Acquisition Module Research Articles

Near-zero-power infrared relay based on microfluidic switch and metamaterial absorber

Internet of Things sensor nodes, which integrate information acquisition, processing, exchange, and execution modules, have widely been used for unattended industrial production, environmental monitoring, and other fields. However, limited battery power constrains the lifespan of the sensor nodes. In this paper, we propose a near-zero-power infrared relay consists of microfluidic switches and a metamaterial absorber (MA). When target appears, the MA absorbs the infrared energy emitted from the target and uses it to turn on the microfluidic switch. When valid information is not present, the microfluidic switch is in “off” state with a high resistance of over 109 Ω. The infrared relay with a pair of microfluidic switches shows common mode suppression capability against environmental temperature variation. We further demonstrate a sensor node consists of the infrared relay and a MoS2 photodetector. In a standby mode, the sensor node shows near-zero power consumption. As target infrared signal occurs, the photodetector is wakened by the infrared relay and illustrates excellent optical sensing performance. The simplicity of this approach provides a route for significantly extending the lifespan of sensor nodes powered by batteries, especially the sensor nodes for detecting infrequent but critical events.

Construction of an intelligent agricultural irrigation control platform based on PLC technology

Abstract This paper firstly constructs a PLC-based intelligent irrigation control system, analyzes the requirements of its system functions, and determines three major modules of the system: data acquisition module, intelligent irrigation module, and Web service module. Then the system fuzzy control process is determined. According to the moisture value collected by the soil moisture sensor, the average is taken, and the deviation and deviation change rate is obtained by calculating the difference with the set value, and the control value is obtained by querying the previously deposited fuzzy control table through a series of transformations, and the command is executed according to the program setting. The automatic irrigation requirement is achieved by controlling the solenoid valve on and off. Finally, the analysis of system functions in terms of sensor accuracy, system function testing, and temperature and air humidity prediction accuracy was carried out. Regarding sensor accuracy, the error of relative soil moisture content is within 3%, and the relative error of soil temperature is within 0.5. In the system control function test, the solenoid valve will open for irrigation when the soil relative water content is lower than 40% or higher than 70% of the warning range, and the lighting will be turned on when the light intensity is lower than 200 Lux, and the system control is in line with the expectation. The intelligent irrigation system is of great significance to agricultural development.

Parametric BIM-based life cycle assessment framework for optimal sustainable design

The construction sector is liable for a sizable amount of CO2 emissions and waste. Life Cycle Assessment (LCA) is considered one of the crucial tools that aids in evaluating the impacts of construction emissions. This research aims to quantify the life cycle impacts of the initial and recurrent embodied emissions, operating and reuse/disposal emissions, and utilizing Building Information Modeling (BIM) for a more holistic life cycle approach. The research proposes a parametric BIM-based LCA framework for quantifying the environmental impacts and evaluating the effects of material selection for both embodied and operating emissions. In addition, it considers the different reuse scenarios and percentages and their effect on both the embodied and operating impacts. The proposed framework consists of five main modules: data acquisition module, operating and embodied emissions module, life cycle assessment module, optimization module, and decision-making module. This parametric assessment can be applied for both the conventional and circular approach impacts. For the decision-making process, the resulting emissions are optimized utilizing the Non-dominated Sorting Genetic Algorithm II (NSGA-II) and evaluated through an LCA and Data Envelopment Analysis (DEA) methodology for the material selection. A case study of a residential villa in Cairo is worked out to illustrate the key features of the proposed framework. This assessment analyzes the building materials’ characteristics and efficiency investigating the external walls, internal walls, floors, roofs, and windows design possibilities, and uses visual programming to control the resulting emissions for a more flexible approach. By comparing the integrated LCA and DEA models three optimum design solutions, the conventional approach develops design solutions of higher embodied Global Warming Potential (GWP) than the circular approach. However, it develops lower operating GWP with better applied U-values. The circularity approach employment has reduced the efficiency of the operating GWP due to utilizing materials with high heat transmittance ability.

