Machine Learning

Radio frequency fingerprint identification (RFFI) is an emerging device authentication technique, which exploits the hardware characteristics of the RF front-end as device identifiers. The receiver hardware impairments interfere with the feature extraction of transmitter impairments, but their effect and mitigation have not been comprehensively studied. In this paper, we propose a receiver-agnostic RFFI system by employing adversarial training to learn the receiver-independent features.


Nowadays, the high cost of customer acquisition makes telecom operators encounter the “ceiling”, and even fall into the dilemma of customer acquisition. As market saturation increases, telecom operators need to solve the problem of increasing subscriber stickiness and prolonging subscriber life cycle. Therefore, it is crucial to analyse and predict the churn of telecom users. The dataset is ”Telecom Operator Customer Dataset”. The dataset obtained from the official Kaggle competition website in this study, which comprised 21 fields.


This is a new dataset, including behavioral, biometric, and environmental data, obtained from 39 subjects each spending 1 week to 2 months in smart rooms in Tokyo, Japan. The approximate duration of the experiment is 3 years. This dataset includes personal data, such as the use of home appliances, heartbeat rate, sleep status, temperature, illumination, and meal data. Although there are many datasets that publish these data individually, datasets that publish them all at once, tied to individual IDs, are valuable.


Manual palpation of organs played a vital role in detecting abnormalities in open surgeries. However, surgeons
have lost this ability with the development of minimally invasive surgeries. This challenge led to the development of artificial sensors for palpating the patient's organs and tissue. The majority of research done is related to improving the measurement of tissue compliance by the development of versatile force sensors for surgical


In situations when the precise position of a machine is unknown, localization becomes crucial. It is crucial to identify and ascertain the machine's position. This research focuses on improving the position prediction accuracy over long-range networks using a unique machine learning-based technique. In order to increase the prediction accuracy of the reference point position on the data collected using the fingerprinting approach using LoRa technology, this study suggested an ML-based algorithm.


With the development of recommender systems (RS), several promising systems

have emerged, such as context-aware RS, multi-criteria RS, and group RS. However, the

education domain may not benefit from these developments due to missing information, such

as contexts and multiple criteria, in educational data sets. In this paper, we announce and

release an open data set for educational recommender systems. This data set includes not


Soil analysis is a fundamental practice in modern agriculture, essential for optimizing crop production while minimizing environmental impact. It encompasses the assessment of physical, chemical, and biological properties of soil, providing vital insights into soil health. Key parameters, including texture, pH, nutrient levels, organic matter content, and microbial activity, are assessed. This data guides informed decision-making for crop selection and resource management.


Data were collected through the Twitter API, focusing on specific vocabulary related to wildfires, hashtags commonly used during the Tubbs Fire, and terms and hashtags related to mental health, well-being, and physical symptoms associated with smoke and wildfire exposure. We focused exclusively on the period from October 8 to October 31, aligning precisely with the duration of the Tubbs Fire. The final dataset available for analysis consists of 90,759 tweets.


An experimental study was conducted on a high-voltage glass-type disc (LD-160) to investigate the effect of string arrangements on pollution and icing flashover characteristics. Two Artificial Neural Network (ANN) applications were developed to simulate and calculate the flashover voltage based on the experimental results. The test results showed that the inverted T-type arrangement can improve the pollution flashover voltage and increase the icing flashover voltage of insulator strings compared to the traditional arrangement of the I-string.


This data repository comprises three distinct datasets tailored for different predictive modeling tasks. The first dataset is a synthetic dataset designed to simulate multivariate time series patterns, incorporating both linear and non-linear dependencies among input and target features. The second dataset, the Beijing Air Quality PM2.5 dataset, consists of PM2.5 measurements alongside meteorological data like temperature, humidity, and wind speed, with the objective of predicting PM2.5 concentrations.