Real-time Sensor Research Articles

Real-Time Sprinkler Irrigation (RTSI) Scheduling for Improving Wheat Crop Water Productivity in Vertisols

An experiment was conducted at ICAR- Central Institute of Agricultural Engineering (CIAE) Bhopal, Madhya Pradesh, India, during the rabi seasons of 2017-18 and 2018-19 with the objectives of to study improved irrigation scheduling for enhancing water productivity of wheat crops in Vertisols. The experiment involved permanent raised bed cultivation in Vertisols and was laid out in Randomized Block Design (RBD) with two planting systems (elevated bed and flatbed) replicated three times. The elevated bed levels were set as 5, 10, 15 and 20 cm. Soil moisture was continuously monitored using a real-time sensor network sprinkler irrigation, during crop growth period. Field data on soil moisture, crop performance, and yield were regularly recorded at different crop growth stages. The results indicated that both conventional sprinkler irrigation and real-time moisture sensor-based sprinkler irrigation led to substantial water savings of 27 and 35%, respectively with corresponding yield increase of 9 and 15% when compared to gravity (flood) irrigation, showing their effectiveness. Soil moisture variability study revealed that average soil moisture levels significantly varied when bed elevation was 10 cm or more, as compared to control (bed with normal field level) in different crop physiological stages. This variation occurred under sprinkler irrigation in Vertisols for recommended irrigation water depth. Under recommended irrigation water application through sprinkler, the wheat crop yield increased for elevation variations up to 10 cm bed elevation and the yield reduced significantly for more than 15 cm bed elevation. For sprinkler irrigation, the developed irrigation water application prescriptions (water depth/irrigation) include 400 mm irrigation depth (ID) for bed of 0 cm elevation, 476 mm ID for bed of 20 cm elevation and 552 mm ID for 30 cm bed elevation to sustain the wheat crop yield under soil moisture variability in Vertisols.

An intelligent online fault diagnosis system for gas turbine sensors based on unsupervised learning method LOF and KELM

The performance of gas turbine inevitably grades slowly in service. In order to obtain high-precision state assessment, an intelligent online real-time sensor fault diagnosis algorithm was proposed in this paper. This method can automatically establish an accurate diagnosis model in a short time, realize the rapid diagnosis of sensor faults, and can effectively solve the problem of operation data imbalance. Firstly, wavelet analysis quickly converts the high-dimensional time-series sensor signal into a low-dimensional feature vector. Then, the unsupervised method LOF was used to screen the abnormal sensor signals. Finally, the KELM is used to achieve fast online identify the fault modes of the sensors. This fault diagnosis system achieves a faster diagnosis speed while ensuring the accuracy. The effectiveness of the method proposed in this paper was verified on the operational data of a gas turbine, the diagnosis time is about 0.233 s, which greatly increases the diagnosis speed compared with other methods, at the same time, the proposed method can guarantee more than 95 % of diagnosis accuracy.

Obstacle Detection and Avoidance Using Ultrasonic Sensors in Autonomous Robots

Autonomous robots have recently gained traction in a variety of industries due to their efficiency and possible cost savings. However, assuring the safety and dependability of these robots is critical, especially in terms of obstacle detection and avoidance. Ultrasonic sensors, which are known for their low cost, user-friendliness, and dependability, have emerged as a popular and practical solution to this problem. In this paper, the author offer a framework for using numerous ultrasonic sensors in autonomous robots to detect and avoid obstacles.In our approach, real-time sensor data processing is used to correctly identify and quantify the distances to obstacles, which subsequently guides the robot's path adjustment using obstacle avoidance algorithms. The findings show that our proposed framework for multiple ultrasonic sensor-based range and obstacle avoidance is capable of identifying and avoiding obstacles in a variety of situations. Furthermore, this study conducted a comparison analysis between our method and standard single ultrasonic sensor-based obstacle identification and avoidance approaches, indicating that our approach is more accurate, reliable, and robust.This method ensures safe and dependable navigation in a variety of applications, including mobile robots, autonomous vehicles, and drones. Overall, our research advances the development of low-cost, highly dependable autonomous robots for obstacle recognition and avoidance, allowing them to navigate difficult settings.

