1
|
Lin YW, Lin YB, Chang TCY, Lu BX. An Edge Transfer Learning Approach for Calibrating Soil Electrical Conductivity Sensors. SENSORS (BASEL, SWITZERLAND) 2023; 23:8710. [PMID: 37960410 PMCID: PMC10647256 DOI: 10.3390/s23218710] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/27/2023] [Revised: 10/18/2023] [Accepted: 10/23/2023] [Indexed: 11/15/2023]
Abstract
Smart agriculture utilizes Internet of Things (IoT) technologies to enable low-cost electrical conductivity (EC) sensors to support farming intelligence. Due to aging and changes in weather and soil conditions, EC sensors are prone to long-term drift over years of operation. Therefore, regular recalibration is necessary to ensure data accuracy. In most existing solutions, an EC sensor is calibrated by using the standard sensor to build the calibration table. This paper proposes SensorTalk3, an ensemble approach of machine learning models including XGBOOST and Random Forest, which can be executed at an edge device (e.g., Raspberry Pi) without GPU acceleration. Our study indicates that the soil information (both temperature and moisture sensor data) plays an important role in SensorTalk3, which significantly outperforms the existing calibration approaches. The MAPE of SensorTalk3 can be as low as 1.738%, compared to the 7.792% error of the original sensor. Our study indicates that when the errors of uncalibrated moisture and temperature sensors are not larger than 8.3%, SensorTalk3 can accurately calibrate EC. SensorTalk3 can perform model training during data collection at the edge node. When all training data are collected, AI training is also finished at the edge node. Such an AI training approach has not been found in existing edge AI approaches. We also proposed the dual-sensor detection solution to determine when to conduct recalibration. The overhead of this solution is less than twice the optimal detection scenario (which cannot be achieved practically). If the two non-standard sensors are homogeneous and stable, then the optimal detection scenario can be approached. Conventional methods require training calibration AI models in the cloud. However, SensorTalk3 introduces a significant advancement by enabling on-site transfer learning in the edge node. Given the abundance of farming sensors deployed in the fields, performing local transfer learning using low-cost edge nodes proves to be a more cost-effective solution for farmers.
Collapse
Affiliation(s)
- Yun-Wei Lin
- College of Artificial Intelligence, National Yang Ming Chiao Tung University, Tainan 711, Taiwan;
| | - Yi-Bing Lin
- College of Artificial Intelligence, National Yang Ming Chiao Tung University, Tainan 711, Taiwan;
- College of Humanities and Sciences, China Medical University, Taichung 406, Taiwan
- Miin Wu School of Computing, National Cheng Kung University, Tainan 701, Taiwan
- College of Computer Science, National Yang Ming Chiao Tung University, Hsinchu 300, Taiwan
- Department of Computer Science and Information Engineering, Asia University, Taichung 413, Taiwan
- Research Center for Information Technology Innovation, Academia Sinica, Taipei 115, Taiwan
| | | | - Bo-Xun Lu
- College of Artificial Intelligence, National Yang Ming Chiao Tung University, Tainan 711, Taiwan;
| |
Collapse
|
2
|
Kiobia DO, Mwitta CJ, Fue KG, Schmidt JM, Riley DG, Rains GC. A Review of Successes and Impeding Challenges of IoT-Based Insect Pest Detection Systems for Estimating Agroecosystem Health and Productivity of Cotton. SENSORS (BASEL, SWITZERLAND) 2023; 23:4127. [PMID: 37112469 PMCID: PMC10146184 DOI: 10.3390/s23084127] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/23/2023] [Revised: 03/30/2023] [Accepted: 04/03/2023] [Indexed: 06/19/2023]
Abstract
Using artificial intelligence (AI) and the IoT (Internet of Things) is a primary focus of applied engineering research to improve agricultural efficiency. This review paper summarizes the engagement of artificial intelligence models and IoT techniques in detecting, classifying, and counting cotton insect pests and corresponding beneficial insects. The effectiveness and limitations of AI and IoT techniques in various cotton agricultural settings were comprehensively reviewed. This review indicates that insects can be detected with an accuracy of between 70 and 98% using camera/microphone sensors and enhanced deep learning algorithms. However, despite the numerous pests and beneficial insects, only a few species were targeted for detection and classification by AI and IoT systems. Not surprisingly, due to the challenges of identifying immature and predatory insects, few studies have designed systems to detect and characterize them. The location of the insects, sufficient data size, concentrated insects on the image, and similarity in species appearance are major obstacles when implementing AI. Similarly, IoT is constrained by a lack of effective field distance between sensors when targeting insects according to their estimated population size. Based on this study, the number of pest species monitored by AI and IoT technologies should be increased while improving the system's detection accuracy.
