Value Function Mechanism in WSNs-Based Mango Plantation Monitoring System

Mango fruit is one of the main fruit commodities that contributes to Taiwan’s income.The implementation of technology is an alternative to increasing the quality and quantity of mango plantation product productivity.In this study,a Wireless Sensor Networks(“WSNs”)-based intelligent mango plantation monitoring system will be developed that implements deep reinforcement learning(DRL)technology in carrying out prediction tasks based on three classifications:“optimal,”“sub-optimal,”or“not-optimal”conditions based on three parameters including humidity,temperature,and soil moisture.The key idea is how to provide a precise decision-making mechanism in the real-time monitoring system.A value function-based will be employed to perform DRL model called deep Q-network(DQN)which contributes in optimizing the future reward and performing the precise decision recommendation to the agent and system behavior.The WSNs experiment result indicates the system’s accuracy by capturing the real-time environment parameters is 98.39%.Meanwhile,the results of comparative accuracy model experiments of the proposed DQN,individual Q-learning,uniform coverage(UC),and NaÏe Bayes classifier(NBC)are 97.60%,95.30%,96.50%,and 92.30%,respectively.From the results of the comparative experiment,it can be seen that the proposed DQN used in the study has themost optimal accuracy.Testing with 22 test scenarios for“optimal,”“sub-optimal,”and“not-optimal”conditions was carried out to ensure the system runs well in the real-world data.The accuracy percentage which is generated from the real-world data reaches 95.45%.Fromthe resultsof the cost analysis,the systemcanprovide a low-cost systemcomparedtothe conventional system.

Speech Recognition via CTC-CNN Model

In the speech recognition system,the acoustic model is an important underlying model,and its accuracy directly affects the performance of the entire system.This paper introduces the construction and training process of the acoustic model in detail and studies the Connectionist temporal classification(CTC)algorithm,which plays an important role in the end-to-end framework,established a convolutional neural network(CNN)combined with an acoustic model of Connectionist temporal classification to improve the accuracy of speech recognition.This study uses a sound sensor,ReSpeakerMic Array v2.0.1,to convert the collected speech signals into text or corresponding speech signals to improve communication and reduce noise and hardware interference.The baseline acousticmodel in this study faces challenges such as long training time,high error rate,and a certain degree of overfitting.The model is trained through continuous design and improvement of the relevant parameters of the acousticmodel,and finally the performance is selected according to the evaluation index.Excellentmodel,which reduces the error rate to about 18%,thus improving the accuracy rate.Finally,comparative verificationwas carried out from the selection of acoustic feature parameters,the selection of modeling units,and the speaker’s speech rate,which further verified the excellent performance of the CTCCNN_5+BN+Residual model structure.In terms of experiments,to train and verify the CTC-CNN baseline acoustic model,this study uses THCHS-30 and ST-CMDS speech data sets as training data sets,and after 54 epochs of training,the word error rate of the acoustic model training set is 31%,the word error rate of the test set is stable at about 43%.This experiment also considers the surrounding environmental noise.Under the noise level of 80∼90 dB,the accuracy rate is 88.18%,which is the worst performance among all levels.In contrast,at 40–60 dB,the accuracy was as high as 97.33%due to less noise pollution.

An IoT-Based Aquaculture Monitoring System Using Firebase

Indonesia is a producer in the fisheries sector,with production reaching 14.8 million tons in 2022.The production potential of the fisheries sector can be optimally optimized through aquaculture management.One of the most important issues in aquaculture management is how to efficiently control the fish pond water conditions.IoT technology can be applied to support a fish pond aquaculture monitoring system,especially for catfish species(Siluriformes),in real-time and remotely.One of the technologies that can provide this convenience is the IoT.The problem of this study is how to integrate IoT devices with Firebase’s cloud data system to provide reliable and precise data,which makes it easy for fish cultivators to monitor fishpond conditions in real time and remotely.The IoT aquaculture fishpond monitoring use 3 parameters:(1)water temperature;(2)pHwater level;and(3)turbidity level of pond water.IoT devices use temperature sensors,pH sensors,and turbidity sensors,which are integrated with a microcontroller and Wi-Fi module.Data from sensor readings are sent to the Firebase cloud via theWi-Fi module so that it can be accessed in real time by end users with an Androidbased mobile app.The findings are(1)the IoT-based aquaculture monitoring system device has a low error rate in measuring temprature,pH,and turbidity with a percentage of 1.75%,1.94% and 9.78%,respectively.Overall,the total average error of the three components is 4.49%;(2)in cost analysis,IoT-based has a cost-effectiveness of 94.21% compared to labor costs.An IoT-based aquaculture monitoring system using Firebase can be effectively used as a technology for monitoring fish pond conditions in real-time and remotely for fish cultivators that contribute to providing an IoT-based aquaculture monitoring system that produces valid data,is precise,is easy to implement,and is a low-cost system.