Fully enclosed microbeads structured TENG arrays for omnidirectional wind energy harvesting with a portable galloping oscillator

To facilitate the transition of triboelectric nanogenerators (TENG) from early stages to large-scale real-world applications, urgent mass production is imperative, necessitating standardized manufacturing processes. In this study, a novel “pause-and-insert” and “print-in-place” 3D printing approach has been devised, employing widely available fused deposition modeling (FDM) printers along with conductive (as electrodes) and nonconductive (for casing and support) filaments to make encapsulate microbeads triboelectric nanogenerator (MB-TENG). This innovation results in a fully enclosed freestanding-mode TENG pack, seamlessly integrated with a lightweight wind-induced oscillator featuring tuning systems, thus enabling efficient, safe, and noiseless omnidirectional wind energy harvesting. Through adept design and manufacturing techniques, systematic inner-structure optimization has been achieved, yielding superior output and industrialization levels compared to similar efforts. MB-TENG’s surface charge density is as high as 19.9 µC/m2. The average power density is 13.8 W/m3. Moreover, the elimination of postprocessing significantly streamlines standard manufacturing, enhancing the prospects for device commercialization. Beyond its wind energy application, the versatile energy packs can serve as both ocean wave and human motion harvesters within network configurations, capable of powering a massive real-time monitoring sensor array.

Pure-water-soluble colorimetric chemosensors for highly sensitive and rapid detection of hydrogen sulfide: Applications to evaluation of on-site water quality and real-time gas sensors

Hydrogen sulfide (H2S) has adverse effects on humans in various routes through water and air. However, the versatile detection of hydrogen sulfide (H2S) gas in various environments is still challenging. Herein, we report a highly sensitive, rapid, and selective colorimetric chemosensor (IID1) for the detection of H2S in diverse conditions including solution in pure water, thin-film, dyed-fabric, and coated silica in ambient air. The H2S-induced chemical reaction of IID1 results in significant spectral changes in UV-Vis absorption, accompanied by a discernible color change from dark red to colorless. Moreover, IID1 exhibits excellent selectivity among the competitive analytes, with a detection limit of 1.12 ppb and a rapid detection time (<10 s), which is among the highest performances reported for colorimetric H2S chemosensors. The detection mechanism is systemically investigated based on the analyses of UV-Vis absorption, NMR, and mass spectra. Utilizing the high solubility of IID1 in pure water, we successfully evaluate on-site water (river, lake, stream, reservoir, and tap water) quality with excellent accuracy. Furthermore, we demonstrate H2S detection on paper strips and face masks using the IID1. Our results suggest that IID1 is a practical sensor platform for the efficient detection of H2S in various environments.

Monitoring and control system of environmental parameters in swiftlet houses

Almost 23665 swiftlet houses across 63 provinces in Vietnam suffer vast losses of swiftlet nest production due to a lack of monitoring and controlling the suitable environmental parameters in their bird houses. Effectively managing the right factors, such as temperature, humidity, light intensity, sound level, and crowded level, significantly leads to the high production of swiftlet nests. Unfortunately, there are few relevant research in the literature. This research helps to improve economic efficiency in swiftlet nest house farming by applying modern technical methods to monitor essential environmental parameters in the swiftlet house combined with comparative analysis of collected data from real-time continuous sensors. The proposed three-module system can operate on Raspberry Pi, Android mobile applications, and web interface to automatically monitor the swiftlet house and raise warnings for unusual environmental conditions. Our proposed system has been deployed on the authors’ five swiftlet houses that strongly prove the capability and extendability.

The Study of an Adaptive Bread Maker Using Machine Learning.

Bread is one of the most consumed foods in the world, and modern food processing technologies using artificial intelligence are crucial in providing quality control and optimization of food products. An integrated solution of sensor data and machine learning technology was determined to be appropriate for identifying real-time changing environmental variables and various influences in the baking process. In this study, the Baking Process Prediction Model (BPPM) created by data-based machine learning showed excellent performance in monitoring and analyzing real-time sensor and vision data in the baking process to predict the baking stages by itself. It also has the advantage of improving the quality of bread. The volumes of bread made using BPPM were 127.54 ± 2.54, 413.49 ± 2.59, 679.96 ± 1.90, 875.79 ± 2.46, and 1260.70 ± 3.13, respectively, which were relatively larger than those made with fixed baking time (p < 0.05). The developed system is evaluated to have great potential to improve precision and efficiency in the food production and processing industry. This study is expected to lay the foundation for the future development of artificial intelligence and the food industry.

Optimization of Piezoresistive Response of Elastomeric Porous Structures Based on Carbon-Based Hybrid Fillers Created by Selective Laser Sintering.

