A Time-Varying Parameter Estimation Method for Physiological Models Based on Physical Information Neural Networks

In the establishment of differential equations,the determination of time-varying parameters is a difficult problem,especially for equations related to life activities.Thus,we propose a new framework named BioE-PINN based on a physical information neural network that successfully obtains the time-varying parameters of differential equations.In the proposed framework,the learnable factors and scale parameters are used to implement adaptive activation functions,and hard constraints and loss function weights are skillfully added to the neural network output to speed up the training convergence and improve the accuracy of physical information neural networks.In this paper,taking the electrophysiological differential equation as an example,the characteristic parameters of ion channel and pump kinetics are determined using BioE-PINN.The results demonstrate that the numerical solution of the differential equation is calculated by the parameters predicted by BioE-PINN,the RootMean Square Error(RMSE)is between 0.01 and 0.3,and the Pearson coefficient is above 0.87,which verifies the effectiveness and accuracy of BioE-PINN.Moreover,realmeasuredmembrane potential data in animals and plants are employed to determine the parameters of the electrophysiological equations,with RMSE 0.02-0.2 and Pearson coefficient above 0.85.In conclusion,this framework can be applied not only for differential equation parameter determination of physiological processes but also the prediction of time-varying parameters of equations in other fields.

Estimation of spectral responses and chlorophyll based on growth stage effects explored by machine learning methods

Estimation of leaf chlorophyll content(LCC) by proximal sensing is an important tool for photosynthesis evaluation in high-throughput phenotyping. The temporal variability of crop biochemical properties and canopy structure across different growth stages has great impacts on wheat LCC estimation, known as growth stage effects. It will result in the heterogeneity of crop canopy at different growth stages, which would mask subtle spectral response of biochemistry variations. This study aims to explore spectral responses on the growth stage effects and establish LCC models suited for different growth stages. A total number of 864 pairwise samples of wheat canopy spectra and LCC values with 216 observations of each stage were sampled at the tillering, jointing, booting and heading stages in 2021. Firstly, statistical analysis of LCC and spectral response presented different distribution traits and typical spectral variations peak at 470, 520 and 680 nm. Correlation analysis between LCC and reflectance showed typical red edge shifts. Secondly, the testing model of partial least square(PLS) established by the entire datasets to validate the predictive performance at each stage yielded poor LCC estimation accuracy. The spectral wavelengths of red edge(RE) and blue edge(BE) shifts and the poor estimation capability motivated us to further explore the growth stage effects by establishing LCC models at respective growth periods.Finally, competitive adaptive reweighted sampling PLS(CARS-PLS), decision tree(DT) and random forest(RF) were used to select sensitive bands and establish LCC models at specific stages. Bayes optimisation was used to tune the hyperparameters of DT and RF regression. The modelling results indicated that CARS-PLS and DT did not extract specific wavelengths that could decrease the influences of growth stage effects. From the RF out-of-bag(OOB) evaluation, the sensitive wavelengths displayed consistent spectral shifts from BE to GP and from RE to RV from tillering to heading stages. Compared with CARS-PLS and DT,results of RF modelling yielded an estimation accuracy with deviation to performance(RPD) of 2.11, 2.02,3.21 and 3.02, which can accommodate the growth stage effects. Thus, this study explores spectral response on growth stage effects and provides models for chlorophyll content estimation to satisfy the requirement of high-throughput phenotyping.

Information fusion in aquaculture:a state-of the art review

Efficient fish feeding is currently one of biggest challenges in aquaculture to enhance the production of fish quality and quantity. In this review, an information fusion approach was used to integrate multisensor and computer vision techniques to make fish feeding more efficient and accurate. Information fusion is a well-known technology that has been used in different fields of artificial intelligence, robotics, image processing,computer vision, sensors and wireless sensor networks.Information fusion in aquaculture is a growing field of research that is used to enhance the performance of an"industrialized" ecosystem. This review study surveys different fish feeding systems using multi-sensor data fusion, computer vision technology, and different food intake models. In addition, different fish behavior monitoring techniques are discussed, and the parameters of water, p H, dissolved oxygen, turbidity, temperature etc.,necessary for the fish feeding process, are examined.Moreover, the different waste management and fish disease diagnosis techniques using different technologies,expert systems and modeling are also reviewed.

