Articoli di riviste sul tema "Analog-to-feature converter"
Segui questo link per vedere altri tipi di pubblicazioni sul tema: Analog-to-feature converter.
Cita una fonte nei formati APA, MLA, Chicago, Harvard e in molti altri stili
Vedi i top-50 articoli di riviste per l'attività di ricerca sul tema "Analog-to-feature converter".
Accanto a ogni fonte nell'elenco di riferimenti c'è un pulsante "Aggiungi alla bibliografia". Premilo e genereremo automaticamente la citazione bibliografica dell'opera scelta nello stile citazionale di cui hai bisogno: APA, MLA, Harvard, Chicago, Vancouver ecc.
Puoi anche scaricare il testo completo della pubblicazione scientifica nel formato .pdf e leggere online l'abstract (il sommario) dell'opera se è presente nei metadati.
Vedi gli articoli di riviste di molte aree scientifiche e compila una bibliografia corretta.
1
Back, Antoine, Paul Chollet, Olivier Fercoq e Patricia Desgreys. "Power-aware feature selection for optimized Analog-to-Feature converter". Microelectronics Journal 122 (aprile 2022): 105386. http://dx.doi.org/10.1016/j.mejo.2022.105386.
2
Agarwal, Ritika, e Sameer Sonkusale. "Input-Feature Correlated Asynchronous Analog to Information Converter for ECG Monitoring". IEEE Transactions on Biomedical Circuits and Systems 5, n. 5 (ottobre 2011): 459–67. http://dx.doi.org/10.1109/tbcas.2011.2116787.
3
Zhao, Ying Kai, Liang Yin, Zhao Tong Liu, Wei Ping Chen e Xiao Wei Liu. "A 16 Bits 500 kHz Sigma-Delta DAC for Silicon Micro Gyroscope". Key Engineering Materials 645-646 (maggio 2015): 605–9. http://dx.doi.org/10.4028/www.scientific.net/kem.645-646.605.
Abstract (sommario):
In this paper, a 16 Bits 500 kHz Sigma-Delta DAC for Silicon Micro Gyroscope is proposedin order to enhance the precision of the digital to analog converter level.The interpolation filterhas achieved 64 times interpolation function,using three cascaded manner, it employs three level cascaded of FIR filterstructure. It achieves a 64 times oversampling feature. The signalbandwidth of the designs interpolation filter is 100 kHz, SNR reach 106dB. Fifth-order single-loop structure CIFB achieve noise shaping modulator function to verify the stability of the system, after the completion of CSD coefficient coding, signal to noise ratio reached 119.7dB, effective bits reached 19.59. The switched capacitor technology actualize analog reconstruction filter module, and using a typically switched capacitor DAC achieved high jump "0, 1" digital signal is converted into an analog signal, the digital-analog conversion achieved.
4
Manokhin, Mikhail, Paul Chollet e Patricia Desgreys. "Towards Flexible and Low-Power Wireless Smart Sensors: Reconfigurable Analog-to-Feature Conversion for Healthcare Applications". Sensors 24, n. 3 (3 febbraio 2024): 999. http://dx.doi.org/10.3390/s24030999.
Abstract (sommario):
Analog-to-feature (A2F) conversion based on non-uniform wavelet sampling (NUWS) has demonstrated the ability to reduce energy consumption in wireless sensors while employed for electrocardiogram (ECG) anomaly detection. The technique involves extracting only relevant features for a given task directly from analog signals and conducting classification in the digital domain. Building on this approach, we extended the application of the proposed generic A2F converter to address a human activity recognition (HAR) task. The performed simulations include the training and evaluation of neural network (NN) classifiers built for each application. The corresponding results enabled the definition of valuable features and the hardware specifications for the ongoing complete circuit design. One of the principal elements constituting the developed converter, the integrator brought from the state-of-the-art design, was modified and simulated at the circuit level to meet our requirements. The revised value of its power consumption served to estimate the energy spent by the communication chain with the A2F converter. It consumes at least 20 and 5 times less than the chain employing the Nyquist approach in arrhythmia detection and HAR tasks, respectively. This fact highlights the potential of A2F conversion with NUWS in achieving flexible and energy-efficient sensor systems for diverse applications.
5
Triwiyanto, T., Endro Yulianto, I. Dewa Gede Hari Wisana, Muhammad Ridha Mak’ruf, Bambang Guruh Irianto, Endang Dian Setioningsih, Ridho Hanggara Mukti e Dhimas Sugma Herdinanta. "Electromyography Feature Analysis to Recognize the Hand Motion in a Prosthetic Hand Design". Journal of Biomimetics, Biomaterials and Biomedical Engineering 50 (aprile 2021): 25–37. http://dx.doi.org/10.4028/www.scientific.net/jbbbe.50.25.
Abstract (sommario):
The increasing need for prosthetic hands for people with disabilities is one reason for innovation in the field of prosthetic hands to create the best prosthetic hand technology. In the design of EMG-based prosthetic hands, this is determined by several things, among others, the selection of features. The selection of the right features will determine the accuracy of the prosthetic hand Therefore, the purpose of this study is to analysis the time domain feature to obtain the best feature in classifying the hand motion. The contribution of this work is able to detect 4 movements in real time, namely hand close, flexion, extension, and relax. The Electromyograph signal is tapped using an electromyograph (EMG) dry electrode sensor in which there is a circuit of EMG instrumentation amplifier. Furthermore, the analog EMG signal data is processed through the ADC (Analog to Digital Converter) by using MCP3008 device. EMG signal data is processed in Raspberry Pi. A feature extraction process is applied to reduce data and determine the characteristics of each hand movement. Feature extraction used is MAV (mean absolute value), SSI (sign slope integral), VAR (variance), and RMS (root mean square). From the results of the four-time domain feature, then the best feature extraction is determined using scatter plot and Euclidean distance. The results that have been carried out on ten people with each person doing ten sets of movements (hand close, flexion, extension, relax), showing the best Euclidean distance results, is the RMS feature, with a value of 2608.07. This data is the result of the best feature extraction analysis through the method of calculating the distance of feature extraction data using Euclidean distance. This analysis of time domain feature is expected to be useful for further experiment in machine learning implementation so that it can be obtained an effective prosthetic hand.
6
Sahu, Anil Kumar, Vivek Kumar Chandra e G. R. Sinha. "Analysis of Quantization Noise and Power Estimation of Continuous-Time Delta Sigma Analog-to-Digital Converter Using Test Enable Feature For 4G Radios". International Journal of Informatics and Communication Technology (IJ-ICT) 7, n. 2 (1 agosto 2018): 82. http://dx.doi.org/10.11591/ijict.v7i2.pp82-88.
Abstract (sommario):
<span>This paper presents a novel approach for completely test enable feature and low-voltage delta– sigma analog-to-digital (A/D) converters for cutting edge wireless applications. Oversampling feature of ADCs and DACs is enough to meet the requirement related to in-band and adjacent channel leakage ratio (ACLR) execution of 3G/4G portable radio. The quantization noise which is not filtered in ADC is addressed. We have achieved work power-optimization and test enable feature of oversampling ADC is uses in design and simulation so that the problem of quantization error in continues time sigma delta ADC is solved. This paper suggests support to designer for selecting appropriate topologies with various channel arrangements, number of bits and oversampling issues. A test enable feature of CT A/D is presented introducing the test signal generation (TSG) and the COrdinate Rotation Digital Computer (CORDIC) for evaluating the performance of ADC. This helps in addressing the challenge of 4G and upcoming 5G wireless radio. System level plan of a delta–sigma modulator ADC for 4G radios is studied</span><span lang="IN">.</span>
7
Van den Bossche, Alex, Ekaterina Dimitrova, Vencislav Valchev e Firgan Feradov. "A simplified controller and detailed dynamics of constant off-time peak current control". Journal of Electrical Engineering 68, n. 5 (1 settembre 2017): 390–95. http://dx.doi.org/10.1515/jee-2017-0072.
Abstract (sommario):
Abstract A fast and reliable current control is often the base of power electronic converters. The traditional constant frequency peak control is unstable above 50 % duty ratio. In contrast, the constant off-time peak current control (COTCC) is unconditionally stable and fast, so it is worth analyzing it. Another feature of the COTCC is that one can combine a current control together with a current protection. The time dynamics show a zero-transient response, even when the inductor changes in a wide range. It can also be modeled as a special transfer function for all frequencies. The article shows also that it can be implemented in a simple analog circuit using a wide temperature range IC, such as the LM2903, which is compatible with PV conversion and automotive temperature range. Experiments are done using a 3 kW step-up converter. A drawback is still that the principle does not easily fit in usual digital controllers up to now.
8
Kim, Keonwook, e Yujin Hong. "Gaussian Process Regression for Single-Channel Sound Source Localization System Based on Homomorphic Deconvolution". Sensors 23, n. 2 (9 gennaio 2023): 769. http://dx.doi.org/10.3390/s23020769.
Abstract (sommario):
To extract the phase information from multiple receivers, the conventional sound source localization system involves substantial complexity in software and hardware. Along with the algorithm complexity, the dedicated communication channel and individual analog-to-digital conversions prevent an increase in the system’s capability due to feasibility. The previous study suggested and verified the single-channel sound source localization system, which aggregates the receivers on the single analog network for the single digital converter. This paper proposes the improved algorithm for the single-channel sound source localization system based on the Gaussian process regression with the novel feature extraction method. The proposed system consists of three computational stages: homomorphic deconvolution, feature extraction, and Gaussian process regression in cascade. The individual stages represent time delay extraction, data arrangement, and machine prediction, respectively. The optimal receiver configuration for the three-receiver structure is derived from the novel similarity matrix analysis based on the time delay pattern diversity. The simulations and experiments present precise predictions with proper model order and ensemble average length. The nonparametric method, with the rational quadratic kernel, shows consistent performance on trained angles. The Steiglitz–McBride model with the exponential kernel delivers the best predictions for trained and untrained angles with low bias and low variance in statistics.