Improving Speech Enhancement Framework via Deep Learning

Speech plays an extremely important role in social activities.Many individuals suffer from a“speech barrier,”which limits their communication with others.In this study,an improved speech recognitionmethod is proposed that addresses the needs of speech-impaired and deaf individuals.A basic improved connectionist temporal classification convolutional neural network(CTC-CNN)architecture acoustic model was constructed by combining a speech database with a deep neural network.Acoustic sensors were used to convert the collected voice signals into text or corresponding voice signals to improve communication.The method can be extended to modern artificial intelligence techniques,with multiple applications such as meeting minutes,medical reports,and verbatim records for cars,sales,etc.For experiments,a modified CTC-CNN was used to train an acoustic model,which showed better performance than the earlier common algorithms.Thus a CTC-CNN baseline acoustic model was constructed and optimized,which reduced the error rate to about 18%and improved the accuracy rate.

Creating Smart House via IoT and Intelligent Computation

This study mainly uses the concept of the Internet of Things(IoT)to establish a smart house with an indoor,comfortable,environmental,and real-time monitoring system.In the smart house,this investigation employed the temperature-and humidity-sensing module and the lightness module to monitor any con-dition for an intelligent-living house.The data of temperature,humidity,and lightness are transmitted wirelessly to the human-machine interface.The correlation of the weight of the extension theory is used to analyze the ideal and comfortable environment so that people in the indoor environment can feel better thermal comfort and lightness.In this study,improved particle swarm optimization(IPSO)is employed—an effective evolutionary method used to search the function extreme.It is simple and has a fast convergence.The convergence accuracy of this algorithm is not high at the beginning,and it can easily fall into the local extreme points.The effect of the inertia weight in mix extension theory and PSO becomes IPSO-Extension Neural Network(ENN),which was analyzed and found reliable.Motivated by the idea of power function,a new non-linear strategy for decreasing inertia weight(DIW)was proposed based on the existing linear DIW.Then,a novel hierarchical multi-sensor data fusion algorithm adopting this strategy was presented,and the weight factor of the data fusion was estimated.The distinctive feature of this algorithm is its capability of fusing data in a near-optimal manner when there is no available information about the reliability of the information sources,the degree of redundancy/complementarities of the information sources,and the structure of the hierarchy.It obtained effective information from the fusion data,successfully removed the noise disturbance,and achieved favorable results.

Intelligent Home Using Fuzzy Control Based on AIoT

The Internet of Things has grown rapidly in recent years,and the technologies related to it have been widely used in various fields.The idea of this paper is to build a set of Internet of Things systems in a smart home wireless network environment,with the purpose of providing people with a more comfortable,convenient,and safe life.In the sensing layer of the Internet of Things,we discuss the uses of common sensing technologies on the Internet and combine these with Arduino microprocessors to integrate temperature sensing modules,humidity sensing modules,gas sensing modules,and particulate matter 2.5(PM2.5)sensing modules.In the network layer,we discuss using the Wi-Fi wireless networking function composed of a home router and a wireless Wi-Fi chip Espressif system 8266(ESP8266)to transmit the collected home-sensing data to the ThingSpeak cloud database.Finally,in the application layer part,the system uses a mobile device with fuzzy calculation optimization software.The system is also connected remotely for home environment monitoring,so the home environment can be optimized anytime,anywhere.

