An ultrasonic 3-D object identification system using pulse neural network

Author(s):  
Hidetoshi Nonaka
Molecules ◽  
2021 ◽  
Vol 26 (11) ◽  
pp. 3178
Author(s):  
Shan-Ju Yeh ◽  
Jin-Fu Lin ◽  
Bor-Sen Chen

Human skin aging is affected by various biological signaling pathways, microenvironment factors and epigenetic regulations. With the increasing demand for cosmetics and pharmaceuticals to prevent or reverse skin aging year by year, designing multiple-molecule drugs for mitigating skin aging is indispensable. In this study, we developed strategies for systems medicine design based on systems biology methods and deep neural networks. We constructed the candidate genomewide genetic and epigenetic network (GWGEN) via big database mining. After doing systems modeling and applying system identification, system order detection and principle network projection methods with real time-profile microarray data, we could obtain core signaling pathways and identify essential biomarkers based on the skin aging molecular progression mechanisms. Afterwards, we trained a deep neural network of drug–target interaction in advance and applied it to predict the potential candidate drugs based on our identified biomarkers. To narrow down the candidate drugs, we designed two filters considering drug regulation ability and drug sensitivity. With the proposed systems medicine design procedure, we not only shed the light on the skin aging molecular progression mechanisms but also suggested two multiple-molecule drugs for mitigating human skin aging from young adulthood to middle age and middle age to old age, respectively.


2021 ◽  
Vol 16 (2) ◽  
pp. 188-195
Author(s):  
Keyuan Liu ◽  
Haibin Li ◽  
Ya Wang

The weak direct current (DC) signals detected and converted by the photodetector are output to the mobile phone by voltage/frequency switching, and the signals are processed by the mobile phone APP and audio conversion module. The photodetector is equipped with the automatic switching function to design an optical power meter and detect weak signals. Meanwhile, the optical cable identification system is analyzed and combined with the optical power meter to generate an optical fiber sensing network to improve the weak alternating current (AC) signal detection. This network needs data fusion in sensor nodes’ data collection. The cluster routing protocol is introduced and combined with the back propagation neural network (BPNN) to propose a method suitable for this photoelectric transmission and improve the information fusion and accuracy. In the experiment, the optical power meter is output in gears first, and the output waveforms are normal. The photodiode’s optical power is adjusted to obtain different frequencies on the oscilloscope. In the proposed optical fiber sensing network, weak AC signals are amplified significantly, and different optical fiber lines can be distinguished in the optical cables. The proposed information collection method can reduce network communication and node energy consumption.


Author(s):  
V. K. Zheleznyak ◽  
V. B. Tolubko ◽  
L. P. Kriuchkova ◽  
A. P. Provozin

In the work the technology of radio-frequency identification of objects with inductive coupling is considered, using passive electric oscillating circuits tuned to fixed frequencies from the working frequency range as identification features of the object. The choice of the primary measuring transducer and the informative parameter is based on the results of the analysis of the system of inductively coupled active and passive electric oscillation circuits, known from the theory of radio engineering circuits. The parameters of the measuring transducer ensuring the fulfillment of the requirements for identification and localization of objects specified by technological conditions are substantiated. Factors that are potentially dangerous with respect to reducing the information reliability of the measuring transducer are considered, as well as the possibility of reducing their influence to a minimum. The problems of experimental research are formulated. It is shown that the analysis can be performed by software discrete adjustment of the primary measuring transducer and the generator feeding it. In this case, the task of increasing the speed is targeted at decreasing the duration of the step of tuning the primary measuring transducer. The required reliability of object identification is achieved by: ensuring high stability of the frequencies of the generator supplying the primary measuring transducer; accuracy and stability of tuning of the primary measuring transducer to the frequencies of the supplying generator; protection of the primary measuring transducer from the influence of interference generated by external sources and other measuring converters of the object identification system (electromagnetic compatibility of the object identification system); sufficient magnitude of the response of the primary measuring transducer to the introduction of passive electrical oscillation circuits; sufficient frequency tuning interval for passive electric oscillation circuits; accuracy and stability of tuning of passive electric oscillation circuits; stability of the detection threshold relative to the initial level of the informative parameter. Electromagnetic compatibility of measuring transducers, whose sensing elements are in the zone of mutual influence, is provided by synchronizing the operation of measuring transducers with shunting of inactive sensors, screening, mutual orientation and spacing of sensing elements.


2021 ◽  
Vol 2 ◽  
Author(s):  
Chengjie Li ◽  
Lidong Zhu ◽  
Zhongqiang Luo ◽  
Zhen Zhang ◽  
Yilun Liu ◽  
...  

In space-based AIS (Automatic Identification System), due to the high orbit and wide coverage of the satellite, there are many self-organizing communities within the observation range of the satellite, and the signals will inevitably conflict, which reduces the probability of ship detection. In this paper, to improve system processing power and security, according to the characteristics of neural network that can efficiently find the optimal solution of a problem, proposes a method that combines the problem of blind source separation with BP neural network, using the generated suitable data set to train the neural network, thereby automatically generating a traditional blind signal separation algorithm with a more stable separation effect. At last, through the simulation results of combining the blind source separation problem with BP neural network, the performance and stability of the space-based AIS can be effectively improved.


Sign in / Sign up

Export Citation Format

Share Document