9
Yeh, Yun Chi, Tsung Fu Chien, Cheng Yuan Chang e Tsui Shiun Chu. "A Mahalanobis Distance Measurement Method to Analyze Current Waveform for Determining the Motor’s Quality Types". Applied Mechanics and Materials 870 (settembre 2017): 317–22. http://dx.doi.org/10.4028/www.scientific.net/amm.870.317.
Abstract (sommario):
This study proposes a Mahalanobis Distance Measurement (MDM) method to analyze current waveform for determining the motor’s quality types. The MDM method consists of three major stages: (i) the preprocessing stage which is for enlarging motor current waveforms’ amplitude and eliminating noises, and includes signal amplitude amplifier, filter circuit (eliminating noises), and analog-to-digital converter (ADC) parts, (ii) the qualitative features stage which is for qualitative feature selection on motor current waveforms, and (iii) the classification stage which is for determining motor quality types using the MDM method. It can recognize defective motors and their defective types in less than 0.5 second. In the experiment, the total classification accuracy (TCA) was approximately 99.03% in average. The proposed method has the advantages of good detection results, no complex mathematic computations, hi-speed, and hi-reliability.
10
Fang, Ni, Dong Wang, Xiangming Sun, Chaosong Gao, Ran Chen, Zhuo Zhou, Shiqiang Zhou, Cheng Lian e Zijian Lang. "50.3 ps time resolution and an 11-channel time measuring chip for Topmetal detectors". Journal of Instrumentation 19, n. 03 (1 marzo 2024): C03047. http://dx.doi.org/10.1088/1748-0221/19/03/c03047.
Abstract (sommario):
Abstract The Topmetal detector, utilized in this investigation, is a direct-type CMOS pixel sensor known for its distinctive feature of employing exposed metal at the top of each pixel to directly capture external charged particles. This method generates electrical signals through the induction of charge. At present, it is mainly used in gas pixel detector(GPD) and particle beam monitoring. In this paper, we present a new front-end design aimed at enhancing the capabilities of the Topmetal pixel detector. The focus is on incorporating a Time-Digital Conversion (TDC) ASIC into the front-end, with the objective of achieving high-precision time measurement in addition to superior position resolution. The function of the TDC is achieved by the two reverse delay chains, 11 edge acquisition circuits Time-to-Amplitude Converter (TAC), analog gate, weight count module, and Wilkinson Analog-to-Digital Converter (ADC). Coarse time measurement is implemented based on a counter with a working frequency of 500 MHz, and fine time measurement is implemented by the combination of TAC and ADC. The design prototype was taped out with the GSMCR130 nm technology. Test results show that this circuit can handle up to 11 consecutive cases, with the minimum time interval of adjacent cases being 500 ps and the bin size up to 2 ps. The time measurement precision is better than 50.3 ps RMS and the PVT(Process Voltage Temperature) robustness of the input delay chain circuit is validated, showing the stable performance of the design.
11
Liu, Huan, Hao Bin Dong, Jian Ge, Pei Pei Guo, Bing Jie Bai e Cheng Zhang. "An Improved Tuning Control Algorithm Based on SVD for FID Signal". Journal of Advanced Computational Intelligence and Intelligent Informatics 21, n. 1 (20 gennaio 2017): 133–38. http://dx.doi.org/10.20965/jaciii.2017.p0133.
Abstract (sommario):
The free induction decay (FID) quality signal of a proton precession magnetometer is closely related to tuning precision. To solve the commonly used current tuning problem method, we propose improving control algorithm tuning based on singular value decomposition (SVD). The space matrix is constructed by acquiring an analog-to-digital converter (ADC) for untuned FID signals, then conducting SVD to eliminate noise and obtain a useful signal. The fast Fourier transform (FFT) is then applied to the denoised FID signal to extract the time-frequency feature. Based on theory analysis, simulation modeling and actual FID signal testing, results show that compared to general tuning methods such as peak detection and auto correlation, our proposed algorithm improves sensor tuning precision and shortens tuning process time to one second or less.
12
Ghadigaonkar, Rajas, Vedant Barai e Prof Amit Kukreja. "Smart Automated Irrigation System using Wireless Technology". International Journal for Research in Applied Science and Engineering Technology 12, n. 4 (30 aprile 2024): 4629–34. http://dx.doi.org/10.22214/ijraset.2024.61033.
Abstract (sommario):
Abstract: The need for agricultural output has surged due to the exponential rise of the world population, resulting in a strain on water supplies and a need for more effective irrigation systems. The goal of this project is to optimize water utilization in agricultural settings by presenting an automated and intelligent irrigation system. Based on current soil moisture levels, the system monitors and regulates irrigation using soil moisture sensors, an Arduino Nano, and a Raspberry Pi 3B+. By converting analog signals from the soil moisture sensor into digital data, the Arduino Nano serves as an analog-to-digital converter. This digital data is sent to the Raspberry Pi 3B+, which acts as the central control unit. A MOSFET is then triggered to activate a relay that is coupled to a 5V DC water pump when the moisture levels drop below a certain threshold. The system also has wireless connection, which enables remote control and monitoring via an Android application. Users have the ability to manually override the automatic system if needed, monitor the moisture content of the soil, and turn on or off the water pump. This feature improves the usability and flexibility of the system.
13
Faghani, Maral, Hamidreza Rezaee-Dehsorkh, Nassim Ravanshad e Hamed Aminzadeh. "Ultra-Low-Power Voice Activity Detection System Using Level-Crossing Sampling". Electronics 12, n. 4 (5 febbraio 2023): 795. http://dx.doi.org/10.3390/electronics12040795.
Abstract (sommario):
This paper presents an ultra-low-power voice activity detection (VAD) system to discriminate speech from non-speech parts of audio signals. The proposed VAD system uses level-crossing sampling for voice activity detection. The useless samples in the non-speech parts of the signal are eliminated due to the activity-dependent nature of this sampling scheme. A 40 ms moving window with a 30 ms overlap is exploited as a feature extraction block, within which the output samples of the level-crossing analog-to-digital converter (LC-ADC) are counted as the feature. The only variable used to distinguish speech and non-speech segments in the audio input signal is the number of LC-ADC output samples within a time window. The proposed system achieves an average of 91.02% speech hit rate and 82.64% non-speech hit rate over 12 noise types at −5, 0, 5, and 10 dB signal-to-noise ratios (SNR) over the TIMIT database. The proposed system including LC-ADC, feature extraction, and classification circuits was designed in 0.18 µm CMOS technology. Post-layout simulation results show a power consumption of 394.6 nW with a silicon area of 0.044 mm2, which makes it suitable as an always-on device in an automatic speech recognition system.
14
Ratnawati, Nur, e Sunardi Sunardi. "Load Characteristics with Current Detection Using an Arduino Based ACS712 Sensor". Buletin Ilmiah Sarjana Teknik Elektro 2, n. 2 (21 luglio 2020): 83. http://dx.doi.org/10.12928/biste.v2i2.1522.
Abstract (sommario):
This study discusses tools for digital current monitoring using an Arduino-based ACS712 sensor. The current sensor ACS712 5A uses the principle of hall effect and is a current sensor whose circuit complexity is simple. The purpose of this microcontroller is to read data obtained from the sensor using the Analog to Digital Converter (ADC) feature and then display it in the serial monitor. The ATMEGA328 microcontroller is assisted by a current measuring circuit equipped with a sensor mounted in series against the circuit to be measured in order to measure the current flowing in the circuit. The test results show that the sensor can measure the current value at its peak value with an error value of -0.066 and a standard deviation value of 0.011419. Based on the test results it can be seen that the tool can work well and has a good accuracy rate.
15
Fernández, Alejandro, Pedro Fernández, Fernando Peña e David Blanco. "On-Machine CIS SoC-Based Layerwise Inspection System for MEX Additive Manufacturing". Key Engineering Materials 961 (11 ottobre 2023): 143–50. http://dx.doi.org/10.4028/p-p0iycb.
Abstract (sommario):
Additive manufacturing processes build three-dimensional objects usually following a layer-upon-layer strategy. An interesting feature of this strategy is that each layer could be inspected before the next one is deposited. On-machine integration of layerwise inspection systems would not only allow for early characterization of the dimensional and geometric quality of the part, but also for the detection of intralayer defects. Contact image sensors (CIS), such as those used in desktop flatbed scanners, could be used for this purpose since they would provide bi-dimensional digital images of the whole layer and its neighborhood. CIS images combine high resolutions with a reduced acquisition time. In this work, a material extrusion (MEX) additive manufacturing system, with layerwise inspection capabilities is proposed. The system has been equipped with the CIS that Epson uses in its Perfection V39 flatbed scanner. The sensor provides two analog output signals, each one consisting on 2584 voltage levels, that represent the amount of light reflected by the material. This analog information is sent to a parallel AD converter, where an 8-bit encoding is assigned to each one of the pixels on the digitized image. To overcome microcontroller-related problems, a Zynq®-7000 system-on-chip (SoC) has been used. This SoC integrates an ARM® based processor, with the hardware programming of a field programmable gate array (FPGA). This architecture ensures an accurate and controlled readout of the various AD converters. The resultant digital image of each layer could then be then processed using different algorithms to detect defects, extract the geometry of the layer contour and characterize the dimensional and geometric quality of the object. In the example provided, a forced error consisting on 0.2 mm height local deviations, caused by a variation in extrusion temperature, was identified from 2D grayscale images obtained with the CIS sensor.