Measurement investigation on the feasibility of shallow geothermal energy for heating and cooling applied in agricultural greenhouses of Shouguang City: Ground temperature profiles and geothermal potential

The use of electrical energy for heating and cooling systems to control the temperature in greenhouses will lead to high production and product costs.To solve this problem,shallow geothermal energy as a local source of energy could be applied.In this study,a measurement model,the distribution profiles of temperature,and a preliminary assessment of the geothermal potential in the shallow zone at depths of 0.1 m to 3.6 m in Shouguang City,Shandong Province,eastern China were presented.The measurement results showed that the annual average temperature at depths of 0.1–3.6 m ranged from 13.1℃ to 17.6℃.Preliminary assessment results of the geothermal potential showed that the daily average temperature difference between the air and at depths of 1.5–3.6 m was mainly from 10℃ to 25℃ during the winter months and between-15℃ and-5℃ during the summer months.Therefore,the heating systems could operate during January,February,November,and December.In May,June,and July,the cooling systems could be applied.Moreover,the measurement model gave good stability results,and it could be used in combination with the monitoring of the groundwater table,a survey of the thermal conductivity of the soil,climate change studies,which helps reduce unnecessary time and costs.

A portable viable Salmonella detection device based on microfluidic chip and recombinase aided amplification

creening of foodborne pathogens is important to prevent contaminated foods from their supply chains.n this study, a portable detection device was developed for rapid, sensitive and simple detection of viable almonella using a finger-actuated microfluidic chip and an improved recombinase aided amplification (RAA) assay. Improved propidium monoazide(PMAxx) was combined with RAA to enable this device to distinguish viable bacteria from dead ones. The modification of PMAxx into dead bacteria, the magnetic xtraction of nucleic acids from viable bacteria and the RAA detection of extracted nucleic acids were performed using the microfluidic chip on its supporting device by finger press-release operations. The fluorescent signal resulting from RAA amplification of the nucleic acids was collected using a USB camera nd analyzed using a self-developed smartphone App to quantitatively determine the bacterial concenration. This device could detect Salmonella typhimurium in spiked chicken meats from 1.3 × 10^(2) CFU/m L o 1.3 × 10^(7) CFU/m L in 2 h with a lower detection limit of 130 CFU/m L, and has shown its potential for on-site detection of foodborne pathogens.

Fault Diagnosis System for Aquaculture Networking Based on Neural Network

In view of existing problems at current aquaculture networking, such as nonlinear characteristic of fault and faults are easily affected by many factors, a fault diagnosis model based on neural network was proposed. In the building process of the model, the common fault types in the field of aquaculture networking were first analyzed and the types of fault mode were summarized. Afterwards, the evaluation indices of fault diagnosis were made, and eventually the fault diagnosis system of aquaculture networking was constructed using neural network principle. The fault diagnosis system could not only reduce the communication burden, but also have high diagnostic rate. Thus, it could be well applied in the fault dia^osis system for aquaculture networking.

Magnetorheological elastomer and smartphone enable microfluidic biosensing of foodborne pathogen

Rapid detection of foodborne pathogens is crucial to prevent the outbreaks of foodborne diseases.In this work,we proposed a novel microfluidic biosensor based on magnetorheological elastomer(MRE)and smartphone.First,micropump and microvalves were constructed by deforming the MRE under magnetic actuation and integrated into the microfluidic biosensor for fluidic control.Then,the micropump was used to deliver immune porous gold@platinum nanocatalysts(Au@PtNCs),bacterial sample,and immunomagnetic nanoparticles(MNPs)into a micromixer,where they were mixed,incubated and magnetically separated to obtain the Au@PtNC-bacteria-MNP complexes.After 3,3',5,5'-tetramethylbenzidine and hydrogen peroxide were injected and catalyzed by the Au@PtNCs,smartphone was used to measure the color of the catalysate for quantitative analysis of target bacteria.Under optimal conditions,this biosensor could detect Salmonella typhimurium quantitatively and automatically in 1 h with a linear detection range of 8.0×10^(1) CFU/mL to 8.0×10^(4) CFU/mL and a detection limit of 62 CFU/mL.The microfluidic biosensor was compact in size,simple to use,and efficient for detection,and might be used for in-field screening of foodborne pathogens to prevent food poisoning.

