The traditional super-resolution method has limited ability of feature extraction and feature expression, which cannot meet the requirements of high quality image in practical application. This paper mainly applies the relevant theories of deep learning to image super-resolution reconstruction technology. By comparing three classical network models used for image super-resolution (SR), finally a generative adversarial network (GAN) is selected to implement image super-resolution, which is called SRGAN. SRGAN consists of a generator and a discriminator that uses both perceived loss and counter loss to enhance the realism of the output image in detail. Compared with other algorithms, although the improvement of PSNR and SSIM values of the SGRAN network obtained by the final training is not obvious, the output high-resolution images are the best in the subjective feelings of human eyes, and the reconstruction effect in the image details is far higher than that of other networks.
In order to reduce the burden of child care and better child care.A cradle with artificial intelligence technology is designed for families to raise child . The data of baby shaking are collected and analyzed by the Micro Control Unit, so that the cradle bed can bionic cradle shaking. The SVM database training of infant crying can realize the recognition of infant crying and determine the specific meaning of crying, such as hunger, excretion, pain and other factors, and timely inform parents; Based on ROS robot operating system and iflytek platform, it can carry out natural language interaction and autonomous navigation. Parents can call the baby cradle and let it reach the designated position automatically to achieve autonomous obstacle avoidance and path planning without manual interference. At the same time, the camera can view the baby's status and transmit the real-time picture to the mobile phone APP.
The formation of successful corporate strategy among vertically integrated organizations is predicated upon a plethora of dynamic relationships among buyer-seller firms. Albeit growing in interest, there is a paucity of research that focuses on predicting the nature of interfirm relationships among Japanese keiretsu members. Discerning this knowledge can help formulate successful strategic decisions, such as whether to continue procuring parts or increasing future investments in partner firms. As studies on predicting interfirm relationships among keiretsu member firms has been scant, this research offers insights by illustrating a newer approach for making decisions regarding corporate strategy. Using data collected on transaction from Yokokai—parts suppliers of Mazda—in this study a new model is developed to predict the nature of interfirm relationships using the degree index and DEA model. The primary contribution of this research is that interfirm relationships not only depend on future trends, but are also determined by the interactions among member firms of a keiretsu.
The original intention of this device is to allow people to use social book resources more effectively. Users can share the books in their hands through this device. Multiple devices connected by cloud servers can form a book storage network to realize the circulation of paper books. The camera is used for the ISBN code identification of books, the WiFi module is used for the wireless network communication between the device and the background server, the bluetooth module is used for the near distance communication between the device and the mobile terminal, and the infrared module is used for detecting the storage state of the device. Equipment ISBN read, storage of equipment state inspection, such as simple data processing done by the device with a built-in MCU, user registration, user reading habits, such as book search more complex data calculated by the background server processing,.By borrowing the concept of distributed computing, implements the equipment, and efficient use of server resources, reduce the workload of the entire system at the same time.
Evaluating the test suite that contains redundant test cases is necessary to ensure the efficiency of the testing and reducing the cost of testing. The principle of redundant test cases on this research is any test cases on a similar path executed with a similar high value of normalized Euclidean distance. The first, the similarity calculated between the test cases and path coverage uses Euclidean distance. The value of the Euclidean distance on the test case with the lowest value of distance indicating highly similar and possibly executing similar lines of code. The normalized Euclidean distance is using to normalize the value from Euclidean distance result. The experiment uses two java programs. Each redundancy score is 0.37 and 0.67, respectively. It means 37% and 67% of the test cases should be avoided because there are inefficiency test cases on the test suite. The research confirms redundant test cases can be identified by Euclidean distance and normalized Euclidean distance to evaluate the test suite.
In this paper, the dynamic characteristics of a chaotic system without equilibrium point are studied. Through numerical simulation and theoretical analysis, the chaos characteristics of the system without equilibrium point are studied. In this paper, the synchronous control method based on state observer is used. First, the state observer system is designed according to the original system. And then the simulation results are obtained. At the end of this paper, we give the advantages and disadvantages of this synchronization method.
Before the smart home has appeared in people's vision, people do not have a deep understanding. But we may think something is insignificant in daily life. The article designs a simple, convenient, easy way to operate, and connected with the real life of smart home system. This design is based on the STC89C52 microcomputer as the control system, the smoke sensor and temperature and humidity sensor is used to detect the external environment. The system uses the button to adjust the threshold of the smoke concentration limit. LCD1602 can display the sampled external environment information in real time. This system can be used for anti-theft in shopping malls, warehouse, bank and other occasions. The device has a strong guiding significance for the current people's daily life.
Quad-rotor UAV is an unmanned aircraft controlled by radio remote control equipment and independent program control device. In the past five years, unmanned intelligent equipment has attracted extensive attention. At present, the application of UAV in aerial photography, agriculture, plant protection, mapping and other fields has greatly expanded the application of UAV itself. Our UAV is based on TI MSP432, which can be connected to PC via USB port. This printed circuit board is used to transmit the program for the flight control of UAV. The OpenMV module serves as the data source of the line patrol controller, which is the top-level controller, the same level as the remote controller. The IMU unit calculates information to attitude controller, in order to keep the flight of UAV stable. After the IMU solution information is fused with the optical flow sensor, the information is sent to the horizontal controller to control the flight of the UAV in the horizontal direction. Similarly, After the IMU information is fused with the laser height information, the height controller is applied to control the flight height of UAV.
This paper aims at developing a system that will help in in-home care for elderly or disabled people. The system can record the patient vital parameters such as temperature, SpO2, ECG, heart rate, bed moisture and fall off sensor with features of the system ability to adapt new sensors if needed. The system could be installed at the bathroom or shower area at the patient terminal and transmit the critical situations such as high or low values to an alarming system. The system will be developed using the National Instrument Wireless Sensor Network (NI-WSN) to control the crucial events transmission and LabVIEW software to design the user interface.
With the progress of the times, remote sensing technology has become more and more mature, and remote sensing data has become more and more complex with the continuous progress of technology. Remote sensing data has the characteristics of unstructured and large amount of data, so the distributed system can be used to store it. In this paper, according to the characteristics of space remote sensing data, we build a distributed storage system for space remote sensing data. According to the unstructured characteristics of space remote sensing data, distributed storage is used to store the data in virtual environment Hadoop distributed cluster is built to realize the distributed storage of space remote sensing data.