Manual Control Research Articles

Automated oxygen administration versus manual control in acute cardiovascular care: a randomised controlled trial.

Oxygen therapy is commonly administered to patients with acute cardiovascular conditions during hospitalisation. Both hypoxaemia and hyperoxia can cause harm, making it essential to maintain oxygen saturation (SpO2) within a target range. Traditionally, oxygen administration is manually controlled by nursing staff, guided by intermittent pulse oximetry readings. This study aimed to compare standard manual oxygen administration with automated oxygen administration (AOA) using the O2matic device. In this randomised controlled trial, 60 patients admitted to a cardiac department with an acute cardiovascular condition requiring oxygen therapy were randomised to either standard care (manual oxygen administration) or AOA via the O2matic device. The primary outcome was the percentage of time spent within the desired SpO2 range (92%-96% or 94%-98%) over 24 hours. Patients had a mean age of 75.8±12.4 years, with an average SpO2 of 93%. Those in the AOA group (n=25) spent significantly more time within the target SpO2 range (median 87.0% vs 60.6%, p<0.001) compared with the standard care group (n=28). Time spent below the desired SpO2 range was significantly lower in the AOA group (7.9% vs 33.6%, p<0.001). No significant differences in time spent above the desired SpO2 range were observed between the two groups. AOA with the O2matic device is superior to standard manual control in maintaining SpO2 within the target range in patients hospitalised with acute cardiovascular conditions. The automated systems significantly reduce the time spent in hypoxaemia without increasing hyperoxia. NCT05452863.

Long-distance hand tractor controlled by android system in Wetland Field

Modernization of agricultural practices is essential to overcome challenges such as decreasing agricultural labor and decreasing agricultural land in Indonesia. This research examines the development and performance of a hand tractor that is controlled remotely via an Android-based system using the NodeMCU ESP8266 module and a WiFi network. This study focuses on the technical and operational performance of hand tractors in wetlands. Modifications were made to the tractor, by installing three DC motors to control the clutch and gas levers. Tests were carried out on the control system accuracy and response time to assess the system's suitability for field operations. The research results show that the Android system has 100% accuracy in executing all commands given, but the response time decreases as the distance between the Android device and the WiFi module increases, with an average delay reaching 6,8 seconds for a maximum 100 m distance. Field efficiency testing shows that a tractor with Android control has a work efficiency of 70.48% in the plowing process and 75.33% in the harrowing process, lower than with manual control which reaches an efficiency of more than 95%. Despite response delays and reduced efficiency, the system is an important step toward agricultural mechanization, especially in labor-intensive wetlands.

Device to Measure, Monitor and Control Variables for Agricultural Purposes

The measurement of meteorological variables is important for decision-making in the field. Accurate data can help farmers optimize their activities to improve food production. Traditional methods of monitoring variables can be expensive or complex for small-scale farmers to use. This indicates a need for low-cost and user-friendly devices. Currently, there is technology for developing these types of devices, which could be useful to automate processes based on variable monitoring and improve food production. Due to this, a device based on the Arduino Mega&amp;lt;SUP&amp;gt;TM&amp;lt;/SUP&amp;gt; board was developed to monitor air temperature, relative humidity, rain, and soil moisture. In addition, equipment was developed to be controlled based on a rain gauge. The device has a TFT touch screen for easy-user interaction and 4 menus for information display (summary, floor, date-time and manual equipment control). The program of the device required more lines of code (59.65%) to establish user-device interaction compared to its internal processes (18.66%) and variable declarations (21.68%). A container was 3D printed to house all the integrated circuits and the device was tested under both indoor (Jun-10, 2024 to July-17, 2024) and outdoor (Jul-22, 2024 to Aug-18, 2024) conditions. Under indoor conditions, a 3% difference was found in the temperature measurements taken under the same conditions (using DS18B20 and MLX90614 sensors). Under outdoor conditions it was found that the air temperature decreased by an average of 2.33°C when increasing the height from 8ft to 16ft and the relative humidity decreased by an average 3.48% when increasing the height from 8ft to 16ft. There was a 3.4% difference in total rain measured by the rain gauges. Finally, the developed device performed adequately during the two months of testing in both conditions, measuring variables and controlling equipment (the equipment went from waiting mode to rain harvesting mode 92 times).