An improved method for prediction of tomato photosynthetic rate based on WSN in greenhouse

In order to improve the efficiency of CO2 fertilizer and promote high quality and yield,it is necessary to precisely control CO2 fertilizer by wireless sensor network based on a model of photosynthetic rate prediction in greenhouse.An experiment was carried out on tomato plants in greenhouse for photosynthetic rate prediction modeling combined rough set and BP neural network.In data acquiring phase,plants growth information and greenhouse environmental information that may have influences on photosynthetic rate,including plant height,stem diameter,the number of leaves and chlorophyll content of functional leaves,air temperature,air humidity,light intensity,CO2 concentration and soil moisture,which were measured.And LI-6400XT photosynthetic rate instrument was used for obtaining net photosynthetic rate of functional leaf.After preliminary processing,135 sets of data were obtained.And twelve of them were used for model test of neural network,while the others were used for modeling.All of the data were normalized before modeling.Two models were built to predict photosynthetic rate based on BP neural network.One had total nine input parameters.The other had six input parameters,chlorophyll content,air temperature,air humidity,light intensity,CO2 concentration,and soil moisture,which were reducted from original nine based on attributes reduction theory of rough set.Both two models have one output parameter,the net photosynthetic rate of single leaf.The genetic algorithm was adopted to reduct attributes.Since continuous data cannot be processed by rough set,the K-mean cluster method was used to discretize the data of nine input parameters before attributes reduction.The prediction results of two models showed that the model with six input parameters had a mean absolute error of 0.6958,an average relative error of 7.28%,a root-mean-square error of 0.7428,and a correlation coefficient of 0.9964,while the other model respectively had 0.4026,4.53%,0.3245 and 0.9965,which proved that the model with minimum attributes had higher prediction accuracy.On the other hand,the number of iterations was used to represent the neural network train speed.The result showed that the model with six input parameters had an iteration of 544,while the other had 1038.Hence,the reduction model was applied to controlling CO2 concentration.The net photosynthetic rates at different CO2 concentrations were predicted at a certain condition.The results had the same curve trend with theory analysis,and a high prediction accuracy,which proved that the model was useful for CO2 concentration control.

A microfluidic biosensor for rapid detection of Salmonella typhimurium based on magnetic separation,enzymatic catalysis and electrochemical impedance analysis

Rapid screening of foodborne pathogens is of great significance to ensure food safety.A microfluidic biosensor based on immunomagnetic separation,enzyme catalysis and electrochemical impedance analysis was developed for rapid and sensitive detection of S.typhimurium.First,the bacterial sample,the magnetic nanoparticles(MNPs)modified with capture antibodies,and the enzymatic probes modified with detection antibodies and glucose oxidase(GOx)were simultaneously injected into the microfluidic chip,followed by mixing and incubation to form MNP-bacteria-probe sandwich complexes.Then,glucose with high impedance was injected into the chip and catalyzed by the GOx on the complexes into hydrogen peroxide with high impedance and gluconic acid with low impedance,which was finally measured using the low-cost interdigitated microelectrode and the electrochemical impedance analyzer to determine the target bacteria.Under the optimal conditions,this biosensor could quantitatively detect S.typhimurium at the concentrations from 1.6×10^(2) CFU/m L to 1.6×10^(6) CFU/m L in 1 h with the low detection limit of 73 CFU/m L.Besides,this biosensor was demonstrated with good feasibility for practical applications by detecting the S.typhimurium spiked chicken meat samples.

