OutlierNets: Highly Compact Deep Autoencoder Network Architectures for On-Device Acoustic Anomaly Detection

Human operators often diagnose industrial machinery via anomalous sounds. Given the new advances in the field of machine learning, automated acoustic anomaly detection can lead to reliable maintenance of machinery. However, deep learning-driven anomaly detection methods often require an extensive amount of computational resources prohibiting their deployment in factories. Here we explore a machine-driven design exploration strategy to create OutlierNets, a family of highly compact deep convolutional autoencoder network architectures featuring as few as 686 parameters, model sizes as small as 2.7 KB, and as low as 2.8 million FLOPs, with a detection accuracy matching or exceeding published architectures with as many as 4 million parameters. The architectures are deployed on an Intel Core i5 as well as a ARM Cortex A72 to assess performance on hardware that is likely to be used in industry. Experimental results on the model’s latency show that the OutlierNet architectures can achieve as much as 30x lower latency than published networks.

Download Full-text

Edge Computing for Data Anomaly Detection of Multi-Sensors in Underground Mining

Electronics ◽

10.3390/electronics10030302 ◽

2021 ◽

Vol 10 (3) ◽

pp. 302

Author(s):

Chunde Liu ◽

Xianli Su ◽

Chuanwen Li

Keyword(s):

Energy Consumption ◽

Anomaly Detection ◽

Underground Mining ◽

Heterogeneous Data ◽

Edge Computing ◽

Sensor Nodes ◽

Detection Methods ◽

Detection Accuracy ◽

Clustering Methods ◽

Safety Warning

There is a growing interest in safety warning of underground mining due to the huge threat being faced by those working in underground mining. Data acquisition of sensors based on Internet of Things (IoT) is currently the main method, but the data anomaly detection and analysis of multi-sensors is a challenging task: firstly, the data that are collected by different sensors of underground mining are heterogeneous; secondly, real-time is required for the data anomaly detection of safety warning. Currently, there are many anomaly detection methods, such as traditional clustering methods K-means and C-means. Meanwhile, Artificial Intelligence (AI) is widely used in data analysis and prediction. However, K-means and C-means cannot directly process heterogeneous data, and AI algorithms require equipment with high computing and storage capabilities. IoT equipment of underground mining cannot perform complex calculation due to the limitation of energy consumption. Therefore, many existing methods cannot be directly used for IoT applications in underground mining. In this paper, a multi-sensors data anomaly detection method based on edge computing is proposed. Firstly, an edge computing model is designed, and according to the computing capabilities of different types of devices, anomaly detection tasks are migrated to different edge devices, which solve the problem of insufficient computing capabilities of the devices. Secondly, according to the requirements of different anomaly detection tasks, edge anomaly detection algorithms for sensor nodes and sink nodes are designed respectively. Lastly, an experimental platform is built for performance comparison analysis, and the experimental results show that the proposed algorithm has better performance in anomaly detection accuracy, delay, and energy consumption.

Download Full-text

An Optimized Stacking Ensemble Model for Phishing Websites Detection

Electronics ◽

10.3390/electronics10111285 ◽

2021 ◽

Vol 10 (11) ◽

pp. 1285

Author(s):

Mohammed Al-Sarem ◽

Faisal Saeed ◽

Zeyad Ghaleb Al-Mekhlafi ◽

Badiea Abdulkarem Mohammed ◽

Tawfik Al-Hadhrami ◽

...