Research on power management circuit of magnetic field energy harvesting for wireless sensor

In order to solve the power supply problem of wireless sensors in the power cable environment, the changing magnetic field around the cable is used, and the open energy harvesting coil and power management circuit are used to supply power to the sensor. However, improving circuit applicability and output efficiency is the key. For this reason, through the circuit principle and simulation analysis, the basic model of the power management circuit is established, and the overvoltage protection and energy storage unit are designed for the special environment of the cable to solve the problem of circuit protection and energy supply dead zone. Then reduce the circuit loss according to the circuit topology design. Finally, an experimental platform is built to verify the output effect of the power management circuit. The voltage induced by the magnetic induction power acquisition module can obtain a stable and reliable output voltage through the power management circuit, which can realize the self-sufficiency of the power supply of the wireless sensor.

LEAF BLIGHT DETECTION USING DEEP LEARNING

Plant leaf blight is a common disease that affects many crops, causing significant economic losses in agriculture. Early detection of blight is essential for farmers to prevent the spread of the disease, control its severity, and improve crop yields. Manual detection of blight is time-consuming and often unreliable, making it necessary to use advanced technologies for accurate and efficient detection. Plant leaf blight detection systems can help farmers monitor their crops in real-time and identify blight at an early stage. This enables farmers to take appropriate measures such as crop rotation, timely application of fungicides, and improving plant nutrition to prevent the spread of the disease. By using plant leaf blight detection systems, farmers can reduce the economic losses caused by the disease and ensure the availability of healthy crops for consumption. This project presents a smart system for leaf blight detection that uses deep learning and convolutional neural networks (CNN) and is implemented on an Android platform. The system comprises an image acquisition module, a pre-processing module, and a leaf blight classification module. The image acquisition module captures images of leaves from a mobile camera, while the pre-processing module enhances the quality of images by removing noise and enhancing contrast. The leaf blight classification module uses a pre-trained CNN model to accurately classify images into healthy or diseased categories and provide the Confidence level of the Blight (disease) present.

The system for distributed energy resources testing according to the IEEE 1547-2018 standard

PurposeThis paper aims to propose a new approach to testing distributed energy resources (DERs) in compliance with the IEEE 1547-2018 standard and describes a new, integrated testing and validation system.Design/methodology/approachThe system is built on the virtual instrumentation paradigm, using acquisition modules to measure physical quantities, while signal processing, including intensive calculations of required parameters, data processing, manipulation and reporting are performed on a computing device.FindingsIntensive laboratory measurements were performed on a laboratory prototype of a microgrid that emulates DERs. The results obtained using the system described were compared with the measurements obtained by the reference instruments. As all the results match, the usability of the system was verified.Practical implicationsThis approach to the realization of the testing and validation system has obvious advantages compared to the classical instruments and provides significant flexibility in multiple aspects. First, the system described integrates all the functions of different instruments into one measuring system, making the entire testing and validation process significantly cheaper and faster. Second, the implementation of the system is possible on different computing platforms depending on specific needs. Third, the software implementation of the system functions enables simple upgrading and the introduction of new functions or changes to existing ones according to changes in the standard. Finally, the system described is designed to automatically provide reports on compliance with the standard.Originality/valueThis paper emphasizes the advantages of the proposed approach over classical testing. The value of the paper is reflected in the applicability and practical implications of the proposed and described hardware and software technical solutions.

Autonomous Broadband Current Meter on a High-Voltage Electrode

The design of an autonomous noise-proof current meter on a high-voltage electrode is proposed, based on the use of an annular non-inductive shunt with its axially symmetrical connection to the input of the data acquisition module. The parameters of two design options are calculated: high-frequency, with a frequency band of 0–10 GHz, but with a lower limit of the measured current, and relatively low-frequency, with a band of 0–100 MHz, and a high limit of the measured current.

