Variation In Position Research Articles

Predicting cognitive decline in a low‐dimensional representation of brain morphology

AbstractBackgroundIdentifying early signs of neurodegeneration due to Alzheimer’s disease (AD) is a necessary first step towards preventing cognitive decline. Individual cortical thickness measures, available after processing anatomical magnetic resonance imaging (MRI), are sensitive markers of neurodegeneration. However, cortical decline in aging and high inter‐individual variability complicates the determination of AD‐related neurodegeneration on trajectories. Further, the high‐dimensional nature of these trajectories necessitate the use of a transformation into lower‐dimensional spaces in order to perform comparative statistical analyses, model decline, and identify criteria differentiating pathological from normal trajectories.MethodIn this project, we computed trajectories in a 2D representation of a 62‐dimensional manifold of individual cortical thickness measures. To compute this representation, we used a nonlinear dimension reduction algorithm called Uniform Manifold Approximation and Projection (UMAP). We first created a UMAP embedding on measurements from 6,237 cognitively healthy participants (3,556 women) aged 18 to 100 years old from the NOMIS database. We then projected longitudinal data from 537 mild cognitively impaired (MCI) subjects and 340 AD subjects from ADNI into this embedding. Each participant had multiple visits (n = 2), one year apart. Finally, differences in trajectories were analysed by clustering the reduced data and comparing the positional variations through time between MCI and AD subjects. The validity of the approach was verified through cross‐validation.ResultFirst, the embedding was shown to be positively associated (r = 0.65) with participants' age (see figure 1) in the NOMIS data. When projected in this space, differences between ADNI’s MCI and AD distributions were found (see figure 2). Average trajectories between clusters were shown to be significantly different between MCI and AD subjects (see figure 3). Moreover, we showed that some clusters and trajectories between clusters were more prone to host AD subjects. Finally, cross‐validation showed an accuracy of up to 72% at predicting cognitive decline in MCI participants over 2,000 bootstrap iterations.ConclusionA 2D low‐dimensional cortical thickness representation embeds sufficient discriminatory information as to predict decline to AD in MCI participants with strong accuracy.

Multi-data-driven model-based control to improve the accuracy of overhang structures in laser powder bed fusion

The additive manufacturing process of laser powder bed fusion (LPBF) has gained significant attention due to its potential to fabricate complex structures. In this paper, we propose an open-loop multi-data-driven model-based control (MMC) architecture to improve the accuracy and quality of overhang structures fabricated through LPBF. Overhang structures are particularly challenging due to thermal and structural complexities. Traditional methods often require support structures, which can increase costs and reduce efficiency. Our MMC architecture integrates data-driven models with real-time monitoring using photodiode measurements. The proposed MMC architecture consists of energy density modeling, infrared correction, and reference voltage modeling. The energy density model is established for both solid substrates and overhang structures to optimize laser power, while the infrared correction model compensates for measurement errors caused by melt pool position variations. The reference voltage model enables real-time process monitoring. Experimental results demonstrate the effectiveness of the proposed MMC architecture in producing high-quality overhang structures without the need for support materials. The architecture offers a significant advancement in LPBF process control by reducing 49.9% of residual material of overhang structures, enabling the fabrication of intricate geometries with improved accuracy and efficiency.

Predicting cognitive decline in a low‐dimensional representation of brain morphology

AbstractBackgroundIdentifying early signs of neurodegeneration due to Alzheimer’s disease (AD) is a necessary first step towards preventing cognitive decline. Individual cortical thickness measures, available after processing anatomical magnetic resonance imaging (MRI), are sensitive markers of neurodegeneration. However, cortical decline in aging and high inter‐individual variability complicates the determination of AD‐related neurodegeneration on trajectories. Further, the high‐dimensional nature of these trajectories necessitate the use of a transformation into lower‐dimensional spaces in order to perform comparative statistical analyses, model decline, and identify criteria differentiating pathological from normal trajectories.MethodIn this project, we computed trajectories in a 2D representation of a 62‐dimensional manifold of individual cortical thickness measures. To compute this representation, we used a nonlinear dimension reduction algorithm called Uniform Manifold Approximation and Projection (UMAP). We first created a UMAP embedding on measurements from 6,237 cognitively healthy participants (3,556 women) aged 18 to 100 years old from the NOMIS database. We then projected longitudinal data from 537 mild cognitively impaired (MCI) subjects and 340 AD subjects from ADNI into this embedding. Each participant had multiple visits (n ≥ 2), one year apart. Finally, differences in trajectories were analysed by clustering the reduced data and comparing the positional variations through time between MCI and AD subjects. The validity of the approach was verified through cross‐validation.ResultFirst, the embedding was shown to be positively associated (r = 0.65) with participants' age (see figure 1) in the NOMIS data. When projected in this space, differences between ADNI’s MCI and AD distributions were found (see figure 2). Average trajectories between clusters were shown to be significantly different between MCI and AD subjects (see figure 3). Moreover, we showed that some clusters and trajectories between clusters were more prone to host AD subjects. Finally, cross‐validation showed an accuracy of up to 72% at predicting cognitive decline in MCI participants over 2,000 bootstrap iterations.ConclusionA 2D low‐dimensional cortical thickness representation embeds sufficient discriminatory information as to predict decline to AD in MCI participants with strong accuracy.

