scholarly journals Low-Altitude Aerial Video Surveillance via One-Class SVM Anomaly Detection from Textural Features in UAV Images

Information ◽  
2021 ◽  
Vol 13 (1) ◽  
pp. 2
Author(s):  
Danilo Avola ◽  
Luigi Cinque ◽  
Angelo Di Mambro ◽  
Anxhelo Diko ◽  
Alessio Fagioli ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Video Surveillance ◽  
A Priori ◽  
Support Vector ◽  
Small Scale ◽  
Textural Features ◽  
Low Altitude ◽  
Common Items ◽  
Uav Images ◽  
Aerial Video

In recent years, small-scale Unmanned Aerial Vehicles (UAVs) have been used in many video surveillance applications, such as vehicle tracking, border control, dangerous object detection, and many others. Anomaly detection can represent a prerequisite of many of these applications thanks to its ability to identify areas and/or objects of interest without knowing them a priori. In this paper, a One-Class Support Vector Machine (OC-SVM) anomaly detector based on customized Haralick textural features for aerial video surveillance at low-altitude is presented. The use of a One-Class SVM, which is notoriously a lightweight and fast classifier, enables the implementation of real-time systems even when these are embedded in low-computational small-scale UAVs. At the same time, the use of textural features allows a vision-based system to detect micro and macro structures of an analyzed surface, thus allowing the identification of small and large anomalies, respectively. The latter aspect plays a key role in aerial video surveillance at low-altitude, i.e., 6 to 15 m, where the detection of common items, e.g., cars, is as important as the detection of little and undefined objects, e.g., Improvised Explosive Devices (IEDs). Experiments obtained on the UAV Mosaicking and Change Detection (UMCD) dataset show the effectiveness of the proposed system in terms of accuracy, precision, recall, and F1-score, where the model achieves a 100% precision, i.e., never misses an anomaly, but at the expense of a reasonable trade-off in its recall, which still manages to reach up to a 71.23% score. Moreover, when compared to classical Haralick textural features, the model obtains significantly higher performances, i.e., ≈20% on all metrics, further demonstrating the approach effectiveness.

Anomalous Human Activity Detection Based on Online One-Class SVM with N-Grams Kernel

2010 ◽  
Vol 143-144 ◽  
pp. 648-652
Author(s):  
Xu Dong Zhu ◽  
Zhi Jing Liu
Keyword(s):  
Anomaly Detection ◽  
Sequence Similarity ◽  
Novelty Detection ◽  
A Priori ◽  
Support Vector ◽  
Computationally Efficient ◽  
Fixed Dimension ◽  
Training Samples ◽  
Online Learning Algorithms ◽  
Priori Information

We present a novel online unsupervised anomaly detection method for human activities. The proposed approach is based on one-class support vector machine (OCSVM) clustering, where the novelty detection SVM capabilities are used for the identification of anomalous activities. Particular attention is given to activity classification in absence of a priori information on the distribution of outliers. Activities are represented by variable-length event sequences, but the most commonly used kernels are defined on fixed-dimension spaces. To solve the problem, we develop a novel sequence-similarity kernel, the n-grams kernel. Our kernel is conceptually simple and efficient to compute and performs well in comparison with state-of-the-art methods for anomaly detection. Moreover, most SVM algorithms require large number of memory to store the kernel matrix, or repeated access to the training samples. This makes it infeasible for online anomaly detection. In this paper, we develop simple and computationally efficient online learning algorithms for anomaly detection.

scholarly journals Is It Possible to Forecast the Price of Bitcoin?