Diagnosis of patellofemoral osteoarthritis using enhanced sequential deep learning techniques

The surface electromyography (sEMG) signal is a complex interference pattern resulting from the electrical activity of contracting muscles, which directly correlates with muscle activity and exercise level. Patellofemoral osteoarthritis (PF OA) refers to the softening and destruction of the articular cartilage of the knee cap, which is important to diagnose in the early phase. The aim of this study is to develop a predictive model, called the Enhanced Sequencing Deep Learning (PESDL) Algorithm, to detect PF OA from the sEMG signal. The algorithm consists of four main modules: (i) Data Acquisition Module (DAM), (ii) Signal Preprocessing Module (SPM), (iii) Data Augmentation and Concatenation Module (DACM), and (iv) Lower Limb Classification (LLC). The sEMG signals from five core muscles of the lower limb were acquired during stepping stairs up and down, and machine learning was used to obtain the muscle activation data signals. The acquired data was preprocessed, augmented, concatenated, and shuffled. Three feedforward deep networks (RNN, LSTM, and GRU) were used to classify the lower limb sEMG time-sequence data, with the GRU network showing better performance than the other two. The model's performance was evaluated using seven performance measures and 10-fold cross-validation. The maximum values of feedforward deep networks (RNN), LSTM, and GRU for the five muscles (RF, BF, VM, ST, and FX) using seven performance measures were as follows: RNN (0.961, 0.154, 0.943, 0.244, 1.0, 1.0, 0.899), LSTM (0.967, 0.147, 0.945, 0.217, 0.997, 1.0, 0.927), and GRU (0.976, 0.111, 0.949, 0.212, 0.996, 0.998, 0.938), respectively, listed in the order of accuracy, loss, validation accuracy, validation loss, recall, precision, and F1-score. Comparisons with other state-of-the-art models using the same datasets demonstrated the effective performance of the predictive model. The results suggest that RNN models, particularly GRU and LSTM, can be effective for detecting PF OA, and the specific RNN architecture used can have a significant impact on performance.

A Multichannel Portable Platform With Embedded Thermal Management for Miniaturized Dielectric Blood Coagulometry.

This article presents a standalone, multichannel, miniaturized impedance analyzer (MIA) system for dielectric blood coagulometry measurements with a microfluidic sensor termed ClotChip. The system incorporates a front-end interface board for 4-channel impedance measurements at an excitation frequency of 1 MHz, an integrated resistive heater formed by a pair of printed-circuit board (PCB) traces to keep the blood sample near a physiologic temperature of 37 °C, a software-defined instrument module for signal generation and data acquisition, and a Raspberry Pi-based embedded computer with 7-inch touchscreen display for signal processing and user interface. When measuring fixed test impedances across all four channels, the MIA system exhibits an excellent agreement with a benchtop impedance analyzer, with rms errors of ≤0.30% over a capacitance range of 47-330 pF and ≤0.35% over a conductance range of 2.13-10 mS. Using in vitro-modified human whole blood samples, the two ClotChip output parameters, namely, the time to reach a permittivity peak (Tpeak) and maximum change in permittivity after the peak (Δϵr,max) are assessed by the MIA system and benchmarked against the corresponding parameters of a rotational thromboelastometry (ROTEM) assay. Tpeak exhibits a very strong positive correlation (r = 0.98, p < 10-6, n = 20) with the ROTEM clotting time (CT) parameter, while Δϵr,max exhibits a very strong positive correlation (r = 0.92, p < 10-6, n = 20) with the ROTEM maximum clot firmness (MCF) parameter. This work shows the potential of the MIA system as a standalone, multichannel, portable platform for comprehensive assessment of hemostasis at the point-of-care/point-of-injury (POC/POI).

