Wireless wearable devices enable convenient acquisition of photoplethysmograph signals. A limitation of continual measurement is the resource-constrained processing and limited battery capacity. To solve the transmission power consumption problem, we propose an information reduction method, AutoPPGEncoder. The AutoPPGEncoder is an autoencoder trained with conventional mean squared error (mse) loss and mse systolic peak amplitude loss. The scheduling of impact from two losses improves the raw signal reconstruction by preserving the systolic peak in the reconstructed signal. Our system reduces the amount of transmitted BLE data from the PPG data by a ratio of 1:7.07. In terms of signal quality, the AutoPPGEncoder performs better than the recent compression technique, deep compressive sensing network (DCSNET) compression in both percentage root-mean-square difference (PRD) and peak amplitude PRD on BIDMC, SensAI, and VitalDB datasets. The AutoPPGEncoder’s power consumption was verified on an NRF54L15-DK board, which reduced the total energy consumption by 0.4 mJ per segment. This demonstrated the capability of the AutoPPGEncoder in IoT applications with power efficiency and the quality of PPG signal transmission.

Unemployed individuals and recent graduates often lack the experience or skills necessary to effectively search and filter job positions on job search websites, hindering their ability to access job listings and requirements. To address this issue, a research process was conducted involving extracting job information from the top job search website in Thailand. The data was then prepared, transformed, and subjected to Matrix Factorization. The data was randomly split into 80% for training and 20% for testing, out of a total of 30,000 records. This data was used to test the performance of a recommendation system utilizing the Collaborative Filtering technique. The Learning Curve, which measures the efficiency of model learning through Training Loss and Validation Loss, showed a continuous decrease in value until it reached its lowest validation loss of 0.0442, indicating a well-fitted model. This research suggests that the model can be effectively used for predicting and creating a prototype of a job recommendation system that connects job opportunities via API to efficiently meet the needs of job seekers and recent graduates.