algorithm. The system consists of image acquisition module, face detection module, display module and data analysis module. At the same time, we adopt the method of empirical research. Using the camera, combined with software named AMcap, the system captures images of crowed during the display of a video regularly. Then, the system detects the faces which are being concerned about this attractive video in images, circling and counting them. In addition, the system displays the data change graph of the crowd face at different moments, and finally calculates the mathematical expected value of crowd attention for further processing such as Big Data technology. After further processing, the system can obtain the data which reflects the degree of concern in a particular sector. Through the above experiment, Facts have proved that the system can easily, accurately and intuitively detect the crowd attention data and has great value in many sectors.
In this paper, we propose a novel integrated circuit and architectural level technique to reduce power consumption of register files in high-performance microprocessors. Our simulation results on 32-nm process show 12.7-14.1% power reduction for ROB (Reorder Buffer)-based microprocessors and 12.4-17.9% power reduction for checkpoint-based microprocessors, respectively, with less than 5% impact on excess time.
In the traditional reliability test for system, the reliability of software is usually regarded as "1", therefore the software and hardware correlated failures cannot be motivated, which lead to the inaccuracy of the reliability evaluation result. An approach of combined reliability test for software-hardware system is proposed in this paper. The combined reliability test profile for software-hardware system is structured primarily, then the comprehensive environment stress test and software reliability test are conducted integratedly, which depicts the actual serve condition of the software-hardware system. Some software and hardware correlated failures can be found in the process of the combined test, which contribute a lot to the accuracy of the system reliability evaluation.
A system for estimating the leakage power, the active power and the delay of the domino OR gates with the sleep transistor based on wavelet neural networks in 45 nm technology is proposed. By studying the impact of the power gating technique (PGT) on the power and delay characteristics, the proposed model could estimate the nonlinear changing of the active power, the leakage power and the delay of the different inputs dynamic OR gates with fast speed convergence and high precision. The trend of the estimating curve is discussed. At last, the comparison between the footer and the header sleep transistor technique is given.
Far field radio frequency (RF) harvesting technique have become popular method to power wireless sensor network (WSN) recently. However, due to the low efficiency of RF energy harvester, RF powered WSN is unable to perform dynamic network allocation. Accordingly, the functionality of WSN is limited. This paper presents a practical RF powered wireless sensor node design that could dynamic join the network and unicast data packet. A non-ideal supercapacitor storage estimate model is proposed. Test result indicated the proposed model can accurate estimate the storage state, the RF energy harvesting node could dynamically join network as far as 10 meter.
Stuck-At-Fault (SAF) defect of memristor generated from immature fabrication and heavy device utilization makes neuromorphic computing systems commercially unavailable. To mitigate this problem, a Reconfigurable Mapping Algorithm (RMA) is proposed in this paper. Based on the analysis for the VGG8 model with CIFAR10 dataset, the experiment results show that the RMA is efficient in restoring the inference accuracy up to 90% (the original accuracy without SAF) under SAFs from 0.1% to 50%, where Stuck-At-One (SA1): Stuck-At-Zero (SA0) = 5:1, 1:5, and 1:1. Additionally, the RMA improves the accuracy more than 50% in presence of high nonlinearity LTP = 4 and LTD = -4 and the standard conductance drift (10 years at 85 degrees Celsius) nearly has no influence on the inference accuracy of the DNN with the RMA.
The interaction area of sea and land,the coastal zone is of ecological fragility.With the fast development of economy and a substantial increase in the population,human impacts more and more on the coastal ecology.It will become a focus of society that how to evaluate the environment impacts produced by the coastal resources exploitation and infrastructure construction.Based on the remote sensing information extraction technique,the assessment indexes system of the eco-environmental basic quality in coastal zone was established,according to the experts grading,the marine expert weight factors were decided with the Delphi technique.The geophysical information system to evaluate the coastal zone environment was built.It was very convenient to assessment the time-space distribution and variation law in the coastal zone studied.The method is useful to build the coastal zone management decision system,and provided the technical support for the sustainable development in coastal zone and government better to manage the coastal zone resources.
This paper applied UVM (Universal Verification Methodology), an advanced verification methodology which was based on SystemVerilog language to build AES (Advanced Encryption Standard) IP verification platform and environment.Functional verification of the AES module, through a large number of testcases and constrained random test could achieve 100% functional coverage.In addition, the testcases will be run by the verification platform with automatic generation.It both can run the specified testcases in the terminal, which can customize the testcases variables through the orientation test method, and can automatically run all the testcases of the verification platform.This method could improve the efficiency and reusability of the verification, and the simulation results show that the AES IP design is successful.
Ancient wooden buildings and structures are of great value and are memorable that shall be protected by the state in the same way as cultural relics. Based on Wireless Sensor Net (WSN), a design of the node system for the ancient wooden building fire prevention is presented. Construction of Wireless Sensor Net which is working at 433 MHz ISM frequency is supplied and is composed of PC internet, Coordinators, nodes. The coordinator is based on ARM s3c2440 microprocessor and Linux operating system, which can communicate with PC and Internet, and can communicate with node system. Nodes can communicate with each other. With many sensor tags, the node can sense environment. Besides, a developed software tool helps to improve the system performance, such as the address matching, anti-collision, checking, identification, and real time calculation. The proposed construction has advantages of simple structure, low cost, and low power loss. Problems of ancient wooden buildings and structures which have been protected by system with wire line have been resolved. The node system overcomes the difficulty of wire lines that are easy to be fired.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
