Time Of Interest Research Articles

Decoding motor imagery tasks using ESI and hybrid feature CNN

Objective. Brain–computer interface (BCI) based on motor imaging electroencephalogram (MI-EEG) can be useful in a natural interaction system. In this paper, a new framework is proposed to solve the MI-EEG binary classification problem. Approach. Electrophysiological source imaging (ESI) technology is used to solve the influence of volume conduction effect and improve spatial resolution. Continuous wavelet transform and best time of interest (TOI) are combined to extract the optimal discriminant spatial-frequency features. Finally, a convolutional neural network with seven convolution layers is used to classify the features. In addition, we also validated several new data augment methods to solve the problem of small data sets and reduce network over-fitting. Main results. The model achieved an average classification accuracy of 93.2% and 95.4% on the BCI Competition III IVa and high-gamma data sets, which is better than most of the published advanced algorithms. By selecting the best TOI for each subject, the classification accuracy rate increased by about 2%. The effects of four data augment methods on the classification results were also verified. Among them, the noise addition and overlap methods are better than the other two, and the classification accuracy is improved by at least 4%. On the contrary, the rotation and flip data augment methods reduced the classification accuracy. Significance. Decoding MI tasks can benefit from combing the ESI technology and the data augment technology, which is used to solve the problem of low spatial resolution and small samples of EEG signals, respectively. Based on the results, the model proposed has higher accuracy and application potential in the task of MI-EEG binary classification.

Simulation-based training to enhance process safety in offshore energy operations: Process tracing through eye-tracking

Systemic risks and human errors are the root causes of process safety incidents in offshore operations. Human factor amounts for more than 70 % of offshore incidents and among those 75 % of them are due to perceptual errors involving rich information displays. Offshore drilling console is one such area where a display of hundreds of parameters and alarms maintains a constant cognitive load on the driller and upon his slight oblivion, severe consequences can follow. One way to study these errors is through a cognitive approach that focuses on the information accusation patterns rather than a behaviorist approach of focusing on the decision outcomes. In this research, we attempt to apply process tracing through eye-tracking methodology to look at information acquisition patterns of participants during a well control simulation. The simulation was designed on a commercial well control drilling simulator to observe the difference in performances by tracking information acquisition patterns of expert and novice participants. Fourteen (n=14) participants were paired into eight teams with each comprising of a driller and a supervisor. Eye-tracking glasses were used to record the fixation and saccade pattern of the participants over the simulator console and displays. For the analysis phase, four time of interests (TOIs) were selected as drilling break detection, kick detection, kick control, and kick circulation. For these TOIs the fixation and saccades pattern of participants on various areas of interest (AOIs) were analyzed through heat and gaze plots. Significant differences in information acquisition patterns of the novice and expert participants were linked to their performance to reveal valuable insights. Such insights are useful in identifying the dominating factors behind performance and can be used for targeted feedback to improve well control training and evaluation.

Large-scale assessment of Prophet for multi-step ahead forecasting of monthly streamflow

Abstract. We assess the performance of the recently introduced Prophet model in multi-step ahead forecasting of monthly streamflow by using a large dataset. Our aim is to compare the results derived through two different approaches. The first approach uses past information about the time series to be forecasted only (standard approach), while the second approach uses exogenous predictor variables alongside with the use of the endogenous ones. The additional information used in the fitting and forecasting processes includes monthly precipitation and/or temperature time series, and their forecasts respectively. Specifically, the exploited exogenous (observed or forecasted) information considered at each time step exclusively concerns the time of interest. The algorithms based on the Prophet model are in total four. Their forecasts are also compared with those obtained using two classical algorithms and two benchmarks. The comparison is performed in terms of four metrics. The findings suggest that the compared approaches are equally useful.