16
Hou, Linjie, Yvtao Liu, Weikun Xie, Zhijian Dai, Wanyv Yang e Yijiu Zhao. "Statistical neural network (SNN) for predicting signal-to-noise ratio (SNR) from static parameters and its validation in 16-bit, 125-MSPS analog-to-digital converters (ADCs)". Review of Scientific Instruments 93, n. 8 (1 agosto 2022): 084701. http://dx.doi.org/10.1063/5.0093709.
Abstract (sommario):
In the analog-to-digital converter (ADC) test process, the static and dynamic performance parameters are the most important, and the tests for these parameters account for the bulk of the ADC test cost. These two types of parameters follow certain relationships, which are incorporated into the ADC test to reduce the cost. In this paper, we focus on the signal-to-noise ratio (SNR), a key indicator of the dynamic performances of ADCs. A statistical neural network (SNN) with two hidden layers was constructed to predict the SNR from the feature variables, which were extracted from the static parameters. A 16-bit, 125-MSPS ADC was used to evaluate the proposed prediction model. Compared to the measured SNR obtained by traditional fast Fourier transform based test methods, the predicted value had a mean average error of only 0.75 dB. In addition, the Shapley additive explanations interpreter was adopted to analyze the feature dependences of the SNN model, and the results demonstrated that the deterioration of the integral nonlinearity-curve-related features could significantly decrease the SNR, which is consistent with previous research results. The reported results demonstrated that, at the cost of a slight loss of accuracy, the proposed SNN can significantly reduce the test complexity, avoid dynamic parameter measurements, and reduce the total test time by about 4%.
17
Liu, Qiuxia. "Intelligent Water Quality Monitoring System Based on Multi-Sensor Data Fusion Technology". International Journal of Ambient Computing and Intelligence 12, n. 4 (ottobre 2021): 43–63. http://dx.doi.org/10.4018/ijaci.2021100103.
Abstract (sommario):
The intelligent water quality monitoring system takes the single chip microcomputer STM32F103C8T6 as the control core to collect signals of each sensor module and converts the collected parameters into effective digital signals by using the internal analog-to-digital converter. The data gathered by the acquisition center is sent to the analysis and processing center through the ZigBee module E18. In the analysis and processing center, data is fused and processed by the single chip microcomputer STC12C5A60S2. The data after fusion is sent to the monitoring management center through the GPRS module SIM800C. For improving the monitoring precision of the system, multi-level data fusion algorithms are used. In the data layer, abnormal values are deleted by abnormal data detection method, and the median average filtering method is used to fuse the data; the algorithm based on weighted estimation fusion is used in the feature layer; the fuzzy control fusion algorithm is used in the decision.
18
Sterling, Mark, Hyekyun Rhee e Mark Bocko. "Automated Cough Assessment on a Mobile Platform". Journal of Medical Engineering 2014 (10 agosto 2014): 1–9. http://dx.doi.org/10.1155/2014/951621.
Abstract (sommario):
The development of an Automated System for Asthma Monitoring (ADAM) is described. This consists of a consumer electronics mobile platform running a custom application. The application acquires an audio signal from an external user-worn microphone connected to the device analog-to-digital converter (microphone input). This signal is processed to determine the presence or absence of cough sounds. Symptom tallies and raw audio waveforms are recorded and made easily accessible for later review by a healthcare provider. The symptom detection algorithm is based upon standard speech recognition and machine learning paradigms and consists of an audio feature extraction step followed by a Hidden Markov Model based Viterbi decoder that has been trained on a large database of audio examples from a variety of subjects. Multiple Hidden Markov Model topologies and orders are studied. Performance of the recognizer is presented in terms of the sensitivity and the rate of false alarm as determined in a cross-validation test.
19
Fine, Jesse, Michael J. McShane, Gerard L. Coté e Christopher G. Scully. "A Computational Modeling and Simulation Workflow to Investigate the Impact of Patient-Specific and Device Factors on Hemodynamic Measurements from Non-Invasive Photoplethysmography". Biosensors 12, n. 8 (4 agosto 2022): 598. http://dx.doi.org/10.3390/bios12080598.
Abstract (sommario):
Cardiovascular disease is the leading cause of death globally. To provide continuous monitoring of blood pressure (BP), a parameter which has shown to improve health outcomes when monitored closely, many groups are trying to measure blood pressure via noninvasive photoplethysmography (PPG). However, the PPG waveform is subject to variation as a function of patient-specific and device factors and thus a platform to enable the evaluation of these factors on the PPG waveform and subsequent hemodynamic parameter prediction would enable device development. Here, we present a computational workflow that combines Monte Carlo modeling (MC), gaussian combination, and additive noise to create synthetic dataset of volar fingertip PPG waveforms representative of a diverse cohort. First, MC is used to determine PPG amplitude across age, skin tone, and device wavelength. Then, gaussian combination generates accurate PPG waveforms, and signal processing enables data filtration and feature extraction. We improve the limitations of current synthetic PPG frameworks by enabling inclusion of physiological and anatomical effects from body site, skin tone, and age. We then show how the datasets can be used to examine effects of device characteristics such as wavelength, analog to digital converter specifications, filtering method, and feature extraction. Lastly, we demonstrate the use of this framework to show the insensitivity of a support vector machine predictive algorithm compared to a neural network and bagged trees algorithm.
20
Gutierrez, Eric, Carlos Perez, Fernando Hernandez e Luis Hernandez. "Time-Encoding-Based Ultra-Low Power Features Extraction Circuit for Speech Recognition Tasks". Electronics 9, n. 3 (29 febbraio 2020): 418. http://dx.doi.org/10.3390/electronics9030418.
Abstract (sommario):
Current trends towards on-edge computing on smart portable devices requires ultra-low power circuits to be able to make feature extraction and classification tasks of patterns. This manuscript proposes a novel approach for feature extraction operations in speech recognition/voice activity detection tasks suitable for portable devices. Whereas conventional approaches are based on either completely analog or digital structures, we propose a “hybrid” approach by means of voltage-controlled-oscillators. Our proposal makes use of a bank a band-pass filters implemented with ring-oscillators to extract the features (energy within different frequency bands) of input audio signals and digitize them. Afterwards, these data will input a digital classification stage such as a neural network. Ring-oscillators are structures with a digital nature, which makes them highly scalable with the possibility of designing them with minimum length devices. Additionally, due to their inherent phase integration, low-frequency band-pass filters can be implemented without large capacitors. Consequently, we strongly benefit from power consumption and area savings. Finally, our proposal may incorporate the analog-to-digital converter into the structure of the own features extractor circuit to make the full conversion of the raw data when triggered. This supposes a unique advantage with respect to other approaches. The architecture is described and proposed at system-level, along with behavioral simulations made to check whether the performance is the expected one or not. Then the structure is designed with a 65-nm CMOS process to estimate the power consumption and area on a silicon implementation. The results show that our solution is very promising in terms of occupied area with a competitive power consumption in comparison to other state-of-the-art solutions.
21
BARYLO, HRYHORII, IGOR HELZHYNSKYY, ROMAN HOLYAKA, TETIANA MARUSENKOVA e MYKOLA KHILCHUK. "EMBEDDED SYSTEM FOR SUPPLY VOLTAGE CONVERTER OF ORGANIC LIGHT-EMITTING DIODE". HERALD OF KHMELNYTSKYI NATIONAL UNIVERSITY 295, n. 2 (maggio 2021): 151–55. http://dx.doi.org/10.31891/2307-5732-2021-295-2-151-155.
Abstract (sommario):
The work is dealing with the problem of developing an embedded system for supply voltage converter of Organic Light-Emitting Diode (OLED) with advanced built-in ability to measure the volt-ampere (I – V) characteristics of structures directly during their operation. This feature is crucial in the development of a new generation of intelligent OLED controllers, which in relation to known solutions, are characterized by reduced power consumption and increased speed of periodic or continuous measurement of the I – V characteristics of OLED structures. On the basis of such measurement the drift of characteristics of OLED structures in the course of their operation is carried out, and therefore, the possibility of operative correction of their power modes is provided. The measurement of I – V characteristics of OLED structures is performed on the transients of voltage generation in the boost circuits of the drivers. To meet the requirements for such measurements, the parameters of the transient pulses must meet certain criteria. The pulse amplitude should be sufficient to scan the I – V characteristics of OLED structures in the whole range of their possible operation, and the shape and rise time should be optimal from the point of view of further detection of these I – V patterns, in particular, regarding their drift in temperature modulation or OLED structure degradation. In a number of tasks scanning and measurement of I – V characteristics should be fast enough to prevent heating, but acceptable for high-precision analog-to-digital conversion. The parameters of the pulses provide the ability to measure the thermal parameters of thermal resistance and its dependence on the duration of heating. The controller is implemented on the basis of programmable systems on the chip, namely on the PSoC 5LP.
22
McClure, W. F., David Moody, D. L. Stanfield e Osamu Kinoshita. "Hand-Held NIR Spectrometry. Part II: An Economical No-Moving Parts Spectrometer for Measuring Chlorophyll and Moisture". Applied Spectroscopy 56, n. 6 (giugno 2002): 720–24. http://dx.doi.org/10.1366/000370202760077432.