Recently, piezoresistive sensors made by 3D printing have gained considerable interest in the field of wearable electronics due to their ultralight nature, high compressibility, robustness, and excellent electromechanical properties. In this work, building on previous results on the Selective Laser Sintering (SLS) of porous systems based on thermoplastic polyurethane (TPU) and graphene (GE)/carbon nanotubes (MWCNT) as carbon conductive fillers, the effect of variables such as thickness, diameter, and porosity of 3D printed disks is thoroughly studied with the aim of optimizing their piezoresistive performance. The resulting system is a disk with a diameter of 13 mm and a thickness of 0.3 mm endowed with optimal reproducibility, sensitivity, and linearity of the electrical signal. Dynamic compressive strength tests conducted on the proposed 3D printed sensors reveal a linear piezoresistive response in the range of 0.1-2 N compressive load. In addition, the optimized system is characterized at a high load frequency (2 Hz), and the stability and sensitivity of the electrical signal are evaluated. Finally, an application test demonstrates the ability of this system to be used as a real-time wearable pressure sensor for applications in prosthetics, consumer products, and personalized health-monitoring systems.

Handling fault detection and diagnosis in incomplete sensor measurements for BAS based HVAC system

Due to the development of sensor networks, Building Automation System (BAS) based heating, ventilation, and air conditioning (HVAC) has gradually replaced traditional HVAC to improve indoor thermal comfort and decrease energy consumption. Because of inevitable faults in sensors or networks, the real-time sensor data may be incomplete with corrupted, lost or undetected missing values. Therefore, Improved Fireworks Algorithm (IFWA)-Long Short-Term Memory (LSTM) is proposed to recover incomplete measurements in BAS HVAC sensors. Because sensor data loss mostly results from incorrect control commands from the BAS system or sensor damage, there is a high probability of concurrent sensor fault. Therefore, Independent Component Analysis (ICA)-K-Nearest Neighbors (KNN) is proposed to monitor the sensor's healthy state under the measurements recovered. This paper discusses the possible causes of incomplete measurement in BAS HVAC sensors and simulates the distribution by experiment. The experiment analyzes the data recovery capability of IFWA-LSTM for different types of missing sensor data in different sensor measurement loss scenarios. The result shows that compared to the comparative methods, IFWA-LSTM achieves a 6.45 %–86.92 % improvement in recovery accuracy and a 0.0041 to 0.6340 improvement in correlation coefficients. Subsequently, it discusses the fault diagnosis rate of ICA-KNN under full measurements and incomplete measurement recovered by IFWA-LSTM. Overall, ICA-KNN achieves an average fault diagnosis rate of 99.86 % and an average fault alarm rate of 0 % under full measurement. When applied to incomplete measurement recovered by IFWA-LSTM, ICA-KNN exhibits an average fault diagnosis rate of 92.18 % and an average fault alarm rate of 1.22 %.

Application research on digital twins of urban earthquake disasters

The digital twin of an earthquake disaster city constructed using digital twin technology can reflect the data of different stages of the earthquake disaster in the virtual space and can ensure high synchronisation and simulation of the two to effectively improve the safety of emergency rescue personnel and the scientific decision-making ability of decision makers. Oblique photogrammetry matched the Light Detection and Ranging (LiDAR) data to complete a high-precision three-dimensional real-scene model. The urban digital twin model was established as a module with the three-dimensional base model generated by the two-dimensional frame data with a fast update speed. Based on the shortest-fault-distance intensity-attenuation model, the seismic intensity was calculated using a known active fault and aftershock sequence, and the applicability of this method was verified. The elastic-plastic time history analysis method was used to calculate the seismic response of the building, and the seismic damage level was visualised using a three-dimensional model. The dynamic changes of earthquake disasters are monitored by sensors in real time and analysed in a digital twin model to provide an optimal scheme for earthquake emergency rescue and accurate evaluation results of earthquake disasters.