Video game play impacts on biological regulation

The current study sought to explain the connection between biological control and video game usage. Specifically, the study examined video game usage at three levels to determine if there were differences in the ability to control biological responses such as heart rate variability to complete different biofeedback activities. A biological feedback software package, ALIVE, was used to measure “heart rate smoothness” and time task completion during a tutorial training, autopilot control video game car race, and manual control video game car race. Participants were instructed to use biological control techniques including breathing and heart rate “smoothness” to complete the biofeedback video games. Results found that there were significant differences in average heart rate smoothness in autopilot and manual car races and the amount of time it took for participants to complete the manual car race between three levels of video game usage. Implications for individuals’ biological control on behaviors such as relaxation and emotions were discussed.

Method for Determining the Conditions for Ensuring Stable Rearward Movement of a Semi-trailer Combination with Non-turning Semi-trailer Wheels

The efficiency of organising freight transport and using motor transport in a Smart City depends on a set of its properties, which in the process of operation determine its suitability for use in given operating conditions. Vehicles have different overall dimensions and designs, which determine their maneuverability and directional stability, their ability to make a curve-line movement in the city, as well as to move safely in reverse. Nowadays, tractor-trailer combinations with non-turning semi-trailer wheels are widely used for freight transport. Such a scheme of vehicle construction does not ensure its directional stability when reversing, which can lead to the folding of the tractor and semi-trailer and loss of mobility of the combination. In the absence of additional special systems, the driver controls the rearward movement of the road train using the steering wheel and rear-view mirrors, and the accuracy of delivery to the object depends on the level of the driver's training. The research of driver's reaction time spent on situation assessment, decision making, and realisation has been carried out. It has been revealed that with manual control, there are difficulties connected with training of drivers to estimate the parameters of movement and control of the road train, in particular, with the process of parking and its accurate delivery to the object. With the help of the developed mathematical model of the rearward movement of the road train and the proposed new turn control law, the research of maneuvering of the road train during its delivery to the object has been carried out and the results confirming the possibilities of building an automated system allowing to reduce the influence of the human factor on the parking process, as well as to reduce the time required to perform the maneuver have been obtained. The conducted analysis of system stability with the help of Routh–Hurwitz criterion has determined the conditions of providing stability of the system moving in reverse. The method of controlling the backward movement of the road train and the design of the device realising it has been developed. The results of simulation modeling allowed us to find the necessary values for the control law for the movement of road trains of different lengths, as well as the preferred variants of the initial positions of the road train for the realisation of its precise delivery to the object.

Early-stage Testing of Thermal Power Dispatch Simulator for Subjective Mental Workload and Evolution Time

The excess thermal energy produced by nuclear power plants (NPPs) during low electricity demands can be utilized in industrial processes, such as hydrogen production, through a thermal power dispatch (TPD) system. Initial testing of the first iteration of a single-train TPD design with a manual control mode at the Idaho National Lab (INL) revealed a high operator workload and degraded control capability. The current study evaluated the impact of an enhanced dual-train TPD design on operators’ subjective mental workload and evolution task-time while completing two operating scenarios in manual and automatic control modes. The results showed no statistically significant difference between participants’ mental workload using both control modes. Evolution time in automatic control mode took a shorter time than in manual control, with participants completing all evolutions in less than the 10-min set as the design specification limit. The shorter evolution time is discussed within the context of plant safety and operational efficiency.

Intelligent Verification Tool for Surgical Information of Ophthalmic Patients-A Study Based on Artificial Intelligence Technology.