Abstract (sommario):
The design and performance of a low-cost no-moving-parts handheld NIR spectrometer are discussed. Dubbed the TWmeter, this device was conceived for use by researchers and others in developing countries unable to afford more costly technology found in developed countries. Two design features contribute to the novelty of this spectrometer: (1) three unfiltered light emitting diodes (LEDs) with peak emissions at 700, 880, and 940 nm for measuring chlorophyll in plant tissue and moisture in paper, and (2) a silicon intensity-to-frequency detector (a silicon detector with an integral voltage-to-frequency converter). The latter feature allows an ordinary microcomputer to obtain intensity measurements by counting for a fixed length of time, thus avoiding the need for higher-priced analog-to-digital hardware. Performance tests, using multiple linear regression for calibration, demonstrate that chlorophyll and moisture can be determined with a root mean squared standard error of prediction of 0.99 mg/cm2 of leaf surface for a range of 1–8 mg/cm2 and 1.04% (wet basis) for a range of 30–65% moisture, respectively. Development of the TWmeter (costing less than $300 US), demonstrates that spectrometry need not be costly.
23
Neudeck, Philip G., David J. Spry, Michael J. Krasowski, Liangyu Chen, Lawrence C. Greer, Carl W. Chang, Dorothy Lukco, Glenn M. Beheim e Norman F. Prokop. "Upscaling of 500 °C Durable SiC JFET-R Integrated Circuits". Additional Conferences (Device Packaging, HiTEC, HiTEN, and CICMT) 2021, HiTEC (1 aprile 2021): 000064–68. http://dx.doi.org/10.4071/2380-4491.2021.hitec.000064.
Abstract (sommario):
Abstract At HiTEC 2018, NASA Glenn Research Center reported the first demonstration of yearlong 500 °C operation of ceramic-packaged “Generation 10” ~200-transistor integrated circuits (ICs) based on two-level interconnect silicon carbide (4H-SiC) junction field effect transistors and resistors (JFET-R). This HiTEC 2021 submission updates on-going efforts at NASA Glenn spanning two subsequent prototype IC generations “11 and 12” to increase both complexity and durability of these ICs. Increased chip complexities of around 1000 transistors/chip for Gen. 11 and near 3000 transistors/chip for Gen. 12 are made possible by reductions in minimum layout feature sizes (including resistor width shrinkage from 6 μm to 2 μm) coupled with enlarged die size (from 3 × 3 mm to 5 × 5 mm). Gen. 11 ICs electrically tested to date include an 8-bit delta-sigma analog to digital converter (ADC) as well as upscaled random access memory (RAM) and nearly 1 kbit read only memory (ROM). However, Gen. 11 prototype ICs exhibited significantly lower yield and durability than Gen. 10 ICs. Development of revised processing is being investigated towards mitigating these issues in subsequent Gen. 12 fabrication run currently in progress.
24
Mansour, Noureddine, Mohamed Bin Shams e Hussain Ismail. "Model predictive controller for a retrofitted heat exchanger temperature control laboratory experiment". Indonesian Journal of Electrical Engineering and Computer Science 25, n. 2 (1 febbraio 2022): 857. http://dx.doi.org/10.11591/ijeecs.v25.i2.pp857-866.
Abstract (sommario):
This paper aims to demonstrate the practical aspects of process control theory for undergraduate students at the Department of Chemical Engineering at the University of Bahrain. Both, the ubiquitous proportional integral derivative (PID) as well as model predictive control (MPC) and their auxiliaries were designed and implemented in a real-time framework. The latter was realized through retrofitting an existing plate-and-frame heat exchanger unit that has been operated using an analog PID temperature controller. The upgraded control system consists of a personal computer (PC), low-cost interface using X-transposed-region (XTR) converter, national instruments USB 6008 data acquisition card, and LabVIEW software. LabVIEW control design and simulation modules were used to design and implement the PID and MPC controllers. The performance of the designed controllers was evaluated while controlling the outlet temperature of the retrofitted plate-and-frame heat exchanger. The distinguished feature of the MPC controller in handling input and output constraints was perceived in real-time. From a pedagogical point of view, realizing the theory of process control through practical implementation was substantial in enhancing the student’s learning and the instructor’s teaching experience
25
Veluthedath Shajihan, Shaik Althaf, Raymond Chow, Kirill Mechitov, Yuguang Fu, Tu Hoang e Billie F. Spencer. "Development of Synchronized High-Sensitivity Wireless Accelerometer for Structural Health Monitoring". Sensors 20, n. 15 (27 luglio 2020): 4169. http://dx.doi.org/10.3390/s20154169.
Abstract (sommario):
The use of digital accelerometers featuring high sensitivity and low noise levels in wireless smart sensors (WSSs) is becoming increasingly common for structural health monitoring (SHM) applications. Improvements in the design of Micro Electro-Mechanical System (MEMS) based digital accelerometers allow for high resolution sensing required for SHM with low power consumption suitable for WSSs. However, new approaches are needed to synchronize data from these sensors. Data synchronization is essential in wireless smart sensor networks (WSSNs) for accurate condition assessment of structures and reduced false-positive indications of damage. Efforts to achieve synchronized data sampling from multiple WSS nodes with digital accelerometers have been lacking, primarily because these sensors feature an internal Analog to Digital Converter (ADC) to which the host platform has no direct access. The result is increased uncertainty in the ADC startup time and thus worse synchronization among sensors. In this study, a high-sensitivity digital accelerometer is integrated with a next-generation WSS platform, the Xnode. An adaptive iterative algorithm is used to characterize these delays without the need for a dedicated evaluation setup and hardware-level access to the ADC. Extensive tests are conducted to evaluate the performance of the accelerometer experimentally. Overall time-synchronization achieved is under 15 µs, demonstrating the efficacy of this approach for synchronization of critical SHM applications.
26
Иншаков, Александр, Aleksandr Inshakov, Иван Курбаков, Ivan Kurbakov, Мария Курбакова e Mariya Kurbakova. "USING OF ACCELERATION CHARACTERISTICS OF THE ENGINE AND THE TURBOCHARGER FOR SUPERCHARGING SYSTEM DIAGNOSING". Bulletin Samara State Agricultural Academy 2, n. 3 (27 luglio 2017): 34–39. http://dx.doi.org/10.12737/17451.
Abstract (sommario):
The purpose of the research is to identify the peculiarities of interconnection of dynamic characteristics of the turbocharger TKR 6.1 and the engine D-245-35 in the presence of a fault in the pressurization system. In the practice of fault finding in the system of supercharging of automotive engine widely used method of diagnosis, OS-nated steak subs on the measurement of the boost pressure in the nominal modes. In terms of the service companies due to the lack of brake stands to estimate the load mode is often not possible. For acceleration of the turbocharger and engine at the department of mobile power tools, national research of Mordovsky State University named after N. P. Ogarev created diagnostic complex consisting of forming unit of the source signals, the optical sensor shaft speed of the turbocharger, sensor of frequency of rotation of the motor shaft, the linear displacement transducer arm balancing machines, analog-to-digital Converter, software and a personal computer. The tests were carried out on the engine MMZ D-245-35, with an installed turbocharger TKR-6.1, simulation of the working regimes was carried out on the roller-brake stand. The test results obtained a series of characteristics of the acceleration of the turbocharger engine D-245-35 and TKR-6.1 with a step input exposure. Analysis of the data showed that the presence of a malfunction of the boost «leak turbine inlet», «air filter clogged» leads to an increase in the transient time and reducing the frequency of rotation of the rotor TKR in all modes. Spaced- out characteristic obtained in idling mode in the fault conditions «loss of gases after the compressor» is accompanied by the growth of the amplitude value of the shaft speed TCR and the reduction of time of transition. This feature of the waveform of the acceleration allows us to identify faults of this kind in the diagnosis of the supercharging system.
27
Tulpule, Bhal, Bruce Ohme, Mark Larson, Al Behbahani, John Gerety e Al Steines. "A System On Chip (SOC) ASIC chipset for Aerospace and Energy Exploration Applications". Additional Conferences (Device Packaging, HiTEC, HiTEN, and CICMT) 2014, HITEC (1 gennaio 2014): 000278–84. http://dx.doi.org/10.4071/hitec-tha11.
Abstract (sommario):
This paper describes the design, key features and applications of a System On Chip (SOC) ASIC (Application Specific Integrated Circuit) chipset which was developed by Embedded Systems LLC as a part of the Smart Node based distributed control system architecture under an Air Force SBIR (Small Business Innovative Research) program {4}. The analog part of the SOC chipset has been implemented by Honeywell International under a subcontract using their high temperature SOI (Silicon On Insulator) Process. The complete chipset is expected to be available in early 2015. The key feature of the SOC chipset is that it is a reconfigurable and scalable building block that can be used to interface with most typical aerospace control system sensors and actuators. The SOC chipset captures all of the necessary functions required to power and interface with sensors such as RTD (Resistance Temperature Detectors), Strain Gauges (SG), Thermo Couples (TC) and transducers for measuring mass flow, speed, position or angle. The SOC chipset also contains all of the pre- and post-processing functions to convert electrical signals into digital words and send them on a data bus under the control of a host microprocessor. Finally, the SOC chipset contains PWM (Pulse Width Modulation) circuitry required to interface with external drives for actuators, motors, shutoff Valves etc. The SOC chipset can be powered from a Mil-Std-704F compliant power source or a conditioned DC power source. The chipset can be combined with other devices, such as memory, processor and A to D Converter to implement a high temperature capable Smart Node for localized management of sensors and actuators as a part of a distributed architecture or used as a scalable building block in a more complex function such as a FADEC (Full Authority Digital Engine Control). It is believed that the versatility of the SOC chipset makes it a well suited, affordable, scalable building block for not only aerospace controls but also for diverse applications such as down-hole drilling, energy exploration, wind farms etc. where high temperature electronics and /or high level of miniaturization is required.