Spatio-temporal similarity of network-constrained moving object trajectories using sequence alignment of travel locations

Data analysis based on the similarity of vehicle trajectories in a vehicular network is emerging as a new exciting paradigm that is important for law enforcement applications (e.g., the analysis of criminal tracking, road traffic security and traffic scheduling). Spatio-temporal data analysis plays an important role in many applications, including transportation infrastructure, border security and inland security. To analyze the moving patterns of vehicles on a road network, a measure for determining the similarity of vehicle trajectories with respect to space and time has to be defined. Although previous research has addressed the trajectory similarity problem, most of the studies focus on Euclidian distance instead of network distance. This paper deals with the variations in applying a spatio-temporal similarity measure with given Points of Interest (POI) and Time of Interest (TOI), treating spatial similarity as a combination of structural and sequence similarities that is evaluated using the techniques of dynamic programming. The similarity set thus formed will be used by the remote database to broadcast trigger-based messages to participating vehicles in a neighborhood for future route- and information-sharing activities. The performance of the scheme is evaluated using experiments on standard real-life data.

Assessment of Skin Microvascular Function and Dysfunction With Laser Speckle Contrast Imaging

In recent years, skin microcirculation has been considered an easily accessible and potentially representative vascular bed to evaluate and understand the mechanisms of microvascular function and dysfunction.1–3 Vascular dysfunction (including impaired endothelium-dependent vasodilation) induced by different pathologies is evident in the cutaneous circulation.4–7 It has been suggested that the skin microcirculation may mirror generalized systemic vascular dysfunction in magnitude and underlying mechanisms.1 Furthermore, minimally invasive skin-specific methodologies using laser systems make the cutaneous circulation a useful translational model for investigating mechanisms of skin physiology and skin pathophysiology induced either by skin disease itself or by other diseases such as vascular, rheumatologic, and pneumologic. To date, the skin has been used as a circulation model to investigate vascular mechanisms in a variety of diseased states, including hypercholesterolemia,8 Alzheimer disease,9 carpal tunnel syndrome,10 schizophrenia,11 hypertension,6 renal disease,12 type 2 diabetes,13 peripheral vascular disease,14 atherosclerotic coronary artery disease,2 heart failure,15 systemic sclerosis,16 obesity,17 primary aging,18,19 and sleep apnea.20 Assessment of skin microvascular function can be done by both invasive and noninvasive techniques. Among noninvasive techniques, laser systems are mainly used.21 The recent development of the laser speckle contrast imaging (LSCI) technique for monitoring skin microvascular function enables its use as a surrogate end point in clinical trials. LSCI allows for noncontact, real-time, and noninvasive monitoring of cutaneous blood flow changes.22,23 Recent evidence has shown that the LSCI technique dramatically reduces the variability of clinical measurements compared with laser Doppler flowmetry (LDF), making the technique a fascinating tool to facilitate microvascular studies in clinical routine.23,24 In this review, we describe …

A NOTE ON FRANCIS DAY'S "THE FISHES OF GREAT BRITAIN AND IRELAND"

Between 1880 and 1884 Francis Day (1829-1889) published his monumental work on British fishes. It is a book which represents the fruits of a life time's interest in fishes, at first in India where Day was successively Deputy SurgeonGeneral of the Madras Army and Inspector General of Fisheries in India, and after his retirement to Cheltenham, in England. As a text book for the naturalist interested in British fishes it is still without peer, although with the passage of time much of the nomenclature has changed, and there have been many additions to this fauna. Its present utility, however, can be judged by the scarcity of copies offered for sale and the price they command. It might be noted in passing that Day personally drew all the one hundred and seventy-nine plates (some containing several figures), in itself a formidable task for a man not trained as an artist. Many of his plates have been paid the compliment (sometimes unacknowledged) of use in later books on British fishes and marine life. The reason Day acted as his own artist is mentioned briefly in his preface to the work; his usual artist Mr. Mintern being already committed to illustrate a publication on the same subject by Dr. A. Gunther, who was not prepared to release him for work on Day's book. Most authors in citing this work for bibliographic purposes give the publication date as 1880-1884, thus following the title pages which were, of course, issued with the last part of the work. In fact, the volumes were issued in eight parts during those four years, and although no question of nomenclatural priority arises with this work (which contains no new scientific name) it seems worth while to record the year of publication of each part if only to avoid the usual cumbersome citation of dates. The source of these dates is the contemporary issues of The Zoological Record.