This dataset is captured from a Mirai type botnet attack on an emulated IoT network in OpenStack. Detailed information on the dataset is depicted in the following work. Please cite it when you use this dataset for your research.

  • Kalupahana Liyanage Kushan Sudheera, Dinil Mon Divakaran, Rhishi Pratap Singh, and Mohan Gurusamy, "ADEPT: Detection and Identification of Correlated Attack-Stages in IoT Networks," in IEEE Internet of Things Journal.


This dataset contains the database of the transport block (TB) configurations .


Message Queuing Telemetry Transport (MQTT) protocol is one of the most used standards used in Internet of Things (IoT) machine to machine communication. The increase in the number of available IoT devices and used protocols reinforce the need for new and robust Intrusion Detection Systems (IDS). However, building IoT IDS requires the availability of datasets to process, train and evaluate these models. The dataset presented in this paper is the first to simulate an MQTT-based network. The dataset is generated using a simulated MQTT network architecture.


The dataset consists of 5 pcap files, namely, normal.pcap, sparta.pcap, scan_A.pcap, mqtt_bruteforce.pcap and scan_sU.pcap. Each file represents a recording of one scenario; normal operation, Sparta SSH brute-force, aggressive scan, MQTT brute-force and UDP scan respectively. The attack pcap files contain background normal operations. The attacker IP address is “”. Basic packet features are extracted from the pcap files into CSV files with the same pcap file names. The features include flags, length, MQTT message parameters, etc. Later, unidirectional and bidirectional features are extracted.  It is important to note that for the bidirectional flows, some features (pointed as *) have two values—one for forward flow and one for the backward flow. The two features are recorded and distinguished by a prefix “fwd_” for forward and “bwd_” for backward. 



A Indústria enfrenta desafios graves e fracassa sem competitividade. Atacando esta problemática, conferiu-se o oferecimento de maior eficiência a processos industriais para promover a produtividade, elevar a qualidade e impulsionar mudanças. A solução desenvolvida incluiu dispositivos com sensores não invasivos, simples de instalar, que contabilizam os itens sendo transportados em linhas de produção.


Os dados foram coletados utilizando o dispositivo IoT da EnergyNow Tecnologias denominado Prodbox™, o qual opera como um equipamento empregado para intensificar a produtividade e apontar maneiras estratégicas de modificar variáveis que interferem na visão de gestão sobre a produção.

O dispositivo utiliza sensores não obstrutivos para contabilizar o número de itens que atravessam a linha de detecção gerada entre o transmissor e o receptor instalados.

Notadamente, os dados coletados são enviados para a nuvem, onde podem, quando integrados a uma plataforma de análise, ser processados para apresentar indicadores de acompanhamento de produtividade. Um sistema inteligente pode processar os dados coletados e apresentar métricas que permitem ao gestor identificar formas de aumentar a produção, bem como etapas que estão prejudicando a produtividade. Além disso, alertas customizados podem ser configurados para prover informação sobre a parada ou inatividade detectada pelo dispositivo.

Os dados gerados através do dispositivo podem ser utilizados para entender melhor variáveis sobre o ritmo de produção e, a partir delas, fomentar projeções de produção, calculando-se a relação entre itens produzidos e período de tempo necessário (segundos, minutos, horas, dias, semanas, etc).


Algumas sugestões sobre abordagens a serem consideradas:

  • Verifique se políticas de aumento de produtividade estão sendo efetivas.

  • Distribuia melhor os funcionários em etapas diferentes de uma linha de produção.

  • Correlacione etapas de produção com variáveis que estejam interferindo na produtividade para resolver problemáticas internas.


The  database contains the raw range-azimuth measurements obtained from mmWave MIMO radars (IWR1843BOOST deployed in different positions around a robotic manipulator.


The database that contains the raw range-azimuth measurements obtained from mmWave MIMO radars inside a Human-Robot (HR) workspace environment. 


