My background: I am new to ROS (Robot Operating System). I’d like to explore the use of Jetson and Raspberry pi in IoT applications and I am interesting in deep learning. Autonomous cars are one of the targets where deep learning is used. Building the autonomous car software can be…
Let’s explore the final project from our big data class as following. This year we have 7 projects. They look pretty good to me.
Feel free to clap or comment the ones you like.
Centralized Logging Filebeat+Logstash+ Kafka + Elastic + kibana by poon & asamaporn
I am wandering around and try to find a solution to develop face recognition project on Android. My goal is to run facial expression, facial age, gender and face recognition offline on Android (expected version: 7.1).
A big data class this semester (spring 2019) has passed.
Our focus is the platform and big data ecosystem they have practiced. At first, I thought I am going to have one VM and let all students use it. In this case, they will not be worried about the setting…
Since we are interested ontology data extraction for tourism data set, we try to find the way to insert data to the ontology automatically. We have many texts and find it difficult to read these texts and find relations and keywords to discover necessary information. Thus, we create an experimental…
From previous article https://medium.com/@chantrapornchai/arima-for-energy-consumption-data-part-ii-ac779b40586e, we consider using auto-regression using statsmodel with ARIMA. It is difficult to figure out the p,q,d even though we study ACF, PACF. One suggestion is to perform grid search on p,d,q as in https://machinelearningmastery.com/grid-search-arima-hyperparameters-with-python/. …
We explore various face recognition libraries and tools. The tools we explore are OpenCV, Dlib (OpenFace), deep learning tool.
From previous article, https://medium.com/@chantrapornchai/arima-for-energy-data-i-a7b466590af4. We analyze the stationary and decompose the signal.
Next, let’s consider how to use ARIMA for creating prediction model. Try to eliminate stationary using log difference, where ts is the data.
ts_log = np.log(ts)
ts_log_diff = ts_log — ts_log.shift()
We drop NAN value.
To select forecasting model, we break a time series down into systematic and unsystematic components (https://machinelearningmastery.com/decompose-time-series-data-trend-seasonality/)
Systematic components are the recurrence, consistent that we can construct the model for prediction. Non-systematic components are noises.
Generally, the components of the signal can be divided into: