scholarly journals Machine Learning-Assisted Man Overboard Detection Using Radars

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1345
Author(s):  
Vasileios Tsekenis ◽  
Charalampos K. Armeniakos ◽  
Viktor Nikolaidis ◽  
Petros S. Bithas ◽  
Athanasios G. Kanatas
Keyword(s):  
Machine Learning ◽  
Human Motion ◽  
Machine Learning Algorithms ◽  
Full Potential ◽  
Monitoring Equipment ◽  
Integrated Sensor ◽  
Radar Sensors ◽  
Thermal Cameras ◽  
Decision Center ◽  
Automated Surveillance

One of the most crucial emergencies that require instant action to be taken during traveling across water is the so-called man overboard (MOB). Thus, constant monitoring equipment needs to be installed for the fast notice and detection of the victim to be rescued, if an incident happens. Despite the fact that different installations such as radar sensors, thermal cameras etc., can be handy, a combination of these could be beneficial yet it would increase the complexity. Nevertheless, the full potential may be not reached yet. The key component to what needs to be done in order to achieve the utmost accuracy is artificial intelligence (AI). That is, with the aid of AI, one can deploy an automated surveillance system capable of making its own humanlike decisions regarding such incidents like MOB. To achieve this, fully organized real-time cooperation among the concerned system components is essential. The latter holds since in such dynamically changing operational environments like these, information must be distributed fast, errorless and reliably to the decision center. This study aims to analyze and demonstrate the outcome of an integrated sensor-based system that utilizes AI, implemented for ship incidents. Different machine learning algorithms were used where each one of them made use of information that originated from a cluster of radar sensors located remotely. In particular, the deployed system’s objective is to detect human motion so it can be used to protect against potentially fateful events during ship voyages.

scholarly journals Recognition Technology of Athlete’s Limb Movement Combined Based on the Integrated Learning Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Fei Tan ◽  
Xiaoqing Xie
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Learning Algorithm ◽  
Human Motion ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Recording Device ◽  
Table Tennis ◽  
Movement Recognition ◽  
Random Forest Tree

Human motion recognition based on inertial sensor is a new research direction in the field of pattern recognition. It carries out preprocessing, feature selection, and feature selection by placing inertial sensors on the surface of the human body. Finally, it mainly classifies and recognizes the extracted features of human action. There are many kinds of swing movements in table tennis. Accurately identifying these movement modes is of great significance for swing movement analysis. With the development of artificial intelligence technology, human movement recognition has made many breakthroughs in recent years, from machine learning to deep learning, from wearable sensors to visual sensors. However, there is not much work on movement recognition for table tennis, and the methods are still mainly integrated into the traditional field of machine learning. Therefore, this paper uses an acceleration sensor as a motion recording device for a table tennis disc and explores the three-axis acceleration data of four common swing motions. Traditional machine learning algorithms (decision tree, random forest tree, and support vector) are used to classify the swing motion, and a classification algorithm based on the idea of integration is designed. Experimental results show that the ensemble learning algorithm developed in this paper is better than the traditional machine learning algorithm, and the average recognition accuracy is 91%.

scholarly journals Human Motion Recognition by Textile Sensor Based on Machine Learning Algorithms

2018 ◽  
Author(s):  
Chi Cuong Vu ◽  
Jooyong Kim
Keyword(s):  
Machine Learning ◽  
Wearable Sensors ◽  
Learning Algorithms ◽  
Human Motion ◽  
Machine Learning Algorithms ◽  
Identification Rate ◽  
Human Motion Recognition ◽  
Textile Sensor ◽  
Wearable Products ◽  
Walled Carbon Nanotubes

Wearable sensors for human physiological monitoring have attracted tremendous interest from researchers in recent years. However, most of the research was only done in simple trials without any significant analytical algorithms. This study provides a way of recognizing human motion by combining textile stretch sensors based on single-walled carbon nanotubes (SWCNTs) and spandex fabric (PET/SP) and machine learning algorithms in a realistic applications. In the study, the performance of the system will be evaluated by identification rate and accuracy of the motion standardized. This research aims to provide a realistic motion sensing wearable products without unnecessary heavy and uncomfortable electronic devices.