Collapse
Affiliation(s)
- Denis O. Kiobia
- College of Engineering, University of Georgia, Tifton, GA 31793, USA
| | | | - Kadeghe G. Fue
- Department of Agricultural Engineering, School of Engineering Science and Technology, Sokoine University of Agriculture, Morogoro P.O. Box 3003, Tanzania
| | - Jason M. Schmidt
- Department of Entomology, University of Georgia, Tifton, GA 31793, USA
| | - David G. Riley
- Department of Entomology, University of Georgia, Tifton, GA 31793, USA
| | - Glen C. Rains
- College of Engineering, University of Georgia, Tifton, GA 31793, USA
- Department of Entomology, University of Georgia, Tifton, GA 31793, USA
| |
Collapse
|
3
|
Alraho S, Zaman Q, Abd H, König A. Integrated Sensor Electronic Front-Ends with Self-X Capabilities. CHIPS 2022; 1:83-120. [DOI: 10.3390/chips1020008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/01/2023]
Abstract
The ongoing vivid advance in integration technologies is giving leverage both to computing systems as well as to sensors and sensor systems. Both conventional computing systems as well as innovative computing systems, e.g., following bio-inspiration from nervous systems or neural networks, require efficient interfacing to an increasing diversity of sensors under the constraints of metrology. The realization of sufficiently accurate, robust, and flexible analog front-ends (AFE) is decisive for the overall application system and quality and requires substantial design expertise both for cells in System-on-Chip (SoC) or chips in System-in-Package (SiP) realizations. Adding robustness and flexibility to sensory systems, e.g., for Industry 4.0., by self-X or self-* features, e.g., self-monitoring, -trimming, or -healing (AFEX) approaches the capabilities met in living beings and is pursued in our research. This paper summarizes on two chips, denoted as Universal-Sensor-Interface-with-self-X-properties (USIX) based on amplitude representation and reports on recently identified challenges and corresponding advanced solutions, e.g., on circuit assessment as well as observer robustness for classic amplitude-based AFE, and transition activities to spike domain representation spiking-analog-front-ends with self-X properties (SAFEX) based on adaptive spiking electronics as the next evolutionary step in AFE development. Key cells for AFEX and SAFEX have been designed in XFAB xh035 CMOS technology and have been subject to extrinsic optimization and/or adaptation. The submitted chip features 62,921 transistors, a total area of 10.89 mm2 (74% analog, 26% digital), and 66 bytes of the configuration memory. The prepared demonstrator will allow intrinsic optimization and/or adaptation for the developed technology agnostic concepts and chip instances. In future work, confirmed cells will be moved to complete versatile and robust AFEs, which can serve both for conventional as well as innovative computing systems, e.g., spiking neurocomputers, as well as to leading-edge technologies to serve in SOCs.
Collapse
|
4
|
Abstract
This review presents the state-of-the-art research on IoT systems for optimized greenhouse environments. The data were analyzed using descriptive and statistical methods to infer relationships between the Internet of Things (IoT), emerging technologies, precision agriculture, agriculture 4.0, and improvements in commercial farming. The discussion is situated in the broader context of IoT in mitigating the adverse effects of climate change and global warming in agriculture through the optimization of critical parameters such as temperature and humidity, intelligent data acquisition, rule-based control, and resolving the barriers to the commercial adoption of IoT systems in agriculture. The recent unexpected and severe weather events have contributed to low agricultural yields and losses; this is a challenge that can be resolved through technology-mediated precision agriculture. Advances in technology have over time contributed to the development of sensors for frost prevention, remote crop monitoring, fire hazard prevention, precise control of nutrients in soilless greenhouse cultivation, power autonomy through the use of solar energy, and intelligent feeding, shading, and lighting control to improve yields and reduce operational costs. However, particular challenges abound, including the limited uptake of smart technologies in commercial agriculture, price, and accuracy of the sensors. The barriers and challenges should help guide future Research & Development projects and commercial applications.
Collapse
|
5
|
Lin YB, Chou SL. SpecTalk: Conforming IoT Implementations to Sensor Specifications. SENSORS 2021; 21:s21165260. [PMID: 34450708 PMCID: PMC8397945 DOI: 10.3390/s21165260] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/12/2021] [Revised: 07/29/2021] [Accepted: 07/30/2021] [Indexed: 11/18/2022]
Abstract
Due to the fast evolution of Sensor and Internet of Things (IoT) technologies, several large-scale smart city applications have been commercially developed in recent years. In these developments, the contracts are often disputed in the acceptance due to the fact that the contract specification is not clear, resulting in a great deal of discussion of the gray area. Such disputes often occur in the acceptance processes of smart buildings, mainly because most intelligent building systems are expensive and the operations of the sub-systems are very complex. This paper proposes SpecTalk, a platform that automatically generates the code to conform IoT applications to the Taiwan Association of Information and Communication Standards (TAICS) specifications. SpecTalk generates a program to accommodate the application programming interface of the IoT devices under test (DUTs). Then, the devices can be tested by SpecTalk following the TAICS data formats. We describe three types of tests: self-test, mutual-test, and visual test. A self-test involves the sensors and the actuators of the same DUT. A mutual-test involves the sensors and the actuators of different DUTs. A visual-test uses a monitoring camera to investigate the actuators of multiple DUTs. We conducted these types of tests in commercially deployed applications of smart campus constructions. Our experiments in the tests proved that SpecTalk is feasible and can effectively conform IoT implementations to TACIS specifications. We also propose a simple analytic model to select the frequency of the control signals for the input patterns in a SpecTalk test. Our study indicates that it is appropriate to select the control signal frequency, such that the inter-arrival time between two control signals is larger than 10 times the activation delay of the DUT.
