Grow-light smart monitoring system leveraging lightweight deep learning for plant disease classification

This work focuses on a novel lightweight machine learning approach to the task of plant disease classification,posing as a core component of a larger grow-light smart monitoring system.To the extent of our knowledge,this work is the first to implement lightweight convolutional neural network architectures leveraging down-scaled versions of inception blocks,residual connections,and dense residual connections applied without pre-training to the PlantVillage dataset.The novel contributions of this work include the proposal of a smart monitor-ing framework outline;responsible for detection and classification of ailments via the devised lightweight net-works as well as interfacing with LED grow-light fixtures to optimize environmental parameters and lighting control for the growth of plants in a greenhouse system.Lightweight adaptation of dense residual connections achieved the best balance of minimizing model parameters and maximizing performance metrics with accuracy,precision,recall,and F1-scores of 96.75%,97.62%,97.59%,and 97.58%respectively,while consisting of only 228,479 model parameters.These results are further compared against various full-scale state-of-the-art model architectures trained on the PlantVillage dataset,of which the proposed down-scaled lightweight models were capable of performing equally to,if not better than many large-scale counterparts with drastically less com-putational requirements.

Wearable Smart Sensor System for Medical Monitoring with an Assessment of the Level of Blood Loss and Pain Shock Because of Trauma or Injury

Blood loss in peacetime is mainly due to the normal menstrual cycle in women or diseases with surgical intervention. In wartime, blood loss in military personnel is a characteristic sign of a closed or open injury of the body during internal or external bleeding. Access to clinical care for wounded military personnel injured on the battlefield is limited and has long delays compared to patients in peacetime. Most of the deaths of wounded military personnel on the battlefield occur within the first hour after being wounded. The most common causes are delay in providing medical care, loss of time for diagnosis, delay in stabilization of pain shock and large blood loss. Some help in overcoming these problems is provided by the data in the individual capsule, which each soldier of the modern army possesses;however, data in an individual capsule is not sufficient to provide emergency medical care in field and hospital conditions. This paper considers a project for development of a smart real-time monitoring wearable system for blood loss and level of shock stress in wounded persons on the battlefield, which provides medical staff in field and hospital conditions with the necessary information to give timely medical care. Although the hospital will require additional information, the basic information about the victims will already be known before he enters the hospital. It is important to emphasize that the key term in this approach is monitoring. It is tracking, and not a one-time measurement of indicators, that is crucial in a valid definition of bleeding.

Smart Healthcare Activity Recognition Using Statistical Regression and Intelligent Learning

In this present time,Human Activity Recognition(HAR)has been of considerable aid in the case of health monitoring and recovery.The exploitation of machine learning with an intelligent agent in the area of health informatics gathered using HAR augments the decision-making quality and significance.Although many research works conducted on Smart Healthcare Monitoring,there remain a certain number of pitfalls such as time,overhead,and falsification involved during analysis.Therefore,this paper proposes a Statistical Partial Regression and Support Vector Intelligent Agent Learning(SPR-SVIAL)for Smart Healthcare Monitoring.At first,the Statistical Partial Regression Feature Extraction model is used for data preprocessing along with the dimensionality-reduced features extraction process.Here,the input dataset the continuous beat-to-beat heart data,triaxial accelerometer data,and psychological characteristics were acquired from IoT wearable devices.To attain highly accurate Smart Healthcare Monitoring with less time,Partial Least Square helps extract the dimensionality-reduced features.After that,with these resulting features,SVIAL is proposed for Smart Healthcare Monitoring with the help of Machine Learning and Intelligent Agents to minimize both analysis falsification and overhead.Experimental evaluation is carried out for factors such as time,overhead,and false positive rate accuracy concerning several instances.The quantitatively analyzed results indicate the better performance of our proposed SPR-SVIAL method when compared with two state-of-the-art methods.

Internet of Things Based Smart Irrigation System Using ESP WROOM32

Farming has been the most prominent and fundamental activity for generations.As the population has been mul-tiplying exponentially,the demand for agricultural yield is growing relentlessly.Such high demand in production through traditional farming methodologies often falls short in terms of efficiency due to the limitations of manual labour.In the era of digitization,smart agricultural solutions have been emerging through the windows of Internet of Things and Artificial Intelligence to improve resource management,optimize the process of farming and enhance the yield of crops,hence,ensuring sustainable growth of the increasing production.By implementing modern technologies in the field of farming we can enable telemetry through which farmers can remotely monitor and gather real time data on the desired parameters.It also gives accurate and precise measurements when compared to traditional measurement techniques.This research paper focuses on an IoT based approach for smart monitoring using ESP WROOM 32 microcontroller that helps farmers identify real-time parameters of temperature,moisture and humidity of their field.Real-time data on temperature,moisture,and humidity enables farmers to make informed decisions about irrigation and crop protection.Furthermore,the use of smart monitoring ensures accurate and precise measurements,surpassing the limitations of traditional techniques.

Subway rail transit monitoring by built-in sensor platform of smartphone

Smartphone,as a smart device with multiple built-in sensors,can be used for collecting information(e.g.,vibration and location).In this paper,we propose an approach for using the smartphone as a sensing platform to obtain real-time data on vehicle acceleration,velocity,and location through the development of the corresponding application software and thereby achieve the green concept based monitoring of the track condition during subway rail transit.Field tests are conducted to verify the accuracy of smartphones in terms of the obtained data’s standard deviation(SD),Sperling index(SI),and International Organization for Standardization(ISO)-2631 weighted acceleration index(WAI).A vehicle-positioning method,together with the coordinate alignment algorithm for a Global Positioning System(GPS)free tunnel environment,is proposed.Using the time-domain integration method,the relationship between the longitudinal acceleration of a vehicle and the subway location is established,and the distance between adjacent stations of the subway is calculated and compared with the actual values.The effectiveness of the method is verified,and it is confirmed that this approach can be used in the GPS-free subway tunnel environment.It is also found that using the proposed vehicle-positioning method,the integral error of displacement of a single subway section can be controlled to within 5%.This study can make full use of smartphones and offer a smart and eco-friendly approach for human life in the field of intelligent transportation systems.

Feasibility and Application Study of Optical Voltage/Current Sensors Using FBG

This paper concludes the case study work on the optical sensor, which is a new method for voltage and current measurement. Fiber Bragg gratings (FBG) have been developed and used for decades in the telecommunication industry. In recent years, FBG sensors have found wide applications in monitoring strain, temperature, voltage and current across all industries. As the process of constructing a robust smart grid, thousands of miles of optical-fibers have been deployed along the power transmission lines for the purpose of power production communication. This paper focuses on using the power optical fiber as voltage/current sensors instead of those copper wired traditional current transformers. By using piezoelectric layers, the optical sensor is able to transform voltage/current magnitude into optical signal, as well as transmit the signal through the optical fiber. The application of using optical fiber will significantly reduce the cost of deploying traditional current transformers all around the power grid. Moreover, the optical sensor is more stable, more accurate and faster, with such characteristics, the smart grid monitoring system could be much better. The application of combining the optical composite low-voltage cable (OPLC) and the optical current sensor in the distribution network for smart distribution monitoring has been analyzed.

Antimicrobial susceptibility of Gram-negative bacteria causing intra-abdominal infections in China： SMART China 2011

Background The Study for Monitoring Antimicrobial Resistance Trends program monitors the activity of antibiotics against aerobic and facultative Gram-negative bacilli （GNBs） from intra-abdominal infections （IAIs） in patients worldwide.Methods In 2011,1 929 aerobic and facultative GNBs from 21 hospitals in 16 cities in China were collected.All isolates were tested using a panel of 12 antimicrobial agents,and susceptibility was determined following the Clinical Laboratory Standards Institute guidelines.Results Among the Gram-negative pathogens causing IAIs,Escherichia coli （47.3％） was the most commonly isolated,followed by Klebsiella pneumoniae （17.2％）,Pseudomonas aeruginosa （10.1％）,and Acinetobacter baumannii （8.3％）.Enterobacteriaceae comprised 78.8％ （1521/1929） of the total isolates.Among the antimicrobial agents tested,ertapenem and imipenem were the most active agents against Enterobacteriaceae,with susceptibility rates of 95.1％ and 94.4％,followed by amikacin （93.9％） and piperacillin/tazobactam （87.7％）.Susceptibility rates of ceftriaxone,cefotaxime,ceftazidime,and cefepime against Enterobacteriaceae were 38.3％,38.3％,61.1％,and 50.8％,respectively.The leastactive agent against Enterobacteriaceae was ampicillin/sulbactam （25.9％）.The extended-spectrum β-lactamase （ESBL） rates among E.coli,K.pneumoniae,Klebsiella oxytoca,and Proteus mirabilis were 68.8％,38.1％,41.2％,and 57.7％,respectively.Conclusions Enterobacteriaceae were the major pathogens causing IAIs,and the most active agents against the study isolates （including those producing ESBLs） were ertapenem,imipenem,and amikacin.Including the carbapenems,most agents exhibited reduced susceptibility against ESBL-positive and multidrug-resistant isolates.