Keyword(s):

Machine Learning ◽

Random Forests ◽

Ensemble Method ◽

Detection Methods ◽

Detection Accuracy ◽

Ensemble Model ◽

Security Attacks ◽

Data Set ◽

Machine Learning Methods ◽

Ensemble Machine Learning

Security attacks on legitimate websites to steal users’ information, known as phishing attacks, have been increasing. This kind of attack does not just affect individuals’ or organisations’ websites. Although several detection methods for phishing websites have been proposed using machine learning, deep learning, and other approaches, their detection accuracy still needs to be enhanced. This paper proposes an optimized stacking ensemble method for phishing website detection. The optimisation was carried out using a genetic algorithm (GA) to tune the parameters of several ensemble machine learning methods, including random forests, AdaBoost, XGBoost, Bagging, GradientBoost, and LightGBM. The optimized classifiers were then ranked, and the best three models were chosen as base classifiers of a stacking ensemble method. The experiments were conducted on three phishing website datasets that consisted of both phishing websites and legitimate websites—the Phishing Websites Data Set from UCI (Dataset 1); Phishing Dataset for Machine Learning from Mendeley (Dataset 2, and Datasets for Phishing Websites Detection from Mendeley (Dataset 3). The experimental results showed an improvement using the optimized stacking ensemble method, where the detection accuracy reached 97.16%, 98.58%, and 97.39% for Dataset 1, Dataset 2, and Dataset 3, respectively.

Download Full-text

Augmented Reality and Machine Learning Incorporation Using YOLOv3 and ARKit

Applied Sciences ◽

10.3390/app11136006 ◽

2021 ◽

Vol 11 (13) ◽

pp. 6006

Author(s):

Huy Le ◽

Minh Nguyen ◽

Wei Qi Yan ◽

Hoa Nguyen

Keyword(s):

Machine Learning ◽

Augmented Reality ◽

Object Detection ◽

Feature Detection ◽

Detection Methods ◽

Detection Accuracy ◽

Data Annotation ◽

Machine Learning Model ◽

Potential Benefits ◽

Feature Detection And Tracking

Augmented reality is one of the fastest growing fields, receiving increased funding for the last few years as people realise the potential benefits of rendering virtual information in the real world. Most of today’s augmented reality marker-based applications use local feature detection and tracking techniques. The disadvantage of applying these techniques is that the markers must be modified to match the unique classified algorithms or they suffer from low detection accuracy. Machine learning is an ideal solution to overcome the current drawbacks of image processing in augmented reality applications. However, traditional data annotation requires extensive time and labour, as it is usually done manually. This study incorporates machine learning to detect and track augmented reality marker targets in an application using deep neural networks. We firstly implement the auto-generated dataset tool, which is used for the machine learning dataset preparation. The final iOS prototype application incorporates object detection, object tracking and augmented reality. The machine learning model is trained to recognise the differences between targets using one of YOLO’s most well-known object detection methods. The final product makes use of a valuable toolkit for developing augmented reality applications called ARKit.

Download Full-text

Approaches for Monitoring the Energy Consumption with Machine Learning Methods

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.805.79 ◽

2015 ◽

Vol 805 ◽

pp. 79-85

Author(s):

Christian Gebbe ◽

Johannes Glasschröder ◽

Gunther Reinhart

Keyword(s):

Machine Learning ◽

Energy Consumption ◽

Anomaly Detection ◽

Energy Demand ◽

Sensor Data ◽

Detection Methods ◽

Energy Costs ◽

Threshold Values ◽

Production Methods ◽

Static Threshold

In times of rising energy costs and increasing customer awareness of sustainable production methods, many manufacturers take measures to reduce their energy consumption. However, after the realization of such activities the energy demand often tends to increase again due to e.g. leaks, clogged filters, defect valves or suboptimal parameter settings. In order to prevent this, it is necessary to quickly identify such increases by continuously monitoring the energy consumption and counteracting accordingly. Currently, the monitoring is either performed manually or by setting static threshold values. The manual control can be time consuming for large amounts of sensor data. By setting static threshold values only a fraction of the inefficiencies are disclosed. Another option is to use anomaly detection methods from the area of machine learning, which compare the actual sensor values with the expected ones. In this paper an overview about existing anomaly detection methods, which can be applied for this purpose, is presented.