EEG electrode localization with 3D iPhone scanning using point-cloud electrode selection (PC-ES)

Objective. Electroencephalography source imaging (ESI) is a valuable tool in clinical evaluation for epilepsy patients but is underutilized in part due to sensitivity to anatomical modeling errors. Accurate localization of scalp electrodes is instrumental to ESI, but existing localization devices are expensive and not portable. As a result, electrode localization challenges further impede access to ESI, particularly in inpatient and intensive care settings. Approach. To address this challenge, we present a portable and affordable electrode digitization method using the 3D scanning feature in modern iPhone models. This technique combines iPhone scanning with semi-automated image processing using point-cloud electrode selection (PC-ES), a custom MATLAB desktop application. We compare iPhone electrode localization to state-of-the-art photogrammetry technology in a human study with over 6000 electrodes labeled using each method. We also characterize the performance of PC-ES with respect to head location and examine the relative impact of different algorithm parameters. Main Results. The median electrode position variation across reviewers was 1.50 mm for PC-ES scanning and 0.53 mm for photogrammetry, and the average median distance between PC-ES and photogrammetry electrodes was 3.4 mm. These metrics demonstrate comparable performance of iPhone/PC-ES scanning to currently available technology and sufficient accuracy for ESI. Significance. Low cost, portable electrode localization using iPhone scanning removes barriers to ESI in inpatient, outpatient, and remote care settings. While PC-ES has current limitations in user bias and processing time, we anticipate these will improve with software automation techniques as well as future developments in iPhone 3D scanning technology.

Slope position controls prescribed fire effects on soil: a case study in the high-elevation grassland of Itatiaia National Park

ABSTRACT There is a need for greater knowledge about the medium- and long-term effects of prescribed fire management on soil in ecosystems prone to wildfires and more vulnerable to climate change. This study examined the short- and medium-term effects of prescribed fire on soil chemical properties and chemical fractions of soil organic matter (SOM) in two positions of the landscape in a high-elevation grassland environment. The ecosystem is located in the mountain peaks of southeastern Brazil associated with the Atlantic Forest biome. Prescribed fire was conducted in 2017 to reduce understory vegetation and thus prevent potential severe wildfires. Soil samples were collected at the layers of 0.00-0.10, 0.10-0.20, and 0.20-0.40 m, at eight composite sampling. The composite samples were collected on five different occasions: before the prescribed fire, and 10, 30, 90, and 240 days after the prescribed fire. Soil chemical properties, total organic carbon, labile C, and chemical fractionation of SOM were analyzed. All soil properties investigated were affected by the prescribed fire, with variations in landscape position, duration of effect, and soil layer. In the backslope area, the medium-term effect of fire was negative and induced soil degradation and induced soil degradation. In the footslope area, the system showed greater resilience to the effects of fire, as indicated by the recovery of the soil’s chemical properties. These results can help assess the suitability of controlled burning of vegetation for managing risks of fire in mountainous regions, such as high-elevation grasslands.

Anatomical Variations of the Greater Palatine Foramen in Different Facial Skeletal Relationships and its Implications on LeFort 1 Osteotomy (Trimble's Modification).

