scholarly journals Deep Learning on Multi Sensor Data for Counter UAV Applications—A Systematic Review

Sensors ◽  
2019 ◽  
Vol 19 (22) ◽  
pp. 4837 ◽  
Author(s):  
Stamatios Samaras ◽  
Eleni Diamantidou ◽  
Dimitrios Ataloglou ◽  
Nikos Sakellariou ◽  
Anastasios Vafeiadis ◽  
...  
Keyword(s):  
Deep Learning ◽  
Information Fusion ◽  
Rapid Evolution ◽  
Learning Technologies ◽  
Ease Of Use ◽  
Sensor Data ◽  
Wide Range ◽  
Challenging Tasks ◽  
Sensor Information ◽  
Novel Concept

Usage of Unmanned Aerial Vehicles (UAVs) is growing rapidly in a wide range of consumer applications, as they prove to be both autonomous and flexible in a variety of environments and tasks. However, this versatility and ease of use also brings a rapid evolution of threats by malicious actors that can use UAVs for criminal activities, converting them to passive or active threats. The need to protect critical infrastructures and important events from such threats has brought advances in counter UAV (c-UAV) applications. Nowadays, c-UAV applications offer systems that comprise a multi-sensory arsenal often including electro-optical, thermal, acoustic, radar and radio frequency sensors, whose information can be fused to increase the confidence of threat’s identification. Nevertheless, real-time surveillance is a cumbersome process, but it is absolutely essential to detect promptly the occurrence of adverse events or conditions. To that end, many challenging tasks arise such as object detection, classification, multi-object tracking and multi-sensor information fusion. In recent years, researchers have utilized deep learning based methodologies to tackle these tasks for generic objects and made noteworthy progress, yet applying deep learning for UAV detection and classification is considered a novel concept. Therefore, the need to present a complete overview of deep learning technologies applied to c-UAV related tasks on multi-sensor data has emerged. The aim of this paper is to describe deep learning advances on c-UAV related tasks when applied to data originating from many different sensors as well as multi-sensor information fusion. This survey may help in making recommendations and improvements of c-UAV applications for the future.

scholarly journals Modern Approaches to Detect and Classify Comment Toxicity Using Neural Networks

2020 ◽  
Vol 27 (1) ◽  
pp. 48-61 ◽  
Author(s):  
Sergey V. Morzhov
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Language Processing ◽  
Rapid Evolution ◽  
Learning Technologies ◽  
Training Set ◽  
Online Platforms ◽  
Processing Algorithms ◽  
New Algorithms

The growth of popularity of online platforms which allow users to communicate with each other, share opinions about various events, and leave comments boosted the development of natural language processing algorithms. Tens of millions of messages per day are published by users of a particular social network need to be analyzed in real time for moderation in order to prevent the spread of various illegal or offensive information, threats and other types of toxic comments. Of course, such a large amount of information can be processed quite quickly only automatically. that is why there is a need to and a way to teach computers to “understand” a text written by humans. It is a non-trivial task even if the word “understand” here means only “to classify”. the rapid evolution of machine learning technologies has led to ubiquitous implementation of new algorithms. A lot of tasks, which for many years were considered almost impossible to solve, are now quite successfully solved using deep learning technologies. this article considers algorithms built using deep learning technologies and neural networks which can successfully solve the problem of detection and classification of toxic comments. In addition, the article presents the results of the developed algorithms, as well as the results of the ensemble of all considered algorithms on a large training set collected and tagged by Google and Jigsaw.

scholarly journals AI-Based Sensor Information Fusion for Supporting Deep Supervised Learning

Sensors ◽  
2019 ◽  
Vol 19 (6) ◽  
pp. 1345 ◽  
Author(s):  
Carson Leung ◽  
Peter Braun ◽  
Alfredo Cuzzocrea
Keyword(s):  
Supervised Learning ◽  
Information Fusion ◽  
Smart Cities ◽  
Satellite System ◽  
Sensor Data ◽  
Fusion System ◽  
Sensor Information ◽  
Global Navigation Satellite ◽  
Effective Integration ◽  
The Internet Of Things