28
Teslyuk, V. M., R. V. Zaharyuk, R. D. Ivantsiv, M. Ya Seneta, K. I. Tkachuk e A. V. Koval. "DEVELOPMENT OF THE ACCELERATION MEASURING METHOD". Ukrainian Journal of Information Technology 4, n. 2 (2022): 33–39. http://dx.doi.org/10.23939/ujit2022.02.033.
Abstract (sommario):
The existing acceleration measuring methods are analyzed in the article. An overview of modern research on this topic is also provided. A new method of measuring acceleration in the form of an electrical circuit using a stable frequency generator is developed. Among the already known methods, the following three groups are highlighted in the analysis: methods based on compensatory accelerometers with discrete output; methods based on accelerometers with the analog-to-digital converter; measurement techniques, which use mounted elements. The main difference between the proposed method and the existing ones is the use of circuits of two resonant circles with built-in capacitance sensors, developed according to microelectromechanical system technologies. The principle of operation of the acceleration measuring device is described in the article, and its structural diagrams are provided. The peculiarities of the functioning of its components are analyzed. The main advantages of using the proposed method are highlighted. It is described the technical difference of this method from those already implemented ones, which also lies in the presence of an additional transformer. Based on the proposed method of measuring acceleration in the form of an electrical circuit, the operating frequency characteristics of the device are investigated. The stages of conversion of accelerometer signals are described in the article as well as the forms of input and output signals. The use of two resonant circles within built capacity sensors and the stable frequencies generator in the scheme of acceleration measuring device allows for measurement of the frequency characteristics changes in resonant circuits with minimum capacity changes in sensors. The resulting frequency value is linear in the range of the accelerometer frequency due to the frequency characteristics of the first and second resonance circles, which are reversed and symmetrical about the horizontal axis. A feature of the developed new measurement method is the possibility of using this scheme at very low input voltages. Due to the proposed method, it is possible to increase the accuracy of acceleration measurement and expand the working capabilities of the device. In its turn, it allows applying this device in vibration and position variation conditions.
29
Postek, M. T., e A. E. Vladar. "The bright future of digital imaging in scanning electron microscopy". Proceedings, annual meeting, Electron Microscopy Society of America 51 (1 agosto 1993): 768–69. http://dx.doi.org/10.1017/s0424820100149672.
Abstract (sommario):
One of the major advancements applied to scanning electron microscopy (SEM) during the past 10 years has been the development and application of digital imaging technology. Advancements in technology, notably the availability of less expensive, high-density memory chips and the development of high speed analog-to-digital converters, mass storage and high performance central processing units have fostered this revolution. Today, most modern SEM instruments have digital electronics as a standard feature. These instruments, generally have 8 bit or 256 gray levels with, at least, 512 × 512 pixel density operating at TV rate. In addition, current slow-scan commercial frame-grabber cards, directly applicable to the SEM, can have upwards of 12-14 bit lateral resolution permitting image acquisition at 4096 × 4096 resolution or greater. The two major categories of SEM systems to which digital technology have been applied are:In the analog SEM system the scan generator is normally operated in an analog manner and the image is displayed in an analog or "slow scan" mode.
30
Plyler, Patrick N., Mary Easterday e Thomas Behrens. "The Effects of Extended Input Dynamic Range on Laboratory and Field-Trial Evaluations in Adult Hearing Aid Users". Journal of the American Academy of Audiology 30, n. 07 (luglio 2019): 634–48. http://dx.doi.org/10.3766/jaaa.18003.
Abstract (sommario):
AbstractDigital hearing aids using a 16-bit analog-to-digital converter (ADC) provide a 96-dB input dynamic range. The level at which the ADC peak clips and distorts input signals ranges between 95 and 105 dB SPL. Recent research evaluated the effect of extending the input dynamic range in a commercially available hearing aid. Although the results were promising, several limitations were noted by the authors. Laboratory testing was conducted using recordings from hearing aids set for a flat 50-dB loss; however, field testing was conducted with hearing aids fitted for their hearing loss. In addition, participants rarely encountered input levels of sufficient intensity to adequately test the feature and were unable to directly compare aids with and without extended input dynamic range (EIDR) under identical conditions.The effects of EIDR under realistic and repeatable test conditions both within and outside the laboratory setting were evaluated.A repeated measures design was used. The experiment was single-blinded.Twenty adults (14 males and six females) between the ages of 30 and 71 years (average age 62 years) who were experienced hearing aid users participated.Each participant was fit with Oticon Opn hearing instruments binaurally using the National Acoustics Laboratory-Nonlinear 1 fitting strategy. Participants completed a two-week trial period using hearing aids with EIDR and a two-week trial period without EIDR. The initial EIDR condition trial period was counterbalanced. After each trial, laboratory evaluations were obtained at 85 dBC using the Connected Speech Test, the Hearing in Noise Test, and the acceptable noise level (ANL). Satisfaction ratings were conducted at 85 dBC using speech in quiet and in noise as well as music. Field-trial evaluations were obtained using the abbreviated profile of hearing aid benefit (APHAB). Satisfaction ratings were also conducted in the field at 85 dBC using speech and music. After the study, each participant indicated which trial period they preferred overall. Repeated measures analysis of variances were conducted to assess listener performance. Pairwise comparisons were then completed for significant main effects.In the laboratory, results did not reveal significant differences between EIDR conditions on any speech perception in noise test or any satisfaction rating measurement. In the field, results did not reveal significant differences between the EIDR conditions on the APHAB or on any of the satisfaction rating measurements. Nine participants (45%) preferred the EIDR condition. Fifteen participants (75%) indicated that speech clarity was the most important factor in determining the overall preference. Sixteen participants (80%) preferred the EIDR condition that resulted in the lower ANL.The use of EIDR in hearing aids within and outside the laboratory under realistic and repeatable test conditions did not positively or negatively impact performance or preference. Results disagreed with previous findings obtained in the laboratory that suggested EIDR improved performance; however, results agreed with previous findings obtained in the field. Future research may consider the effect of hearing aid experience, input level, and noise acceptance on potential benefit with EIDR.
31
MARTYNIUK, Tatiana, Andryi KOZHEMIAKO, Gennadiy BORTNYK e Oleksandr VOINALOVYCH. "ANALYSIS OF FEATURES OF ANALOG-TO-DIGITAL CONVERSION “DURATION-CODE”". Herald of Khmelnytskyi National University. Technical sciences 317, n. 1 (febbraio 2023): 135–38. http://dx.doi.org/10.31891/2307-5732-2023-317-1-135-138.
Abstract (sommario):
The article presents the analysis results of the features of the analog-to-digital conversion of a continuous value as the duration of the input signal into the output digital code. Converters that work according to this principle are known as analog-code converters, and the conversion principle is a type of well-known pulse-width modulation (PWM). Information of a different nature can be used as input analog information, for example, the duration of an optical, electrical or sound signal. Specifically, the principle of this conversion with further processing of digital information uses a well-known logic-time basis, since the main operational parameter of the conversion is the duration of time, and the processing of digital data is performed according to the rules of picture logic with natural parallelism of processing on a two-dimensional field of information presentation. A feature of this approach to the conversion of input signals duration is the coding of output digital information in unit codes. In this case, two well-known unit codes are involved: unit normal and unit positional codes. This is because unit encoding is best suited for duration-to-code analog-to-digital conversion due to the quantization of the input signal duration by the trigger time of a line bistable elements. It is shown that the most acceptable implementation in terms of speed and energy consumption is the symbiosis of these two codes, since the unit normal code is faster when recording information, but loses to the unit positional code in terms of energy consumption when storing data. Taking into account the controllability of a unit positional code, the area of its effective application is the coding of the states of control devices and the addressing of the contents of storage devices, for example, as part of associative processors.
32
Sugi, Takenao, Ryosuke Baba, Yoshitaka Matsuda, Satoru Goto, Naruto Egashira, Ayame Oishi e Takao Yamasaki. "A COMMUNICATION AID SYSTEM BY FEATURE EXTRACTION OF ELECTROOCULOGRAPHIC SIGNALS". Biomedical Engineering: Applications, Basis and Communications 31, n. 06 (dicembre 2019): 1950048. http://dx.doi.org/10.4015/s1016237219500480.
Abstract (sommario):
People with serious movement disabilities due to neurodegenerative diseases have problems in their communication with others. Considerable numbers of communication aid systems have been developed in the past. Especially, some of the systems driven by eye movements are thought to be effective for such people. Electrooculographic (EOG) signal reflects the eye movement and the specific pattern of eye movement can be seen in EOG signals. This paper proposes a communication aid system by extracting the features of EOG. The system consists of a computer, analog-to-digital converter, biological amplifier and two monitors. Two monitors, one for a system user and the other for other people, display the same information. Five items are presented in the monitor, and a user selects those items according to the situation in the communication. Selection of the items is done by combining three eye movements: gaze at left, gaze at right and successive blinks. Basic concept of the communication aid system was designed by taking into account the current state of a subject’s movement disability. Then, the design of a screen and the algorithm for detecting eye movement pattern from EOG were determined by using the data of normal healthy subjects. The system worked almost perfectly for normal healthy subjects. Then, the developed system was operated by a subject with serious movement disability. Parts of the system operation were regarded as satisfactory level, and some miss-operation were also seen.
33
Wu, Chenxu, Yibai Xue, Han Bao, Ling Yang, Jiancong Li, Jing Tian, Shengguang Ren, Yi Li e Xiangshui Miao. "Forward stagewise regression with multilevel memristor for sparse coding". Journal of Semiconductors 44, n. 10 (1 ottobre 2023): 104101. http://dx.doi.org/10.1088/1674-4926/44/10/104101.