To determine the positional variations of the greater palatine foramen in different facial skeletal relationships and discuss its surgical implications on the Trimble's modification of Lefort I osteotomy. This retrospective study examined 50 computed tomography scans of patients a total of 100 sides. The sample was divided into four groups: Class 1, Class 2, Class 3 malocclusion and Unilateral cleft lip and palate). The outcome variables included the distance between anterior, middle and posterior points of the GPF to the distal of second molar and variables to assess relative position of the GPF to the posterior maxilla. Outcome measures were to demonstrate intra- and intergroup variability. Fifty patients (100 sides) were divided into four groups. This included 23 males and 27 females with a mean age of 24.1years. Significant intergroup variability was observed between all the parameters that demonstrate the relative position of the GPF to (i) the maxillary second molar and (ii) the posterior maxilla. The analysis revealed that the GPF was positioned significantly anterior in Class 2 patients when compared with Class 3 patients. The GPF exhibits significant positional variability in different facial skeletal relationships which should be borne in mind while designing and performing the Trimble's modification of the Lefort 1 osteotomy.

Effect of body position on ventilation distribution in healthy newborn infants: an observational study

ObjectivesNewborn infants have unique respiratory physiology compared with older children and adults due to their lungs’ structural and functional immaturity and highly compliant chest wall. To date, ventilation distribution has...

Variations of the Femoral Artery Position in Relation to Femoral Vein and Mid-inguinal Point: A Cadaveric Study

Introduction: Femoral artery is one of the major arteries in human body. It is more preference for catheterization in some medical procedures. This study was designed to identify anatomical variations of the femoral artery position, in relation to femoral vein and mid-inguinal point of human cadavers. Methods: Dissection was performed on 22 cadavers. The associations were analyzed using Fisher’s Exact test and correlation test. Results: There was superolateral positioning detected. Distal traversing was only observed on the left thigh. Bivariate analysis showed that there was a significant association of distance from anterior superior iliac spine (ASIS) to femoral artery between the right and left thigh. However, there was no significant association of distance from mid-inguinal point (MIP) to femoral artery between the right and left thigh, position of femoral artery to MIP between the right and left thigh and distance of traversing point between the right and left thigh. Conclusion: This study showed that distance from ASIS to mid-point of femoral artery was significantly associated with the left-right sided of cadavers, while distance from MIP to femoral artery, position of femoral artery to MIP and distance of traversing point were not significantly associated with the left-right sided of cadavers. These informations may help in diagnostic cardiac catheterization procedures and coronary interventions.

Niche overlap between sympatric cichlid species of the genus Rocio (Cichliformes: Cichlidae) in Guatemala

AbstractRocio is a small genus of Neotropical freshwater fishes that is distributed in Atlantic drainages of northern Middle America. Two species of Rocio, R. spinosissima and R. octofasciata, exhibit sympatry in the Río Dulce basin in eastern Guatemala. Rocio spinosissima is endemic to the Río Dulce basin, while R. octofasciata has a larger geographic range that includes this area. Our goal was to explore the ecological and morphological variation shown by these two closely related species and determine their differences. A combination of field work, analysis of museum specimens, and ecological niche modelling helped to better understand the differences in habitat and environmental characteristics, along with the body shape variation. Local‐scale environmental data suggest that both species inhabit lentic environments, with R. spinosissima using narrower and low canopy‐covered habitats and R. octofasciata inhabiting areas with a larger range of environmental characteristics. Ecological Niche Models indicated that land cover, soil, precipitation, and temperature largely define the distribution of both species. Body shape differs between species, with R. spinosissima exhibiting a rounder and deeper body while R. octofasciata is more elongated. Specimens of R. octofasciata across its distribution also show variation in head shape, mouth position, fin, and caudal peduncle characteristics, possibly as a response to trophic strategies that reduce competition. Similarities in their environments and morphologies allow us to identify broadly overlapping niches in the two species of Rocio, while the fine scale differences documented between species will have conservation implications for the endemic R. spinosissima.

Trophic Structure and a Temporal Shift in Trophic Diversity of Mobile Consumers in a Subarctic Estuary

Quantifying trophic relationships within and between species in terms of trophic position, ontogeny and trophic diversity provides information on community-level structure and function. Little attention has been focused on examining the trophic structure and temporal changes of communities in freshwater-marine coupled systems in the subarctic and associated impacts of anthropogenic activity on trophic interactions. Therefore, the objective of this study was to quantify the trophic position of mobile consumers (15 species in total) within the lower Churchill River area (Churchill, Manitoba, Canada), examine trophic position variation in relation to ontogeny, and measure the trophic diversity of a fish assemblage before (1993–1995) and after (2019–2020) the installation of the Churchill River weir in the late 1990s. We used stable isotopes (δ13C and δ15N) to quantify individual and group-level variation in trophic position of thirteen fish species and two seal species and also assessed six community-level metrics of a three fish species assemblage between time periods. Overall, species that mainly foraged on freshwater resources occupied lower trophic positions than species that mainly consumed marine resources. Trophic position increased with fish age only in cisco, fourhorn sculpin, Greenland cod and northern pike. A temporal shift from a trophically diverse to a more trophically redundant fish assemblage occurred between 1993–1995 and 2019–2020. As a result, these predator species now play similar trophic roles. Information on the long-term change in trophic structure of this sub-Arctic estuarine system may help with understanding how anthropogenic activity and climate change have influenced the trophic diversity of a fish assemblage inhabiting this system.