In recent years, artificial intelligence (AI) and its subarea of deep learning have drawn the attention of many researchers. At the same time, advances in technologies enable the generation or collection of large amounts of valuable data (e.g., sensor data) from various sources in different applications, such as those for the Internet of Things (IoT), which in turn aims towards the development of smart cities. With the availability of sensor data from various sources, sensor information fusion is in demand for effective integration of big data. In this article, we present an AI-based sensor-information fusion system for supporting deep supervised learning of transportation data generated and collected from various types of sensors, including remote sensed imagery for the geographic information system (GIS), accelerometers, as well as sensors for the global navigation satellite system (GNSS) and global positioning system (GPS). The discovered knowledge and information returned from our system provides analysts with a clearer understanding of trajectories or mobility of citizens, which in turn helps to develop better transportation models to achieve the ultimate goal of smarter cities. Evaluation results show the effectiveness and practicality of our AI-based sensor information fusion system for supporting deep supervised learning of big transportation data.

Based on D - S Evidence Theory of Solution Concentration Detection Method Research

2014 ◽  
Vol 494-495 ◽  
pp. 869-872
Author(s):  
Xian Bao Wang ◽  
Shi Hai Zhao ◽  
Guo Wei
Keyword(s):  
Information Fusion ◽  
Evidence Theory ◽  
Solution Concentration ◽  
Sensor Data ◽  
Fusion Technology ◽  
Feedback Information ◽  
Multiple Sensors ◽  
Multi Sensor Data Fusion ◽  
Single Sensor ◽  
Sensor Information

According to the theory of multi-sensor information fusion technology, based on D - S evidence theory to fuse of multiple sensors feedback information from different angles for detecting solution concentration, and achieving the same judgment; This system uses of D - S evidence theory of multi-sensor data fusion method, not only make up the disadvantages of using a single sensor, but also largely reduce the uncertainty of the judgment. Additionally this system improves the rapidity and accuracy of the solution concentration detection, and broadens the application field of multi-sensor information fusion technology.

scholarly journals Joint Learning of Temporal Models to Handle Imbalanced Data for Human Activity Recognition

2020 ◽  
Vol 10 (15) ◽  
pp. 5293 ◽  
Author(s):  
Rebeen Ali Hamad ◽  
Longzhi Yang ◽  
Wai Lok Woo ◽  
Bo Wei
Keyword(s):  
Deep Learning ◽  
Activity Recognition ◽  
Human Activity ◽  
Smart Home ◽  
Short Term Memory ◽  
Recognition System ◽  
Human Activity Recognition ◽  
Sensor Data ◽  
Temporal Models ◽  
Wide Range

Human activity recognition has become essential to a wide range of applications, such as smart home monitoring, health-care, surveillance. However, it is challenging to deliver a sufficiently robust human activity recognition system from raw sensor data with noise in a smart environment setting. Moreover, imbalanced human activity datasets with less frequent activities create extra challenges for accurate activity recognition. Deep learning algorithms have achieved promising results on balanced datasets, but their performance on imbalanced datasets without explicit algorithm design cannot be promised. Therefore, we aim to realise an activity recognition system using multi-modal sensors to address the issue of class imbalance in deep learning and improve recognition accuracy. This paper proposes a joint diverse temporal learning framework using Long Short Term Memory and one-dimensional Convolutional Neural Network models to improve human activity recognition, especially for less represented activities. We extensively evaluate the proposed method for Activities of Daily Living recognition using binary sensors dataset. A comparative study on five smart home datasets demonstrate that our proposed approach outperforms the existing individual temporal models and their hybridization. Furthermore, this is particularly the case for minority classes in addition to reasonable improvement on the majority classes of human activities.

scholarly journals Deep Learning on Computational-Resource-Limited Platforms: A Survey

2020 ◽  
Vol 2020 ◽  
pp. 1-19 ◽  
Author(s):  
Chunlei Chen ◽  
Peng Zhang ◽  
Huixiang Zhang ◽  
Jiangyan Dai ◽  
Yugen Yi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Pervasive Computing ◽  
Learning Technologies ◽  
Smart Sensors ◽  
Huge Amount ◽  
Computational Optimization ◽  
Computational Overhead ◽  
Resource Limited ◽  
Wide Range