109 Animal Behavior Analysis Using Unsupervised Machine Learning Techniques

Abstract With recent technological advances, Global Positioning Systems (GPS) and other tracking sensors can collect large amounts of data and transfer information to the cloud and then to producers to remotely monitor livestock health and well-being. Currently, supervised machine learning, such as random forest and linear or quadratic discriminant analysis techniques are used to develop algorithms to identify changes in animal behavior that may be associated with well-being concerns. Supervised machine learning requires behavior observation of monitored animals and may hinder normal expression. However, recording behavioral observations is time consuming and expensive. Our goal was to design a new unsupervised machine learning framework to identify animal behavior without the utilization of human observations. The framework contains two steps. The first step is to segment the tracking data of the animal using time series segmentation, and the second step is to group the segments into clusters where each cluster represents one type of behavior. To validate the applicability of our proposed framework, we utilize GPS tracking data collected at 2-minute intervals from eight cows from May 28 to June 22, 2018, in a 1096 ha rangeland pasture near Prescott, Arizona. After extensive experiments, our framework can partition the movement of the cow using the speed, direction, and distance of the cow from water. These segments were grouped into meaningful behavior clusters using clustering analysis. Speed was the most successful feature for clustering into behaviors. Results are similar to approaches based only on expert knowledge, that rely on speed for classification. Our study demonstrated that we can directly use unlabeled data to group animal behaviors from GPS tracking data. The proposed unsupervised two-step framework allows the analysis of cattle tracking data without direct human observation of behaviors. It is applicable for analyzing the immense amount of data that can be obtained from real-time tracking and sensor devices.

Deep learning and IoT enabled digital twin framework for monitoring open-pit coal mines

Early detection of cracks enables timely mitigation and maintenance actions, ensuring the safety of personnel and equipment within the open-pit coal mine. Monitoring open-pit coal mines and cracks is essential for the safety of workers and for saving national assets. Digital twins (DTs) can be crucial in open-pit coal mine crack detection. DTs enable continuous real-time monitoring of the open-pit mine, including its structures and surrounding environment. Various sensors and internet-of-things devices can be deployed to collect data on factors such as ground movement and strain. Integrating this data into the DT makes it possible to identify and analyze anomalous behavior or changes that may indicate crack formation or propagation. Deep learning-based networks are a crucial factor in detecting open-pit coal mine cracks. In this work, we propose a deep learning-based densely connected lightweight network incorporated into the DT-based framework for detecting cracks and taking predictive maintenance-based decisions by combining historical data, real-time sensor data, and predictive models. The proposed DT-based framework provides insights into the potential crack formation, allowing for proactive maintenance and mitigation measures. We compare the performance of our proposed network on different evaluation measures such as precision, recall, overall accuracy, mean average precision, F1-score, and kappa coefficient, where our proposed lightweight multiscale feature fusion-based network outperformed all other state-of-the-art deep neural networks. We also achieved the best performance on mean average precision by surpassing all other models. Additionally, we also compared the performance of our proposed network with U-Net and recurrent neural network on model training and prediction time benchmarks by outperforming those cutting-edge models.

Multiutility &amp; Customizable Environment Monitoring System With The Healthcare Utilities

IoT based approach of the Remote Monitoring System (RMS). To serve data to the user over long distances wirelessly, Chatbots, web servers and cloud storage could be the best alternative of all and to make the device which satisfies the user's needs we have combined all of them to create a multi utility environmental parameters monitoring and recording system. The device is capable of broadcasting real-time sensor data over the cloud server, social media and a local host web server with the speed depending upon the internet. Integration of API has enabled the device to connect with social media and cloud storage services.

Microarchitectured strontium doped silver niobate embedded ecoflex composite films for highly efficient box-type mechanical energy harvesters

Understanding the increasing energy demands and probable utilization of mechanical energy harvesters, current research is highly focused on enhancing their performance/applicability in everyday life. Herein, we proposed a box-type hybrid nanogenerator (BT-HNG) consisting of acetone-dissolved microarchitectured strontium (Sr) doped silver niobate (ASNb)/ecoflex composite film as a highly efficient mechanical energy harvester. The simple and unique microarchitectured (MA) master mold was fabricated by immersing a plastic petri dish inside the acetone which was further utilized to obtain MA-composite films. The ASNb microparticles (MPs) with varying the Sr doping concentration were synthesized and further loaded inside the ecoflex film to enhance its dielectric properties. The MA-ASNb/ecoflex composite films were utilized as a negative triboelectric material and copper as a positive triboelectric material for the fabrication of HNG operating in a contact-separation mode. The ASNb filler concentration inside the ecoflex film was optimized in the aspect of Sr doping and filler concentrations to obtain the highest electricity from respective HNG. The highly efficient and stable electrical output produced by the HNG was further utilized to power various small-scale electronics. The BT-HNG producing unique direct current electrical output was developed by integrating five similar HNGs in it. The enhancement in the electrical output with successive addition of each HNG was thoroughly investigated. The proposed BT-HNG was successfully demonstrated as a real-time sensor that can be utilized to turn on the lamps situated at stairs, corridors, etc. in human presence. The enclosed BT-HNG along with a heavy weighing block was demonstrated to harvest vibrational/linear movements into electricity.