scholarly journals Multi-Layer Hidden Markov Model Based Intrusion Detection System

2018 ◽  
Vol 1 (1) ◽  
pp. 265-286 ◽  
Author(s):  
Wondimu Zegeye ◽  
Richard Dean ◽  
Farzad Moazzami
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov ◽  
Detection System ◽  
Traffic Monitoring ◽  
Machine Learning Algorithms ◽  
Full Potential ◽  
Multi Phase

The all IP nature of the next generation (5G) networks is going to open a lot of doors for new vulnerabilities which are going to be challenging in preventing the risk associated with them. Majority of these vulnerabilities might be impossible to detect with simple networking traffic monitoring tools. Intrusion Detection Systems (IDS) which rely on machine learning and artificial intelligence can significantly improve network defense against intruders. This technology can be trained to learn and identify uncommon patterns in massive volume of traffic and notify, using such as alert flags, system administrators for additional investigation. This paper proposes an IDS design which makes use of machine learning algorithms such as Hidden Markov Model (HMM) using a multi-layer approach. This approach has been developed and verified to resolve the common flaws in the application of HMM to IDS commonly referred as the curse of dimensionality. It factors a huge problem of immense dimensionality to a discrete set of manageable and reliable elements. The multi-layer approach can be expanded beyond 2 layers to capture multi-phase attacks over longer spans of time. A pyramid of HMMs can resolve disparate digital events and signatures across protocols and platforms to actionable information where lower layers identify discrete events (such as network scan) and higher layers new states which are the result of multi-phase events of the lower layers. The concepts of this novel approach have been developed but the full potential has not been demonstrated.

scholarly journals Deep Learning for Deep Waters: An Expert-in-the-Loop Machine Learning Framework for Marine Sciences

2021 ◽  
Vol 9 (2) ◽  
pp. 169
Author(s):  
Igor Ryazanov ◽  
Amanda T. Nylund ◽  
Debabrota Basu ◽  
Ida-Maja Hassellöv ◽  
Alexander Schliep
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Machine Learning Algorithms ◽  
Full Potential ◽  
Acoustic Data ◽  
Learning Framework ◽  
Machine Learning Methods ◽  
Deep Waters ◽  
The One ◽  
Relative Scarcity

Driven by the unprecedented availability of data, machine learning has become a pervasive and transformative technology across industry and science. Its importance to marine science has been codified as one goal of the UN Ocean Decade. While increasing amounts of, for example, acoustic marine data are collected for research and monitoring purposes, and machine learning methods can achieve automatic processing and analysis of acoustic data, they require large training datasets annotated or labelled by experts. Consequently, addressing the relative scarcity of labelled data is, besides increasing data analysis and processing capacities, one of the main thrust areas. One approach to address label scarcity is the expert-in-the-loop approach which allows analysis of limited and unbalanced data efficiently. Its advantages are demonstrated with our novel deep learning-based expert-in-the-loop framework for automatic detection of turbulent wake signatures in echo sounder data. Using machine learning algorithms, such as the one presented in this study, greatly increases the capacity to analyse large amounts of acoustic data. It would be a first step in realising the full potential of the increasing amount of acoustic data in marine sciences.

scholarly journals Accuracy of diagnostic classification algorithms using cognitive-, electrophysiological-, and neuroanatomical data in antipsychotic-naïve schizophrenia patients

2018 ◽  
Vol 49 (16) ◽  
pp. 2754-2763 ◽  
Author(s):  
Bjørn H. Ebdrup ◽  
Martin C. Axelsen ◽  
Nikolaj Bak ◽  
Birgitte Fagerlund ◽  
Bob Oranje ◽  
...  
Keyword(s):  
Machine Learning ◽  
Diagnostic Accuracy ◽  
Clinical Symptoms ◽  
Diffusion Tensor ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
First Episode ◽  
Full Potential ◽  
Symptom Remission

