To see the other types of publications on this topic, follow the link: Encodage joint.
Journal articles on the topic 'Encodage joint'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Encodage joint.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Wu, Jiahua, and Hyo-Jong Lee. "A New Multi-Person Pose Estimation Method Using the Partitioned CenterPose Network." Applied Sciences 11, no. 9 (May 7, 2021): 4241. http://dx.doi.org/10.3390/app11094241.
Full textAbstract:
In bottom-up multi-person pose estimation, grouping joint candidates into the appropriately structured corresponding instance of a person is challenging. In this paper, a new bottom-up method, the Partitioned CenterPose (PCP) Network, is proposed to better cluster the detected joints. To achieve this goal, we propose a novel approach called Partition Pose Representation (PPR) which integrates the instance of a person and its body joints based on joint offset. PPR leverages information about the center of the human body and the offsets between that center point and the positions of the body’s joints to encode human poses accurately. To enhance the relationships between body joints, we divide the human body into five parts, and then, we generate a sub-PPR for each part. Based on this PPR, the PCP Network can detect people and their body joints simultaneously, then group all body joints according to joint offset. Moreover, an improved l1 loss is designed to more accurately measure joint offset. Using the COCO keypoints and CrowdPose datasets for testing, it was found that the performance of the proposed method is on par with that of existing state-of-the-art bottom-up methods in terms of accuracy and speed.
2
Vlutters, Mark, Edwin H. F. van Asseldonk, and Herman van der Kooij. "Ankle muscle responses during perturbed walking with blocked ankle joints." Journal of Neurophysiology 121, no. 5 (May 1, 2019): 1711–17. http://dx.doi.org/10.1152/jn.00752.2018.
Full textAbstract:
The ankle joint muscles can contribute to balance during walking by modulating the center of pressure and ground reaction forces through an ankle moment. This is especially effective in the sagittal plane through ankle plantar- or dorsiflexion. If the ankle joints were to be physically blocked to make an ankle strategy ineffective, there would be no functional contribution of these muscles to balance during walking, nor would these muscles generate afferent output regarding ankle joint rotation. Consequently, ankle muscle activation for the purpose of balance control would be expected to disappear. We have performed an experiment in which subjects received anteroposterior pelvis perturbations during walking while their ankle joints could not contribute to the balance recovery. The latter was realized by physically blocking the ankle joints through a pair of modified ankle-foot orthoses. In this article we present the lower limb muscle activity responses in reaction to these perturbations. Of particular interest are the tibialis anterior and gastrocnemius medialis muscles, which could not contribute to the balance recovery through the ankle joint or encode muscle length changes caused by ankle joint rotation. Yet, these muscles showed long-latency responses, ~100 ms after perturbation onset. The response amplitudes were dependent on the perturbation magnitude and direction, as well as the state of the leg. The results imply that ankle muscle responses can be evoked without changes in proprioceptive information of those muscles through ankle rotation. This suggest a more centralized regulation of balance control, not strictly related to the ankle joint kinematics. NEW & NOTEWORTHY Walking human subjects received forward-backward perturbations at the pelvis while wearing “pin-shoes,” a pair of modified ankle-foot orthoses that physically blocked ankle joint movement and reduced the base of support of each foot to a single point. The lower leg muscles showed long-latency perturbation-dependent activity changes, despite having no functional contributions to balance control through the ankle joint and not having been subjected to muscle length changes through ankle joint rotation.
3
Wen, Yu-Hui, Lin Gao, Hongbo Fu, Fang-Lue Zhang, and Shihong Xia. "Graph CNNs with Motif and Variable Temporal Block for Skeleton-Based Action Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 8989–96. http://dx.doi.org/10.1609/aaai.v33i01.33018989.
Full textAbstract:
Hierarchical structure and different semantic roles of joints in human skeleton convey important information for action recognition. Conventional graph convolution methods for modeling skeleton structure consider only physically connected neighbors of each joint, and the joints of the same type, thus failing to capture highorder information. In this work, we propose a novel model with motif-based graph convolution to encode hierarchical spatial structure, and a variable temporal dense block to exploit local temporal information over different ranges of human skeleton sequences. Moreover, we employ a non-local block to capture global dependencies of temporal domain in an attention mechanism. Our model achieves improvements over the stateof-the-art methods on two large-scale datasets.
4
Bosco, G., R. E. Poppele, and J. Eian. "Reference Frames for Spinal Proprioception: Limb Endpoint Based or Joint-Level Based?" Journal of Neurophysiology 83, no. 5 (May 1, 2000): 2931–45. http://dx.doi.org/10.1152/jn.2000.83.5.2931.
Full textAbstract:
Many sensorimotor neurons in the CNS encode global parameters of limb movement and posture rather than specific muscle or joint parameters. Our investigations of spinocerebellar activity have demonstrated that these second-order spinal neurons also may encode proprioceptive information in a limb-based rather than joint-based reference frame. However, our finding that each foot position was determined by a unique combination of joint angles in the passive limb made it difficult to distinguish unequivocally between a limb-based and a joint-based representation. In this study, we decoupled foot position from limb geometry by applying mechanical constraints to individual hindlimb joints in anesthetized cats. We quantified the effect of the joint constraints on limb geometry by analyzing joint-angle covariance in the free and constrained conditions. One type of constraint, a rigid constraint of the knee angle, both changed the covariance pattern and significantly reduced the strength of joint-angle covariance. The other type, an elastic constraint of the ankle angle, changed only the covariance pattern and not its overall strength. We studied the effect of these constraints on the activity in 70 dorsal spinocerebellar tract (DSCT) neurons using a multivariate regression model, with limb axis length and orientation as predictors of neuronal activity. This model also included an experimental condition indicator variable that allowed significant intercept or slope changes in the relationships between foot position parameters and neuronal activity to be determined across conditions. The result of this analysis was that the spatial tuning of 37/70 neurons (53%) was unaffected by the constraints, suggesting that they were somehow able to signal foot position independently from the specific joint angles. We also investigated the extent to which cell activity represented individual joint angles by means of a regression model based on a linear combination of joint angles. A backward elimination of the insignificant predictors determined the set of independent joint angles that best described the neuronal activity for each experimental condition. Finally, by comparing the results of these two approaches, we could determine whether a DSCT neuron represented foot position, specific joint angles, or none of these variables consistently. We found that 10/70 neurons (14%) represented one or more specific joint-angles. The activity of another 27 neurons (39%) was significantly affected by limb geometry changes, but 33 neurons (47%) consistently elaborated a foot position representation in the coordinates of the limb axis.
5
Day, James, Leah R. Bent, Ingvars Birznieks, Vaughan G. Macefield, and Andrew G. Cresswell. "Muscle spindles in human tibialis anterior encode muscle fascicle length changes." Journal of Neurophysiology 117, no. 4 (April 1, 2017): 1489–98. http://dx.doi.org/10.1152/jn.00374.2016.