Improving the Transmission Efficiency of a WSN with the IACO Algorithm

The goal of this study is to reduce the energy consumption of the sensing network and enhance the overall life cycle of the network.This study proposes a data fusion algorithm for wireless sensor networks based on improved ant colony optimization(IACO)to reduce the amount of data transmitted by wireless sensor networks(WSN).This study updates pheromones for multiple optimal routes to improve the global optimal route in search function.The algorithm proposed in this study can reduce node energy consumption,improve network load balancing and prolong network life cycle.Through data fusion,regression analysis model and information processing of each node,this study uses an improved ant colony algorithm to identify the transferals avoid superfluous energy waste caused by long-span network transferal,set the shortest route and transmit data to the central node.The algorithm proposed in this study is conducive to improving the life cycle and stable network,that is,the most suitable and effective way to improve the energy consumption rate of the sensing nodes.

Image Recognition Based on Deep Learning with Thermal Camera Sensing

As the COVID-19 epidemic spread across the globe,people around the world were advised or mandated to wear masks in public places to prevent its spreading further.In some cases,not wearing a mask could result in a fine.To monitor mask wearing,and to prevent the spread of future epidemics,this study proposes an image recognition system consisting of a camera,an infrared thermal array sensor,and a convolutional neural network trained in mask recognition.The infrared sensor monitors body temperature and displays the results in real-time on a liquid crystal display screen.The proposed system reduces the inefficiency of traditional object detection by providing training data according to the specific needs of the user and by applying You Only Look Once Version 4(YOLOv4)object detection technology,which experiments show has more efficient training parameters and a higher level of accuracy in object recognition.All datasets are uploaded to the cloud for storage using Google Colaboratory,saving human resources and achieving a high level of efficiency at a low cost.

Voice Guidance System for Color Recognition Based on IoT

We often need to identify the colors of such objects as buildings,clothing,photos,and traffic signs in everyday life.Some people cannot distinguish among such colors.This study proposes a method to help people,including colorblind people,identify colors.We establish a platform for color identification that is connected by the Internet of Things(IoT).The Espressif Systems 32(ESP32)single chip is connected to a Wi-Fi communication network to transmit data to the color identification platform.The system interface is displayed in the form of color code and color name display.The speech synthesis module Speech Synthesizer Node 6288(SYN6288)is used to broadcast color-related information.Since there are many color conversion technologies in modern times,or other color recognition methods are not applicable to the guide-blind function.Therefore,the authors use the method of reading out color-related information to directly enable colorblind people to conveniently identify the colors of objects.After experiments:the accuracy of various colors,the accuracy of environmental impact,the comparison of the original sensing experiment and the effect of adding interference light sources,the time required for color sensing to identify various colors,and the interference test results of any color light source,it is proved that the research mentioned in this research.The proposed method can not only improve the rate of recognition of the system in different environments,but can also accurately identify a variety of colors.The platform is integrated with the IoT to allow users to quickly monitor the displayed data.

RFID Positioning and Physiological Signals for Remote Medical Care

The safety of patients and the quality of medical care provided to them are vital for their wellbeing.This study establishes a set of RFID(Radio Fre-quency Identification)-based systems of patient care based on physiological sig-nals in the pursuit of a remote medical care system.The RFID-based positioning system allows medical staff to continuously observe the patient's health and location.The staff can thus respond to medical emergencies in time and appropriately care for the patient.When the COVID-19 pandemic broke out,the proposed system was used to provide timely information on the location and body temperature of patients who had been screened for the disease.The results of experiments and comparative analyses show that the proposed system is superior to competing systems in use.The use of remote monitoring technology makes user interface easier to provide high-quality medical services to remote areas with sparse populations,and enables better care of the elderly and patients with mobility issues.It can be found from the experiments of this research that the accuracy of the position sensor and the ability of package delivery are the best among the other related studies.The presentation of the graphical interface is also the most cordial among human-computer interaction and the operation is simple and clear.