Collapse
Affiliation(s)
- Yi-Bing Lin
- College of Artificial Intelligence, National Yang Ming Chiao Tung University, Hsinchu City 30010, Taiwan
- College of Humanities and Sciences, China Medical University, Taichung 406, Taiwan
- School of Computing, National Cheng Kung University, Tainan 701, Taiwan
- Correspondence:
| | - Sheng-Lin Chou
- Information and Communication Research Laboratories, Industrial Technology Research Institute, Hsinchu City 30010, Taiwan;
| |
Collapse
|
6
|
Langone R, Cuzzocrea A, Skantzos N. Interpretable Anomaly Prediction: Predicting anomalous behavior in industry 4.0 settings via regularized logistic regression tools. DATA KNOWL ENG 2020. [DOI: 10.1016/j.datak.2020.101850] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/02/2023]
|
7
|
Crop Enhancement of Cucumber Plants under Heat Stress by Shungite Carbon. Int J Mol Sci 2020; 21:ijms21144858. [PMID: 32659984 PMCID: PMC7402313 DOI: 10.3390/ijms21144858] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2020] [Revised: 07/04/2020] [Accepted: 07/06/2020] [Indexed: 01/10/2023] Open
Abstract
Heat stress negatively impacts plant growth and yield. The effects of carbon materials on plants in response to abiotic stress and antioxidant activity are poorly understood. In this study, we propose a new method for improving heat tolerance in cucumber (Cucumis sativus L.) using a natural carbon material, shungite, which can be easily mixed into any soil. We analyzed the phenotype and physiological changes in cucumber plants maintained at 35 °C or 40 °C for 1 week. Our results show that shungite-treated cucumber plants had a healthier phenotype, exhibiting dark green leaves, compared to the plants in the control soil group. Furthermore, in the shungite-treated plants, the monodehydroascorbate content (a marker of oxidative damage) of the leaf was 34% lower than that in the control group. In addition, scavengers against reactive oxygen species, such as superoxide dismutase, catalase, and peroxidase were significantly upregulated. These results indicate that the successive pre-treatment of soil with a low-cost natural carbon material can improve the tolerance of cucumber plants to heat stress, as well as improve the corresponding antioxidant activity.
Collapse
|
8
|
Lin YW, Lin YB, Yen TH. SimTalk: Simulation of IoT Applications. SENSORS 2020; 20:s20092563. [PMID: 32365971 PMCID: PMC7248850 DOI: 10.3390/s20092563] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/07/2020] [Revised: 04/21/2020] [Accepted: 04/27/2020] [Indexed: 11/16/2022]
Abstract
The correct implementation and behavior of Internet of Things (IoT) applications are seldom investigated in the literature. This paper shows how the simulation mechanism can be integrated well into an IoT application development platform for correct implementation and behavior investigation. We use an IoT application development platform called IoTtalk as an example to describe how the simulation mechanism called SimTalk can be built into this IoT platform. We first elaborate on how to implement the simulator for an input IoT device (a sensor). Then we describe how an output IoT device (an actuator) can be simulated by an animated simulator. We use a smart farm application to show how the simulated sensors are used for correct implementation. We use applications including interactive art (skeleton art and water dance) and the pendulum physics experiment as examples to illustrate how IoT application behavior investigation can be achieved in SimTalk. As the main outcome of this paper, the SimTalk simulation codes can be directly reused for real IoT applications. Furthermore, SimTalk is integrated well with an IoT application verification tool in order to formally verify the IoT application configuration. Such features have not been found in any IoT simulators in the world.
Collapse
Affiliation(s)
- Yun-Wei Lin
- College of Artificial Intelligence, National Chiao Tung University (NCTU), Hsinchu 300, Taiwan;
| | - Yi-Bing Lin
- Department of Computer Science, National Chiao Tung University (NCTU), Hsinchu 300, Taiwan;
- Correspondence:
| | - Tai-Hsiang Yen
- Department of Computer Science, National Chiao Tung University (NCTU), Hsinchu 300, Taiwan;
| |
Collapse
|
9
|
Verification Method for Accumulative Event Relation of Message Passing Behavior with Process Tree for IoT Systems. INFORMATION 2020. [DOI: 10.3390/info11040232] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022] Open
Abstract
In this paper, we proposed a verification method for the message passing behavior of IoT systems by checking the accumulative event relation of process models. In an IoT system, it is hard to verify the behavior of message passing by only looking at the sequence of packet transmissions recorded in the system log. We proposed a method to extract event relations from the log and check for any minor deviations that exist in the system. Using process mining, we extracted the variation of a normal process model from the log. We checked for any deviation that is hard to be detected unless the model is accumulated and stacked over time. Message passing behavior can be verified by comparing the similarity of the process tree model, which represents the execution relation between each message passing event. As a result, we can detect minor deviations such as missing events and perturbed event order with occurrence probability as low as 3%.
Collapse
|