Nowadays, Internet of Things (IoT) gives rise to a huge amount of data. IoT nodes equipped with smart sensors can immediately extract meaningful knowledge from the data through machine learning technologies. Deep learning (DL) is constantly contributing significant progress in smart sensing due to its dramatic superiorities over traditional machine learning. The promising prospect of wide-range applications puts forwards demands on the ubiquitous deployment of DL under various contexts. As a result, performing DL on mobile or embedded platforms is becoming a common requirement. Nevertheless, a typical DL application can easily exhaust an embedded or mobile device owing to a large amount of multiply and accumulate (MAC) operations and memory access operations. Consequently, it is a challenging task to bridge the gap between deep learning and resource-limited platforms. We summarize typical applications of resource-limited deep learning and point out that deep learning is an indispensable impetus of pervasive computing. Subsequently, we explore the underlying reasons for the high computational overhead of DL through reviewing the fundamental concepts including capacity, generalization, and backpropagation of a neural network. Guided by these concepts, we investigate on principles of representative research works, as well as three types of solutions: algorithmic design, computational optimization, and hardware revolution. In pursuant to these solutions, we identify challenges to be addressed.

From the history of the development of electronic dictionaries: foreign and domestic experience

2020 ◽  
Vol 11 (1) ◽  
pp. 6-12
Author(s):  
O. Y. Balalaieva ◽  
Keyword(s):  
Human Activity ◽  
Current Level ◽  
Ease Of Use ◽  
Advanced Search ◽  
Wide Range ◽  
Promising Area ◽  
History Of ◽  
Machine Readable ◽  
Everyday Communication ◽  
Educational Professional

The purpose of the article is to study the dynamics of electronic dictionaries development abroad and in Ukraine using methods of analysis of scientific sources, comparison, generalization and systematization. Electronic dictionaries have been found to be a relatively new phenomenon in the lexicographic market, evolving from machine-readable dictionaries, exact copies of paper editions to complex digital lexicographic systems with a powerful arsenal of functions over the decades. The stages of development of autonomous and online dictionaries are described. Electronic dictionaries due to the advanced search capabilities, speed, simplicity, ease of use, accessibility and compactness have gained popularity among a wide range of users. Today they are used in many spheres of human activity – scientific, educational, professional, everyday communication. However, the analysis of the current level of development of Ukrainian electronic resources indicates a shortage of electronic dictionaries both common and terminological vocabulary. The lack of electronic dictionaries is due to a number of objective problems, both practical and theoretical, that is why research in the field of domestic computer lexicography is a promising area of further research.

Human Activity Recognition using Fourier Transform Inspired Deep Learning Combination Model

2019 ◽  
Vol 9 (1) ◽  
pp. 16-31
Author(s):  
Kyungkoo Jun
Keyword(s):  
Fourier Transform ◽  
Deep Learning ◽  
Short Term Memory ◽  
Window Size ◽  
Sensor Data ◽  
Data Sets ◽  
Data Set ◽  
Proposed Model ◽  
Testing Data ◽  
Labeling Scheme

Background & Objective: This paper proposes a Fourier transform inspired method to classify human activities from time series sensor data. Methods: Our method begins by decomposing 1D input signal into 2D patterns, which is motivated by the Fourier conversion. The decomposition is helped by Long Short-Term Memory (LSTM) which captures the temporal dependency from the signal and then produces encoded sequences. The sequences, once arranged into the 2D array, can represent the fingerprints of the signals. The benefit of such transformation is that we can exploit the recent advances of the deep learning models for the image classification such as Convolutional Neural Network (CNN). Results: The proposed model, as a result, is the combination of LSTM and CNN. We evaluate the model over two data sets. For the first data set, which is more standardized than the other, our model outperforms previous works or at least equal. In the case of the second data set, we devise the schemes to generate training and testing data by changing the parameters of the window size, the sliding size, and the labeling scheme. Conclusion: The evaluation results show that the accuracy is over 95% for some cases. We also analyze the effect of the parameters on the performance.

scholarly journals Silicon Effects on the Root System of Diverse Crop Species Using Root Phenotyping Technology