Full textAbstract:
Muscle spindles provide exquisitely sensitive proprioceptive information regarding joint position and movement. Through passively driven length changes in the muscle-tendon unit (MTU), muscle spindles detect joint rotations because of their in-parallel mechanical linkage to muscle fascicles. In human microneurography studies, muscle fascicles are assumed to follow the MTU and, as such, fascicle length is not measured in such studies. However, under certain mechanical conditions, compliant structures can act to decouple the fascicles, and, therefore, the spindles, from the MTU. Such decoupling may reduce the fidelity by which muscle spindles encode joint position and movement. The aim of the present study was to measure, for the first time, both the changes in firing of single muscle spindle afferents and changes in muscle fascicle length in vivo from the tibialis anterior muscle (TA) during passive rotations about the ankle. Unitary recordings were made from 15 muscle spindle afferents supplying TA via a microelectrode inserted into the common peroneal nerve. Ultrasonography was used to measure the length of an individual fascicle of TA. We saw a strong correlation between fascicle length and firing rate during passive ankle rotations of varying rates (0.1–0.5 Hz) and amplitudes (1–9°). In particular, we saw responses observed at relatively small changes in muscle length that highlight the sensitivity of the TA muscle to small length changes. This study is the first to measure spindle firing and fascicle dynamics in vivo and provides an experimental basis for further understanding the link between fascicle length, MTU length, and spindle firing patterns. NEW & NOTEWORTHY Muscle spindles are exquisitely sensitive to changes in muscle length, but recordings from human muscle spindle afferents are usually correlated with joint angle rather than muscle fascicle length. In this study, we monitored both muscle fascicle length and spindle firing from the human tibialis anterior muscle in vivo. Our findings are the first to measure these signals in vivo and provide an experimental basis for exploring this link further.
6
Zhang, Fenghao, Lin Zhao, Shengling Li, Wanjuan Su, Liman Liu, and Wenbing Tao. "3D hand pose and shape estimation from monocular RGB via efficient 2D cues." Computational Visual Media 10, no. 1 (February 2023): 79–96. http://dx.doi.org/10.1007/s41095-023-0346-4.
Full textAbstract:
AbstractEstimating 3D hand shape from a single-view RGB image is important for many applications. However, the diversity of hand shapes and postures, depth ambiguity, and occlusion may result in pose errors and noisy hand meshes. Making full use of 2D cues such as 2D pose can effectively improve the quality of 3D human hand shape estimation. In this paper, we use 2D joint heatmaps to obtain spatial details for robust pose estimation. We also introduce a depth-independent 2D mesh to avoid depth ambiguity in mesh regression for efficient hand-image alignment. Our method has four cascaded stages: 2D cue extraction, pose feature encoding, initial reconstruction, and reconstruction refinement. Specifically, we first encode the image to determine semantic features during 2D cue extraction; this is also used to predict hand joints and for segmentation. Then, during the pose feature encoding stage, we use a hand joints encoder to learn spatial information from the joint heatmaps. Next, a coarse 3D hand mesh and 2D mesh are obtained in the initial reconstruction step; a mesh squeeze-and-excitation block is used to fuse different hand features to enhance perception of 3D hand structures. Finally, a global mesh refinement stage learns non-local relations between vertices of the hand mesh from the predicted 2D mesh, to predict an offset hand mesh to fine-tune the reconstruction results. Quantitative and qualitative results on the FreiHAND benchmark dataset demonstrate that our approach achieves state-of-the-art performance.
7
Zill, S. N. "Plasticity and proprioception in insects. I. Responses and cellular properties of individual receptors of the locust metathoracic femoral chordotonal organ." Journal of Experimental Biology 116, no. 1 (May 1, 1985): 435–61. http://dx.doi.org/10.1242/jeb.116.1.435.
Full textAbstract:
The metathoracic femoral chordotonal organ is a joint angle receptor of the locust hindleg. It consists of 45–55 bipolar sensory neurones located distally in the femur and mechanically coupled to the tibia. Responses of receptors of the organ were examined by extracellular and intracellular recording. The organ as a whole encodes the angle of the femorotibial joint but shows substantial hysteresis. Tonic activity is greatest at the extremes of joint position. The organ possesses no direct linkage to tibial muscle fibres and shows no response to resisted muscle contractions in most ranges of joint angle. However, responses to extensor muscle contractions are obtained when the tibia is held in full flexion due to specializations of the femoro-tibial joint. These responses could be of importance in signalling preparedness for a jump. Intracellular soma recordings of activity in individual receptors indicate that the organ contains two types of receptors: phasic units that respond to joint movement and tonic units that encode joint position and also show some response to movement. All units are directionally sensitive and respond only in limited ranges of joint angle. Some phasic units increase firing frequency with increasing rate of movement and thus encode joint velocity. Other phasic units fire only single action potentials and can encode only the occurrence and direction of joint movement. All tonic units increase activity in the extremes of joint position and show substantial hysteresis upon return to more median positions. Direct soma depolarization produces different responses in different types of units: phasic receptors show only transient discharges to current injection; tonic receptors exhibit sustained increases in activity that are followed by periods of inhibition of background firing upon cessation of current injection. Receptors of the chordotonal organ are separable into two major groups, based upon their response characteristics, soma location and dendritic orientation: a dorsal group of receptors contains tonic units that respond in ranges of joint flexion (joint angle 0–80 degrees) and phasic units that respond to flexion movements; a ventral group of sensilla contains tonic units active in ranges of joint extension (joint angle 80–170 degrees) and phasic receptors that respond to extension movements. The response properties of these receptors are discussed with reference to the potential functions of the chordotonal organ in the locust's behavioural repertoire.
8
Ajemian, Robert, Daniel Bullock, and Stephen Grossberg. "Kinematic Coordinates In Which Motor Cortical Cells Encode Movement Direction." Journal of Neurophysiology 84, no. 5 (November 1, 2000): 2191–203. http://dx.doi.org/10.1152/jn.2000.84.5.2191.
Full textAbstract:
During goal-directed reaching in primates, a sensorimotor transformation generates a dynamical pattern of muscle activation. Within the context of this sensorimotor transformation, a fundamental question concerns the coordinate systems in which individual cells in the primary motor cortex (MI) encode movement direction. This article develops a mathematical framework that computes, as a function of the coordinate system in which an individual cell is hypothesized to operate, the spatial preferred direction (pd) of that cell as the arm configuration and hand location vary. Three coordinate systems are explicitly modeled: Cartesian spatial, shoulder-centered, and joint angle. The computed patterns of spatial pds are distinct for each of these three coordinate systems, and experimental approaches are described that can capitalize on these differences to compare the empirical adequacy of each coordinate hypothesis. One particular experiment involving curved motion was analyzed from this perspective. Out of the three coordinate systems tested, the assumption of joint angle coordinates best explained the observed cellular response properties. The mathematical framework developed in this paper can also be used to design new experiments that are capable of disambiguating between a given set of specified coordinate hypotheses.
9
Xu, Guoyan, Qirui Zhang, Du Yu, Sijun Lu, and Yuwei Lu. "JKRL: Joint Knowledge Representation Learning of Text Description and Knowledge Graph." Symmetry 15, no. 5 (May 10, 2023): 1056. http://dx.doi.org/10.3390/sym15051056.
Full textAbstract:
The purpose of knowledge representation learning is to learn the vector representation of research objects projected by a matrix in low-dimensional vector space and explore the relationship between embedded objects in low-dimensional space. However, most methods only consider the triple structure in the knowledge graph and ignore the additional information related to the triple, especially the text description information. In this paper, we propose a knowledge graph representation model with a symmetric architecture called Joint Knowledge Representation Learning of Text Description and Knowledge Graph (JKRL), which models the entity description and relationship description of the triple structure for joint representation learning of knowledge and balances the contribution of the triple structure and text description in the process of vector learning. First, we adopt the TransE model to learn the structural vector representations of entities and relations, and then use a CNN model to encode the entity description to obtain the text representation of the entity. To semantically encode the relation descriptions, we designed an Attention-Bi-LSTM text encoder, which introduces an attention mechanism into the Bi-LSTM model to calculate the semantic relevance between each word in the sentence and different relations. In addition, we also introduce position features into word features in order to better encode word order information. Finally, we define a joint evaluation function to learn the joint representation of structural and textual representations. The experiments show that compared with the baseline methods, our model achieves the best performance on both Mean Rank and Hits@10 metrics. The accuracy of the triple classification task on the FB15K dataset reached 93.2%.
10
BRINGMANN, KATHRIN. "CONGRUENCES FOR DYSON'S RANKS." International Journal of Number Theory 05, no. 04 (June 2009): 573–84. http://dx.doi.org/10.1142/s1793042109002262.
Full textAbstract:
In this paper, we prove infinite families of congruences for coefficients of harmonic Maass forms whose coefficients encode Dyson's rank. This generalizes the earlier joint work of the author with Ken Ono.
11
Okada, J., and Y. Toh. "Peripheral representation of antennal orientation by the scapal hair plate of the cockroach Periplaneta americana." Journal of Experimental Biology 204, no. 24 (December 15, 2001): 4301–9. http://dx.doi.org/10.1242/jeb.204.24.4301.
Full textAbstract:
SUMMARY Arthropods have hair plates that are clusters of mechanosensitive hairs, usually positioned close to joints, which function as proprioceptors for joint movement. We investigated how angular movements of the antenna of the cockroach (Periplaneta americana) are coded by antennal hair plates. A particular hair plate on the basal segment of the antenna, the scapal hair plate, can be divided into three subgroups: dorsal, lateral and medial. The dorsal group is adapted to encode the vertical component of antennal direction, while the lateral and medial groups are specialized for encoding the horizontal component. Of the three subgroups of hair sensilla, those of the lateral scapal hair plate may provide the most reliable information about the horizontal position of the antenna, irrespective of its vertical position. Extracellular recordings from representative sensilla of each scapal hair plate subgroup revealed the form of the single-unit impulses in response to hair deflection. The mechanoreceptors were characterized as typically phasic-tonic. The tonic discharge was sustained indefinitely (>20 min) as long as the hair was kept deflected. The spike frequency in the transient (dynamic) phase was both velocity- and displacement-dependent, while that in the sustained (steady) phase was displacement-dependent.
12
Nan, Jiang, Xiao Xinglei, Liu Shanglun, Chen Guoqing, and Chen Hongwei. "Mechano Growth Factor E Peptide Improves Degenerative Meniscus by Promoting the Proliferation and Migration of Meniscus Cells." Current Topics in Nutraceutical Research 22, no. 2 (February 20, 2024): 716–22. http://dx.doi.org/10.37290/ctnr2641-452x.22:716-722.
Full textAbstract:
This study aimed to examine the effect of the Mechano growth factor E peptide on meniscus repair, which is critical for restoring knee joint function. Meniscal cells harvested from the inner and outer regions of knee joints from patients with osteoarthritis were subjected to Mechano growth factor E peptide treatment to investigate alterations in cell morphology and their effect on cell colony formation. The effect of Mechano growth factor E peptide treatment on cell migration was evaluated using a transwell system, while polymerase chain reaction was utilized to assess the effect of Mechano growth factor E peptide treatment on the mRNA expression level of COL1A1 or COL2A1, which encode for key collagen types. The reparative effect of the Mechano growth factor E peptide on the meniscus was evaluated using a rabbit meniscal defect model and complemented with hematoxylin and eosin staining. We found that Mechano growth factor E peptide administration augments meniscal cell proliferation, migration, and collagen synthesis, thereby enhancing in vivo meniscus repair. This study examined the capacity of the Mechano growth factor E peptide to ameliorate meniscal injury by promoting meniscal cell proliferation and migration.
13
Gunti, Nethra, Sathyanarayanan Ramamoorthy, Parth Patwa, and Amitava Das. "Memotion Analysis through the Lens of Joint Embedding (Student Abstract)." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 11 (June 28, 2022): 12959–60. http://dx.doi.org/10.1609/aaai.v36i11.21616.
Full textAbstract:
Joint embedding (JE) is a way to encode multi-modal data into a vector space where text remains as the grounding key and other modalities like image are to be anchored with such keys. Meme is typically an image with embedded text onto it. Although, memes are commonly used for fun, they could also be used to spread hate and fake information. That along with its growing ubiquity over several social platforms has caused automatic analysis of memes to become a widespread topic of research. In this paper, we report our initial experiments on Memotion Analysis problem through joint embeddings. Results are marginally yielding SOTA.
14
Durrett, Greg, and Dan Klein. "A Joint Model for Entity Analysis: Coreference, Typing, and Linking." Transactions of the Association for Computational Linguistics 2 (December 2014): 477–90. http://dx.doi.org/10.1162/tacl_a_00197.
Full textAbstract:
We present a joint model of three core tasks in the entity analysis stack: coreference resolution (within-document clustering), named entity recognition (coarse semantic typing), and entity linking (matching to Wikipedia entities). Our model is formally a structured conditional random field. Unary factors encode local features from strong baselines for each task. We then add binary and ternary factors to capture cross-task interactions, such as the constraint that coreferent mentions have the same semantic type. On the ACE 2005 and OntoNotes datasets, we achieve state-of-the-art results for all three tasks. Moreover, joint modeling improves performance on each task over strong independent baselines.
15
Bosco, G., A. Rankin, and R. Poppele. "Representation of passive hindlimb postures in cat spinocerebellar activity." Journal of Neurophysiology 76, no. 2 (August 1, 1996): 715–26. http://dx.doi.org/10.1152/jn.1996.76.2.715.
Full textAbstract:
1. We report here about the modulation of dorsal spinocerebellar tract (DSCT) activity by limb posture. In principle, DSCT activity could represent limb position in one of several ways. According to a classical notion of DSCT function, DSCT activity might be expected to correlate with changes in individual joint angles. However, given the evidence for extensive polysynaptic convergence onto DSCT units, it is reasonable to propose that DSCT activity represents more global variables such as the orientation of limb segments or the length and orientation of the whole limb. 2. In six anesthetized cats we recorded the activity of 96 antidromically identified DSCT neurons while a robot arm passively positioned the left hindfoot in 20 positions distributed in the sagittal plane, holding each position for 8 s. For each position we measured the joint angles, limb segment angles, and the length and orientation of the limb axis (defined as the line connecting the hip joint to the hindpaw). We used regression statistics to quantify 1) possible relationships among geometric variables of the hindlimb and 2) relationships between DSCT firing rate and limb variables. 3. First, we found a statistically significant relationship among the joint angles that could be described by a covariance plane accounting for approximately 70 percent of the total variance. Thus the 3 degrees of freedom represented by the joint angles in the sagittal plane are effectively reduced to only 2 by the coupling between joints. This finding resembles that described for the behaving cat during stance. However, the correlation between the hip and ankle angles in the passively displaced hindlimb was just the opposite of that observed during active stance. Moreover, we observed that the length and the orientation of the limb axis is determined simply by a linear combination of the three joint angles. 4. Most of the DSCT neurons (82 of 96) were significantly modulated by changes in foot position (1-way analysis of variance, P < 0.001). For those cells, we explored systematically how their activity was related to limb geometric variables. We found mostly linear relationships between individual joint or limb segments angles and DSCT firing rates. However, although these relationships were statistically significant, the random variance was often quite high. Moreover, approximately 70% of the cells were modulated by more than one joint or limb segment angle, suggesting that a model incorporating global geometric variables might explain a larger fraction of the variance in the neural data. 5. Consequently we tested how well DSCT activity was modulated by the length and the orientation of the limb axis with the use of a linear regression model with length and orientation (or the equivalent linear combination of joint angles) as predictors. We found that this model explained a larger fraction of the variability in the firing pattern of nearly every modulated cell than did any of the single joint models tested. 6. We also attempted to account for the effect of the mechanical joint covariance on this result by accounting for correlated independent variables in the analysis. We used a regression model incorporating all three joint or limb segment angles and performed a backward elimination of insignificant or redundant variables. The result was that 67% of the neurons were independently modulated by at least two joint angles, indicating that the modulation did not necessarily reflect the biomechanical constraint of joint angle covariation, but rather a central convergence of sensory information from more than a single joint. 7. From these results we conclude that the firing rates of a majority of DSCT neurons encode the position of the hindfoot relative to the hip joint.(ABSTRACT TRUNCATED)
16
Hartman, A. B., C. P. Mallett, S. Sheriff, and S. J. Smith-Gill. "Unusual joining sites in the H and L chains of an anti-lysozyme antibody." Journal of Immunology 141, no. 3 (August 1, 1988): 932–36. http://dx.doi.org/10.4049/jimmunol.141.3.932.
Full textAbstract:
Abstract Nucleotide sequences of HyHEL-5, an antibody specific for chicken lysozyme (HEL), indicated unusual joins in the third complementarity-determining region of both the H and L chains. The VK-JK recombination site is unusual in that codon 96, normally derived from the JK gene segment, is deleted entirely, making the L3 one amino acid shorter than normal. Examination of the HyHEL-5 Fab-HEL x-ray structure suggests that the conformation of L3 is clearly important for Ag specificity. A comparison of the HyHEL-5 L3 with that of the structurally related antibody J539 indicates that the deleted residue significantly alters the conformation of the L3 turn. The H chain VH-DH join is also unusual; the VH junction site has probably occurred between the second and third nucleotides of codon 92, with the addition of five random nucleotides that encode for unusual amino acids Leu93 and His94. Although the conformation of H3 is different from what would be predicted from other H3 conformations and is clearly important to the complementarity of HyHEL-5 to HEL, the specific residues at the VH-DH join do not appear to directly contribute to Ag binding. It is not possible to attribute the main chain conformation of H3 to the particular sequence produced by the join; the structural features of H3 may be due to interactions with HEL and/or with other antibody residues.
17
Liu, Chen, Feng Li, Xian Sun, and Hongzhe Han. "Attention-Based Joint Entity Linking with Entity Embedding." Information 10, no. 2 (February 1, 2019): 46. http://dx.doi.org/10.3390/info10020046.
Full textAbstract:
Entity linking (also called entity disambiguation) aims to map the mentions in a given document to their corresponding entities in a target knowledge base. In order to build a high-quality entity linking system, efforts are made in three parts: Encoding of the entity, encoding of the mention context, and modeling the coherence among mentions. For the encoding of entity, we use long short term memory (LSTM) and a convolutional neural network (CNN) to encode the entity context and entity description, respectively. Then, we design a function to combine all the different entity information aspects, in order to generate unified, dense entity embeddings. For the encoding of mention context, unlike standard attention mechanisms which can only capture important individual words, we introduce a novel, attention mechanism-based LSTM model, which can effectively capture the important text spans around a given mention with a conditional random field (CRF) layer. In addition, we take the coherence among mentions into consideration with a Forward-Backward Algorithm, which is less time-consuming than previous methods. Our experimental results show that our model obtains a competitive, or even better, performance than state-of-the-art models across different datasets.
18
de Rooy, Diederik P. C., Roula Tsonaka, Maria L. E. Andersson, Kristina Forslind, Alexandra Zhernakova, Mojca Frank-Bertoncelj, Caroline G. F. de Kovel, et al. "Genetic Factors for the Severity of ACPA-negative Rheumatoid Arthritis in 2 Cohorts of Early Disease: A Genome-wide Study." Journal of Rheumatology 42, no. 8 (June 15, 2015): 1383–91. http://dx.doi.org/10.3899/jrheum.140741.
Full textAbstract:
Objective.Rheumatoid arthritis (RA) that is negative for anticitrullinated protein antibodies (ACPA) is a subentity of RA, characterized by less severe disease. At the individual level, however, considerable differences in the severity of joint destruction occur. We performed a study on genetic factors underlying the differences in joint destruction in ACPA-negative patients.Methods.A genome-wide association study was done with 262 ACPA-negative patients with early RA included in the Leiden Early Arthritis Clinic and related to radiographic joint destruction over 7 years. Significant single-nucleotide polymorphisms (SNP) were evaluated for association with progression of radiographic joint destruction in 253 ACPA-negative patients with early RA included in the Better Anti-Rheumatic Farmaco Therapy (BARFOT) study. According to the Bonferroni correction of the number of tested SNP, the threshold for significance was p < 2 × 10−7 in phase 1 and 0.0045 in phase 2. In both cohorts, joint destruction was measured by Sharp/van der Heijde method with good reproducibility.Results.Thirty-three SNP associated with severity of joint destruction (p < 2 × 10−7) in phase 1. In phase 2, rs2833522 (p = 0.0049) showed borderline significance. A combined analysis of both the Leiden and BARFOT datasets of rs2833522 confirmed this association with joint destruction (p = 3.57 × 10−9); the minor allele (A) associated with more severe damage (for instance, after 7 yrs followup, patients carrying AA had 1.22 times more joint damage compared to patients carrying AG and 1.50 times more joint damage than patients carrying GG). In silico analysis using the ENCODE and Ensembl databases showed presence of H3K4me3 histone mark, transcription factors, and long noncoding RNA in the region of rs2833522, an intergenic SNP located between HUNK and SCAF4.Conclusion.Rs2833522 might be associated with the severity of joint destruction in ACPA-negative RA.
19
Gu, Junhua, Chuanxin Lan, Wenbai Chen, and Hu Han. "Joint Pedestrian and Body Part Detection via Semantic Relationship Learning." Applied Sciences 9, no. 4 (February 21, 2019): 752. http://dx.doi.org/10.3390/app9040752.
Full textAbstract:
While remarkable progress has been made to pedestrian detection in recent years, robust pedestrian detection in the wild e.g., under surveillance scenarios with occlusions, remains a challenging problem. In this paper, we present a novel approach for joint pedestrian and body part detection via semantic relationship learning under unconstrained scenarios. Specifically, we propose a Body Part Indexed Feature (BPIF) representation to encode the semantic relationship between individual body parts (i.e., head, head-shoulder, upper body, and whole body) and highlight per body part features, providing robustness against partial occlusions to the whole body. We also propose an Adaptive Joint Non-Maximum Suppression (AJ-NMS) to replace the original NMS algorithm widely used in object detection, leading to higher precision and recall for detecting overlapped pedestrians. Experimental results on the public-domain CUHK-SYSU Person Search Dataset show that the proposed approach outperforms the state-of-the-art methods for joint pedestrian and body part detection in the wild.
20
Xie, Zhongwei, Ling Liu, Yanzhao Wu, Luo Zhong, and Lin Li. "Learning Text-image Joint Embedding for Efficient Cross-modal Retrieval with Deep Feature Engineering." ACM Transactions on Information Systems 40, no. 4 (October 31, 2022): 1–27. http://dx.doi.org/10.1145/3490519.
Full textAbstract:
This article introduces a two-phase deep feature engineering framework for efficient learning of semantics enhanced joint embedding, which clearly separates the deep feature engineering in data preprocessing from training the text-image joint embedding model. We use the Recipe1M dataset for the technical description and empirical validation. In preprocessing, we perform deep feature engineering by combining deep feature engineering with semantic context features derived from raw text-image input data. We leverage LSTM to identify key terms, deep NLP models from the BERT family, TextRank, or TF-IDF to produce ranking scores for key terms before generating the vector representation for each key term by using Word2vec. We leverage Wide ResNet50 and Word2vec to extract and encode the image category semantics of food images to help semantic alignment of the learned recipe and image embeddings in the joint latent space. In joint embedding learning, we perform deep feature engineering by optimizing the batch-hard triplet loss function with soft-margin and double negative sampling, taking into account also the category-based alignment loss and discriminator-based alignment loss. Extensive experiments demonstrate that our SEJE approach with deep feature engineering significantly outperforms the state-of-the-art approaches.
21
Chen, Yan, Vitaliy Marchenko, and Robert F. Rogers. "Joint Probability-Based Neuronal Spike Train Classification." Computational and Mathematical Methods in Medicine 10, no. 3 (2009): 229–39. http://dx.doi.org/10.1080/17486700802448615.
Full textAbstract:
Neuronal spike trains are used by the nervous system to encode and transmit information. Euclidean distance-based methods (EDBMs) have been applied to quantify the similarity between temporally-discretized spike trains and model responses. In this study, using the same discretization procedure, we developed and applied a joint probability-based method (JPBM) to classify individual spike trains of slowly adapting pulmonary stretch receptors (SARs). The activity of individual SARs was recorded in anaesthetized, paralysed adult male rabbits, which were artificially-ventilated at constant rate and one of three different volumes. Two-thirds of the responses to the 600 stimuli presented at each volume were used to construct three response models (one for each stimulus volume) consisting of a series of time bins, each with spike probabilities. The remaining one-third of the responses where used as test responses to be classified into one of the three model responses. This was done by computing the joint probability of observing the same series of events (spikes or no spikes, dictated by the test response) in a given model and determining which probability of the three was highest. The JPBM generally produced better classification accuracy than the EDBM, and both performed well above chance. Both methods were similarly affected by variations in discretization parameters, response epoch duration, and two different response alignment strategies. Increasing bin widths increased classification accuracy, which also improved with increased observation time, but primarily during periods of increasing lung inflation. Thus, the JPBM is a simple and effective method performing spike train classification.
22
Pynadath, D. V., and M. Tambe. "The Communicative Multiagent Team Decision Problem: Analyzing Teamwork Theories and Models." Journal of Artificial Intelligence Research 16 (June 1, 2002): 389–423. http://dx.doi.org/10.1613/jair.1024.
Full textAbstract:
Despite the significant progress in multiagent teamwork, existing research does not address the optimality of its prescriptions nor the complexity of the teamwork problem. Without a characterization of the optimality-complexity tradeoffs, it is impossible to determine whether the assumptions and approximations made by a particular theory gain enough efficiency to justify the losses in overall performance. To provide a tool for use by multiagent researchers in evaluating this tradeoff, we present a unified framework, the COMmunicative Multiagent Team Decision Problem (COM-MTDP). The COM-MTDP model combines and extends existing multiagent theories, such as decentralized partially observable Markov decision processes and economic team theory. In addition to their generality of representation, COM-MTDPs also support the analysis of both the optimality of team performance and the computational complexity of the agents' decision problem. In analyzing complexity, we present a breakdown of the computational complexity of constructing optimal teams under various classes of problem domains, along the dimensions of observability and communication cost. In analyzing optimality, we exploit the COM-MTDP's ability to encode existing teamwork theories and models to encode two instantiations of joint intentions theory taken from the literature. Furthermore, the COM-MTDP model provides a basis for the development of novel team coordination algorithms. We derive a domain-independent criterion for optimal communication and provide a comparative analysis of the two joint intentions instantiations with respect to this optimal policy. We have implemented a reusable, domain-independent software package based on COM-MTDPs to analyze teamwork coordination strategies, and we demonstrate its use by encoding and evaluating the two joint intentions strategies within an example domain.
23
Wen, Liqun, Donglin Li, Xinglong Pei, Yan Zhang, and Jianhui Wang. "Continuous Estimation of Upper Limb Joint Angle Based on Stacked Denoising Autoencoder." Journal of Physics: Conference Series 2402, no. 1 (December 1, 2022): 012043. http://dx.doi.org/10.1088/1742-6596/2402/1/012043.
Full textAbstract:
Abstract In the human-robot interaction system of the rehabilitation robot for stroke rehabilitation, surface electromyography (sEMG) signal-based continuous joint angle estimation has essential significance and implementation value. However, the existing intra-subject mode is time-consuming and lacks generality, while the adoption of the new inter-subject mode tests the model’s generalization ability; at the same time, the often-adopted multi-feature fusion strategy makes the feature dimensionality too high and increases the computational pressure of the system. In this regard, firstly, four time-domain features of multi-channel sEMG are extracted as the initial features; then, a stacked denoising autoencoder (SDAE) network is constructed to encode the initial set of sEMG features in low dimensions and extract more robust low-dimensional features; finally, an LSTM network is introduced as the regression network between sEMG features and joint angles. The results indicate that the feature extraction method proposed is superior to other methods and can be used for the control of the rehabilitation robot with a stable and accurate continuous joint angle estimation during motion.
24
Shin, Jaehun, Wonkee Lee, Byung-Hyun Go, Baikjin Jung, Youngkil Kim, and Jong-Hyeok Lee. "Exploration of Effective Attention Strategies for Neural Automatic Post-editing with Transformer." ACM Transactions on Asian and Low-Resource Language Information Processing 20, no. 6 (November 30, 2021): 1–17. http://dx.doi.org/10.1145/3465383.
Full textAbstract:
Automatic post-editing (APE) is the study of correcting translation errors in the output of an unknown machine translation (MT) system and has been considered as a method of improving translation quality without any modification to conventional MT systems. Recently, several variants of Transformer that take both the MT output and its corresponding source sentence as inputs have been proposed for APE; and models introducing an additional attention layer into the encoder to jointly encode the MT output with its source sentence recorded a high-rank in the WMT19 APE shared task. We examine the effectiveness of such joint-encoding strategy in a controlled environment and compare four types of decoder multi-source attention strategies that have been introduced into previous APE models. The experimental results indicate that the joint-encoding strategy is effective and that taking the final encoded representation of the source sentence is the more proper strategy than taking such representation within the same encoder stack. Furthermore, among the multi-source attention strategies combined with the joint-encoding, the strategy that applies attention to the concatenated input representation and the strategy that adds up the individual attention to each input improve the quality of APE results over the strategy using the joint-encoding only.
25
Cunningham, Ryan J., and Ian D. Loram. "Estimation of absolute states of human skeletal muscle via standard B-mode ultrasound imaging and deep convolutional neural networks." Journal of The Royal Society Interface 17, no. 162 (January 2020): 20190715. http://dx.doi.org/10.1098/rsif.2019.0715.
Full textAbstract:
The objective is to test automated in vivo estimation of active and passive skeletal muscle states using ultrasonic imaging. Current technology (electromyography, dynamometry, shear wave imaging) provides no general, non-invasive method for online estimation of skeletal muscle states. Ultrasound (US) allows non-invasive imaging of muscle, yet current computational approaches have never achieved simultaneous extraction or generalization of independently varying active and passive states. We use deep learning to investigate the generalizable content of two-dimensional (2D) US muscle images. US data synchronized with electromyography of the calf muscles, with measures of joint moment/angle, were recorded from 32 healthy participants (seven female; ages: 27.5, 19–65). We extracted a region of interest of medial gastrocnemius and soleus using our prior developed accurate segmentation algorithm. From the segmented images, a deep convolutional neural network was trained to predict three absolute, drift-free components of the neurobiomechanical state (activity, joint angle, joint moment) during experimentally designed, simultaneous independent variation of passive (joint angle) and active (electromyography) inputs. For all 32 held-out participants (16-fold cross-validation) the ankle joint angle, electromyography and joint moment were estimated to accuracy 55 ± 8%, 57 ± 11% and 46 ± 9%, respectively. With 2D US imaging, deep neural networks can encode, in generalizable form, the activity–length–tension state relationship of these muscles. Observation-only, low-power 2D US imaging can provide a new category of technology for non-invasive estimation of neural output, length and tension in skeletal muscle. This proof of principle has value for personalized muscle assessment in pain, injury, neurological conditions, neuropathies, myopathies and ageing.
26
Ciszkiewicz, Adam. "Analyzing Uncertainty of an Ankle Joint Model with Genetic Algorithm." Materials 13, no. 5 (March 6, 2020): 1175. http://dx.doi.org/10.3390/ma13051175.
Full textAbstract:
Recent studies in biomechanical modeling suggest a paradigm shift, in which the parameters of biomechanical models would no longer treated as fixed values but as random variables with, often unknown, distributions. In turn, novel and efficient numerical methods will be required to handle such complicated modeling problems. The main aim of this study was to introduce and verify genetic algorithm for analyzing uncertainty in biomechanical modeling. The idea of the method was to encode two adversarial models within one decision variable vector. These structures would then be concurrently optimized with the objective being the maximization of the difference between their outputs. The approach, albeit expensive numerically, offered a general formulation of the uncertainty analysis, which did not constrain the search space. The second aim of the study was to apply the proposed procedure to analyze the uncertainty of an ankle joint model with 43 parameters and flexible links. The bounds on geometrical and material parameters of the model were set to 0.50 mm and 5.00% respectively. The results obtained from the analysis were unexpected. The two obtained adversarial structures were almost visually indistinguishable and differed up to 38.52% in their angular displacements.
27
Labandeira-Rey, Maria, and Jonathan T. Skare. "Decreased Infectivity in Borrelia burgdorferi Strain B31 Is Associated with Loss of Linear Plasmid 25 or 28-1." Infection and Immunity 69, no. 1 (January 1, 2001): 446–55. http://dx.doi.org/10.1128/iai.69.1.446-455.2001.
Full textAbstract:
ABSTRACT Previous reports indicated a correlation between loss of plasmids and decreased infectivity of Borrelia burgdorferi strain B31, suggesting that plasmids may encode proteins that are required for pathogenesis. In this study, we expand on this correlation. Using theB. burgdorferi genomic sequence, we designed primers specific for each plasmid, and by using PCR we catalogued 11 linear and 2 circular plasmids from 49 clonal isolates of a mid-passage B. burgdorferi strain B31, initially derived from infected mouse skin, and 20 clones obtained from mouse skin infected with a low-passage isolate of B. burgdorferi strain B31. Among the 69 clones analyzed, nine distinct genotypes were identified relative to wild-type B. burgdorferi strain B31. Among the nine clonal genotypes obtained, only the 9-kb circular plasmid (cp9), the 25-kb linear plasmid (lp25), and either the 28-kb linear plasmid 1 or 4 (lp28-1 and lp28-4, respectively) were missing, in different combinations. We compared the infectivity of the wild-type strain, containing all known B. burgdorferi plasmids, with those of single mutants lacking either lp28-1, lp28-4, or lp25 and a double mutant missing both cp9 and lp28-1. The infectivity data indicated thatB. burgdorferi strain B31 cells lacking lp28-4 were modestly attenuated in all tissues analyzed, whereas samples missing lp25 were completely attenuated in all tissues, even at the highest inoculum tested. Isolates without lp28-1 infected the joint tissue yet were not able to infect other tissues as effectively. In addition, we have observed a selection in vivo in the skin, bladder, and joint for cells containing lp25 and in the skin and bladder for cells containing lp28-1, indicating that lp25 and lp28-1 encode proteins required for colonization and short-term maintenance in these mammalian tissues. In contrast, there was no selection in the joint for cells containing lp28-1, suggesting that genes on lp28-1 are not required for colonization of B. burgdorferi within the joint. These observations imply that the dynamic nature of the B. burgdorferi genome may provide the genetic heterogeneity necessary for survival in the diverse milieus that this pathogen occupies in nature and may contribute to tropism in certain mammalian host tissues.
28
Wu, Huiyan, and Jun Huang. "Joint Entity and Relation Extraction Network with Enhanced Explicit and Implicit Semantic Information." Applied Sciences 12, no. 12 (June 19, 2022): 6231. http://dx.doi.org/10.3390/app12126231.
Full textAbstract:
The main purpose of the joint entity and relation extraction is to extract entities from unstructured texts and extract the relation between labeled entities at the same time. At present, most existing joint entity and relation extraction networks ignore the utilization of explicit semantic information and explore implicit semantic information insufficiently. In this paper, we propose Joint Entity and Relation Extraction Network with Enhanced Explicit and Implicit Semantic Information (EINET). First, on the premise of using the pre-trained model, we introduce explicit semantics from Semantic Role Labeling (SRL), which contains rich semantic features about the entity types and relation of entities. Then, to enhance the implicit semantic information and extract richer features of the entity and local context, we adopt different Bi-directional Long Short-Term Memory (Bi-LSTM) networks to encode entities and local contexts, respectively. In addition, we propose to integrate global semantic information and local context length representation in relation extraction to further improve the model performance. Our model achieves competitive results on three publicly available datasets. Compared with the baseline model on Conll04, EINET obtains improvements by 2.37% in F1 for named entity recognition and 3.43% in F1 for relation extraction.
29
Peng, Yongfang, Shengwei Tian, Long Yu, Yalong Lv, and Ruijin Wang. "A Joint Approach to Detect Malicious URL Based on Attention Mechanism." International Journal of Computational Intelligence and Applications 18, no. 03 (September 2019): 1950021. http://dx.doi.org/10.1142/s1469026819500214.
Full textAbstract:
To improve the accuracy and automation of malware Uniform Resource Locator (URL) recognition, a joint approach of Convolutional neural network (CNN) and Long-short term memory (LSTM) based on the Attention mechanism (JCLA) is proposed to identify and detect malicious URL. Firstly, the URL features including texture information, lexical information and host information are extracted and filtered, and pre-processed with encode. Then, the feature matrix more relevant to the output are chose according to the weight of the attention mechanism and input to the constructed parallel processing model called CNN_LSTM, combinating CNN and LSTM to get local features. Next, the extracted local features are merged to calculate the global features of the URLs to be detected. Finally, the URLs are classified by the SoftMax classifier using global features, the accuracy of the model in malicious URL recgonition is 98.26%. The experimental results show that the JCLA model proposed in this paper is better than the traditional deep learning model or CNN_LSTM combined model for detecting malicious URLs.
30
Kalaska, John F. "The representation of arm movements in postcentral and parietal cortex." Canadian Journal of Physiology and Pharmacology 66, no. 4 (April 1, 1988): 455–63. http://dx.doi.org/10.1139/y88-075.
Full textAbstract:
Considerable experimental evidence supports the hypothesis that the neocortical processes underlying kinesthetic sensation form a hierarchical series of cells signalling increasingly complex patterns of movement of the body. However, this view has been criticized and the data lack quantitative verification under controlled conditions. These studies have also typically used one-dimensional (reciprocal) movements, even of multiple degree-of-freedom joints such as the wrist or shoulder, and have been restricted to passive movements. This latter limitation is particularly critical, since the response of many muscle receptors is affected by fusimotor activity while that of many articular receptors is sensitive to the level of muscle contractile activity. Both factors introduce significant kinesthetic ambiguity to the signals arising from these receptors during active movement. This ambiguity is evident in the discharge of primary somatosensory cortex proprioceptive cells. Studies in area 5 show that single cells signal shoulder joint movements in the form of broad directional tuning curves. The pattern of activity of the entire population encodes movement direction. The cells appear to encode spatial aspects of movement unambiguously, since their discharge is relatively insensitive to the changes in muscle activity required to produce the same movements under different load conditions. It is not yet certain whether the somesthetic activity in area 5 is a kinesthetic representation that is sequential to and hierarchically superior to that in SI, or whether it is a parallel representation with separate and distinct functions.
31
Shunsheng, Zhang, Du Long, and Wang Wenqin. "LPI radar waveform design based on complementary phase and discrete chaotic frequency joint coding." Journal of Applied Artificial Intelligence 1, no. 1 (October 18, 2024): 293–312. http://dx.doi.org/10.59782/aai.v1i1.264.
Full textAbstract:
In order to reduce the probability of radar radiation signals being detected by enemy passive detection systems, this paper proposes a phase and frequency joint coding low intercept Radar waveform design method. Based on the linear frequency modulation signal, this method uses complementary binary code and chaotic sequence to phase encode the intra-pulse modulation. Code and frequency coding. The numerical simulation results show that the designed waveform exhibits pseudo-random characteristics in the time-frequency domain, and the low recognition performance is improved; The signal has an extremely low peak sidelobe level after matched filtering, showing excellent low intercept performance; its three-dimensional ambiguity function diagram presents an ideal “graph”. Fishing type”, with good distance, speed resolution and anti-interference characteristics.
32
Ding, Mingyu, Zhe Wang, Bolei Zhou, Jianping Shi, Zhiwu Lu, and Ping Luo. "Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (April 3, 2020): 10713–20. http://dx.doi.org/10.1609/aaai.v34i07.6699.