Abstract (sommario):
Abstract Sparse coding is a prevalent method for image inpainting and feature extraction, which can repair corrupted images or improve data processing efficiency, and has numerous applications in computer vision and signal processing. Recently, several memristor-based in-memory computing systems have been proposed to enhance the efficiency of sparse coding remarkably. However, the variations and low precision of the devices will deteriorate the dictionary, causing inevitable degradation in the accuracy and reliability of the application. In this work, a digital-analog hybrid memristive sparse coding system is proposed utilizing a multilevel Pt/Al2O3/AlOx/W memristor, which employs the forward stagewise regression algorithm: The approximate cosine distance calculation is conducted in the analog part to speed up the computation, followed by high-precision coefficient updates performed in the digital portion. We determine that four states of the aforementioned memristor are sufficient for the processing of natural images. Furthermore, through dynamic adjustment of the mapping ratio, the precision requirement for the digit-to-analog converters can be reduced to 4 bits. Compared to the previous system, our system achieves higher image reconstruction quality of the 38 dB peak-signal-to-noise ratio. Moreover, in the context of image inpainting, images containing 50% missing pixels can be restored with a reconstruction error of 0.0424 root-mean-squared error.
34
Postek, M. T., e A. E. Vladar. "The Bright Future of Digital Imaging in Scanning Electron Microscopy". Microscopy Today 2, n. 4 (luglio 1994): 19–20. http://dx.doi.org/10.1017/s1551929500065573.
Abstract (sommario):
One of the major advancements applied to scanning electron microscopy (SEM) during the past 10 years has been the development and application of digital imaging technology. Advancements in technology, notably the availability of less expensive, high-density memory chips and the development of high speed analog-to-digital converters, mass storage and high performance central processing units have fostered this revolution. Today, most modern SEM instruments have digital electronics as a standard feature. These instruments, generally have 8 bit or 256 gray levels with, at least, 512 X 512 pixel density operating at TV rate. In addition, current slow-scan commercial frame-grabber cards, directly applicable to the SEM, can have upwards of 12-14 bit lateral resolution permitting image acquisition at 4096 X 4096 resolution or greater.
35
Jin, Zhiwei. "Application of WCA-RBF Neural Network in Fault Diagnosis of Analog Circuits". International Transactions on Electrical Energy Systems 2023 (30 novembre 2023): 1–12. http://dx.doi.org/10.1155/2023/8812152.
Abstract (sommario):
With the fast growth of electronic technology today, the hybrid circuit of analog and digital circuits has become a trend in the growth of electronic technology. To address fault diagnosis in analog circuits, Haar wavelet is applied for fault feature extraction. The K-means clustering method and pseudoinverse algorithm were used to optimize the center value and weight value of the radial basis function neural network, respectively. The adaptive step size was improved in the wolf pack algorithm, the parameters of the radial basis function neural network were optimized based on the wolf pack algorithm, and a wolf pack algorithm optimized radial basis function neural network model was constructed. The test results show that this model converges after 40 times of training, with an error value of 10−3 and an average value of the mean squared error of 0.45. Comparing the fault diagnosis rates of the original model, genetic algorithm optimized radial basis function neural network model, and wolf colony algorithm optimized radial basis function neural network model, the last model has the best fault diagnosis rate, reaching 95.52%. The wolf colony algorithm is utilized to optimize the radial basis function neural network model to diagnose the faults in the standard filter circuit, and the fault diagnosis rate reaches 96.17%. The findings express that the radial basis function neural network model optimized by the wolf colony algorithm has a good diagnosis effect for different faults in the analog circuit.
36
Wang, Kun, Yukun Huang, Baoqiang Zhang, Huageng Luo, Xiang Yu, Dawei Chen e Zhiqiang Zhang. "Improved Synchronous Sampling and Its Application in High-Speed Railway Bearing Damage Detection". Machines 12, n. 2 (1 febbraio 2024): 101. http://dx.doi.org/10.3390/machines12020101.
Abstract (sommario):
Synchronous analysis is one of the most effective and practical techniques in rotating machinery diagnostics, especially in cases with variable speed operations. A modern analog-to-digital convertor (ADC) usually digitizes an analog signal to an equal time interval data series. Synchronous resampling converts the data series from an equal time interval data series to an equal shaft rotation angle interval data series. This conversion is usually achieved in the digital domain with the aid of shaft speed information, through either direct measurement or identification from a measured vibration signal, which is a time-consuming process. In order to improve the computational efficiency as well as the data processing accuracy, in this paper, a fast synchronous time-point calculation method based on an inverse function interpolation procedure is proposed. By identifying the inverse function of the instantaneous phase with respect to time, the calculation process of synchronous time points is optimized, which results in improved calculation efficiency and accuracy. These advantages are demonstrated by numerical simulations as well as experimental verifications. The numerical simulation results show that the proposed method can improve calculation speed by about five times. The synchronous analysis based on the proposed method was applied to a bearing fault detection in a high-speed rail carriage, which demonstrated the advantages of the proposed algorithm in improving the signal-to-noise ratio (SNR) for bearing damage feature extraction.
37
Fang, Hong-Wen, e Chih-Cheng Lu. "A Real Time and Lossless Encoding Scheme for Patch Electrocardiogram Monitors". Applied Sciences 8, n. 12 (24 novembre 2018): 2379. http://dx.doi.org/10.3390/app8122379.
Abstract (sommario):
Cardiovascular diseases are the leading cause of death worldwide. Due to advancements facilitating the integration of electric and adhesive technologies, long-term patch electrocardiogram (ECG) monitors (PEMs) are currently used to conduct daily continuous cardiac function assessments. This paper presents an ECG encoding scheme for joint lossless data compression and heartbeat detection to minimize the circuit footprint size and power consumption of a PEM. The proposed encoding scheme supports two operation modes: fixed-block mode and dynamic-block mode. Both modes compress ECG data losslessly, but only dynamic-block mode supports the heartbeat detection feature. The whole encoding scheme was implemented on a C-platform and tested with ECG data from MIT/BIH arrhythmia databases. A compression ratio of 2.1 could be achieved with a normal heartbeat. Dynamic-block mode provides heartbeat detection accuracy at a rate higher than 98%. Fixed-block mode was also implemented on the field-programmable gate array, and could be used as a chip for using analog-to-digital convertor-ready signals as an operation clock.
38
Shimose, Shigeru, Kanjuro Makihara e Junjiro Onoda. "Comparison of Analog and Digital Self-Powered Systems in Multimodal Vibration Suppression". Smart Materials Research 2012 (21 febbraio 2012): 1–9. http://dx.doi.org/10.1155/2012/287128.
Abstract (sommario):
This paper compares our analog and digital self-powered systems for vibration suppression, and shows experimental results of multimodal vibration suppression for both self-powered systems. The experimental results are evaluated in light of the damping performance and adaptability under various vibrational conditions. We demonstrate various examples of our innovative vibration suppression method, called “digital self-powered.” Proper status switching of an electric circuit made up of an inductor and a selective switch connected to a piezoelectric transducer attenuates the vibrations. The control logic calculation and the switching events are performed with a digital microprocessor that is driven by the electrical energy converted from the mechanical vibration energy. Therefore, this vibration suppression system runs without any external power supply. The self-powering feature makes this suppression method useful in various applications. To realize an ideal vibration suppression system that is both self-powered and effective in suppressing multimode vibration, sophisticated control logic is implemented in the digital microprocessor. We demonstrate that our digital self-powered system can reduce the vibrational displacements of a randomly excited multimodal structure, by as much as 35.5%.
39
Bere, Gracelia Adelaida, Elizabeth Nurmiyati Tamtjita e Anggraini Kusumaningrum. "Klasifikasi Untuk Menentukan Tingkat Kematangan Buah Pisang Sunpride". Conference SENATIK STT Adisutjipto Yogyakarta 2 (15 novembre 2016): 109. http://dx.doi.org/10.28989/senatik.v2i0.61.
Abstract (sommario):
YIQ (Iuma, In-phase, Quadrature) is a color space used to transmit analog TV signal. This research is conducting a possibility test on using YIQ as color features for fruit ripeness classification, which tested on Sunpride bananas. Classification is done using k-NN algorithm against YIQ values of several ripeness stage. The classification process itself consists of two steps: training and testing. In the training step, values from RGB color space of the images as training samples are converted into YIQ and extracted as features to form the classes, while in testing step, the test image went through the same conversion and feature extraction process, then classified using k-NN against the classes’ features, using k=3 and k=1. There are 120 Sunpride banana images used as test objects, and the results obtained shown that the classification performance using k=3 for Sangat Matang class is 100%, Busuk class is 66,67%, Mengkal class is 60% and Matang class is 60%. Results using k=1 for Sangat Matang class is 100%, Busuk class is 66,67%, Mengkal class is 66,7% and Matang class is 56,67%.Keywords : Classification, YIQ Color Space, Banana Sunpride, Euclidean Distance, k-Nearest Neighbors
40
Khani, Hassan. "X-law detection scheme for monobit transmitted-reference ultra wideband receivers". International Journal of Informatics and Communication Technology (IJ-ICT) 10, n. 2 (1 agosto 2021): 75. http://dx.doi.org/10.11591/ijict.v10i2.pp75-84.