Download Full-text

Mlifdect: Android Malware Detection Based on Parallel Machine Learning and Information Fusion

Security and Communication Networks ◽

10.1155/2017/6451260 ◽

2017 ◽

Vol 2017 ◽

pp. 1-14 ◽

Cited By ~ 8

Author(s):

Xin Wang ◽

Dafang Zhang ◽

Xin Su ◽

Wenjia Li

Keyword(s):

Machine Learning ◽

Information Fusion ◽

Malware Detection ◽

Parallel Machine ◽

Detection Methods ◽

Detection Accuracy ◽

Android Malware ◽

Detection Model ◽

Android Apps ◽

Android Malware Detection

In recent years, Android malware has continued to grow at an alarming rate. More recent malicious apps’ employing highly sophisticated detection avoidance techniques makes the traditional machine learning based malware detection methods far less effective. More specifically, they cannot cope with various types of Android malware and have limitation in detection by utilizing a single classification algorithm. To address this limitation, we propose a novel approach in this paper that leverages parallel machine learning and information fusion techniques for better Android malware detection, which is named Mlifdect. To implement this approach, we first extract eight types of features from static analysis on Android apps and build two kinds of feature sets after feature selection. Then, a parallel machine learning detection model is developed for speeding up the process of classification. Finally, we investigate the probability analysis based and Dempster-Shafer theory based information fusion approaches which can effectively obtain the detection results. To validate our method, other state-of-the-art detection works are selected for comparison with real-world Android apps. The experimental results demonstrate that Mlifdect is capable of achieving higher detection accuracy as well as a remarkable run-time efficiency compared to the existing malware detection solutions.

Download Full-text

A Hybrid Semi-Supervised Anomaly Detection Model for High-Dimensional Data

Computational Intelligence and Neuroscience ◽

10.1155/2017/8501683 ◽

2017 ◽

Vol 2017 ◽

pp. 1-9 ◽

Cited By ~ 14

Author(s):

Hongchao Song ◽

Zhuqing Jiang ◽

Aidong Men ◽

Bo Yang

Keyword(s):

Anomaly Detection ◽

Nearest Neighbor ◽

Dimensional Space ◽

High Dimensional Data ◽

Real Life ◽

Detection Methods ◽

High Dimensional ◽

Detection Accuracy ◽

Detection Model ◽

Anomaly Detector

Anomaly detection, which aims to identify observations that deviate from a nominal sample, is a challenging task for high-dimensional data. Traditional distance-based anomaly detection methods compute the neighborhood distance between each observation and suffer from the curse of dimensionality in high-dimensional space; for example, the distances between any pair of samples are similar and each sample may perform like an outlier. In this paper, we propose a hybrid semi-supervised anomaly detection model for high-dimensional data that consists of two parts: a deep autoencoder (DAE) and an ensemble k-nearest neighbor graphs- (K-NNG-) based anomaly detector. Benefiting from the ability of nonlinear mapping, the DAE is first trained to learn the intrinsic features of a high-dimensional dataset to represent the high-dimensional data in a more compact subspace. Several nonparametric KNN-based anomaly detectors are then built from different subsets that are randomly sampled from the whole dataset. The final prediction is made by all the anomaly detectors. The performance of the proposed method is evaluated on several real-life datasets, and the results confirm that the proposed hybrid model improves the detection accuracy and reduces the computational complexity.

Download Full-text

SHAPEIoT: Secure Handshake Protocol for Autonomous IoT Device Discovery and Blacklisting using Physical Unclonable Functions and Machine Learning

10.5121/csit.2021.111511 ◽

2021 ◽

Author(s):

Cem Ata Baykara ◽

Ilgın Şafak ◽

Kübra Kalkan

Keyword(s):