Design and Performance Analysis of Monitoring System for Seed Metering and Fertilization of Precision Seeder Based on Photoelectric Sensor

In order to realize accurate monitoring of wheat sowing and fertilization process and ensure efficient and reliable sowing operation, an integrated monitoring system of wheat sowing and fertilization based on variable-distance photoelectric sensor is designed. The monitoring system includes the hardware circuit of STM32F103 lower computer and the human-machine interface of the upper computer touch screen. The hardware circuit of the lower computer is composed of OH-1021 photoelectric sensor, signal shaping and amplifying circuit, encoder speed acquisition module, communication module, central processor, and peripheral circuits. The information of seed fertilizer flow and seed fertilizer shaft rotation is obtained through the reflective photoelectric sensor and rotary encoder respectively to judge the running state of sowing. The information is transmitted to the human-machine interface of the upper computer touch screen of MCGS by means of Modbus communication protocol. In the experimental species, the single seed monitoring accuracy of the monitoring system reaches 98.6%. Compared with the test results of the performance test bench of the seed metering device, the monitoring error of the monitoring system is less than 0.3%, the monitoring error of the replay rate is less than 0.6%, and the monitoring accuracy of the seeding amount is greater than 94%. The simulation results of the seed metering monitoring circuit of the lower computer show that the detection distance of the amplifier circuit to the photoelectric sensor of the seed tube changes by [4 mm, 7 mm]. The communication test results of the upper and lower computers show that the accuracy of data transmission reaches 100%, the monitoring system shows that the accuracy of fault detection exceeds 90%, and the response time of lacking, blocking, and leaking is less than 0.3 s. The monitoring system realizes high-precision monitoring of wheat seed metering and fertilization, which is helpful to improve the quality of wheat planting.

Evaluation of SiPM-based readout system with gain stabilization for TL dosimetry

As the silicon photomultiplier (SiPM) technology has developed and matured, it has opened up avenues for its use in various luminescence dosimetry applications. However, the temperature sensitivity of SiPMs needs to be considered in settings where a SiPM-driven system may be affected by heat, such as during thermoluminescence (TL) measurements. This study investigated the TL signal reproducibility and temperature dependence of SiPMs (3×3mm2,50μm) using a Risoe TL/OSL-DA-20 reader, a gain stabilizing driver circuit, and a data acquisition (DAQ) module. The signal variation was insignificant when the temperature varied by less than 2 °C. However, when there was no temperature control, the signal loss occurred due to increased dark counts. We assessed four commercial dosimeters and compared them to conventional TL detection via a photomultiplier tube (PMT) in terms of dose-response, detection limits, and TL glow-curve characteristics. The slope in the dose-response (i.e., sensitivity) of the SiPM-based system was 1.5 to 3 times lower compared to PMT depending on the dosimeter. We explored the viability of TL readings by examining the potential reduction in sensitivity and dark counts due to the SiPM's photon-resolving feature. While the evaluation results of the suggested system demonstrate its practical usefulness, there are still unexplored areas that warrant further investigation. These are discussed in relation to the dark count rate, which is a major parameter that can impede the overall performance.

Automating intersection marking data collection and condition assessment at scale with an artificial intelligence-powered system

Intersection markings play a vital role in providing road users with guidance and information. The conditions of intersection markings will be gradually degrading due to vehicular traffic, rain, and/or snowplowing. Degraded markings can confuse drivers, leading to increased risk of traffic crashes. Timely obtaining high-quality information of intersection markings lays a foundation for making informed decisions in safety management and maintenance prioritization. However, current labor-intensive and high-cost data collection practices make it very challenging to gather intersection data on a large scale. This paper develops an automated system to intelligently detect intersection markings and to assess their degradation conditions with existing roadway Geographic information systems (GIS) data and aerial images. The system harnesses emerging artificial intelligence (AI) techniques such as deep learning and multi-task learning to enhance its robustness, accuracy, and computational efficiency. AI models were developed to detect lane-use arrows (85% mean average precision) and crosswalks (89% mean average precision) and to assess the degradation conditions of markings (91% overall accuracy for lane-use arrows and 83% for crosswalks). Data acquisition and computer vision modules developed were integrated and a graphical user interface (GUI) was built for the system. The proposed system can fully automate the processes of marking data collection and condition assessment on a large scale with almost zero cost and short processing time. The developed system has great potential to propel urban science forward by providing fundamental urban infrastructure data for analysis and decision-making across various critical areas such as data-driven safety management and prioritization of infrastructure maintenance.