The database contains 5 data structures:

i) mmwave_data_test has dimension 900 x 256 x 63. Contains 900 FFT range-azimuth measurements of size 256 x 63: 256-point range samples corresponding to a max range of 11m (min range of 0.5m) and 63 angle bins, corresponding to DOA ranging from -75 to +75 degree. These data are used for testing (validation database). The corresponding labels are in label_test. Each label (from 0 to 5) corresponds to one of the 6 positions (from 1 to 6) of the operator as detailed in the image attached.


ii) mmwave_data_train has dimension 900 x 256 x 63. Contains 900 FFT range-azimuth measurements used for training. The corresponding labels are in label_train.


iii) label_test with dimension 900 x 1, contains the true labels for test data (mmwave_data_test), namely classes (true labels) correspond to integers from 0 to 5. 


iv) label_train with dimension 900 x 1, contains the true labels for train data (mmwave_data_train), namely classes (true labels) correspond to integers from 0 to 5. 


v) p (1 x 900) contains the chosen random permutation for data partition among nodes/device and federated learnig simulation (see python code).


The Here East Digital Twin was a six month trial of a real-time 3D data visualisation platform, designed for the purpose of supporting operational management in the built environment. 


1. View the project video for context:

2. Review details of the Envirosensor implementation:

3. One option for analysing the data is using Spark and Python in a Jupyter Notebook as outlines in the following example GitHub repository:


Internet of Things (IoT) make the world easy, with healthcare applications being the most important. In general, IoT is used to interconnect advanced medical resources and provide smart and effective healthcare services to people. Advanced sensors can either be worn or embedded in patients' bodies, so that their health can be monitored remotely. Information collected in this way can be analyzed, collected, and mined to make an early prediction of diseases. Processing algorithms help physicians to personalize treatment and it helps to make healthcare affordable, with better results.


RPL is the de-facto IPv6-based routing protocol for the Internet of Things (IoT), where networks are mainly formed by sensors and other low capacity devices. However, RPL lacks scalability and is inefficient in any-to-any communications. In this article, we present IoTorii, a layer-two hierarchical protocol that creates routes based on a probe frame, instead of the computation of a distance vector, as in RPL.


To evaluate IoTorii, we implemented RPL and IoTorii in the OMNeT++ 5.2.1 simulator, with the INET 3.6.3 library. After validating IoTorii in OMNeT++, we developed both routing protocols using Contiki-NG which is a real Operating System (OS) for IoT devices. This Dataset includes data collected by OMNeT++ and Cooja simulators.

The Dataset includes two folders to store raw and chart data. The folder of raw data includes all data collected by the simulators. The folder of chart data includes data selected/aggregated by the raw data. Sub folders in this folder are categorized and named based on the simulations. Each sub folder includes three excel files to aggregate the raw data, and 3_plotData.xlsx includes the final data in the excel format, and all text files include the final data to be used as data tables in the TiKZ library of LaTeX.


Development of Industrial IoT System for Anomaly Detection in Smart Factory


7200 .csv files, each containing a 10 kHz recording of a 1 ms lasting 100 hz sound, recorded centimeterwise in a 20 cm x 60 cm locating range on a table. 3600 files (3 at each of the 1200 different positions) are without an obstacle between the loudspeaker and the microphone, 3600 RIR recordings are affected by the changes of the object (a book). The OOLA is initially trained offline in batch mode by the first instance of the RIR recordings without the book. Then it learns online in an incremental mode how the RIR changes by the book.


folder 'load and preprocess offline data': matlab sourcecodes and raw/working offline (no additional obstacle) data files

folder 'lvq and kmeans test': matlab sourcecodes to test and compare in-sample failure with and without LVQ

folder 'online data load and preprocess': matlab sourcecodes and raw/working online (additional obstacle) data files

folder 'OOL': matlab sourcecodes configurable for case 1-4

folder 'OOL2': matlab sourcecodes for case 5

folder 'plots': plots and simulations