With the development of day surgery, the characteristics of "short, frequent and fast" ophthalmic surgery are becoming more prominent. However, nurses are not efficient in verifying patients' surgical information, and problems such as patient privacy leakage are becoming more prominent. To improve the situation, we developed a new augmented reality (AR)-based tool for visual recognition and artificial intelligent (AI) interpretation of the pattern and location of patient surgical skin markings for the verification of the correct surgical site and procedure. The tool can also display a variety of other verbally requested patient information. The purpose of this proposal is to evaluate its feasibility of use by surgical nurses in a real clinical setting. We developed a tool with image recognition technologies to interpretation patient surgical skin markings and match the information obtained with the patients surgical records, thus, verify the patient's surgical information. Verification includes the proper surgical site and type of procedure to be performed. Nurses can interact with the device through its speech recognition capabilities and the device provides them with a variety of other requested patient information via a heads-up display. Three hundred patients in an outpatient ophthalmology clinic were divided into an AR intelligent verification experimental group and a manual verification control group. The accuracy of information verification, work time consumption, and economic cost data were compared between the 2 groups to evaluate the effectiveness of the AR Surgical Information Intelligent Verification Tool in clinical patient surgical information verification. There was no statistically difference in the correct rates of patient surgical information review between the experimental group (95.33%) and the control group (98.67%) (χ2 = 2.934, P = 0.087). The median time for information verification was 10.00 (10.00, 11.00) seconds in the experimental group and 21.00 (20.00, 24.00) seconds in the control group, a statistically difference (Z = 0.000, P < 0.001). The experimental group saved 11 seconds per patient per review compared with the control group. Considering 10,531 surgeries in 2023, printing 1 page of surgical information per 9 patients and requiring 4 copies, 4680 pages of printing paper could be saved. The AR Surgical Information Intelligent Verification Tool has advantages in assisting medical staff in patient surgical information verification, improving nursing efficiency, preventing surgical mark errors or nonstandardization, protecting patient privacy, and saving costs. It has certain research and application value in the scenario of patient surgical information verification in ophthalmic day ward.

Validating effectiveness of crown-of-thorns starfish control thresholds to limit coral loss throughout the Great Barrier Reef

AbstractPopulation irruptions of the Pacific crown-of-thorns starfish (CoTS, Acanthaster cf. solaris) are a key source of coral loss on Australia’s Great Barrier Reef (GBR). CoTS management currently involves their manual control (culling) to threshold densities below which net coral decline theoretically ceases based on analysis of a validated population dynamics model. Spatial variability in coral growth and community composition, and their predicted changes under continuing global warming, necessitate further consideration of current coral representation in CoTS models. Here, we consider the sensitivity of equilibrium coral-CoTS thresholds to coral growth rates and consider how the demographic composition of CoTS at a site may relate to culling thresholds. We found thresholds should be location-specific if the objective of CoTS control is coral recovery, but location-specific thresholds may not be needed if the objective is to limit coral cover loss based on coral growth and CoTS demography. The consequence of using a higher CPUE threshold than the analytical equilibrium coral-CoTS thresholds in terms of coral cover loss is suggested to be limited at coral cover &lt; 40%, and varying control thresholds thereof may make little difference. Introducing a 0.06 CoTS.min−1 threshold for 40–60% coral cover may reduce coral loss at ~ 40% where it is likely greatest. With regional GBR coral cover averaging &lt; 40%, this study validates the 0.04–0.08 CoTS.min−1 tiered threshold system for CoTS control and suggests methods developed from localised studies can be more broadly applicable and well-defined objectives (e.g. avoiding coral cover decline at a site) can help guide what thresholds are used and the sensitivity around these.

A graphics-based digital twin (GBDT) framework for accurate UAV localization in GPS-denied environments

Autonomous navigation of Unmanned Aerial Vehicles (UAVs) is crucial for effective assessment of large-scale civil infrastructure, as manual UAV control is time consuming and prone to mishaps. Autonomous navigation outdoors typically employs GPS signals to enable accurate localization and reduce long-term drifts. However, in many civil engineering applications, GPS signals are either poor or unavailable due to interference and/or multi-path effects. Current approaches for UAV localization in GPS-denied environments, track geometric features such as corners; however, these natural features can be misrepresented due to the presence of occlusions and/or image processing errors, resulting in significant localization errors that can grow with time. AprilTags can reduce localization errors, but installation on large-scale civil infrastructure can be challenging. Therefore, this paper proposes a framework that leverages the wealth of visual and geometric information encoded in a Graphics-Based Digital Twin (GBDT) of a target infrastructure to provide accurate localization of a UAV. The GBDT is comprised of a computer graphics model that faithfully represents a target structure’s geometry, structural features, and visual textures. The visual details of the GBDT are exploited to design an object recognition algorithm that detects GBDTtags, which are distinctive objects (or a collection of components) on the target structure in advance; GBDTtags provide functionality similar to AprilTags. When the camera attached to a UAV detects one or more GBDTtags, the vertices of the GBDTtags are mapped from the image plane into the GBDT coordinate system, allowing for the UAV to be localized. The framework, termed herein as GBDTpose, is first validated numerically using Blender, Gazebo, and Mavros software-in-the-loop (SITL). Subsequently, field validation is carried out using the Kavita and Lalit Bahl Smart Bridge at the University of Illinois Urbana-Champaign (UIUC). Results show that localization in GPS-denied environments can be achieved with 5-50 cm accuracy without the need for physical markers being placed on the structure.

Effects of Automation Exposure and Non-Driving Related Tasks on Manual Driving Performance after Takeover of Manual Control

Prolonged exposure to an automated driving system (ADS) can lead drivers to acclimate to the ADS in maladaptive ways. For example, exposure to a conditional ADS that maintained a time headway of 0.3 s resulted in drivers adopting smaller time headways postautomation, which is attributed to behavioral adaptation. The current study investigated whether drivers adapt to an ADS’ performance over time and if this adaptation differs based on the duration of automation exposure (15 or 25 min) and the task performed during the automation (NDRT or driving-related task). A greater exposure to the automation did not lead drivers to adopt smaller time headways. Surprisingly, drivers who provided a higher evaluation of the automation adopted smaller time headways post-automation than drivers who provided a lower evaluation. Future research should explore the relationship between trust in ADS and driving behavior to guide the development of safer ADSs.

Point of Interest Recognition and Tracking in Aerial Video during Live Cycling Broadcasts

Road cycling races, such as the Tour de France, captivate millions of viewers globally, combining competitive sportsmanship with the promotion of regional landmarks. Traditionally, points of interest (POIs) are highlighted during broadcasts using manually created static overlays, a process that is both outdated and labor-intensive. This paper presents a novel, fully automated methodology for detecting and tracking POIs in live helicopter video streams, aiming to streamline the visualization workflow and enhance viewer engagement. Our approach integrates a saliency and Segment Anything-based technique to propose potential POI regions, which are then recognized using a keypoint matching method that requires only a few reference images. This system supports both automatic and semi-automatic operations, allowing video editors to intervene when necessary, thereby balancing automation with manual control. The proposed pipeline demonstrated high effectiveness, achieving over 75% precision and recall in POI detection, and offers two tracking solutions: a traditional MedianFlow tracker and an advanced SAM 2 tracker. While the former provides speed and simplicity, the latter delivers superior segmentation tracking, albeit with higher computational demands. Our findings suggest that this methodology significantly reduces manual workload and opens new possibilities for interactive visualizations, enhancing the live viewing experience of cycling races.

Dynamics and experimental study of a novel proportional directional valve with displacement feedback groove controlled by high-speed switching valves

The intelligence of hydraulic roof support is an important guarantee for unmanned fully mechanized coal mining face. The water-based medium proportional directional valve is the main factor that restricts the intelligent realization of support system. The support control valve needs to meet the 2/3 (two-position three-way) structure, taking into account both manual and electro-hydraulic control functions. The current water-based proportional valve does not satisfy the structural or functional demands of the support system. In this paper, a novel 2/3 water-based proportional directional valve is presented based on the displacement-flow feedback principle, which has two control modes: manual on-off control and electro-hydraulic proportional control. The proportional valve comprises two main valve spools and two pilot valves. The pilot valve is composed of a 2/3 on-off valve with manual operation capability and a high-speed switching valve group controlled by PWM (Pulse Width Modulation). The mathematical model of the proportional valve is established, and the experimental system is built to verify the characteristics of proportional valve. The proportional valve can meet the special functional requirements of the support. In the proportional control mode, the adjustment of spool displacement is regulated through the modulation of PWM duty ratio, resulting in effective control performance of the proportional valve. Furthermore, the discontinuous flow of the high-speed switching valve causes the pressure fluctuation of the pilot hydraulic bridge. Increasing the carrier frequency of PWM can reduce the amplitude of control chamber pressure and spool displacement fluctuation. The findings of the study can offer valuable insights for the continued advancement and enhancement of water-based proportional valves used in hydraulic roof support systems.

Flight Arrival Scheduling via Large Language Model

The flight arrival scheduling problem is one of the critical tasks in air traffic operations, aiming to ensure that the flight arrive in the correct sequence safely. Existing methods primarily focus on the terminal area and often overlook the presence of training flight at the airport. Due to the limited generalization of traditional methods and varying control practices at different airports, training flight at airports still rely on manual control for arrival sorting. To effectively address these issues, we propose a novel method for slot allocation that leverages the strong reasoning capabilities and generalization potential of large language models (LLMs). Our method conceptualizes the dynamic scheduling problem for training flight as a language modeling problem, a perspective not previously explored. Specifically, we represent the allocator’s inputs and outputs as language tokens, utilizing LLMs to generate conflict-free results based on a language description of requested landing information and assigned training flight information. Additionally, we employ a reset strategy to create a small dataset for scenario-specific samples, enabling LLMs to quickly learn allocation schemes from the dataset. We demonstrated the capability of LLMs in addressing time conflicts by evaluating metrics such as answer accuracy, conflict rate, and total delay time (without the wrong answer). These findings underscore the feasibility of employing LLMs in the field of air traffic control.

A human visual attention analysis model for remote interaction interface of unmanned agricultural vehicles

When unmanned agricultural vehicles (UAVs) encounter unexpected failures or incidents during autonomous operations, a highly efficient remote human–machine interaction (HMI) interface is needed to assist in the manual joint control process. The highly complex cognitive mechanisms and visual characteristics of humans make it difficult to design efficient human–machine interfaces. Therefore, a human visual attention analysis model was proposed based on fully convolutional networks for the remote interaction interface of unmanned agricultural vehicles. First, visual attention experimental software combined with gaze-contingent real-time simulation methods was developed to build the dataset. Subsequently, the human visual attention analysis model (HVAAM) is constructed, and the corresponding training strategy is proposed, which is trained on the ILSVRC2012 standard and self-constructed datasets. The accuracy of the HVAAM analysis on the test dataset was validated. Ultimately, a human–machine interaction test of random failure warning for remote monitoring interface of unmanned plowing operation is performed with a self-developed unmanned electric tractor as the carrier. In the test dataset, the average analysis accuracy of HVAAM was 79.2 %, and the proposed training strategy led to a 20.7 % improvement in the model accuracy. In the unmanned electric tractor human–machine interaction test, HVAAM achieved 77.9 % accuracy in the visual attention analysis of the monitoring interface. This study can effectively facilitate the analysis, design, and optimization of remote monitoring interfaces for unmanned agricultural vehicles.

Use of a hand-worn accelerometer to measure hand differences in Grooved Pegboard Test

Research on laterality, which pertains to the preference for using one hand over the other in daily activities, has recently been a growing topic of investigation. Studies demonstrate that performance differences between the right and left hands arise from distinct strategies in utilizing information for movement execution. To conduct a more comprehensive analysis of these differences, we aimed to investigate various measures using a wrist accelerometer during the execution of a traditional tool to assess manual performance. The proposed hypothesis suggested that tasks performed with the right hand would exhibit shorter movement times due to more efficient real-time information processing. In contrast, tasks performed with the left hand would show shorter reaction times due to movement planning proficiency. Furthermore, we hypothesized that increased task complexity would make these differences more pronounced. The study revealed that, in the less complex task, the right hand outperformed the left hand in execution speed, whereas the left hand demonstrated faster reaction times in the more complex task. The task complexity highlighted the differences, emphasizing the impact of task demands on hand specialization. Using an accelerometer provided valuable insights, indicating potential avenues for refining assessment tools and analyzing manual control. Keywords: motor control, hemispheric specialization, laterality, hand function, dexterity.

CCTV image‐based classification of blocked trash screens

AbstractThis study introduces image‐based classification techniques to identify whether trash screens in urban rivers are blocked. The study obtained 755 images from a CCTV camera surveying a trash screen located on an urban river at Tongwynlais in Cardiff. Manual quality control reduced the dataset to 577 images, labelled as either blocked (80%) or unblocked (20%). The performance of a logistic regression for classification of images was investigated using three different subsets of the labelled images: (1) the original dataset, (2) a balanced but under‐sampled dataset with equal number of blocked and unblocked images, and (3) an augmented dataset with an equal number of blocked and unblocked images using Gaussian noise augmentation to increase the number of unblocked images. Results show that our data‐augmentation method enhanced model accuracy by 8%, successfully classifying images as blocked or unblocked with an accuracy of 88%; by overcoming the bias in the dataset these results also highlight potential solutions to overcome the challenges of operating this methodology across a network of cameras. This enables authorities in both data rich and data scarce regions the ability to take advantage of machine learning to open up the next generation of a distributed, data‐driven flood warning systems, protecting people, infrastructure and the environment.

Sistem Otomatisasi Pemberian Pakan secara Terjadwal untuk Pembibitan Ikan Lele di Fardu Farm Pekanbaru menggunakan PLC dan IoT

&lt;p&gt;&lt;strong&gt;With the increasing global population growth, the demand for fishery products, including catfish, continues to rise. Catfish seed production plays a crucial role in the fisheries production chain, as this stage ensures the availability of high-quality fish seeds. However, fish farmers still face challenges in increasing aquaculture production, especially regarding inefficient manual feeding practices. This research aims to develop an automated catfish feeding system on a schedule at Fardu Farm using a combination of Programmable Logic Controller (PLC) and Internet of Things (IoT) technologies. In this study, the researchers design and implement an automation system that enables scheduled feeding in catfish seedlings. The use of Outseal PLC connected to IoT allows for precise and efficient feeding control. This research conducts testing to verify the system's performance, including measuring the weight of the feed dispensed and testing feeding over specific time periods. The results of the study indicate that this automation system successfully provides timely feeding according to the established schedule. Additionally, manual control using the Blynk platform also yields good responsiveness. Thus, the developed system can enhance efficiency in feeding catfish seedlings at Fardu Farm.&lt;/strong&gt;&lt;/p&gt;&lt;p&gt;&lt;strong&gt;&lt;em&gt;Keywords&lt;/em&gt;&lt;/strong&gt; - &lt;em&gt;Automation, Feeding, Catfish Breeding, PLC, IoT.&lt;/em&gt;&lt;/p&gt;

Stability Analysis Of Two-Position Control System In Interacting Tanks Using Describing Function Method

In a water storage unit consisting of 3 interacting tanks, in its operation there will be problems if manual control is used, because if manual control is not optimal, then when filling water in the three tanks it will cause water overflow, which results in a lot of water being wasted. Two-position control, or "on-off," is a control system that is suitable for use in regulating the water level in the storage unit tank. In a two-position control system, if the frequency of water up and down (Limit Cycle) is large, it will cause an increase in the number of "switching" and "on-off" operations of the switch and solenoid valve per minute, so that the system becomes unstable and will shorten the life of the component. The Describing Function (DF) method is an analysis method that can determine the Limit Cycle frequency based on the width of the water up and down range (hysteresis) of the two-position control system, with the aim of determining the hysteresis parameters that cause the system to be stable.

Test Stand for Microjet Engine Prototypes

To investigate the functionality and performance of a prototype microjet engine, we constructed a versatile test stand tailored to the specifications of a 400 N prototype. This test stand facilitated a comprehensive study by enabling real-time recording of 45 essential parameters for analysis, encompassing temperatures, pressures, speed, fuel flow, thrust, vibration, and various other monitored metrics. All parameters and control elements were seamlessly integrated via a data acquisition and control system, utilizing a compactDAQ (Data Acquisition) system from National Instruments and a custom Virtual Instrument programmed with graphical language. The test stand offers both manual and automated operation modes, with the flexibility for hybrid operation. For instance, following the idle regime, manual control using a potentiometer can seamlessly transition from automated control via a proportional control (P control) mechanism. Before the experimental campaign, rigorous verification and validation tests were conducted to ensure the reliability and accuracy of the setup. The experimental campaign comprised a series of manual tests focusing on the fuel system and automated tests covering starting, idle, working, and stopping regimes. This structured approach allowed for a comprehensive evaluation across different operational scenarios, providing insights into the engine’s behavior and performance under varying conditions.

Implementation of Sugeno Fuzzy Logic Method as an Automatic Humidity and Moisture Control System in Terrarium

A terrarium is a mini ecosystem that requires precise humidity control to ensure plant growth and the survival of animals within it. However, manual humidity control is difficult to implement consistently, especially if the external environment changes. This problem can be overcome by implementing an automatic system based on Sugeno fuzzy logic. This research aims to design and implement an automatic system that is able to control terrarium humidity dynamically using a fuzzy logic approach. This system is designed using humidity sensor data as input which is then processed through Sugeno fuzzy logic to determine appropriate control actions. The method used involves modeling input humidity and temperature sensors, determining fuzzy rules, and defuzzification using the Sugeno method to regulate the automatic irrigation system in the terrarium. Tests were conducted under several different environmental conditions to measure the system's response to changes in humidity and temperature. The research results show that the system is able to maintain terrarium humidity within optimal limits with a low error rate. The system is able to adjust control actions in real-time, produce consistent calculations, and provide humidity stability despite external changes.