In this study, we compare the performance of the XGBoost model with a Support Vector Machine (SVM) model from the literature in predicting a given task. Performance metrics such as the coefficient of determination (R2), root mean squared error (RMSE), and mean absolute error (MAE) were utilized to evaluate and compare the models. The XGBoost model achieved an R² of 0.99, an RMSE of 2.54, and an MAE of 1.96, significantly outperforming the SVM model, which recorded an R² of 0.96 and an RMSE of 6.79. The scatter plot for the XGBoost model further illustrated its superior performance, showing a tight clustering of points around the ideal line (y = x), indicating high accuracy and low prediction errors. These findings suggest that the XGBoost model is highly effective for the given prediction task, likely due to its ability to capture complex patterns and interactions within the data.

<p><em>Calibration is an activity to determine the conventional correctness of the designation value of measuring instruments and measuring materials by comparing them with traceable measuring standards to national standards for units of measure and/or international ones. One example of a tool used for calibration is the Infant Warmer Calibrator. The purpose of this research is to produce a tool that can be used to calibrate and analyze temperature and humidity data on infrant warmers. This tool uses five LM35 type temperature sensors with Arduino as the main controller for this tool, and is also equipped with a DHT11 type humidity sensor, and is also equipped with an SD Card as storage. From the results of the study, different results were obtained with the largest error difference of 1.85% at a test point of 35°C and the smallest error presentation was 1.3% at a test point of 34°C and the tool was functioning properly.</em></p><p><em> </em></p><p><strong><em>Keywords: </em></strong><em>Kalibrator Infant Warmer, Temperature sensor, Humidity Sensor, SD Card.</em></p><p> </p><p class="Abstract" align="center"><strong>ABSTRAK</strong></p><p>Kalibrasi adalah kegiatan untuk menentukan kebenaran konvensional nilai penunjukkan alat ukur dan bahan ukur dengan cara membandingkan terhadap standar ukur yang mampu telusur (traceable) ke standar nasional untuk satuan ukuran dan/atau internasional. Salah satu contoh alat yang digunakan untuk kalibrasi adalah Kalibrator Infant Warmer. Tujuan penelitian ini adalah untuk menghasilkan alat yang dapat digunakan untuk melakukan kalibrasi serta melakukan analisis data suhu dan kelembapan pada <em>infrant warmer</em>. Alat ini menggunakan lima sensor suhu type LM35 dengan arduino sebagai pengotrol utama pada alat ini, dan juga dilengkapi dengan sensor kelembapan type DHT11, dan juga dilengkapi dengan SD Card sebagai penyimpanan. Dari hasil penelitian didapatkan hasil yang berbeda-beda dengan selisih kesalahan terbesar 1,85 % pada test point 35°C dan presentasi kesalahan terkecil yaitu 1,3% pada test point 34°C dan alat sudah berfungsi dengan baik.</p>

<em>Temperature is the most important parameter in monitoring Infant Warmer medical equipment. In this study, temperature monitoring was carried out on the Lullaby GE Infant Warmer using INCU based on Arduino Uno. The temperature setting used was 34 ° C, 35 ° C, 36 ° C and 37 ° C with each setting repeated 3 times. The temperature sensor used in the INCU analyzer for T1 to T4 is DS18B20, while the T5 uses a DHT22 temperature sensor. At the Infant Warmer temperature, a low error value was obtained for all temperature settings, namely a temperature of 34 ° C with an error of 0.02, a temperature of 35 ° C with an error of 0.03, a temperature of 36 ° C with an error of 0.004 and a temperature of 37 ° C with an error of 0. The INCU analyzer output low temperature is at T5, with temperature settings of 34 ° C, 35 ° C, 35 ° C and 37 ° C respectively 0.009, 0.07, 0.11 and 0.28. While the error value on T1 to T4 ranges from 0.37, namely at T3 for a temperature setting of 35 ° C to 0.84, namely at T3 for a setting of 37 ° C. It can be concluded that the INCU analyzer that has a high degree of accuracy is the T5 using the DHT22 temperature sensor.</em>

<p class="Abstract">Hypo-hyperthermia tool is a devive that can stabilize body temperature which decreases or increases temperature dramatically. The design of hypo-hyperthermia devices has been made using Arduino Uno. Functional tests have also been carried out on the hypo-hyperthermia tool to determine the level of success and eligibility. This tool works by utilizing the flow of water to provide the temperature needed by the patient in order to obtain a normal temperature, namely by increasing the temperature of the blanket when the patient has hypothermia and lowering the temperature of the blanket when the patient has hyperthermia. The design of this hypo-hyperthermia tool uses Arduino uno as a processor and DS18B20 sensor for temperature readings. Heaters are also used as water heaters, condensers as water coolers, and water pumps to drive the water cycle from the appliance to the blanket and back to the appliance. The temperature and mode settings will be displayed on the LCD screen. Function test results obtained by comparing the value of the temperature reading in skin mode with a digital thermometer that is obtained an error value of 0.3%. This temperature difference is affected by the room temperature and body temperature of the patient which can change at any time. It was also obtained by comparison of the temperature reading values in blanket mode with a digital thermometer that is obtained the largest error value of 6% at a setting value of 25 °C and the smallest error value of 0.3% at a setting value of 30 °C. This temperature difference is influenced by the temperature of the room at the time of measurement on the blanket is also influenced by the thickness of the hose installed on the blanket, so that the cold temperature in the water is not absorbed properly.</p>

<p><em>One form of physiotherapy is utilizing heat for recovery. Heat therapy can open blood vessels wider, thereby increasing blood flow and supply of oxygen and nutrients to reduce pain in joints, muscles, ligaments and injured tanks. To help health services in the field of physiotherapy the author modifies the therapeutic pillow with Arduino Uno and DS18B20 based as a temperature sensor, LCD as a temperature viewer and a timer and button that functions to choose how long it takes to do therapy. The design of therapeutic pillows is divided into two, namely hardware and software design, hardware design including power supply, a series of drivers and system scenarios. While the software design of this tool uses the Arduino and proteus applications as software. The result of the percentage error at the TP2 measurement is 0.02%. The measurement results on TP3 when the tool is off or off, then the circuit does not get a voltage while when the device is turned on or on the driver circuit gets a voltage of 1.4 Volt. After making the process of making, testing, testing tools and data collection, the author has succeeded in designing a heat therapy pillow using a temperature sensor and ARDUINO UNO based timer controller that can provide convenience when going to heat therapy because it is equipped with an automatically controlled temperature sensor and controller timer. by DS1820 temperature sensor. A therapeutic pillow based on Arduino with 10 minutes of therapy results in a </em><em>temperature of 41</em><em> °C.</em></p><div id="gtx-trans" style="position: absolute; left: 192px; top: 89.9861px;">  </div>