Air pollution perception bias: Mismatch between air pollution exposure and perception of air quality in real-time contexts

Air pollution perception biases hinder the public's awareness of actual air quality. Past studies that examined the association and mismatch between actual and perceived air quality neglected individuals’ dynamic exposure and their activity, travel, spatial, temporal, and social contexts. Using data collected with real-time air pollutant sensors and ecological momentary assessment (EMA), this study investigated the association and mismatch between momentary air pollution exposure and perceived air quality. It also examined how activity type, travel mode, spatial and temporal contexts, and social factors contribute to this disparity. The results show that exposure to air pollution is significantly higher in residential areas (1.777 μg/m3) and transportation land-use areas (2.863 μg/m3) compared to commercial areas. Exposure in the evening is 1.308 μg/m3 higher than in the afternoon. Working or studying activities are associated with 2.863 μg/m3 lower exposure, and individuals perceive air quality as good when working or studying and in residential areas. Conversely, individuals assess air quality as poor in railway travel contexts and being accompanied by friends. This study also reveals the nonstationary association between air pollution exposure and perceived air quality. The odds of underestimating air pollution are 1.8–2.7 times as high as that in residential areas and 2.1 to 2.6 times that in transportation land-use areas when compared to commercial areas. Implementing targeted mitigation measures in these contexts can enhance public awareness of air pollution.

Chromogenic probe adhered porous polymer monolith as real-time solid-state sensor for the detection of ultra-trace toxic mercury ions

The escalating predicament of water pollution has spurred the development of new chromogenic materials for the efficient detection/screening of toxic mercuric (Hg2+) ions. In this study, we report a simple and efficient detection stratagem by infusing a chromogenic ion-receptor (BTDA), i.e., 4-(benzothiazol-2-yl)-N, N-dimethylaniline onto a structurally intertwined meso-/macro-pore polymer template for the target-specific sensing of ultra-trace Hg2+. The structural/surface features of the monolithic polymer template, prepared from glycidyl methacrylate (GMA) monomer crosslinked with ethylene glycol dimethacrylate (EGDMA), facilitate voluminous infusion and uniform decoration of ion-receptor molecules across the continuous porous poly(GMA-co-EGDMA) framework, resulting in a solid-state colorimetric sensory system. The bimodal polymer network's intriguing surface and structural morphology of the chromogenic sensor material are interpreted using scanning/transmission electron microscopy, X-ray diffraction, photoelectron spectroscopy, energy dispersive X-ray spectrometry, optical spectroscopy, surface area, porosity and thermal analysis. The proposed Hg2+ sensor offers a linear response range of 1–150 μg/L, with a detection and quantification limit of 0.29 and 0.97 μg/L, respectively. The poly(GMA-co-EGDMA)-BTDA sensor exhibits a quick ion-sensing response (40 s) with distinct color transitions from pastel yellow to olive as a function of increasing Hg2+ concentration. The matrix tolerance studies for the proposed sensory system reveal high selectivity for Hg2+, with a recovery of ≥99.2% in on-site environmental samples. The sensor material exhibits excellent data reproducibility and reliability up to seven cycles of reusability.

Smart implements by leveraging ISOBUS: Development and evaluation of field applications

Increased labor scarcity and input costs, as well as the demand for ecologically more sound control of growing conditions while maintaining yield and quality in both viticulture as well as horticulture have proliferated the requirements for the current technologies such as implements and autonomous vehicles used in these domains. The increasing employment of such technology, however, brings up the issue of compatibility, in terms of data exchange, connectivity, and communication between the implements and autonomous vehicles used. Besides that, conducting the connection and communication in a standardized means adds more complexity to the issue. To properly address the above-mentioned issue, this work focused on developing a middleware that introduced the ISO 11783 standard-based communication to the setup for both, a weeder robot and a combination of a sprayer and a retrofitted tractor. The developed middleware also considered the information exchange with external systems such as real-time decision-making sensor systems and a farming controller to accurately carry out the field applications of weeding and spraying. The correctness of the weeding quality computation and the spraying coverage indicating the performance of the developed setups were verified before conducting in-field applications. The subsequent in-field weeding application indicated an adequate evaluation of the weeding quality with a variation from 94 to 100 % and zeros in the regions of the weeding path where the weeding was not necessary. The assessment of the spraying applications based on the comparison between the prescribed and the as-applied information showed a mean value of 1.08×104 mm3 m-2 for the absolute deviation from the maximum prescribed rate. Further analyses indicated that the as-applied rate varied with a deviation of 10 % during the field application, which was below the defined threshold.

