Machine Learning

Supplementary materials for manuscript: Self-absorption Correction in X-ray Fluorescence Computed Tomography with Deep Convolutional Neural Network, 


This repository includes the DDPG, MADDPG, HHCDA, and MAHHCDA based on the paper "AI-Based and Mobility-aware Energy Efficient Resource Allocation and Trajectory Design for NFV enabled Aerial Networks".


This dataset has information of 83 patients from India. This dataset contains patients’ clinical history, histopathological features, and mammogram. The distinctive aspect of this dataset lies in its collection of mammograms that have benign tumors and used in subclassification of benign tumors. 


The simulation code for the paper:

"AoI-Aware Resource Allocation for Platoon-Based C-V2X Networks via Multi-Agent Multi-Task Reinforcement Learning"


The overall architecture of the proposed MARL framework is shown in the figure.


Modified MADDPG: This algorithm trains two critics (different from legacy MADDPG) with the following functionalities:


The demand for technologies relying on the radio spectrum, such as mobile communications and IoT, has been growing exponentially. As a consequence, providing access to the radio spectrum is becoming increasingly more important. The ever-growing wireless traffic and the increasing scarcity of available spectrum warrants efficient management of the radio spectrum. At the same time, machine learning (ML) is becoming ubiquitous and has found applications in many fields for its ability to identify patterns and assist with decision-making processes.


The proposed dataset, termed PC-Urban (Urban Point Cloud), is captured with an Ouster LiDAR sensor with 64 channels. The sensor is installed on an SUV that drives through the downtown of Perth, Western Australia (WA), Australia. The dataset comprises over 4.3 billion points captured for 66K sensor frames. The labelled data is organized as registered and raw point cloud frames, where the former has a different number of registered consecutive frames. We provide 25 class labels in the dataset covering 23 million points and 5K instances.


This dataset supports researchers in the validation process of solutions such as Intrusion Detection Systems (IDS) based on artificial intelligence and machine learning techniques for the detection and categorization of threats in Cyber Physical Systems (CPS). To that aim, data have been acquired from a water distribution hardware-in-the-loop testbed which emulates water passage between nine tanks via solenoid-valves, pumps, pressure and flow sensors. The testbed is composed by a real partition which is virtually connected to a simulated one.



This data set contains 100,000 pcd files taken by LiDAR, a 3-D image sensor, of a vehicle orbiting an indoor field.

Data Acquisition

The indoor field was built as a 1/60 scale model of an intersection, where two vehicles kept moving along pre-fixed tracks independently of each other.

The size of the vehicles was 0.040 m  × 0.035 m × 0.240 m 

We captured the indoor field by two LiDAR sensor units, which was commercialized by Velodyne.


Human Activity Recognition (HAR) is the process of handling information from sensors and/or video capture devices under certain circumstances to correctly determine human activities. Nowadays, several simple and automatic HAR methods based on sensors and Artificial Intelligence platforms can be easily implemented.

In this challenge, participants are required to determine the nurse care daily activities by utilizing the accelerometer data collected from the smartphone, which is the cheapest and easy-to-implement way in real life.

Last Updated On: 
Wed, 06/30/2021 - 21:50
Citation Author(s): 
Sayeda Shamma Alia, Kohei Adachi, Paula Lago, Le Nhat Tan, Haru Kaneko, Sozo Inoue

The dataset consists of 751 videos, each containing the performance one of the handball actions out of 7 categories (passing, shooting, jump-shot, dribbling, running, crossing, defence). The videos were manually extracted from longer videos recorded in handball practice sessions.