An automated optical inspection (AOI) platform for three-dimensional (3D) defects detection on glass micro-optical components (GMOC)

With the widespread deployment of wavelength division multiplexing (WDM), optical transceivers increasingly use many glass micro-optical components (GMOC). Visual inspection of these GMOCs is a critical manufacturing step to ensure quality and reliability. However, manual inspection is often labor-intensive and time-consuming due to the transparent nature of glass components and the small, randomly located defects in three dimensions. Although automated optical inspection (AOI) exists, it has not yet been able to provide the desired level of accuracy and efficiency.This paper reports the development of an AOI platform for 3D defect detection on GMOCs. The platform incorporates 3D video acquisition and a novel two-stage neural network machine-learning algorithm. It includes a robotic arm for moving parts in 3D, a camera with an illumination module for video acquisition, and a video streaming processing unit with a machine vision algorithm for real-time defect detection on a production line. The robotic arm enables multi-perspective video capture of a test sample without refocusing. The two-stage machine learning network uses a modified YOLOv4 architecture with color channel separation (CCS) convolution, an image quality evaluation (IQE) module, and a frame fusion module to integrate the single frame detection results. This network can process multi-perspective video streams in real-time for defects detection in a coarse-to-fine manner. The AOI platform was trained with only 30 samples and achieved promising performances with a recall rate of 1, a detection accuracy of 97%, and an inspection time of 48 s per part.

A Fast Magnetic Flux Density Measurement Method With Skip-Echo Acquired Turbo Spin Echo (SATE).

The measurements of magnetic flux density ( Bz) needed in magnetic resonance electrical impedance tomography (MREIT) and magnetic resonance current density imaging (MRCDI) techniques often utilize spin echo (SE)-based sequences for data acquisition. The low imaging speed of SE-based methods significantly hampers the clinical applications of MREIT and MRCDI. Here, we propose a new sequence for substantially accelerating the acquisition of Bz measurements. A skip-echo acquired turbo spin echo (SATE) imaging sequence based on the conventional turbo spin echo (TSE) technique was proposed by adding a skip-echo module in front of the TSE acquisition module. The skip-echo module consisted of a series of refocusing pulses without acquisition. In SATE, amplitude-modulated crusher gradients were used to remove the stimulated echo pathways, and the radiofrequency (RF) pulse shape was specially selected to preserve more signals. In efficiency evaluation experiments performed on a spherical gel phantom, we demonstrated that SATE had improved measurement efficiency compared to the conventional TSE sequence via skipping one echo before acquiring signals. The accuracy of the Bz measurements by SATE was validated against those by the multi-echo injection current nonlinear encoding (ME-ICNE) method, while SATE was able to accelerate the data acquisition up to 10-fold. Volumetric coverage of Bz maps obtained in the phantom, pork, and human calf illustrated that SATE can reliably measure volumetric Bz distributions within clinically acceptable time. The proposed SATE sequence provides a fast and effective approach for volumetric coverage of Bz measurements, greatly facilitating the clinical applications of MREIT and MRCDI techniques.

The investigation of a portable solar telescope with a high gain metamaterial antenna for F10.7 radio flux measurement.

A high gain and high aperture efficiency metamaterial (MTM) antenna is applied to a solar telescope in this paper. First, a portable solar telescope including the MTM antenna and a receiving system is presented. Next, the theory of the MTM antenna is proposed and analyzed based on the ray-tracing model. The designed MTM antenna is composed of a dual circularly polarized Fabry-Pérot resonant antenna (FPRA) and four phase correction metasurfaces (PCMs). The proposed PCMs act as the reflection surface and the phase correction surface at the same time. Every PCM consists of 2 × 18 optimized artificial magnetic conductor (AMC) units. To solve the parallel incidence and narrow bandwidth problems of AMC units, a nonuniform partially reflective surface is designed. Compared with traditional FPRA, the proposed MTM antenna has an increase in peak gain of 37.5% and an aperture efficiency of 11.4%. Then, a receiving system composed of the receiver, equatorial mount, data acquisition module, and display module is presented for solar radio signal processing. Finally, the designed MTM antenna and solar telescope are simulated and measured. A good agreement between the simulation and measurement is observed and can be used to verify this design.

IOT Based Smart Chair to Help with Back Pain

Abstract: This Poor sitting posture is a common cause of low back pain, as it places excessive pressure on muscles and discs. To address this issue, smart office chairs have been developed using IoT, wireless communication, sensing, and intelligent control technologies. This paper proposes and implements a system for detecting incorrect sitting positions using a smart chair equipped with two tactile pressure sensor mats, vibration actuators, NodeMCU , a data acquisition module, and a cloud server. The system notifies users of incorrect sitting positions through visual and vibration feedback, which is received through a mobile application. Simple rules were defined to process sensor data to recognize wrong sitting postures, and the data collected from smart chairs were stored in a MongoDB database using a private cloud solution from QNAP. The Node-RED application was proposed for the entire logic implementation.

Developing a data-driven hydraulic excavator fuel consumption prediction system based on deep learning

With the aggravation of the global energy crisis, fuel consumption has become a key indicator for excavator manufacturers and policymakers. However, traditional experimental and theoretical approaches, which are complicated to calculate and dependent on the laboratory environment, are difficult to be applied in engineering. A data-driven prediction system consisting of data acquisition, feature decomposition, fuel consumption prediction, and performance evaluation modules, is developed to achieve excavator fuel consumption prediction during operation. The characteristic parameters of excavator energy consumption are collected through the established data acquisition module and the superfluous noise is eliminated by the feature decomposition module. A prediction model based on Informer is proposed in the fuel consumption prediction module to solve the drawback that the neural network model cannot capture key information in long series data in parallel, thus improving the prediction accuracy. Finally, the effectiveness of different prediction methods is verified by the performance prediction module.

Driver vigilance detection based on deep learning with fused thermal image information for public transportation

Autonomous-rail Rapid Transit (ART) is a new type of road public transportation with an automatic driving function, and it is one of the main places for epidemic spread. Scientific wearing of masks has been proven to be an extremely effective way to prevent an epidemic. However, drivers wearing masks make it difficult for traditional driver alert detection methods based on facial information to operate effectively. This paper proposes an ART driver alert detection system based on multimodal information fusion and deep learning, which can be applied to drivers wearing masks. The detection system is mainly divided into three modules: data acquisition module, preprocessing module, and vigilance detection module. The data acquisition module collects real-time face thermal imaging data, and environment temperature information of 13 people in the vigilance and fatigue state of the ART simulated driving environment. The preprocessing module proposes a face thermal imaging key information extraction method based on the constraints between Yolov5 and thermal image interframe constraints and extracts the mean temperature information and the hot voxel information (HV) of the eyes, forehead, and mask areas. Then the extracted information and the environment temperature information are transmitted together to the vigilance detection module for learning and classification. The vigilance detection module proposes a lightweight hybrid-attention optimization network, and this paper extracts training sets and testing sets from the data of 13 subjects. And the training set data is enhanced. Each sample is 90 frames. The maximum accuracy rate of the testing set reaches 99.57%. The feasibility of the detection system proposed in this paper is proved, which makes the thermal imaging and attention model show great potential in the application of traffic safety operation and maintenance.

