This paper proposes a new performance evaluation process for time-frequency distributions (TFD) by designing a reference optimal TFD and novel accuracy and resolution measures. The motivation comes from the need for a TFD performance evaluation method that is objective, capable of quantifying the TFD accuracy and resolution, can determine the performance difference among different TFDs, and suitable for signals with an arbitrary number of components, instantaneous frequency and amplitude. We formulate the proposed optimal TFD, namely the piece-wise spline Wigner-Ville distribution (PW-WVD), by decomposing a standard non-stationary signal model using piece-wise linear frequency modulated (LFM) basis and by exploiting the Wigner-Ville distribution optimality for LFM signals. We compare the designed PW-WVD to conventional optimal TFDs and show that the former is more suitable to serve as a reference for TFD performance evaluation. Using the PW-WVD we derive TFD accuracy and resolution measures, compare them to conventional approaches, and analyze their sensitivity to form a TFD selection criteria. We evaluate the accuracy and resolution of twelve different TFDs and develop precise TFD selection strategies with or without prior information on the signal parameters. Results indicate that the compact kernel distribution is the best performing TFD given no prior information on the signal parameters and different TFDs must be selected upon the availability of prior information.
Modern technology has pushed us into the information age, making it easier to generate and record vast quantities of new data. Datasets can help in analyzing the situation to give a better understanding, and more importantly, decision making. Consequently, datasets, and uses to which they can be put, have become increasingly valuable commodities. This article describes the DroneRF dataset: a radio frequency (RF) based dataset of drones functioning in different modes, including off, on and connected, hovering, flying, and video recording. The dataset contains recordings of RF activities, composed of 227 recorded segments collected from 3 different drones, as well as recordings of background RF activities with no drones. The data has been collected by RF receivers that intercepts the drone's communications with the flight control module. The receivers are connected to two laptops, via PCIe cables, that runs a program responsible for fetching, processing and storing the sensed RF data in a database. An example of how this dataset can be interpreted and used can be found in the related research article "RF-based drone detection and identification using deep learning approaches: an initiative towards a large open source drone database" (Al-Sa'd et al., 2019).
The accurate prediction of neurodevelopmental outcomes of newborns suffering from hypoxic–ischemic cerebral injury during childbirth is vital to assist clinicians to correctly plan the newborn care and help enhance the newborn's quality of life and reduce the social and financial costs. For newborns at high risk of prenatal brain injury, the multichannel electroencephalogram (EEG) is a valuable non-invasive screening, diagnostic, and monitoring tool. However, advances have been hampered by the amount of data and their complexity, the dependence on labor, and expertise-intensive manual processes involved in identifying and interpreting EEGs. A realistic way for dealing effectively with the big data formed by this vast amount of information is an intelligent knowledge-based computerized real-time system. The study reported in this chapter aims at minimizing the social and financial costs via early detection of brain disorders by extracting relevant patterns from the big data, therefore reducing the dimensionality of the problem and then automatically detecting newborn EEG features that best predict neurodevelopmental outcomes. This is achieved by developing high-resolution time–frequency (TF) techniques for EEG pre-processing, artefact detection/removal algorithms, and machine learning techniques. This study exploits the additional information provided by the nonstationarities of newborn EEG signals observed in the (t, f) plane and develops novel techniques for analyzing multichannel newborn EEG signals. Specifically, for the pre-processing of newborn EEG signals, this study proposes (1) a set of TF features for newborn EEG artefact detection and (2) a TF matched filtering technique and a TF blind source separation method for artefact removal. Finally, for the classification of newborn EEG abnormalities, classifiers based on support vector machines are designed that use TF features extracted from time–frequency representations of the multichannel EEG signals. The overall developed system can be implemented in a standalone EEG device or included as an add-on to existing medical devices. The research study described in this chapter provides a solution to the need for objective and automated detection and classification of newborn EEG abnormalities potentially resulting in a significant clinical impact.
The higher brain functions arise from coordinated neural activity between distinct brain regions, but the spatial, temporal, and spectral complexity of these functional connectivity networks (FCNs) has challenged the identification of correlates with neurobehavioral phenotypes. Characterizing behavioral correlates of early life FCNs is important to understand the activity dependent emergence of neurodevelopmental performance and for improving health outcomes. Here, we develop an analysis pipeline for identifying multiplex dynamic FCNs that combine spectral and spatiotemporal characteristics of the newborn cortical activity. This data-driven approach automatically uncovers latent networks that show robust neurobehavioral correlations and consistent effects by in utero drug exposure. Altogether, the proposed pipeline provides a robust end-to-end solution for an objective assessment and quantitation of neurobehaviorally meaningful network constellations in the highly dynamic cortical functions.
