DeepLearning_Anomalies_Detection_with_Bluetooth_Sensor_Data

Final Year Project. Constructing models to create offline anomalies detection using Travel Time Data collected from Bluetooth sensors along the route.

The Bluetooth sensor Data is collected from Coronation Drive and Milton Road Corridors located in Bribane in 2017 and early 2018, which shown in the link below: https://www.google.com/maps/@-27.483276,152.9775122,14z/data=!3m1!4b1!4m2!6m1!1s1UYOOSCqlAaE-H2yjm_OhaoaDLF1qKgpo

The dataset details are as follow:

Column 0: id

Column 1: mac_id

Column 2: node_id

Column 3: date

Column 4: time

Column 5: duration

Models used in this project are LSTM Autoencoder and 1D-Convolution NN Autoencoder.

As the dataset has no label about when and where the anomalies occured, outliers at different time intervals labelled as anomalies to test out the performance of the model. The purpose of this project is to test out the capability of Neural Network to capture the anomalies of route by bluetooth sensor data and further looks for a optimal model approach to do so. Further development may be real-time anomalies detection.

DeepLearning Anomalies Detection with Bluetooth Sensor Data

Related tags

Overview

DeepLearning_Anomalies_Detection_with_Bluetooth_Sensor_Data

Owner

An unsupervised learning framework for depth and ego-motion estimation from monocular videos

Official PyTorch Implementation of "AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting".

Video Instance Segmentation using Inter-Frame Communication Transformers (NeurIPS 2021)

PyTorch implementation of PP-LCNet

Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network.

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

Official PyTorch implementation of "Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics".

Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images

🔅 Shapash makes Machine Learning models transparent and understandable by everyone

Code for A Volumetric Transformer for Accurate 3D Tumor Segmentation

FEMDA: Robust classification with Flexible Discriminant Analysis in heterogeneous data

Select, weight and analyze complex sample data

This repo is the official implementation of "L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization".

Probabilistic-Monocular-3D-Human-Pose-Estimation-with-Normalizing-Flows

Source code for the paper: Variance-Aware Machine Translation Test Sets (NeurIPS 2021 Datasets and Benchmarks Track)

Code for "Discovering Non-monotonic Autoregressive Orderings with Variational Inference" (paper and code updated from ICLR 2021)

PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks

Competitive Programming Club, Clinify's Official repository for CP problems hosting by club members.

Subnet Replacement Attack: Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks

Syllabic Quantity Patterns as Rhythmic Features for Latin Authorship Attribution