Plants ◽  
2021 ◽  
Vol 10 (5) ◽  
pp. 885
Author(s):  
Pooja Tripathi ◽  
Sangita Subedi ◽  
Abdul Latif Khan ◽  
Yong-Suk Chung ◽  
Yoonha Kim
Keyword(s):  
Root System ◽  
Root Morphology ◽  
Morphological Traits ◽  
Crop Production ◽  
Spatial Configuration ◽  
Global Climate ◽  
Learning Technologies ◽  
Climate Change Scenarios ◽  
Crop Species ◽  
Wide Range

Roots play an essential function in the plant life cycle, as they utilize water and essential nutrients to promote growth and plant productivity. In particular, root morphology characteristics (such as length, diameter, hairs, and lateral growth) and the architecture of the root system (spatial configuration in soil, shape, and structure) are the key elements that ensure growth and a fine-tuned response to stressful conditions. Silicon (Si) is a ubiquitous element in soil, and it can affect a wide range of physiological processes occurring in the rhizosphere of various crop species. Studies have shown that Si significantly and positively enhances root morphological traits, including root length in rice, soybean, barley, sorghum, mustard, alfalfa, ginseng, and wheat. The analysis of these morphological traits using conventional methods is particularly challenging. Currently, image analysis methods based on advanced machine learning technologies allowed researchers to screen numerous samples at the same time considering multiple features, and to investigate root functions after the application of Si. These methods include root scanning, endoscopy, two-dimensional, and three-dimensional imaging, which can measure Si uptake, translocation and root morphological traits. Small variations in root morphology and architecture can reveal different positive impacts of Si on the root system of crops, with or without exposure to stressful environmental conditions. This review comprehensively illustrates the influences of Si on root morphology and root architecture in various crop species. Furthermore, it includes recommendations in regard to advanced methods and strategies to be employed to maintain sustainable plant growth rates and crop production in the currently predicted global climate change scenarios.

scholarly journals U-Infuse: Democratization of Customizable Deep Learning for Object Detection

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2611
Author(s):  
Andrew Shepley ◽  
Greg Falzon ◽  
Christopher Lawson ◽  
Paul Meek ◽  
Paul Kwan
Keyword(s):  
Deep Learning ◽  
Intellectual Property ◽  
Object Detection ◽  
Image Data ◽  
Learning Technologies ◽  
Training Data ◽  
Learning Models ◽  
Ecological Data ◽  
Single Class ◽  
Large Numbers

Image data is one of the primary sources of ecological data used in biodiversity conservation and management worldwide. However, classifying and interpreting large numbers of images is time and resource expensive, particularly in the context of camera trapping. Deep learning models have been used to achieve this task but are often not suited to specific applications due to their inability to generalise to new environments and inconsistent performance. Models need to be developed for specific species cohorts and environments, but the technical skills required to achieve this are a key barrier to the accessibility of this technology to ecologists. Thus, there is a strong need to democratize access to deep learning technologies by providing an easy-to-use software application allowing non-technical users to train custom object detectors. U-Infuse addresses this issue by providing ecologists with the ability to train customised models using publicly available images and/or their own images without specific technical expertise. Auto-annotation and annotation editing functionalities minimize the constraints of manually annotating and pre-processing large numbers of images. U-Infuse is a free and open-source software solution that supports both multiclass and single class training and object detection, allowing ecologists to access deep learning technologies usually only available to computer scientists, on their own device, customised for their application, without sharing intellectual property or sensitive data. It provides ecological practitioners with the ability to (i) easily achieve object detection within a user-friendly GUI, generating a species distribution report, and other useful statistics, (ii) custom train deep learning models using publicly available and custom training data, (iii) achieve supervised auto-annotation of images for further training, with the benefit of editing annotations to ensure quality datasets. Broad adoption of U-Infuse by ecological practitioners will improve ecological image analysis and processing by allowing significantly more image data to be processed with minimal expenditure of time and resources, particularly for camera trap images. Ease of training and use of transfer learning means domain-specific models can be trained rapidly, and frequently updated without the need for computer science expertise, or data sharing, protecting intellectual property and privacy.

Sign in / Sign up

Export Citation Format

Share Document