AbstractBackgroundA wealth of clinical studies have identified objective biomarkers, which separate schizophrenia patients from healthy controls on a group level, but current diagnostic systems solely include clinical symptoms. In this study, we investigate if machine learning algorithms on multimodal data can serve as a framework for clinical translation.MethodsForty-six antipsychotic-naïve, first-episode schizophrenia patients and 58 controls underwent neurocognitive tests, electrophysiology, and magnetic resonance imaging (MRI). Patients underwent clinical assessments before and after 6 weeks of antipsychotic monotherapy with amisulpride. Nine configurations of different supervised machine learning algorithms were applied to first estimate the unimodal diagnostic accuracy, and next to estimate the multimodal diagnostic accuracy. Finally, we explored the predictability of symptom remission.ResultsCognitive data significantly classified patients from controls (accuracies = 60–69%;pvalues = 0.0001–0.009). Accuracies of electrophysiology, structural MRI, and diffusion tensor imaging did not exceed chance level. Multimodal analyses with cognition plus any combination of one or more of the remaining three modalities did not outperform cognition alone. None of the modalities predicted symptom remission.ConclusionsIn this multivariate and multimodal study in antipsychotic-naïve patients, only cognition significantly discriminated patients from controls, and no modality appeared to predict short-term symptom remission. Overall, these findings add to the increasing call for cognition to be included in the definition of schizophrenia. To bring about the full potential of machine learning algorithms in first-episode, antipsychotic-naïve schizophrenia patients, carefula priorivariable selection based on independent data as well as inclusion of other modalities may be required.

scholarly journals A Useful Guide to Lectin Binding: Machine-Learning Directed Annotation of 57 Unique Lectin Specificities

2021 ◽  
Author(s):  
Daniel Bojar ◽  
Lawrence Meche ◽  
Guanmin Meng ◽  
William Eng ◽  
David F. Smith ◽  
...  
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Viral Infections ◽  
Lectin Binding ◽  
Machine Learning Algorithms ◽  
Full Potential ◽  
Motif Analysis ◽  
Binding Motifs ◽  
Binding Data ◽  
Detailed Interpretation

ABSTRACTGlycans are critical to every facet of biology and medicine, from viral infections to embryogenesis. Tools to study glycans are rapidly evolving, however the majority of our knowledge is deeply dependent on binding by glycan binding proteins (e.g., lectins). The specificities of lectins, which are often naturally isolated proteins, have not been well- defined, making it difficult to leverage their full potential for glycan analysis. Herein, we use glycan microarray analysis of 116 commercially available lectins, including different preparations of the same lectin, to extract the specific glycan features required for lectin binding. Data was obtained using the Consortium for Functional Glycomics microarray (CFG v5.0) containing 611 glycans. We use a combination of machine learning algorithms to define lectin specificity, mapping inputs (glycan sequences) to outputs (lectin-glycan binding) for a large-scale evaluation of lectin-glycan binding behaviours. Our motif analysis was performed by integrating 68 manually defined glycan features with systematic probing of computational rules for significant binding motifs using mono- and disaccharides- and linkages. Using a combination of machine learning and manual annotation of the data, we created a detailed interpretation of glycan-binding specificity for 57 unique lectins, categorized by their major binding motifs: mannose, complex-type N-glycan, O-glycan, fucose, sialic acid and sulfate, GlcNAc and chitin, Gal and LacNAc, and GalNAc. Our work provides fresh insights into the complex binding features of commercially available lectins in current use, providing a critical guide to these important reagents.

scholarly journals Human Motion Recognition by Textile Sensors Based on Machine Learning Algorithms

Sensors ◽  
2018 ◽  
Vol 18 (9) ◽  
pp. 3109 ◽  
Author(s):  
Chi Vu ◽  
Jooyong Kim
Keyword(s):  
Machine Learning ◽  
Wearable Sensors ◽  
Learning Algorithms ◽  
Electronic Devices ◽  
Human Motion ◽  
Machine Learning Algorithms ◽  
Identification Rate ◽  
Textile Sensors ◽  
Human Motion Recognition ◽  
Walled Carbon Nanotubes

Wearable sensors for human physiological monitoring have attracted tremendous interest from researchers in recent years. However, most of the research involved simple trials without any significant analytical algorithms. This study provides a way of recognizing human motion by combining textile stretch sensors based on single-walled carbon nanotubes (SWCNTs) and spandex fabric (PET/SP) and machine learning algorithms in a realistic application. In the study, the performance of the system will be evaluated by identification rate and accuracy of the motion standardized. This research aims to provide a realistic motion sensing wearable product without unnecessary heavy and uncomfortable electronic devices.

scholarly journals Crop Yield Prediction through Proximal Sensing and Machine Learning Algorithms

Agronomy ◽  
2020 ◽  
Vol 10 (7) ◽  
pp. 1046 ◽  
Author(s):  
Farhat Abbas ◽  
Hassan Afzaal ◽  
Aitazaz A. Farooque ◽  
Skylar Tang
Keyword(s):  
Machine Learning ◽  
Crop Yield ◽  
Precision Agriculture ◽  
Growing Season ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Full Potential ◽  
K Nearest Neighbor ◽  
Statistical Parameters ◽  
Proximal Sensing

Proximal sensing techniques can potentially survey soil and crop variables responsible for variations in crop yield. The full potential of these precision agriculture technologies may be exploited in combination with innovative methods of data processing such as machine learning (ML) algorithms for the extraction of useful information responsible for controlling crop yield. Four ML algorithms, namely linear regression (LR), elastic net (EN), k-nearest neighbor (k-NN), and support vector regression (SVR), were used to predict potato (Solanum tuberosum) tuber yield from data of soil and crop properties collected through proximal sensing. Six fields in Atlantic Canada including three fields in Prince Edward Island (PE) and three fields in New Brunswick (NB) were sampled, over two (2017 and 2018) growing seasons, for soil electrical conductivity, soil moisture content, soil slope, normalized-difference vegetative index (NDVI), and soil chemistry. Data were collected from 39–40 30 × 30 m2 locations in each field, four times throughout the growing season, and yield samples were collected manually at the end of the growing season. Four datasets, namely PE-2017, PE-2018, NB-2017, and NB-2018, were then formed by combing data points from three fields to represent the province data for the respective years. Modeling techniques were employed to generate yield predictions assessed with different statistical parameters. The SVR models outperformed all other models for NB-2017, NB-2018, PE-2017, and PE-2018 dataset with RMSE of 5.97, 4.62, 6.60, and 6.17 t/ha, respectively. The performance of k-NN remained poor in three out of four datasets, namely NB-2017, NB-2018, and PE-2017 with RMSE of 6.93, 5.23, and 6.91 t/ha, respectively. The study also showed that large datasets are required to generate useful results using either model. This information is needed for creating site-specific management zones for potatoes, which form a significant component for food security initiatives across the globe.

scholarly journals Object detection for automotive radar point clouds – a comparison

2021 ◽  
Vol 3 (1) ◽  
Author(s):  
Nicolas Scheiner ◽  
Florian Kraus ◽  
Nils Appenrodt ◽  
Jürgen Dickmann ◽  
Bernhard Sick
Keyword(s):  
Machine Learning ◽  
Object Detection ◽  
Point Clouds ◽  
Machine Learning Algorithms ◽  
Future Research ◽  
Automotive Radar ◽  
Data Set ◽  
Radar Sensors ◽  
Adverse Weather ◽  
Algorithm Comparison

AbstractAutomotive radar perception is an integral part of automated driving systems. Radar sensors benefit from their excellent robustness against adverse weather conditions such as snow, fog, or heavy rain. Despite the fact that machine-learning-based object detection is traditionally a camera-based domain, vast progress has been made for lidar sensors, and radar is also catching up. Recently, several new techniques for using machine learning algorithms towards the correct detection and classification of moving road users in automotive radar data have been introduced. However, most of them have not been compared to other methods or require next generation radar sensors which are far more advanced than current conventional automotive sensors. This article makes a thorough comparison of existing and novel radar object detection algorithms with some of the most successful candidates from the image and lidar domain. All experiments are conducted using a conventional automotive radar system. In addition to introducing all architectures, special attention is paid to the necessary point cloud preprocessing for all methods. By assessing all methods on a large and open real world data set, this evaluation provides the first representative algorithm comparison in this domain and outlines future research directions.

Sign in / Sign up

Export Citation Format

Share Document