Machine Learning ◽

Anomaly Detection ◽

Network Simulation ◽

Anomalous Behavior ◽

Machine Learning Algorithms ◽

Detection Accuracy ◽

Session Key ◽

Device Discovery ◽

Handshake Protocol ◽

Iot Devices

This paper proposes a new lightweight handshake protocol implemented on top of the Constrained Application Protocol (CoAP) that can be used in device discovery and ensuring the IoT network security by autonomously managing devices of any computational complexity using whitelisting and blacklisting. A Physical Unclonable Function (PUF) is utilized for the session key generation in the proposed handshake protocol. The CoAP server performs real-time device discovery using the proposed handshake protocol, and anomaly detection using machinelearning algorithms to ensure the security of the IoT network. To the best of our knowledge, the presented PUF-based handshake protocol is the first to performs blacklisting and whitelisting. Whitelisted IoT devices not displaying anomalous behavior can join and remain in the IoT network. IoT devices that display anomalous behavior are autonomously blacklisted by the CoAP server and are either disallowed from joining the IoT network or are removed from the IoT network. Simulation results show that amongst the five machine learning algorithms studied, the stacking classifier displays the highest overall anomaly detection accuracy of 99.98%. Based on the results of the network simulation performed, the CoAP server is capable of blacklisting malicious IoT devices within the network with perfect accuracy.

Download Full-text

Hyperspectral Anomaly Detection Based on Separability-Aware Sample Cascade

Remote Sensing ◽

10.3390/rs11212537 ◽

2019 ◽

Vol 11 (21) ◽

pp. 2537 ◽

Cited By ~ 2

Author(s):

Dandan Ma ◽

Yuan Yuan ◽

Qi Wang

Keyword(s):

Anomaly Detection ◽

Large Scale ◽

Hyperspectral Image ◽

Superior Performance ◽

Detection Methods ◽

Background Information ◽

Detection Accuracy ◽

Layer By Layer ◽

Edge Preserving ◽

Image Pixels

A hyperspectral image usually covers a large scale of ground scene, which contains various materials with different spectral properties. When directly exploring the background information using all the image pixels, complex spectral interactions and inter-/intra-difference of different samples will significantly reduce the accuracy of background evaluation and further affect the detection performance. To address this problem, this paper proposes a novel hyperspectral anomaly detection method based on separability-aware sample cascade model. Through identifying separability of hyperspectral pixels, background samples are sifted out layer-by-layer according to their separable degrees from anomalies, which can ensure the accuracy and distinctiveness of background representation. First, as spatial structure is beneficial for recognizing target, a new spectral–spatial feature extraction technique is used in this work based on the PCA technique and edge-preserving filtering. Second, depending on different separability computed by sparse representation, samples are separated into different sets which can effectively and completely reflect various characteristics of background across all the cascade layers. Meanwhile, some potential abnormal targets are removed at each selection step to avoid their effects on subsequent layers. Finally, comprehensively taking different good properties of all the separability-aware layers into consideration, a simple multilayer anomaly detection strategy is adopted to obtain the final detection map. Extensive experimental results on five real-world hyperspectral images demonstrate our method’s superior performance. Compared with seven representative anomaly detection methods, our method improves the average detection accuracy with great advantages.

Download Full-text

Log Message Anomaly Detection with Oversampling

10.31224/osf.io/d4e6a ◽

2020 ◽

Author(s):

Amir Farzad ◽

T. Aaron Gulliver

Keyword(s):

Machine Learning ◽

Feature Extraction ◽

Anomaly Detection ◽

Learning Algorithms ◽

Imbalanced Data ◽

Machine Learning Algorithms ◽

Detection Accuracy ◽

Data Sets ◽

Significant Challenge ◽

Proposed Model

Imbalanced data is a significant challenge in classification with machine learning algorithms. This is particularly important with log message data as negative logs are sparse so this data is typically imbalanced. In this paper, a model to generate text log messages is proposed which employs a SeqGAN network. An Autoencoder is used for feature extraction and anomaly detection is done using a GRU network. The proposed model is evaluated with three imbalanced log data sets, namely BGL, OpenStack, and Thunderbird. Results are presented which show that appropriate oversampling and data balancing improves anomaly detection accuracy.

Download Full-text