Abstract (sommario):
<p>In ultra-wideband (UWB) communications, monobit receivers offer a low complexity implementation but at the same time exhibit a great performance loss. In this paper, a novel detection scheme, denoted as <em>x</em>-law detection (XLD), is proposed to diminish the performance loss caused by employing monobit analog-to-digital converters in transmitted-reference (TR) UWB receivers. Simulation results show that if the optimal value is employed for <em>x</em>, the XLD-based monobit weighted TR (MWTR) receiver can achieve 14.2~15.5 dB and 8~9.2 dB performance gain over the conventional MWTR receiver in LOS and NLOS scenarios, respectively. Moreover, the XLD-based MWTR receiver performance with the optimal value of <em>x</em> is only 1.6~3 dB away from the optimum MWTR receiver performance in intra-vehicle UWB channels. Additionally, the XLD-based MWTR receiver is not sensitive to the summation interval. This feature decreases the receiver complexity and guarantees a robust performance over different multipath channels. The significant performance improvement of the XLD scheme comes at a limited complexity increase. Thus, the XLD approach is a good candidate for TR-based and other training-based monobit receivers requiring low complexity, high performance, and low power consumption.</p>
41
Shchanikov, S. A. "The use of memristive devices in machine vision systems". Genes & Cells 18, n. 4 (15 dicembre 2023): 831–34. http://dx.doi.org/10.17816/gc623429.
Abstract (sommario):
The comparison results of processing units with memristive devices versus modern hardware accelerators of artificial neural networks (ANNs) based on traditional electronic components, as presented in the review [1], demonstrate numerous advantages across all major indicators such as throughput, energy efficiency, accuracy, and others. This report analyzes the current state of memristive devices in addressing machine vision issues. Special attention is paid to the concept of [2] neuromorphic machine vision systems (MVS) based on memristive devices. This concept’s distinct feature lies in its fully analog system, commencing from information input to its output. It encompasses sensory and neural components. The sensory part is responsible for gathering visual information and transferring it to the neural segment for processing through the ANN model algorithm. A specific instance for implementing the input channel of the sensor component involves connecting a photodiode (PD) and a memristor in a single circuit. When the circuit is flipped in reverse bias and light falls on the PD, a photocurrent flows through it from the cathode to the anode. Depending on the light intensity and exposure time, this photocurrent alters the resistance of the memristor, thereby converting illumination into resistance. If visual information doesn’t require encoding with memristor resistances, they can be replaced with a load resistance of the same nominal value for all channels. Irrespective of the input channel variant, the signal encoding visual information is fed into the neural part without digitization. Memristors act as synapses as part of the neural part. They can be used to implement synapses in both traditional formal ANN architectures, where input information is multiplied by a pre-programmed weight, and synapses for spiking neural networks, where a memristor exhibits synaptic plasticity mechanisms similar to those in biological neural networks [3]. If the output from the suggested MVS input channel variants is connected to a device that operates on the “integrate and fire” principle, the device can be deemed as not only an input for a structured ANN, but also a presynaptic neuron for a spiking ANN. The neuron’s frequency of spikes will depend on the light intensity; the brighter the light, the higher the frequency of spikes and vice versa. Faster charge accumulation occurs in channels with low resistance. The complete analog machine vision system will function as a spike neural network, without incorporating any analog-to-digital or digital-to-analog converters. Compared to digital machine vision systems, this approach will significantly decrease energy consumption while producing wearable and on-board electronics with distinct tactical and technical features. This design can be tailored to the size of modern matrices of photo and video fixation devices and employed as a hardware accelerator for the ANN models currently used to process images, and it can serve as a foundation for advancing this area.
42
Guldi, Dirk. "(Invited) Step-Change in Solar Energy Conversion Schemes". ECS Meeting Abstracts MA2022-01, n. 7 (7 luglio 2022): 641. http://dx.doi.org/10.1149/ma2022-017641mtgabs.
Abstract (sommario):
At the heart of unlocking the potential of global clean, renewable energy is the concerted effort of Advanced Charge Management (ACM) and Advanced Photon Management (APM). Recent advances regarding molecular ACM have documented the maturity of energy conversion schemes. Adding now APM to ACM by means of down- and/or up-conversion and creating synergies is essential to further boost the efficiency of these sun-driven energy conversion schemes. A full-fledged comprehension of APM is essential as an enabler for creating versatile platforms that are broadly applicable not only in the area of solar electricity, but also solar fuels. APM is, in the molecular context, based on either down-converting photons by means of Singlet Fission (SF), on one-hand, or on Triplet Fusion (TF)/Two Photon Absorptions (TPA) for up-converting them, on the other hand. To harvest photons in the high-energy regime, SF, the molecular analog to multiple exciton generation, stands out. It allows high-energy, singlet-excited states to be down-converted into twice as many low-energy, triplet-excited states, thereby improving solar-cell performance. This is, however, limited to the part of the solar spectrum, where, for example, the SF-materials feature a significant absorption cross-section. To harvest photons in the low-energy regime, necessitates non-resonant, indirect excitation via TF/TPA. Our transdisciplinary research has enabled in recent years to gather a comprehensive understanding of molecular down- and up-conversion.
43
Druzhinin, A. A., A. P. Kutrakov, S. I. Nichkalo e V. M. Stasiv. "Information and measuring system on the basis of strain sensors based on silicon microcrystals". Технология и конструирование в электронной аппаратуре, n. 3 (2018): 9–14. http://dx.doi.org/10.15222/tkea2018.3.09.
Abstract (sommario):
One of the promising directions of development of information and measuring systems for monitoring and diagnostics is the use of intelligent sensors of various physical quantities, in particular pressure, temperature, deformation, acceleration, etc. The main functional feature that distinguishes such sensors is the possibility of signal processing directly in the measuring zone, which involves the temperature compensation of the output signal, linearization of the transformation function. Along with primary converters, intelligent sensors include analog-to-digital and digital-to-analog converters, microcontroller, memory-storage device, input/output interfaces. However, the technologies used today for the creation of existing microelectronic sensors are quite complex and require special process equipment and materials, that leads to an increase in their value. The aim of this work is to develop an information and measurement system for use in conjunction with mechanical sensors based on strain gauges made of silicon whiskers in terms to provide a higher efficiency. The deformation and temperature characteristics of sensors of mechanical quantities (pressure, force and deformation) with strain gauges on the basis of p-type Si whiskers (ρ=0.005—0.02 Ω∙cm) in the temperature range from –60 to +60°C were analyzed. It has been established that at a deformation level of ±6∙10–4 relative units, the high values of sensitivity and linearity of strain gauge characteristics are maintained, and the hysteresis effect due to the characteristics of elastic elements is shown to the smallest extent. It is shown that the temperature dependence of relative change in the resistance of strain gauge resistors based on p-Si whiskers with resistivity of 0.005 Ω∙cm is characterized by the smallest nonlinearity. This simplifies the problem of compensation of the temperature errors, which are typical for such sensors. The temperature coefficient of resistance for strain gauges was found to be 0.15%/°Ñ. The information and measuring system was developed on the basis of pressure sensor with strain gauges made of silicon whiskers (ρ=0.005 Ω∙cm). This pressure sensor provides the simultaneous measurement of pressure and temperature in the ranges 0...100 kPa and –60...+60°Ñ, respectively. The measuring channel of the developed system was based on the AVR ATmega328P microcontroller, which provides the ability to create modern high-precision distributed data gathering and display systems. As a result of testing, satisfactory results were obtained regarding stability, sensitivity and measurement ranges of the developed information and measuring system. The main measurement error did not exceed 0.1%. The measuring circuit can be easily adapted to a new task without making any significant changes to its hardware, the function of the device is easily adjusted by changing the work program.
44
Mohabati, Zeynab, e Maryam Khoddam. "Improving the Performance of Distance Relay Using Wavelet Transform". Tehnički glasnik 15, n. 4 (1 novembre 2021): 483–90. http://dx.doi.org/10.31803/tg-20210518000021.
Abstract (sommario):
With proliferation of power grids, different types of faults are more likely to occur. The purpose of system protection relays is to detect abnormal signals that indicate faults in the transmission system and to separate the fault section from the rest of the system to prevent the fault from propagating to other parts of the system. Proliferation of electronic devices led to creation of digital relays made of microprocessors. Hence, analog measurements are converted into digital signals for processing by microprocessors. Air grids are more likely to cause faults than other components of the power system; thus, disturbances affecting the system must be detected quickly and accurately. Therefore, the problem of fault detection and classification is an important factor for economic exploitation of the power grid. Accurate fault handling results in faster repair operations, better system availability, lower operating costs and timesavings. The proposed design in this study was based on detecting the type of fault caused in transmission lines. In order to improve the condition of the relays in the transmission grid, analysis of the signals reached to the relay on both sides of the line was used to detect the fault and its type. The main purpose was to quickly detect the type of fault using wavelet transform. For this purpose, the signal was sampled after the fault occurs and the feature signal was extracted after analysis by wavelet transform. These features were included in the decision tree classifier and the type of the fault was decided.
45
Rao, Dr Tavanam Venkata. "Manhole Management System". International Journal for Research in Applied Science and Engineering Technology 9, n. VI (30 giugno 2021): 4262–65. http://dx.doi.org/10.22214/ijraset.2021.35668.
Abstract (sommario):
A smart city is the future goal of providing cleaner and better services to society. Smart underground infrastructure is an important feature to consider when implementing a smart city. Monitoring the drainage system plays a vital role in keeping the city clean and healthy. The supervision is incompetent, this results in slow treatment of drainage problems and takes more time to resolve. In order to alleviate all of these problems, the system is being developed with a wireless sensor network consisting of sensor nodes. The project aims to design a well management system using IOT that will notify the management station via email when a well exceeds its thresholds, and the system will also monitor the data from the sensors on the LCD module, the system will reduce the risk of death for manual collectors that clean the underground drain and also benefits the public. The project uses a water level sensor, a water flow sensor, an SR04 ultrasonic sensor, a temperature sensor, a gas sensor, an Arduino UNO atmega328 microcontroller and a Raspberrypi3 processor. This project "MANHOLE MANAGEMENT SYSTEM" helps to send signals from sensors. This project consists of Raspberry Pi3 and Arduino Uno, the two microcontrollers that are connected to each other.The signals received by the Arduino from the sensors are converted from analog signals into digital signals with the help of the ADC on the Arduino board and then processed and sent to the Raspberry Pi, it takes this as input data and the Raspberry Pi is sent to an E. -Mail to the appropriate authority. The status of the project is displayed on the LCD module.
46
Paul, Ankita, Md Abu Saleh Tajin, Anup Das, William M. Mongan e Kapil R. Dandekar. "Energy-Efficient Respiratory Anomaly Detection in Premature Newborn Infants". Electronics 11, n. 5 (23 febbraio 2022): 682. http://dx.doi.org/10.3390/electronics11050682.
Abstract (sommario):
Precise monitoring of respiratory rate in premature newborn infants is essential to initiating medical interventions as required. Wired technologies can be invasive and obtrusive to the patients. We propose a deep-learning-enabled wearable monitoring system for premature newborn infants, where respiratory cessation is predicted using signals that are collected wirelessly from a non-invasive wearable Bellypatch put on the infant’s body. We propose a five-stage design pipeline involving data collection and labeling, feature scaling, deep learning model selection with hyperparameter tuning, model training and validation, and model testing and deployment. The model used is a 1-D convolutional neural network (1DCNN) architecture with one convolution layer, one pooling layer, and three fully-connected layers, achieving 97.15% classification accuracy. To address the energy limitations of wearable processing, several quantization techniques are explored, and their performance and energy consumption are analyzed for the respiratory classification task. Results demonstrate a reduction of energy footprints and model storage overhead with a considerable degradation of the classification accuracy, meaning that quantization and other model compression techniques are not the best solution for respiratory classification problem on wearable devices. To improve accuracy while reducing the energy consumption, we propose a novel spiking neural network (SNN)-based respiratory classification solution, which can be implemented on event-driven neuromorphic hardware platforms. To this end, we propose an approach to convert the analog operations of our baseline trained 1DCNN to their spiking equivalent. We perform a design-space exploration using the parameters of the converted SNN to generate inference solutions having different accuracy and energy footprints. We select a solution that achieves an accuracy of 93.33% with 18x lower energy compared to the baseline 1DCNN model. Additionally, the proposed SNN solution achieves similar accuracy as the quantized model with a 4× lower energy.
47
Prokhorenko, А., S. Kravchenko e E. Solodkii. "DIGITAL TWIN OF GAS RECIPROCATING COMPRESSOR UNIT: CONCEPT, ARCHITECTURE & PILOT IMPLEMENTATION". Internal Combustion Engines, n. 2 (26 luglio 2021): 68–72. http://dx.doi.org/10.20998/0419-8719.2021.2.09.
Abstract (sommario):
Combination of information and operational technologies has led to a new way of production, to a new technological revolution, known as Industry 4.0. The Digital Twin plays a central role in this technology. The Digital Twin is a predictive maintenance tool, and allows you to simulate various options for device failures taking into account their operation modes, environmental influences and various degrees of wear. The concept of creating a digital twin of a real physical object of research is proposed - an AJAX DPS-180 internal combustion engine with a gas piston compressor, which is designed to pump gas from gas wells. A feature of its work is autonomous long-term operation in the field with the remoteness of the service personnel, direct environmental impact and ensuring the reliability and stability of work. Therefore, monitoring the parameters of the engine with the subsequent prediction of its failures is especially important. The work on creating a digital twin for AJAX DPS-180 is being carried out in cooperation and with the support of Armco-Engineering, the operator of this equipment.
Six stages of the process of creating a digital twin of a given object are shown: collection and preliminary processing of data on the technical state of a real object; early detection of malfunctions, predicting the time of failure; service planning; optimization of financial and time resources for service. Equipping a real object with various sensors made it possible to continuously collect data on its technical condition, and technologies of the industrial Internet of things, such as Big Data and the predictive statistical model, predict failure times with high accuracy.
The developed and implemented schemes for equipping an object with data collection equipment and a diagram of the flow of this data in the Internet of Things are presented. The basis of the data collection system is a microcontroller, a set of a crankshaft speed sensor and thermocouples, a multiplexer and 16-bit analog-to-digital converters that convert thermo-EMF of thermocouples. At the moment, channels for measuring the speed, coolant and exhaust gas temperatures have been implemented. It is proposed to use the ThingSpeak server as a remote resource as a cloud aggregator and carrier of this data. The MATLAB mathematical package integrated into the resource is used as a data analyzer.
48
Zhang, Jie. "Mining and Teaching Design of Civic and Political Elements in Digital Electronics Technology Course Based on Markov Modeling". Applied Mathematics and Nonlinear Sciences 9, n. 1 (18 dicembre 2023). http://dx.doi.org/10.2478/amns.2023.2.01536.
Abstract (sommario):
Abstract This paper proposes a course knowledge resource extraction method based on the improved Hidden Markov Model and combines the method with hierarchical classification ideas. The improved Hidden Markov Model is used in the study of the text classification process of course knowledge resources, the expected cross entropy selects the feature words, and the semantic space composition is obtained by using the implicit semantic indexing method. When setting the observation output probability matrix for the HMM classifier model, the improved TFIDF method is introduced to reflect the semantic relations between feature words. An evaluation criterion such as macro-micro mean is used to analyze the performance of the whole text set classification and gradually improve the HMM model. Finally, the HMM resource information extraction model has been improved to mine the elements of civics in digital electronics technology courses. It is found that in the compulsory textbook knowledge of digital electronics technology, the trigger knowledge has the greatest integration degree with the Civic-Political elements with a percentage of 0.3382, followed by the analog-digital and digital-analog converter knowledge with a percentage of 0.2818. In the textbook column on digital electronics technology, the extended knowledge has the greatest integration degree with the Civic-Political elements with a percentage of 0.5043, followed by the strengthened category column with a percentage of 0.1712. The analysis of the students’ different Civic-Political dimensions after the instruction has been done. In the political identity category, national sentiment, scientific spirit and ecological environment topics improved by 7.23, 2.01, 3.2 and 2.14 points, respectively. It shows that students can improve their cultural knowledge in digital electronics and establish a correct worldview, life view, and values.
49
Xu, Shaofu, Binshuo Liu, Sicheng Yi, Jing Wang e Weiwen Zou. "Analog spatiotemporal feature extraction for cognitive radio-frequency sensing with integrated photonics". Light: Science & Applications 13, n. 1 (14 febbraio 2024). http://dx.doi.org/10.1038/s41377-024-01390-9.
Abstract (sommario):
AbstractAnalog feature extraction (AFE) is an appealing strategy for low-latency and efficient cognitive sensing systems since key features are much sparser than the Nyquist-sampled data. However, applying AFE to broadband radio-frequency (RF) scenarios is challenging due to the bandwidth and programmability bottlenecks of analog electronic circuitry. Here, we introduce a photonics-based scheme that extracts spatiotemporal features from broadband RF signals in the analog domain. The feature extractor structure inspired by convolutional neural networks is implemented on integrated photonic circuits to process RF signals from multiple antennas, extracting valid features from both temporal and spatial dimensions. Because of the tunability of the photonic devices, the photonic spatiotemporal feature extractor is trainable, which enhances the validity of the extracted features. Moreover, a digital-analog-hybrid transfer learning method is proposed for the effective and low-cost training of the photonic feature extractor. To validate our scheme, we demonstrate a radar target recognition task with a 4-GHz instantaneous bandwidth. Experimental results indicate that the photonic analog feature extractor tackles broadband RF signals and reduces the sampling rate of analog-to-digital converters to 1/4 of the Nyquist sampling while maintaining a high target recognition accuracy of 97.5%. Our scheme offers a promising path for exploiting the AFE strategy in the realm of cognitive RF sensing, with the potential to contribute to the efficient signal processing involved in applications such as autonomous driving, robotics, and smart factories.
50
Chen, Yitong, Maimaiti Nazhamaiti, Han Xu, Yao Meng, Tiankuang Zhou, Guangpu Li, Jingtao Fan et al. "All-analog photoelectronic chip for high-speed vision tasks". Nature, 25 ottobre 2023. http://dx.doi.org/10.1038/s41586-023-06558-8.
Abstract (sommario):
AbstractPhotonic computing enables faster and more energy-efficient processing of vision data1–5. However, experimental superiority of deployable systems remains a challenge because of complicated optical nonlinearities, considerable power consumption of analog-to-digital converters (ADCs) for downstream digital processing and vulnerability to noises and system errors1,6–8. Here we propose an all-analog chip combining electronic and light computing (ACCEL). It has a systemic energy efficiency of 74.8 peta-operations per second per watt and a computing speed of 4.6 peta-operations per second (more than 99% implemented by optics), corresponding to more than three and one order of magnitude higher than state-of-the-art computing processors, respectively. After applying diffractive optical computing as an optical encoder for feature extraction, the light-induced photocurrents are directly used for further calculation in an integrated analog computing chip without the requirement of analog-to-digital converters, leading to a low computing latency of 72 ns for each frame. With joint optimizations of optoelectronic computing and adaptive training, ACCEL achieves competitive classification accuracies of 85.5%, 82.0% and 92.6%, respectively, for Fashion-MNIST, 3-class ImageNet classification and time-lapse video recognition task experimentally, while showing superior system robustness in low-light conditions (0.14 fJ μm−2 each frame). ACCEL can be used across a broad range of applications such as wearable devices, autonomous driving and industrial inspections.