We present BusTr, a machine-learned model for translating road traffic forecasts into predictions of bus delays, used by Google Maps to serve the majority of the world's public transit systems where no official real-time bus tracking is provided. We...
Object detection has been a focus of research in human-computer interaction. Skin area detection has been a key to different recognitions like face recognition, human motion detection, pornographic and nude image prediction, etc. Most of the research...
Uncertainty estimation is crucial for machine learning models to detect out-of-distribution (OOD) inputs. However, the conventional discriminative deep learning classifiers produce uncalibrated closed-set predictions for OOD data. A more robust class...
This paper explores using a deep learning Long Short-Term Memory (LSTM) model for accurate stock price prediction and its implications for portfolio design. Despite the efficient market hypothesis suggesting that predicting stock prices is impossible...
A Flask-based web app that displays blog posts, offers a name-based gender and age guessing game, and shows random numbers. Utilizes APIs like Genderize.io and Agify.io for name-based predictions. Blog data is sourced from a local JSON file. (⭐ 0)
ContactInfo" is a React app predicting age and gender from names using agify.io and genderize.io APIs. It features a simple interface for name input and showcases the predictions, emphasizing efficient API interaction and result caching. (⭐ 0)
Long-range correlations are essential across numerous machine learning tasks, especially for data embedded in Euclidean space, where the relative positions and orientations of distant components are often critical for accurate predictions. Self-atten...
The Five-hundred-meter Aperture Spherical radio Telescope (FAST) has started the Commensal Radio Astronomy FasT Survey (CRAFTS). In this paper, we use the technical parameters of FAST derived from commissioning observations to simulate the completene...
Motivation: Molecular signatures for predicting breast cancer prognosis could greatly improve care through personalization of treatment. Computational analyses of genome-wide expression datasets have identified such signatures, but these signatures l...
Predicting the number of citations of scholarly documents is an upcoming task in scholarly document processing. Besides the intrinsic merit of this information, it also has a wider use as an imperfect proxy for quality which has the advantage of bein...
The typical binding energy of heavy hadron spectroscopy makes the system accessible to perturbative calculations in terms of non-relativistic QCD. Within NRQCD the predictions of heavy quarkonium energy levels rely on the accurate description of the...