Connectivity of wireless sensor networks for plant growth in greenhouse

Wireless sensor networks have been applied in farmland and greenhouse.However,poor connectivity always results in a lot of nodes isolation in the network in a scenario.For this reason,the network connectivity is worth considering to improve its quality,especially when the collected data cannot be sent to the data center because of the obstacles such as the growth of crop plants and weeds.Therefore,how to reduce the effect of crop growth on network connectivity,and enable the reliable transmission of field information,are the key problems to be resolved.To solve these problems,the method which adds long distance routing nodes to the WSN to reduce the deterioration of WSN connectivity during the growth of plants was proposed.To verify this method,the network connectivity of the deployed WSN was represented by the rank of connection matrix based on the graph theory.Consequently,the rank with value of 1 indicates a fully connected network.Moreover,the smaller value of rank means the better connectedness.In addition,the network simulator NS2 simulation results showed that the addition of long-distance backup routing nodes can improve the network connectivity.Furthermore,in experiments,using ZigBee-based wireless sensor network,a remote monitoring system in greenhouse was established,which can obtain environmental information for crops,e.g.temperature,humidity,light intensity and other environmental parameters as well as the wireless link quality especially.Experimental results showed adding of long-distance backup routing nodes can guarantee network connectivity in the region where received signal strength indication(RSSI)was poor,i.e.RSSI value was less than−100 dBm,and the energy was low.In conclusion,this method was essential to improve the connectivity of WSN,and the optimized method still needs further research.

Estimation of chlorophyll content in maize canopy using wavelet denoising and SVR method

In order to estimate the chlorophyll content of maize plant non-destructively and rapidly,the research was conducted on maize at the heading stage using spectroscopy technology.The spectral reflectance of maize canopy was measured and processed following wavelet denoising and multivariate scatter correction(MSC)to reduce the noise influence.Firstly,the signal to noise ratio(SNR)and curve smoothness(CS)were used to evaluate the denoising effect of different wavelet functions and decomposition levels.As a result,the Sym6 wavelet basis function and the 5th level decomposition were determined to denoise the original signal.The MSC method was used to eliminate the scattering effect after denoising.Then three spectral ranges were extracted by interval partial least squares(IPLS)including the 525-549 nm,675-749 nm and 850-874 nm.Finally,the chlorophyll content estimation model was developed by using support vector regression(SVR)method.The calibration Rc2 of the SVR model was 0.831,the RMSEC was 1.3852 mg/L;the validation Rv2 was 0.809,the RMSEP was 0.8664 mg/L.The results show that the SNR and CS indicators can be used to select the parameters for wavelet denoising and model can be used to estimate the chlorophyll content of maize canopy in the field.

Underwater image quality enhancement of sea cucumbers based on improved histogram equalization and wavelet transform

Sea cucumbers usually live in an environment where lighting and visibility are generally not controllable,which cause the underwater image of sea cucumbers to be distorted,blurred,and severely attenuated.Therefore,the valuable information from such an image cannot be fully extracted for further processing.To solve the problems mentioned above and improve the quality of the underwater images of sea cucumbers,pre-processing of a sea cucumber image is attracting increasing interest.This paper presents a newmethod based on contrast limited adaptive histogram equalization and wavelet transform(CLAHE-WT)to enhance the sea cucumber image quality.CLAHE was used to process the underwater image for increasing contrast based on the Rayleigh distribution,and WTwas used for de-noising based on a soft threshold.Qualitative analysis indicated that the proposed method exhibited better performance in enhancing the quality and retaining the image details.For quantitative analysis,the test with 120 underwater images showed that for the proposed method,the mean square error(MSE),peak signal to noise ratio(PSNR),and entropy were 49.2098,13.3909,and 6.6815,respectively.The proposed method outperformed three established methods in enhancing the visual quality of sea cucumber underwater gray image.