لمراقبة ورصد أنشطة واشارات المخ، دون الحاجة لأي عملیات (EEG) یستخدم الرسم أو التخطیط الكھربائي للدماغ
للدماغجراحیة، وھي تعد الأداة الأكثر استخداما في الكشف عن أي شذوذأو نوبات غیر طبیعیة مثل نوبات الصرع. وقد أظھرت دراسات حدیثة، أن الكشف الآلي لنوبات حدیثي الولادة، ساعد علماء الفسیولوجیا العصبیة في تشخیص الاشارات الدماغیة بشكل أكبر من الكشف الیدوي، حیث أن الكشف الیدوي یحتاج إلى وقت وجھد أكبر وھوذو فعالیة أقل بكثیر، إلا أنھ لا یزال یفتقر إلى المتانة الضروریة والمطلوبة للتطبیق السریري.علاوة على ذلك؛ فكما یقوم الرسم الكھربائي بتسجیل الأنشطة والإشارات الدماغیة الداخلیة، فھو یسجل أیضا أي نشاط أو اشارات خارجیة، مما یؤدي إلى -(artifacts) :حدوث خلل في مدى دقة وفعالیة الكشف عن النوبات الدماغیة الداخلیة، ویطلق على تلك الاشارات مسمى (نتاج صنعي) . 0.5٪ولادة حدیثة في -٪تعد نوبات الصرع من أكثر المشكلات العصبیة انتشارا، وھي تصیب ما یقارب 0.1المستشفیات. حیث أن حدیثي الولادة المصابین بنوبات الصرع ھم أكثر عرضة للوفاة، وكما تشیر التقاریر الى أنھم 70مرة أكثر. لذا یعد الكشف المبكر والدقیق للنوبات الدماغیة -معرضین للإصابة بالشلل الدماغي الشدید بما یقارب 55لحدیثي الولادة مھم جدا لمنع الضرر العصبي على المدى الطویل. لقد تم القیام بالعدید من المحاولات التي كانتتھدف الى تصمیم نموذج التخطیط الكھربائي والنتاج الصنعي لدماغ حدیثي الولادة, إلا أن معظمھا لم یعر أي اھتمام الى قضیة تعدد القنوات. إضافة الى ذلك, استخدمت ھذه النماذج , كل على حدة, أو نوبات الصرع. تھدف ھذه الدراسة الى تصمیم نماذج مصطنعة من شأنھا (artifact) لإختبار كاشفات النتاج الصنعيأن تولد اشارات دماغیة متعددة القنوات سلیمة أو معطلة وذلك لفحص مدى دقة فعالیة خوارزمیات الكشف عن نوبات ضمن بیئة یمكن السیطرة علیھا. (artifact) الصرع و النتاج الصنعي في ھذه الأطروحة, یتكون نموذج الرسم الكھربائي المصطنع لحدیثي الولادة من : قناة محاكاة واحده للرسم الكھربائي, نموذج رأس, 21قطب كھربائي و معادلات إنتشار. حیث تھدف جمیعھا لإنتاج إشاراة سلیمة متعدده القنوات للتخطیط عن طریق استخدام اشارات مصطنعة (artifact) الكھربائي للدماغ.علاوة على ذلك, لقد تم تصمیم نموذجالنتاج الصنعيفي نطاقالوقت و (artifact) لإتلاف الرسم الكھربائي للدماغ. بعد ذلك تم انشاء برنامج لكشف و إزالةالنتاج الصناعينطاقالوقت و التردد المشترك. تم تحسین برنامج الكشف النتاج الصناعيالى ابعد ما یمكن بینما تمت عملیة تقییم أداء الإزالة. وفي الختام تم التمكن من تطویر تقنیة الكشف الآلي عن نوبات الصرع, وذلك بتوظیف صفات مدمجة و صفات الذي تم التأكد من صحتھ. (SVM) جدیدة للقنوات المتعددة لإستخدامھا للمصنفلقد أظھرت النتائج أن نموذج الرسم الكھربائي المصطنع لحدیثي الولادة یحاكي الرسمالكھربائي الحقیقي لحدیثي الولادة بمتوسط ترابط 0.62, و أنالرسم الكھربائي المتضرر للدماغ قد یؤدي الى حدوث ھبوطفي مدى دقة متوسط الكشف عن نوبات الصرع من 100%الى 70.9%. وقد أشارت أیضا الى أن استخدام الكشف والإزالة عن النتاج الصنعي (artifact) یؤدي الى تحسن مستوى الدقة الى نسبة 89.6 %, وأن توظیف الصفات الجدیدة للقنوات المتعددة یزید من
تحسنھا لتصل الى نسبة 94.4 % مما یعمل على دعم متانتھا.
The health and safety hazards posed by worn crane lifting ropes mandate periodic inspection for damage. This task is time-consuming, prone to human error, halts operation, and may result in the premature disposal of ropes. Therefore, we propose using deep learning and computer vision methods to automate the process of detecting damaged ropes. Specifically, we present a novel vision-based system for detecting damage in synthetic fiber rope images using convolutional neural networks (CNN). We use a camera-based apparatus to photograph the lifting rope's surface, while in operation, and capture the progressive wear-and-tear as well as the more significant degradation in the rope's health state. Experts from Konecranes annotate the collected images in accordance with the rope's condition; normal or damaged. Then, we pre-process the images, design a CNN model in a systematic manner, evaluate its detection and prediction performance, analyze its computational complexity, and compare it with various other models. Experimental results show the proposed model outperforms other techniques with 96.4% accuracy, 95.8% precision, 97.2% recall, 96.5% F1-score, and 99.2% AUC. Besides, they demonstrate the model's real-time operation, low memory footprint, robustness to various environmental and operational conditions, and adequacy for deployment in industrial systems.
Social distancing is crucial to restrain the spread of diseases such as COVID-19, but complete adherence to safety guidelines is not guaranteed. Monitoring social distancing through mass surveillance is paramount to develop appropriate mitigation plans and exit strategies. Nevertheless, it is a labor-intensive task that is prone to human error and tainted with plausible breaches of privacy. This paper presents a privacy-preserving adaptive social distance estimation and crowd monitoring solution for camera surveillance systems. We develop a novel person localization strategy through pose estimation, build a privacy-preserving adaptive smoothing and tracking model to mitigate occlusions and noisy/missing measurements, compute inter-personal distances in the real-world coordinates, detect social distance infractions, and identify overcrowded regions in a scene. Performance evaluation is carried out by testing the system's ability in person detection, localization, density estimation, anomaly recognition, and high-risk areas identification. We compare the proposed system to the latest techniques and examine the performance gain delivered by the localization and smoothing/tracking algorithms. Experimental results indicate a considerable improvement, across different metrics, when utilizing the developed system. In addition, they show its potential and functionality for applications other than social distancing.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
