Figure 6 - uploaded by Alexandr Savinov
Content may be subject to copyright.
Source publication
This paper describes an approach to detecting anomalous behavior of devices by analyzing their event data. Devices from a fleet are supposed to be connected to the Internet by sending log data to the server. The task is to analyze this data by automatically detecting unusual behavioral patterns. Another goal is to provide analysis templates that ar...
Context in source publication
Context 1
... without changing the number of rows (as described in Section 2), define new aggregated features by grouping rows into intervals and then applying several aggregate functions (as described in Section 3), choose a data analysis algorithm (as described in Section 4), and finally write the result with anomaly score to an output file or database. Fig. 6 is an example of how data aggregation step in the analysis workflow can be defined using the wizard. First, it is necessary to choose an aggregation interval. In this example, it is 1 hour which means that the behavior of devices will be analyzed on hourly basis. In other words, any behavioral pattern or characteristic is defined by ...
Similar publications
Internet of things (IOT) imagines a world where every device at any place can be connected. Home Automation system is growing rapidly and now becoming the requirement of the modern world. IoT based Home Automation System is getting more important as it increases security, comfort and improves the quality of life. In this paper, we have proposed the...
Establishment of RESTful APIs is a foundational component in creation of current full-stack Web applications; our programs effectively manage a lot of data; enable clean communication between the clients and the servers; and offer improved and enhanced user interfaces. This paper aims at explaining and demystifying processes of constructing and con...
Be it industry or academia, Internet of the Things (IoT) has become buzzword today. Everyone is expecting a system of gadgets controlled by web without human intervention. The concept has opened many possibilities and a fear of failure too. All over the world the research is going on and few organizations have already started implementing the conce...
This paper presents the on-going work of MyDNAmark crowdsourcing biodiversity mobile application which enable the researchers and public alike to collaboratively record the species information and observation. The MyDNAmark application utilizes the Cordova API and various other APIs such as RESTful and Google Map to provide a means to display the c...
The Payment Switch is an integral component of all modern payment and banking systems in India. The NPCI currently provides a simulator to test payment switches. However, this system has a few disadvantages viz. it lacks an API, it requires manual generation of each test case and during high server loads, the testing process may take a long time. C...
Citations
... Specialized ML techniques are required to perform AD in the context of sensor networks. As most IoT systems provide streaming sensor data, methods are required to cope with time series data either directly or by preprocessing the time series to discrete events [22]. Anomalies occur infrequently and can be either unior multivariate. ...
Anomalies and faults can be detected, and their causes verified, using both data-driven and knowledge-driven techniques. Data-driven techniques can adapt their internal functioning based on the raw input data but fail to explain the manifestation of any detection. Knowledge-driven techniques inherently deliver the cause of the faults that were detected but require too much human effort to set up. In this paper, we introduce FLAGS, the Fused-AI interpretabLe Anomaly Generation System, and combine both techniques in one methodology to overcome their limitations and optimize them based on limited user feedback. Semantic knowledge is incorporated in a machine learning technique to enhance expressivity. At the same time, feedback about the faults and anomalies that occurred is provided as input to increase adaptiveness using semantic rule mining methods. This new methodology is evaluated on a predictive maintenance case for trains. We show that our method reduces their downtime and provides more insight into frequently occurring problems.
... Authors in [44] extend Sipresk, a big data analytic platform, to detect, classify and report events in Ontario highways in a minimum delay. In [45], authors propose an anomaly detection system for asynchronous events coming from a fleet of devices. The system defines an analysis workflow for each specific use case, and it is deployed as a Cloud Web service exposing all functionalities via REST API. ...
... The design is based on the service computing life-cycle model introduced in [59]. This reference stipulates VOLUME 8, 2020 [37] Optimized hybrid fog/cloud provisioning Ben Abdallah et al. [39] Efficient incremental layered DL-based image processing Yangui et al. [40] Support of the whole IoT application life cycle Cramer et al. [45] Cloud Web service via REST API Lyu et al. [46] Efficient hyper-ellipsoidal clustering algorithm at fog resources Thamilarasu et al. [47] Efficient DL algorithm for IoT anomaly detection Rettig et al. [51] Online Anomaly Detecting for streaming application Abdellatif al. [57] Adaptable and energy efficient monitoring for WSN (limited to WSN) Pahl et al. [58] Block-chain based solution for a trusted orchestration in fog and cloud that services and applications, including IoT applications provisioning process consists of three phases: (i) Development, (ii) deployment and (iii) management. The READ-IoT architecture specification is inline with this model. ...