A Review on the Impacts of Toposequence on Soil Properties

This study demonstrates the significant influence of toposequence position on soil properties and hydrological conditions, affecting crop yield. Variations in toposequence position lead to differences in soil properties; physical and chemical properties may vary minimally or maximally depending on the slope’s location. As slope increases, soil moisture and organic carbon rise, while bulk density, pH, and soil temperature decrease. Soils along a toposequence reveal that landscape position, erosion, aspect, and drainage impact soil depth, particle size distribution, and CEC. Understanding topography’s influence on soil characteristics is crucial for evaluating soil productivity and devising conservation strategies. This knowledge is essential for assessing soil value and avoiding uneven input distribution in agricultural fields on diverse terrains. This review paper summarizes the impacts of toposequence on soil physical and chemical properties. The study utilized databases such as Google Scholar, African Journals Online (AJOL), Scopus, Web of Science, ScienceDirect, and Directory of Open Access Journals (DOAJ) to identify relevant studies.

Abstract 13784: Impact of the Variation of Aortomitral Positional Anatomy for the Atrioventricular Conduction Disorder in the Mitral Valve Surgery

Introduction: Advances in cardiac imaging have provided detailed anatomical information, including the variation of the aortic root rotation. This variation affected the distance between membranous septum and right fibrous trigone, that might be synonymous with variation of the conduction system location. However, clinical significance has been unknown. We aimed to analyze the variation of the aorto-mitral position and its relationship of conduction disorder in the mitral valve surgery. Methods: This study included 180 patients underwent simple mitral valve surgery (valve repair: n=159, replacement: n=21). The anatomical variations were classified by preoperative three-dimensional transesophageal echocardiography (3D-TEE), and postoperative occurrence of new conduction disorder was analyzed. Results: As in the image, the variations in the aorto-mitral position were classified into Lateral (14%) or Center appearance (86%) groups, which was further classified to Center (83%), Lateral (14%), or Medial rotation (3%) groups. Atrioventricular conduction disorder was observed as first-degree block (n=24 (13%)) including complete right bundle branch block (n=1 (0.6%)). This disorder newly occurred more in the Lateral appearance compared to the Center (36% vs 10%, p=0.0003). The prolongation of the PR interval (msec) between the pre and postoperative period (ΔPR) was greater in the Lateral appearance than the Center (+17 vs +14, p=0.02). Regarding the aortic root rotation, the conduction disorder occurred in 6%, 27% and 20% patients, and each ΔPR was +2, +16 and +22 of the Center , Lateral , and Medial rotation respectively. Conduction disorder occurred more in the Lateral rotation than the Center (p=0.0017), persisting one year after the surgery (19% vs 2%, p=0.0059). Conclusion: The variation of the aorto-mitral position could be classified by 3D-TEE. The Lateral rotation would be a risk of atrioventricular conduction disorder in the mitral valve surgery.

What do brain endocasts tell us? A comparative analysis of the accuracy of sulcal identification by experts and perspectives in palaeoanthropology.

Palaeoneurology is a complex field as the object of study, the brain, does not fossilize. Studies rely therefore on the (brain) endocranial cast (often named endocast), the only available and reliable proxy for brain shape, size and details of surface. However, researchers debate whether or not specific marks found on endocasts correspond reliably to particular sulci and/or gyri of the brain that were imprinted in the braincase. The aim of this study is to measure the accuracy of sulcal identification through an experiment that reproduces the conditions that palaeoneurologists face when working with hominin endocasts. We asked 14 experts to manually identify well-known foldings in a proxy endocast that was obtained from an MRI of an actual invivo Homo sapiens head. We observe clear differences in the results when comparing the non-corrected labels (the original labels proposed by each expert) with the corrected labels. This result illustrates that trying to reconstruct a sulcus following the very general known shape/position in the literature or from a mean specimen may induce a bias when looking at an endocast and trying to follow the marks observed there. We also observe that the identification of sulci appears to be better in the lower part of the endocast compared to the upper part. The results concerning specific anatomical traits have implications for highly debated topics in palaeoanthropology. Endocranial description of fossil specimens should in the future consider the variation in position and shape of sulci in addition to using models of mean brain shape. Moreover, it is clear from this study that researchers can perceive sulcal imprints with reasonably high accuracy, but their correct identification and labelling remains a challenge, particularly when dealing with extinct species for which we lack direct knowledge of the brain.