Development of Fast Protection System with Xilinx ZYNQ SoC for RAON Heavy-Ion Accelerator

The development of the fast protection system (FPS) was driven by the critical need to safeguard internal components of the accelerator from beam damage and minimize operational downtime. During accelerator operation, various faults can occur, posing a significant risk. The FPS acts as a rapid response system, initiating a shutdown signal to a reliable chopper system to prevent beam damage and ensure the operational availability of the accelerator. To meet the stringent shut off time requirements specific to critical faults, the FPS was designed to respond within 50 µs, while the total FPS time, including acquisition, redundancy, and processing, needed to be less than 20 µs. In order to achieve these goals, a customized FPS was developed for the RAON heavy-ion accelerator, utilizing the Xilinx ZYNQ system-on-chip (SoC). The FPS system comprised seven acquisition modules, one mitigation module with an embedded SoC, and employed optical fiber connections for efficient data transmission. This article provides a comprehensive account of the design, development, and testing of the FPS system. Experimental tests were conducted to validate its performance. These tests included verifying the accuracy of cyclic redundancy checks, acquiring interlock signals in short pulses, and measuring the delay time during abnormal signal occurrences. Of particular significance is the measurement of the total signal processing time for a 1 km optical cable in the RAON system, which was determined to be 9.8 µs. This result successfully met the stringent requirement of 20 µs for the FPS time. The ability of the FPS to operate within the desired time frame demonstrates its effectiveness in protecting the accelerator’s components from beam damage and minimizing downtime. Consequently, the FPS ensures the operational availability of the accelerator while maintaining the safety and integrity of its internal systems. By providing a detailed account of the FPS’s design, development, and testing, this article contributes valuable insights into the capabilities of the FPS in real-world accelerator scenarios. The successful implementation of the RAON-optimized FPS with the Xilinx ZYNQ SoC reaffirms its effectiveness as a fast and reliable protection system, thus enhancing the overall operational performance of the accelerator.

Wi-CL: Low-Cost WiFi-Based Detection System for Nonmotorized Traffic Travel Mode Classification

Traffic travel mode identification and classification are crucial for the development of intelligent transportation systems (ITSs). At present, scholars have investigated the classification of motorized and nonmotorized traffic travel in various road environments; however, the classification of walking and bicycle modes in nonmotorized travel has been largely ignored. Therefore, in this paper, we investigate nonmotorized traffic travel and propose a new low-cost nonmotorized traffic travel mode classification system, known as the Wi-Fi classification (Wi-CL) system that uses Wi-Fi signal detectors and the refined characteristics of nonmotorized travel modes. The Wi-CL system includes four modules: data acquisition module, data processing module, feature extraction module, and mode classification module. In the data acquisition module, the proposed system detects the Wi-Fi signals of traffic participants in road environments. In addition, we propose a received signal strength indicator (RSSI) filtering algorithm for hybrid traffic networks that effectively addresses surrounding obstacles and environmental noise. In the feature extraction module, we extract relevant traffic features to construct a mode classification model. Finally, a recurrent neural network (RNN) framework based on the long short-term memory (LSTM) algorithm is successfully implemented in the mode classification module for traffic travel mode identification. To validate the effectiveness of the Wi-CL system, extensive experiments were conducted using field data collected by Wi-Fi detectors installed at the South China University of Technology (SCUT). The experimental results show that the proposed RSSI filtering algorithm achieves excellent signal filtering results in real road traffic environments. In addition, the constructed travel speed estimation algorithm outperforms other baseline models in four different scenarios (flat-peak walking, midday peak walking, flat-peak cycling, and midday peak cycling), achieving an overall classification accuracy of 97.92%. In summary, our Wi-CL system is a feasible approach for nonmotorized traffic travel mode classification.