Utilizing Blockchain Technology to Improve WSN Security for Sensor Data Transmission

This paper proposes a method for improving the data security of wireless sensor networks based on blockchain technology.Blockchain technology is applied to data transfer to build a highly secure wireless sensor network.In this network,the relay stations use microcontrollers and embedded devices,and the microcontrollers,such as Raspberry Pi and Arduino Yun,represents mobile databases.The proposed system uses microcontrollers to facilitate the connection of various sensor devices.By adopting blockchain encryption,the security of sensing data can be effectively improved.A blockchain is a concatenated transaction record that is protected by cryptography.Each section contains the encrypted hash of the previous section,the corresponding timestamp,and transaction data.The transaction data denote the sensing data of the wireless sensing network.The proposed system uses a hash value representation calculated by the Merkel-tree algorithm,which makes the transfer data of the system difficult to be tamped with.However,the proposed system can serve as a private cloud data center.In this study,the system visualizes the data uploaded by sensors and create relevant charts based on big data analysis.Since the webpage server of the proposed system is built on an embedded operating system,it is easy to model and visualize the corresponding graphics using Python or JavaScript programming language.Finally,this study creates an embedded system mobile database and web server,which can utilize JavaScript program language and Node.js runtime environment to apply blockchain technology to mobile databases.The proposed method is verified by the experiment using about 1600 data records.The results show that the possibility of data being changed is very small,and the probability of data being changed is almost zero.

Utilizing the Improved QPSO Algorithm to Build a WSN Monitoring System

This research uses the improved Quantum Particle Swarm Optimization(QPSO)algorithm to build an Internet of Things(IoT)life comfort monitoring system based on wireless sensing networks.The purpose is to improve the quality of intelligent life.The functions of the system include automatic basketball court lighting system,monitoring of infants’sleeping posture and accidental falls of the elderly,human thermal comfort measurement and other related life comfort services,etc.On the hardware system of the IoT,this research is based on the latest version of ZigBee 3.0,which uses optical sensors,3-axis accelerometers,and temperature/humidity sensors in the IoT perception layer.In the network transmission layer,the central network architecture is used for connection.In the application layer,we have designed a graphical interface for real-time values and information that can be read at any time and place using mobile devices.In this study,authors use the improved QPSO algorithm in the calculation part,so that the target can be effectively positioned outside the numerous surveillance data.This study uses various sensor data fusion technologies to make the IoT system becomes able to provide more extensive and even better services than ever before.In short,this research work has proven to be an effective way to reduce power consumption,improve medical quality and provide higher comfort for intelligent lift level.

A Sensor Network Web Platform Based on WoT Technology

This study proposes a Web platform,the Web of Things(WoT),whose Internet of Things(IoT)architecture is used to develop the technology behind a new standard Web platform.When a remote sensor passes data to a microcontroller for processing,the protocol is often not known.This study proposes a WoT platform that enables the use of a browser in a mobile device to control a remote hardware device.An optimized code is written using an artificial intelligencebased algorithm in a microcontroller.Digital data convergence technology is adopted to process the packets of different protocols and place them on the Web platform for access by other mobile devices.The platform has high efficiency and cross-platform advantages,with no limitation on the operating system.Message queueing telemetry transport(MQTT)technology is used to simplify the original HTTP protocol.Assume that the mobile device is a subscriber,i.e.,the controller,and a microcontroller that connects the sensing device is the publisher.The publishers and subscribers of MQTT need not know each other if they share a message broker.The intermediate agent role is much like a router.Publishers and subscribers do not need to interact,and publishers do not have to wait for subscriber confirmation to cause interactive permission be locked.Nor must publishers and subscribers be online at the same time,and they are free to choose when to get messages.The proposed WoT method is compared with the traditional IoT method regarding data transfer.The results show that the proposed method can save time in processing large amounts of data,as the traditional IoT method wastes time,especially in data format transfer.

Home Monitoring of Pets Based on AIoT

With technological and social development in recent decades,people have begun pursuing more comfortable lives that frequently feature household pets that are treated like members of the family.On average,one out of every three households has a pet.This has also led to the creation and growth of many businesses in the pet industry.A few companies have developed a system that allows busy office workers to remotely care for pets at home based on the Internet of Things and an intelligent adjustment function.As owners of two dogs,the authors of this study observed their pets’living habits and recorded environmental conditions that appear suitable for them.These data were then used to develop an automatic control system to care for pets.The observational data on the pets’habits and environment were written in a program in Arduino by using the ESP8266 Wi-Fi module.The module and booster module control is the switch and setting of various household appliances.According to the loop setting of the program,the system does not need to manually switch or adjust the electrical settings of the environment.Instead,the pet's living environment is assessed by using various sensors.The use of Arduino programs helps develop a system that can automatically adjust the environment to one that is most suitable for the pet's comfort.