Radio Refractivity Impact on Signal Strength of Mobile Communication

This research investigated radio refractivity impact on signal strength of mobile communication. The mobile communication signal strengths of two popular networks in Nigeria, 9Mobile and MTN, were considered. In the 2100 MHz-3 G band, 9Mobile transmits in the downlink spectrum of 2130.00–2140.00 MHz, while MTN transmits in the downlink spectrum of 2110.00–2120.00 MHz. Also, 9Mobile transmits in the downlink spectrum of 791–821 MHz in the 800 MHz band and 1805–1880 MHz in the 1800 MHz, while MTN transmits in the downlink spectrums of 2620–2690 MHz in the 2600 MHz band; all in the 4 G band. Using the instrument of a mobile station in each station (location) in some selected cities in southern Nigeria, the signal strengths were measured. A cell signal monitor (version 5.1.1) mobile application installed in an Android (transceiver) device (having two SIM slots) constituted the mobile station. To achieve high accuracy, there was a restriction in measuring transmission from specific cells. Hourly measurement of signal strengths was carried out and instantaneously corresponding weather parameters were recorded. Weather parameters for this investigation; atmospheric temperature and pressure; and relative humidity were excerpted online from the Nigeria Meteorological Agency (NIMET) hourly weather report for the various cities where the stations were situated. The hourly radio refractivity was computed using the 2015 International Telecommunication Union–Radio-communication sector (ITU-R) recommended model. Overall, the results indicate that there was no established linear relationship between signal strength and radio refractivity since the overall average R value is 0.0123691 and the overall average standard deviation of R values is 0.1112165. The inconsistencies in the linear relationships obtained from different locations and cells could be due to variations in topography, antenna properties, seasonal variations, wind and position, and distance of the receiver from the transmitter.

Reinforcement Learning With Stereo-View Observation for Robust Electronic Component Robotic Insertion

In modern manufacturing, assembly tasks are a major challenge for robotics. In the manufacturing industry, a wide range of insertion tasks can be found, from peg-in-hole insertion to electronic parts assembly. Robotic stations designed for this problem often use conventional hybrid force-position control to perform preprogrammed trajectories, such as e.g. a spiral path. However, electronic parts require more sophisticated techniques due to their complex geometry and susceptibility to damage. Production line assembly tasks require high robustness to initial position and rotation variations due to component grip imperfections. Robustness to partially obscured camera view is also mandatory due to multi stage assembly process. We propose a stereo-view method based on reinforcement learning (RL) for the robust assembly of electronic parts. Applicability of our method to real-world production lines is verified through test scenarios. Our approach is the most robust to applied perturbations of all tested methods and can potentially be transferred to environments unseen during learning.

Robustness of hypofractionated breast radiotherapy after breast-conserving surgery with free breathing.

This study aimed to evaluate the robustness with respect to the positional variations of five planning strategies in free-breathing breast hypofractionated radiotherapy (HFRT) for patients after breast-conserving surgery. Twenty patients who received breast HFRT with 42.72 Gy in 16 fractions were retrospectively analyzed. Five treatment planning strategies were utilized for each patient, including 1) intensity-modulated radiation therapy (IMRT) planning (IMRTpure); 2) IMRT planning with skin flash tool extending and filling the fluence outside the skin by 2cm (IMRTflash); 3) IMRT planning with planning target volume (PTV) extended outside the skin by 2cm in the computed tomography dataset (IMRTePTV); 4) hybrid planning, i.e., 2 Gy/fraction three-dimensional conformal radiation therapy combined with 0.67 Gy/fraction IMRT (IMRThybrid); and 5) hybrid planning with skin flash (IMRThybrid-flash). All plans were normalized to 95% PTV receiving 100% of the prescription dose. Six additional plans were created with different isocenter shifts for each plan, which were 1mm, 2mm, 3mm, 5mm, 7mm, and 10mm distally in the X (left-right) and Y (anterior-posterior) directions, namely, (X,Y), to assess their robustness, and the corresponding doses were recalculated. Variation of dosimetric parameters with increasing isocenter shift was evaluated. All plans were clinically acceptable. In terms of robustness to isocenter shifts, the five planning strategies followed the pattern IMRTePTV, IMRThybrid-flash, IMRTflash, IMRThybrid, and IMRTpure in descending order. V 95% of IMRTePTV maintained at 99.6% ± 0.3% with a (5,5) shift, which further reduced to 98.2% ± 2.0% with a (10,10) shift. IMRThybrid-flash yielded the robustness second to IMRTePTV with less risk from dose hotspots, and the corresponding V 95% maintained >95% up until (5,5). Considering the dosimetric distribution and robustness in breast radiotherapy, IMRTePTV performed best at maintaining high target coverage with increasing isocenter shift, while IMRThybrid-flash would be adequate with positional uncertainty<5mm.