Forecasting ◽  
2021 ◽  
Vol 3 (2) ◽  
pp. 377-420
Author(s):  
Julien Chevallier ◽  
Dominique Guégan ◽  
Stéphane Goutte
Keyword(s):  
Data Analytics ◽  
Daily Variation ◽  
A Priori ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Market Growth ◽  
Network Support ◽  
Market Participants ◽  
Nearest Neighbours ◽  
Stationary Behavior

This paper focuses on forecasting the price of Bitcoin, motivated by its market growth and the recent interest of market participants and academics. We deploy six machine learning algorithms (e.g., Artificial Neural Network, Support Vector Machine, Random Forest, k-Nearest Neighbours, AdaBoost, Ridge regression), without deciding a priori which one is the ‘best’ model. The main contribution is to use these data analytics techniques with great caution in the parameterization, instead of classical parametric modelings (AR), to disentangle the non-stationary behavior of the data. As soon as Bitcoin is also used for diversification in portfolios, we need to investigate its interactions with stocks, bonds, foreign exchange, and commodities. We identify that other cryptocurrencies convey enough information to explain the daily variation of Bitcoin’s spot and futures prices. Forecasting results point to the segmentation of Bitcoin concerning alternative assets. Finally, trading strategies are implemented.

scholarly journals Identifying the Branch of Kiwifruit Based on Unmanned Aerial Vehicle (UAV) Images Using Deep Learning Method

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4442
Author(s):  
Zijie Niu ◽  
Juntao Deng ◽  
Xu Zhang ◽  
Jun Zhang ◽  
Shijia Pan ◽  
...  
Keyword(s):  
Deep Learning ◽  
Unmanned Aerial Vehicle ◽  
Semantic Segmentation ◽  
Dynamic Monitoring ◽  
Support Vector ◽  
Distribution Maps ◽  
Time Operation ◽  
Aerial Vehicle ◽  
Uav Images ◽  
Segmentation Image

It is important to obtain accurate information about kiwifruit vines to monitoring their physiological states and undertake precise orchard operations. However, because vines are small and cling to trellises, and have branches laying on the ground, numerous challenges exist in the acquisition of accurate data for kiwifruit vines. In this paper, a kiwifruit canopy distribution prediction model is proposed on the basis of low-altitude unmanned aerial vehicle (UAV) images and deep learning techniques. First, the location of the kiwifruit plants and vine distribution are extracted from high-precision images collected by UAV. The canopy gradient distribution maps with different noise reduction and distribution effects are generated by modifying the threshold and sampling size using the resampling normalization method. The results showed that the accuracies of the vine segmentation using PSPnet, support vector machine, and random forest classification were 71.2%, 85.8%, and 75.26%, respectively. However, the segmentation image obtained using depth semantic segmentation had a higher signal-to-noise ratio and was closer to the real situation. The average intersection over union of the deep semantic segmentation was more than or equal to 80% in distribution maps, whereas, in traditional machine learning, the average intersection was between 20% and 60%. This indicates the proposed model can quickly extract the vine distribution and plant position, and is thus able to perform dynamic monitoring of orchards to provide real-time operation guidance.

Bridge health anomaly detection using deep support vector data description

2021 ◽  
Author(s):  
JianXi Yang ◽  
Fei Yang ◽  
Likai Zhang ◽  
Ren Li ◽  
Shixin Jiang ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Support Vector ◽  
Support Vector Data Description ◽  
Vector Data ◽  
Data Description ◽  
Deep Support

scholarly journals Machine Learning for Statistical Modeling

2021 ◽  
Vol 26 (3) ◽  
pp. 1-17
Author(s):  
Urmimala Roy ◽  
Tanmoy Pramanik ◽  
Subhendu Roy ◽  
Avhishek Chatterjee ◽  
Leonard F. Register ◽  
...  
Keyword(s):  
Machine Learning ◽  
Time Distribution ◽  
Switching Time ◽  
A Priori ◽  
Random Access ◽  
Spin Transfer Torque ◽  
Support Vector ◽  
Micromagnetic Simulations ◽  
Physical Systems ◽  
Computational Resources