Logistic Regression and Internet of Things Based Smart Irrigation to Predict Crops Water Need

Irrigation is crucial to agriculture. Due to advancements in technology, when we go outside or whenever crops need to be watered, we no longer need to rely on someone to perform irrigation. Many researchers have attempted to irrigate crops automatically, but accuracy, timeliness, and cost concerns are rarely addressed and given top priority. The proposed approach carries out autonomous watering, which results in smart irrigation, using a wireless sensor network, real-time sensors, and irrigation system control. By using this method, waste is decreased and the necessary water is kept in the container. Instead than just evaluating soil moisture, automated irrigation takes into account the type of crop, the weather, and soil moisture to determine whether the crops need to be watered. By taking into account the aforementioned three factors, a machine learning technique called logistic regression is utilized to estimate the need for water. The logistic regression model, which is based on the values of the three parameters given, forecasts the watering needs of the plants using an arduino-based IoT circuitry. The strategy outlined is advantageous in terms of accuracy, timeliness, and cost. The results of the proposed model has proven its betterment in performance and the amount of automation over the existing irrigation systems. The IoT and machine learning combined model is useful from the point of view of its accuracy, cost and timeliness in predicting water needs for crops as well as full automation is enabled in the irrigation system with this approach.

Ultrasensitive Bio-H2S Gas Sensor Based on Cu2O-MWCNT Heterostructures.

Developing a respiratory analysis disease diagnosis platform for the H2S biomarker has great significance for the real-time detection of various diseases. However, achieving highly sensitive and rapid detection of H2S gas at the parts per billion level at low temperatures is one of the most critical challenges for developing portable exhaled gas sensors. Herein, Cu2O-multiwalled carbon nanotube (MWCNT) heterostructures with excellent gas sensitivity to H2S at room temperature and a lower temperature were successfully synthesized by a facile two-dimensional (2D) electrodeposition in situ assembly method. The combination of Cu2O and MWCNTs via the principle of optimal conductance growth not only reduced the initial resistance of the material but also provided an ideal interfacial barrier structure. Compared to the response of the pure Cu2O sensor, that of the Cu2O-MWCNT sensor to 1 ppm of H2S increased nearly 800 times at room temperature, and the response time decreased by more than 500 s. In addition to the excellent sensitivity with detection limits as low as 1 ppb, the Cu2O-MWCNT sensor was extremely selective with low-temperature adaptability. The sensor had a response value of 80.6 to 0.1 ppm of H2S at -10 °C, which is difficult to achieve with sensors based on oxygen adsorption/desorption mechanisms. The sensor was used for the detection of real oral exhaled breath, confirming its feasibility as a real-time disease monitoring sensor. The Cu2O-MWCNT heterostructures maximized the advantages of the individual components and laid the experimental foundation for future applications of highly sensitive portable breath analysis platforms for monitoring H2S.

A smartphone-based fluorescent sensor for rapid detection of multiple pathogenic bacteria

In this study, we developed a fluorescent sensor for the sensitive detection of multiple pathogenic bacteria based on magnetic separation, fluorescent probes, and smartphone image processing. A microchannel device was assembled using high-transparency resin and 3D printing technology. This device was combined with a smartphone and an external lens to develop a fluorescent sensor for autonomous detection of multiple pathogenic bacteria. Three fluorescence probes with different fluorescence were synthesized from highly specific aptamers and tetraphenylethylene derivatives. These fluorescent probes can make Staphylococcus aureus, Escherichia coli, and Pseudomonas aeruginosa emit different colors of fluorescence. Using the enrichment performance of molecularly imprinted materials, separation and detection of bacteria can be achieved simultaneously. Finally, with the Red-Green-Blue (RGB) analysis functionality of a smartphone, real-time field detection was realized with a sensitivity of 102 CFU/mL and a detection time of 40 min. This work provides a simple, inexpensive, and real-time sensor for the detection of multiple pathogens in medical diagnostics, food testing, and environmental analyses.