Short‐circuit current difference of parallel strands in winding turns and its influence on the distribution of electromagnetic force

AbstractTransformer winding turns often consist of multiple parallel strands. The spatial position variation of each strand affects the leakage inductance of each branch, resulting in an uneven distribution of short‐circuit currents within the winding turns. And this unevenness persists even when transposition structures are implemented. Traditional methods in transformer analysis frequently overlooked the distribution characteristics of short‐circuit currents when calculating electromagnetic forces. A frequency‐domain calculation method for analysing the current distribution in winding turns was proposed, with a deviation of less than 3% compared to existing analysis methods. Two typical 110 kV transformer models were utilised to investigate the influence of uneven current distribution on the spatial distribution of electromagnetic forces. The spatial distribution of short‐circuit electromagnetic forces in low‐voltage (LV) windings exhibited significant changes, with maximum change rates of 10% and 61.2% for axial and radial electromagnetic force, respectively, in a LV winding with 4 parallel strands. The research also analysed how strand radial width and axial height affect current distribution unevenness and proposed specific design principles to mitigate these disparities in winding design. The findings offer valuable insights for selecting structural parameters and assessing short‐circuit stability during transformer design.

Manipulation of surface plasmon polariton fields excitation at quantum-size slit in a dielectric and graphene interface

The dispersion relation of surface plasmon polaritons is controlled and modified at the interface of atomic and Graphene medium. The beats patterns and moire fringes spacing are modified from vectorial character of the waves and parameters of the driving fields coupled with system energy levels. The beats patterns are investigated with the influence of control fields and its parameters. It is reported that the phase shifts Φ1,2 are the strong functions of the probe detuning and distance x along the interface. The light and surface plasmon polariton waves polarization is a strong oscillation function of both the position and time variation as well as driving fields parameters. The maximum value of phase sensitivity SΦ1 is 600 and SΦ2 is 400 radian per unit change of refractive index of the atomic medium at x=20λ. This work is particularly useful for surface plasmon resonance sensors technology.

Characteristic performance and analysis of the positional variation of the charge generation layer to enhance the performance of OLEDs

Characteristic performance and analysis of the positional variation of the charge generation layer to enhance the performance of OLEDs

Online cross session electromyographic hand gesture recognition using deep learning and transfer learning

In recent years, hand gesture recognition in human-computer interfaces is usually based on surface electromyography because the signals are non-intrusive and are not affected by the variations of light, position, and orientation of the hand. Deep learning algorithms have become increasingly more prominent in gesture recognition for the ability to automatically learn features from large amounts of data. However, delicate and complicated network structures brought by deep learning, which are elaborately designed for cross session tasks, need more computing time to be trained and tested, which can hardly be applied to the online system. In this study, an online electromyographic hand gesture recognition method using deep learning and transfer learning is proposed. The deep learning model includes a feature extractor, a label classifier, and a gesture predictor. The feature extractor is based on the temporal convolutional network, which is designed to learn high-level discriminant features from the input signals. The label classifier includes three fully connected layers, designed to classify hand gesture labels using the feature vector which is produced by the feature extractor. The gesture predictor uses a threshold voting algorithm to predict the gesture, used at the stage of testing to perform the online recognition. Transfer learning technique is used to transfer model parameters from one pre-trained model, which costs less time and can be applied for online applications. The proposed model is verified on both the Myo dataset and the public NinaPro database. The proposed transfer learning scheme is shown to systematically and significantly enhance the performance of the proposed model on the two datasets, only using no more than three sessions to retrain the label predictor can achieve the accuracy of more than 90% of that obtained though the normal training of the whole parts of the model using full training sessions.