Rapid on-line non-destructive detection of the moisture content of corn ear by bioelectrical impedance spectroscopy

Moisture content of corn directly affects its quality and storage time,and the rapid on-line detection of the moisture content of corn ears not threshed or in vivo in the fields is required.Because of the special shape of corn ear,the rapid,low cost and non-destructive bioelectrical impedance measurement is more suitable for its moisture content detection.Using the four-electrode method with the Agilent E4980A precision LCR meter,the electrical impedance spectroscopies of the sweet corn ears and waxy corn ears at different moisture contents were acquired.The frequency range of the detection was from 20 Hz to 2 MHz and to enhance the contact,the attached-type electrodes were wrapped in cotton soaked with 0.1%NaCl solution.The impedance data over the frequency range from 300 Hz to 5 kHz were used to obtain the parameters of the bio-impedance Cole-Cole model.The results showed a good linear correlation(coefficient of determination R2=0.960)between the equivalent parallel resistance R∞of sweet corn ear and the moisture content value determined by standard chemical method.The research proved that the bioelectrical impedance spectroscopy can be used for detecting the moisture content of corn ear.

Identification of maize seed varieties based on near infrared reflectance spectroscopy and chemometrics

False seeds can often be seen in the maize seed market,leading to a serious decline in maize yield.Those existing variety identification methods are expensive,time consuming,and destructive to seeds.The aim of this study is to develop a cheap,fast and non-destructive method which can robustly identify large amounts of maize seed varieties based on near-infrared reflectance spectroscopy(NIRS)and chemometrics.Because it is difficult to establish models for every variety in the market,this study mainly investigated the performance of models based on a large number of samples(more than 40 major varieties in the market).The reflectance spectra of maize seeds were collected by two modes(bulk kernels mode and single kernel mode).Both collection modes can be applied to identification,but only the single kernel mode can be applied to purity sorting.The spectra were pretreated with smoothing,the first derivative and vector normalization;and then principal component analysis(PCA),linear discriminant analysis(LDA)and biomimetic pattern recognition(BPR)were applied to establish identification models.The environmental factors such as producing areas and years have a significant influence on the performance of the models.Therefore,the method to improve the robustness of the models was investigated in this study.New indexes(correct acceptance degree(CAD),correct rejection degree(CRD)and correct degree(CD))were defined to analyze the performance of the models more accurately.Finally,the models obtained a mean correct discrimination rate of over 90%,and exhibited robust properties for samples harvested from different areas and years.The results showed that NIR technology combined with chemometrics methods such as PCA,LDA,and BPR could be a suitable and alternative technique to identify the authenticity of maize seed varieties.

Universality of an improved photosynthesis prediction model based on PSO-SVM at all growth stages of tomato

CO_(2)concentration is an environmental factor affecting photosynthesis and consequently the yield and quality of tomatoes.In this study,a photosynthesis prediction model for the entire growth stage of tomatoes was constructed to elevate CO_(2)level on the basis of crop requirements and to evaluate the effect of CO_(2)elevation on leaf photosynthesis.The effect of CO_(2)enrichment on tomato photosynthesis was investigated using two CO_(2)enrichment treatments at the entire growth stage.A wireless sensor network-based environmental monitoring system was used for the real-time monitoring of environmental factors,and the LI-6400XT portable photosynthesis system was used to measure the net photosynthetic rate of tomato leaf.As input variables for the model,environmental factors were uniformly preprocessed using independent component analysis.Moreover,the photosynthesis prediction model for the entire growth stage was established on the basis of the support vector machine(SVM)model.Improved particle swarm optimization(PSO)was also used to search for the best parameters c and g of SVM.Furthermore,the relationship between CO_(2)concentration and photosynthetic rate under varying light intensities was predicted using the established model,which can determine CO_(2)saturation points at the various growth stages.The determination coefficients between the simulated and observed data sets for the three growth stages were 0.96,0.96,and 0.94 with the improved PSO-SVM and 0.89,0.87,and 0.86 with the original PSO-SVM.The results indicate that the improved PSO-SVM exhibits a high prediction accuracy.The study provides a basis for the precise regulation of CO_(2)enrichment in greenhouses.