We propose a methodology to perform process variation-aware device and circuit design using fully physics-based simulations within limited computational resources, without developing a compact model. Machine learning (ML), specifically a support vector regression (SVR) model, has been used. The SVR model has been trained using a dataset of devices simulated a priori, and the accuracy of prediction by the trained SVR model has been demonstrated. To produce a switching time distribution from the trained ML model, we only had to generate the dataset to train and validate the model, which needed ∼500 hours of computation. On the other hand, if 10 6 samples were to be simulated using the same computation resources to generate a switching time distribution from micromagnetic simulations, it would have taken ∼250 days. Spin-transfer-torque random access memory (STTRAM) has been used to demonstrate the method. However, different physical systems may be considered, different ML models can be used for different physical systems and/or different device parameter sets, and similar ends could be achieved by training the ML model using measured device data.

scholarly journals Preserving Privacy in Multimedia Social Networks Using Machine Learning Anomaly Detection

2020 ◽  
Vol 2020 ◽  
pp. 1-14 ◽  
Author(s):  
Randa Aljably ◽  
Yuan Tian ◽  
Mznah Al-Rodhaan
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Access Control ◽  
Anomaly Detection ◽  
Privacy Preservation ◽  
Support Vector ◽  
Detection Techniques ◽  
Access Control Models ◽  
Control Models ◽  
Multimedia Social Networks

Nowadays, user’s privacy is a critical matter in multimedia social networks. However, traditional machine learning anomaly detection techniques that rely on user’s log files and behavioral patterns are not sufficient to preserve it. Hence, the social network security should have multiple security measures to take into account additional information to protect user’s data. More precisely, access control models could complement machine learning algorithms in the process of privacy preservation. The models could use further information derived from the user’s profiles to detect anomalous users. In this paper, we implement a privacy preservation algorithm that incorporates supervised and unsupervised machine learning anomaly detection techniques with access control models. Due to the rich and fine-grained policies, our control model continuously updates the list of attributes used to classify users. It has been successfully tested on real datasets, with over 95% accuracy using Bayesian classifier, and 95.53% on receiver operating characteristic curve using deep neural networks and long short-term memory recurrent neural network classifiers. Experimental results show that this approach outperforms other detection techniques such as support vector machine, isolation forest, principal component analysis, and Kolmogorov–Smirnov test.

scholarly journals Carbon stocks of homestead forests have a mitigation potential to climate change in Bangladesh

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Tarit Kumar Baul ◽  
Tajkera Akhter Peuly ◽  
Rajasree Nandi ◽  
Lars Holger Schmidt ◽  
Shyamal Karmakar
Keyword(s):  
Species Diversity ◽  
Stand Structure ◽  
Diversity Index ◽  
Carbon Stocks ◽  
Small Scale ◽  
Species Diversity Index ◽  
C Stocks ◽  
Homestead Forests ◽  
C Stock ◽  
Low Altitude

AbstractA total of 176 homestead forests at three altitudes in the Chittagong Hill Tracts, Bangladesh were randomly surveyed to estimate carbon (C) stocks and how stand structure affects the biomass C. All woody vegetations were measured, and litter and soil (0–30 cm depth) were sampled. The tree biomass C stock in the top two altitude forests was up to 37–48% higher than in low altitude, owing to significantly higher tree density and species diversity. An increase in species diversity index by one unit increased the biomass stock by 23 Mg C ha−1. The C stock of litterfall in low altitude forests was 22–28% higher than in the top two altitude due to the deposition of litters downslope and deliberate use of mulch for soil improvement and conservation, resulting in up to 5% higher total soil C. The topsoil C was 10–25% higher than the deeper soil, depending on the altitude. The forest stored 89 Mg C ha−1, indicating a potential for C sequestration in trees outside forest. This study would help policymakers to strengthen the recognition of small-scale forests for mitigation in REDD + (reducing emissions from deforestation and forest degradation, the role of conservation, sustainable management of forests, and enhancement of forest carbon stocks) and support owners through C credits from sustainably managed forests.

Sign in / Sign up

Export Citation Format

Share Document