Internet of Things (IoT) enables a myriad of applications by interconnecting software to physical objects. The objects range from wireless sensors to robots and include surveillance cameras. The applications are often critical (e.g. physical intrusion detection, fire fighting) and latency-sensitive. On the one hand, such applications rely on specific protocols (e.g. MQTT, COAP) and the network to communicate with the objects under very tight timeframe. On the other hand, anomalies (e.g. communication noise, sensors’ failures, security attacks) are likely to occur in open IoT systems and can result by sending false alerts or the failure to properly detect critical events. To address that, IoT systems have to be equipped with anomaly detection processing in addition to the required event detection capability. This is a key feature that enables reliability and efficiency in IoT. However, anomaly detection systems can be themselves object of failures and attacks, and then can easily fall short to accomplish their mission. This paper introduces a Reliable Event and Anomaly Detection Framework for the Internet of Things (READ-IoT for short). The designed framework integrates events and anomalies detection into a single and common system that centralizes the management of both concepts. To enforce its reliability, the system relies on a reputation-aware provisioning of detection capabilities that takes into account the vulnerability of the deployment hosts. As for validation, READ-IoT was implemented and evaluated using two real life applications, i.e. a fire detection and an unauthorized person detection applications. Several scenarios of anomalies and events were conducted using NSL-KDD public dataset, as well as, generated data to simulate routing attacks. The obtained results and performance measurements show the efficiency of READ-IoT in terms of event detection accuracy and real-time processing.
... In the context of IoT, authors in (Cramer et al., 2018) propose an approach to detect anomalous behavior of devices by analyzing event data. In fact, data is analyzed to detect automatically unusual behavior patterns. ...
... Outlier detection is defined as finding patterns in data that behaves unexpectedly [4]. Objective of outlier detection is to find devices by their behavior that differs from the expected and previously observed in the field of IoT [5]. ...
... They discussed that user behavior outlier detection is an imperative phase of user behavior analysis that can be used for the detection of events of an anomalous user from network traffic data and event. A methodology for the detection of abnormal actions of devices by examining their data of events has been proposed in [5]. Authors discussed that devices are associated with the internet and they are sending their log information to the server. ...
In Internet of things (IoT) millions of devices are intelligently connected for providing smart services. Especially in indoor localization environment, that is one of the most concerning topic of smart cities, internet of things and wireless sensor networks. Many technologies are being used for localization purpose in indoor environment and Wi-Fi using received signal strengths (RSSs) is one of them. Wi-Fi RSSs are sensitive to reflection, refraction, interference and channel noise that cause irregularity in signal strengths. The irregular and anomalous RSS values, used in a Wi-Fi indoor localization environment, cannot define the location of any unknown node correctly. Therefore, this research has developed an outlier detection technique named as iF_Ensemble for Wi-Fi indoor localization environment by analyzing RSSs using the combination of supervised, unsupervised and ensemble machine learning methods. In this research isolation forest (iForest) is used as an unsupervised learning method. Supervised learning method includes support vector machine (SVM), K-nearest neighbor (KNN) and random forest (RF) classifiers with stacking that is an ensemble learning method. For the evaluation purpose accuracy, precision, recall, F-score and ROC-AUC curve are used. The evaluation of used machine learning method provides high accuracy of 97.8 percent with proposed outlier detection methods and almost 2 percent improvement in the accuracy of localization process in indoor environment after eliminating outliers.
... The importance of identifying such elements is given by the fact that we can discover unexpected behaviours in the process that generated the data under analysis (e.g., a series of readings from sensor data to represent a failure in the sensor itself or a network trace that signals an intrusion in the system). This is the main reason why anomaly detection has gained more and more importance in recent years in many fields, like network intrusion detection, law enforcement to detect criminal activities, detection of anomalies in IoT devices communication / behaviour, and many more (Cramer et al., 2018;Caithness and Wallom, 2018). ...
... The third revolution was to introduce flexible manufacturing, robotics and quality control and optimization by 1970. Each of these revolutions have named it by number: Industry X.0, where X is the ordinal number of the revolution [14]. During the fair in Hannover, Germany in 2011, the term Industrie 4.0 (original of the German language) was coined, which is the fourth industrial revolution [3], [15] and was later officially announced. ...
... Since AWS provides a free layer, it has been used in comparisons and projects [74], [75]. Bosch IoT Suite is based on open standards and open source [14], and it has the capacity to execute independent local projects or it can be implemented as a hosted service in different clouds. Bosch IoT has a device layer, a device management layer to perform software and configuration updates, an integration layer, an application and analysis layer, a security layer, and an administration layer. ...
The emerging technologies that make up Industry 4.0, include the Internet of Things and big data. The haptic interfaces have been used in different industries, but apparently, they are not integrated with the two technologies mentioned above. This work aims to know what the current use of IoT is, haptic interfaces and big data in the manufacturing industry. In turn, the fact of implementing an IoT platform leads to selecting an architecture that adapts to the needs of a specific organization. That is why this work also seeks to describe the IoT architectures available in the literature. Finally, we seek to know what the potential benefits for the manufacturing industry are combining IoT, haptic interfaces and big data in an intelligent environment enabled by machine learning. To have a better understanding, this work includes the description of the relevant concepts of the topic, including the description of supervised learning algorithms. In the end, this work allows us to open the door to other areas of research for future research.