Measurement and prediction of tomato canopy apparent photosynthetic rate

Given the lack of technical conditions and research methods,instruments that can measure the canopy apparent photosynthetic rate have low precision and are rarely studied.Comparative studies on canopy apparent photosynthetic rate and single leaf photosynthetic rate are also relatively few.This study aims to measure and predict the canopy apparent photosynthetic rate of tomato.A canopy apparent photosynthetic rate measuring system,which was comprised of a wireless sensor network(WSN),an assimilation chamber,and a LI-6400XT photosynthetic rate instrument was established.The system was used to determine the greenhouse environmental parameters and CO2 absorptive capacity of the whole growth stage of tomato.A semi-closed assimilation chamber was designed as a side opening to conveniently measure the canopy apparent photosynthetic rate.WSN nodes were placed in the chamber to monitor environmental parameters,including air temperature,air humidity,and assimilation chamber temperature.A grid and pixel conversion method was used to measure the whole plant leaf areas of tomato.As a semi-closed measurement system,the assimilation chamber was used to calculate the canopy apparent photosynthetic rate.To conduct a comparative research on the canopy apparent photosynthetic rate and the single leaf photosynthetic rate,the LI-6400XT portable photosynthesis system was used to measure the single leaf photosynthetic rate,and the support vector machine was used to establish the prediction model of canopy apparent photosynthetic rate.The experimental results indicated that the correlation coefficients of the photosynthesis prediction model in the seeding and flowering stages were 0.9420 and 0.9226,respectively,showing the high accuracy of the SVM model.

PSO-SVM applied to SWASV studies for accurate detection of Cd(II)based on disposable electrode

Square wave anodic stripping voltammetry(SWASV)is an effective method for the detection of Cd(II),but the presence of Pb(II)usually has some potential and negative interference on the SWASV detection of Cd(II).In this paper,a novel method was proposed to predict the concentration of Cd(II)in the presence of Pb(II)based on the combination of chemically modified electrode(CME),machine learning algorithms(MLA)and SWASV.A Bi film/ionic liquid/screen-printed electrode(Bi/IL/SPE)was prepared and used for the sensitive detection of trace Cd(II).The parameters affecting the stripping currents were investigated and optimized.The morphologies and electrochemical properties of the modified electrode were characterized by scanning electron microscopy(SEM)and SWASV.The measured SWASV spectrograms obtained at different concentrations were used to build the mathematical models for the prediction of Cd(II),which taking the combined effect of Cd(II)and Pb(II)into consideration on the SWASV detection of Cd(II),and to establish a nonlinear relationship between the stripping currents of Pb(II)and Cd(II)and the concentration of Cd(II).The proposed mathematical models rely on an improved particle swarm optimization-support vector machine(PSO-SVM)to assess the concentration of Cd(II)in the presence of Pb(II)in a wide range of concentrations.The experimental results suggest that this method is suitable to fulfill the goal of Cd(II)detection in the presence of Pb(II)(correlation coefficient,mean absolute error and root mean square error were 0.998,1.63 and 1.68,respectively).Finally,the proposed method was applied to predict the trace Cd(II)in soil samples with satisfactory results.

