Real-time demand prediction is a critical input for dynamic bus routing. While many researchers have developed numerous complex methods to predict short-term transit demand, the applications have been limited to short, stable time frames and a few stations. How these methods perform in highly dynamic environments has not been studied, nor has their performance been systematically compared. We built an open-source infrastructure with five common methodologies, including econometric and deep learning approaches, and assessed their performance under stable and highly dynamic conditions. We used a time series from smartcard data to predict demand for the following day for the BRT system in Bogota, Colombia. The dynamic conditions in the time series include a month-long protest and the COVID-19 pandemic. Both conditions triggered drastic shifts in demand. The results reveal that most tested models perform similarly in stable conditions, with MAAPE varying from 0.08 to 0.12. The benchmark demonstrated that all models performed significantly worse in both dynamic conditions compared to the stable conditions. In the month-long protest, the increased MAAPE ranged from 0.14 to 0.24. Similarly, during the COVID-19 pandemic, the increased MAAPE ranged from 0.12 to 0.82. Notably, in the COVID-19 pandemic condition, an LSTM model with adaptive training and a multi-output design outperformed other models, adapting faster to disruptions. The prediction error stabilized within approximately 1.5 months, whereas other models continued to exhibit higher error rates even a year after the start of the pandemic. The aim of this open-source codebase infrastructure is to lower the barrier for other researchers to replicate and reproduce models, facilitate a collective effort within the research community to improve the benchmarking process and accelerate the advancement of short-term ridership prediction models.

Using the below source code we will specify the optimizer as stochastic gradient descent and will mention the learning rate as 0.001. After that, we will compile the model with loss functions for both outputs. Note: We can mention different loss functions for different outputs. In the same way, we can also mention different metrics for different outputs. Using the below syntax we will train the model for 500 epochs.

It is frequent to encounter class imbalance when developing models for real-world applications. This occurs when there are substantially more instances associated with one class than with the other. For example, in a Credit Risk Modeling project, when looking at the status of loans in historical data, most of the loans being granted have probably been paid in full. If models susceptible to class imbalance are used, defaulted loans would probably not have much relevance in the training process, as the overall loss continues to decrease when the model focuses on the majority class. To make the model pay more attention to examples where the loan was defaulted, class weights can be used so that the prediction error is larger when an instance of the underrepresented class is incorrectly classified.

Image classification is used to solve several Computer Vision problems; right from medical diagnoses, to surveillance systems, on to monitoring agricultural farms. There are innumerable possibilities to explore using Image Classification. If you have completed the basic courses on Computer Vision, you are familiar with the tasks and routines involved in Image Classification tasks. Image Classification tasks follow a standard flow – where you pass an image to a deep learning model and it outcomes the class or the label of the object present. While learning Computer Vision, most often a project that would be equivalent to your first hello world project, will most likely be an image classifier. You attempt to solve something like the digit recognition on MNIST Digits dataset or maybe the Cats and Dog Classification problem.

If you're already familiar with deep learning, by this time, you got that this is a multi-output problem because we're trying to solve this mutiple tasks at the same time. As we're going to use keras for implementation, a multi-output model can be implemented through Functional API, and not sequential API. As per the data, we've 5 tasks at the hand, out of which face alignment is the main one. So, we're going to train the model for these 5 tasks together using a multi-output model. We will train the main task(face alignment) with different auxiliary tasks to evaluate the effectiveness of deep multi-task learning.