Optimal control algorithm of fertigation system in greenhouse based on EC model

Two new control algorithms based on MSP430 microcontroller unit(MCU)were developed to improve the performance of a fertigation system controlled by the electrical conductivity(EC)value of an irrigation nutrient solution in a greenhouse.The first algorithm is incremental proportional-integral-derivative(PID),and the second one is a two-stage combination algorithm(PID+fuzzy).With an improved multi-line mixing Venturi tube,several sets of experiments were conducted for a fertilizer absorption test under two conditions,namely,various suction lines and different EC target values settings.Under the first condition,with an EC target value of 2.0 mS/cm and opening of various suction pipes,the steady-state times are 186 s,172 s,134 s,and 122 s corresponding to the opening of one to four suction pipes,respectively,for PID+fuzzy control.The corresponding values are 220 s,196 s,158 s,and 148 s for incremental PID control.Under the second condition,four suction pipes are opened with different target EC values of 1.5 mS/cm,2.0 mS/cm,and 2.5 mS/cm,and the shortest response time and the minimum overshoot were obtained for PID+fuzzy control when the target EC value is 1.5 mS/cm,which are 96 s and 0.18 mS/cm,respectively.While the corresponding values are 112 s and 0.4 mS/cm,respectively for incremental PID control.The two control strategies can adjust the EC value to the target value for real-time control,but the combination control algorithm can be implemented more rapidly,accurately,and steadily with a small overshoot compared with incremental PID control.The combination algorithm(PID+fuzzy)control strategy also possesses better properties for automatic fertigation control in greenhouses than the incremental PID control strategy,the combination algorithm provides an optimal way of water and fertilizer management for crops in greenhouses which will contribute to water and fertilizer saving.

Measurement of soil electrical conductivity based on direct digital synthesizer(DDS)and digital oscilloscope

A soil electrical conductivity(EC)measurement system based on direct digital synthesizer(DDS)and digital oscilloscope was developed.The system took the“current-voltage four-electrode method”as the design principal and adopted a six-pin structure of the probe,two center pins to measure the soil EC in shallow layer,two outside pins to measure the soil EC in deep layer,and two middle pins for inputting the driving current.A signal generating circuit using DDS technology was adopted to generate sine signals,which was connected with the two middle pins.A digital oscilloscope was used to record and store the two soil output signals with noises in microseconds,which were from the two center pins and two outside pins,respectively.Then a digital bandpass filter was used to filter the soil output signals recorded by the digital oscilloscope.Compared with the traditional analog filter circuit,the digital filter could filter out the noises of all frequency except for the frequency of the excitation source.It could improve the effect of filtering and the accuracy of the soil EC measurement system.The DDS circuit could provide more stable sine signals with larger amplitudes.The use of digital oscilloscope enables us to analyze the soil output signals in microseconds and measure the soil EC more accurately.The new soil EC measurement system based on DDS and digital oscilloscope can provide a new effective tool for soil sensing in precision agriculture.

Sustainable energy management of solar greenhouses using open weather data on MACQU platform

Precision energy management is very important for sustainability development of solar greenhouses,since huge energy demand for agricultural production both in quantity and quality.A proactive energy management,according to the optimal energy utilization in a look-ahead period with weather prediction,is presented and tested in this research.A multi-input-multi-output linear model of the energy balance of solar greenhouses based on on-line identification system can simulate greenhouse behavior and allow for predictive control.The good time allocation of available solar energy can be achieved by intelligent use of controls,such as store/retrieve fans and ventilation windows,i.e.solar energy to warm up the air or to be stored in the storage elements(wall,soil,etc.)or to be exhausted to outside.The proactive energy management can select an optimal trajectory of air temperature for the forecasted weather period to minimize plants’thermal‘cost’defined by an‘expert’in terms of set-points for the specific crop.The selection of temperature trajectory is formulated as a generalized traveling salesman problem(GTSP)with precedence constraints and is solved by a genetic algorithm(GA)in this research.The simulation study showed good potential for energy saving and timely allocation to prevent excessive crop stress.The active control elements in addition to predefining and applying,within energy constraints,optimal climate in the greenhouse,it also reduces the energy deficit,i.e.the working hours of the‘heater’in the sustained freezing weather,as well as the ventilation hours,that is,more energy harvest in the warm days.This intelligent solar greenhouse management system is being migrated to the web for serving a‘customer base’in the Internet Plus era.The capacity,of the concrete ground CAUA system(CAUA is an abbreviations from both China Agricultural University and Agricultural University of Athens),to implement web‘updates’of criteria,open weather data and models,on which control actions are based,is what makes use of Cloud Data for closing the loop of an effective Internet of Things(IoT)system,based on MACQU(MAnagement and Control for QUality)technological platform.