Full textAbstract:
A major challenge for video semantic segmentation is the lack of labeled data. In most benchmark datasets, only one frame of a video clip is annotated, which makes most supervised methods fail to utilize information from the rest of the frames. To exploit the spatio-temporal information in videos, many previous works use pre-computed optical flows, which encode the temporal consistency to improve the video segmentation. However, the video segmentation and optical flow estimation are still considered as two separate tasks. In this paper, we propose a novel framework for joint video semantic segmentation and optical flow estimation. Semantic segmentation brings semantic information to handle occlusion for more robust optical flow estimation, while the non-occluded optical flow provides accurate pixel-level temporal correspondences to guarantee the temporal consistency of the segmentation. Moreover, our framework is able to utilize both labeled and unlabeled frames in the video through joint training, while no additional calculation is required in inference. Extensive experiments show that the proposed model makes the video semantic segmentation and optical flow estimation benefit from each other and outperforms existing methods under the same settings in both tasks.
33
Purcell, P., A. Jheon, M. P. Vivero, H. Rahimi, A. Joo, and O. D. Klein. "Spry1 and Spry2 Are Essential for Development of the Temporomandibular Joint." Journal of Dental Research 91, no. 4 (February 10, 2012): 387–93. http://dx.doi.org/10.1177/0022034512438401.
Full textAbstract:
The temporomandibular joint (TMJ) is a specialized synovial joint essential for the function of the mammalian jaw. The main components of the TMJ are the mandibular condyle, the glenoid fossa of the temporal bone, and a fibrocartilagenous disc interposed between them. The genetic program for the development of the TMJ remains poorly understood. Here we show the crucial role of sprouty ( Spry) genes in TMJ development. Sprouty genes encode intracellular inhibitors of receptor tyrosine kinase (RTK) signaling pathways, including those triggered by fibroblast growth factors (Fgfs). Using in situ hybridization, we show that Spry1 and Spry2 are highly expressed in muscles attached to the TMJ, including the lateral pterygoid and temporalis muscles. The combined inactivation of Spry1 and Spry2 results in overgrowth of these muscles, which disrupts normal development of the glenoid fossa. Remarkably, condyle and disc formation are not affected in these mutants, demonstrating that the glenoid fossa is not required for development of these structures. Our findings demonstrate the importance of regulated RTK signaling during TMJ development and suggest multiple skeletal origins for the fossa. Notably, our work provides the evidence that the TMJ condyle and disc develop independently of the mandibular fossa.
34
Li, Lin, Jia-Ning Guo, Qi Wu, and Jian Zhang. "Dimming Control Scheme of Visible Light Communication Based on Joint Multilevel Time-Shifted Coding." Electronics 11, no. 10 (May 18, 2022): 1602. http://dx.doi.org/10.3390/electronics11101602.
Full textAbstract:
Dimming control is an essential objection in the signal designing of visible light communication (VLC), which requires improving the communication performance of the system as much as possible while considering the illumination quality. Here, we studied the problem of high-efficiency transmission in an indoor VLC multi-core light-emitting diode (LED) communication model while considering dimming constraints, and propose a dimming method based on joint multilevel multi-LED time-shifted coding (ML-MTSC). The scheme utilizes the code structure of time-shifted space–time codes to encode and uses pulse amplitude modulation (PAM) to expand it to achieve the dimming control function in the proposed scenario. Simulation results show that the ML-MTSC dimming control scheme proposed in this paper has improved spectral efficiency and error performance compared with the traditional scheme.
35
Cao, Pengcheng, Weiwei Liu, Guangjie Liu, Jiangtao Zhai, Xiao-Peng Ji, Yuewei Dai, and Huiwen Bai. "Design a Wireless Covert Channel Based on Dither Analog Chaotic Code." International Journal of Digital Crime and Forensics 13, no. 2 (March 2021): 115–33. http://dx.doi.org/10.4018/ijdcf.2021030108.
Full textAbstract:
To conceal the very existence of communication, the noise-based wireless covert channel modulates secret messages into artificial noise, which is added to the normal wireless signal. Although the state-of-the-art work based on constellation modulation has made the composite and legitimate signal undistinguishable, there exists an imperfection on reliability due to the dense distribution of covert constellation points. In this study, the authors design a wireless covert channel based on dither analog chaotic code to improve the reliability without damaging the undetectability. The dither analog chaotic code (DACC) plays the role as the error correcting code. In the modulation, the analog variables converted from secret messages are encode into joint codewords by chaotic mapping and dither derivation of DACC. The joint codewords are mapped to artificial noise later. Simulation results show that the proposed scheme can achieve better reliability than the state-of-the-art scheme while maintaining the similar performance on undetectability.
36
Jun, Kooksung, Keunhan Lee, Sanghyub Lee, Hwanho Lee, and Mun Sang Kim. "Hybrid Deep Neural Network Framework Combining Skeleton and Gait Features for Pathological Gait Recognition." Bioengineering 10, no. 10 (September 27, 2023): 1133. http://dx.doi.org/10.3390/bioengineering10101133.
Full textAbstract:
Human skeleton data obtained using a depth camera have been used for pathological gait recognition to support doctor or physician diagnosis decisions. Most studies for skeleton-based pathological gait recognition have used either raw skeleton sequences directly or gait features, such as gait parameters and joint angles, extracted from raw skeleton sequences. We hypothesize that using skeleton, joint angles, and gait parameters together can improve recognition performance. This study aims to develop a deep neural network model that effectively combines different types of input data. We propose a hybrid deep neural network framework composed of a graph convolutional network, recurrent neural network, and artificial neural network to effectively encode skeleton sequences, joint angle sequences, and gait parameters, respectively. The features extracted from three different input data types are fused and fed into the final classification layer. We evaluate the proposed model on two different skeleton datasets (a simulated pathological gait dataset and a vestibular disorder gait dataset) that were collected using an Azure Kinect. The proposed model, with multiple types of input, improved the pathological gait recognition performance compared to single input models on both datasets. Furthermore, it achieved the best performance among the state-of-the-art models for skeleton-based action recognition.
37
Tang, Pan, Shiqi Shao, Dapeng Zhou, and Huihua Hu. "Understanding the Collaborative Process and Its Effects on Perceived Outcomes during Emergency Response in China: From Perspectives of Local Government Sectors." Sustainability 13, no. 14 (July 7, 2021): 7605. http://dx.doi.org/10.3390/su13147605.
Full textAbstract:
In contemporary China, the rapidly urbanized cities are exposed to a broad range of natural and human-made emergencies, such as COVID-19. Responding to emergencies successfully requires widespread participation of local government sectors that engages in diversified collaboration behaviors across organizational boundaries for achieving sustainability. However, the multi-organizational collaborative process is highly dynamic and complex, as well as its outcomes are uncertain underlying the emergency response network. Examining characteristics of the collaborative process and exploring how collaborative behaviors local governmental sectors engaging in the impact their perceived outcomes is essential to understand how disastrous situations are addressed by collaborative efforts in emergency management. This research investigates diversified collaborative behaviors in emergency response and then examines this using a multi-dimensional model consisting of joint decision making, joint implementation, compromised autonomy, resource sharing, and trust building. We surveyed 148 local governments and their affiliated sectors in China in-depth understanding how collaborative processes contribute to perceived outcomes from perspectives of participating sectors in the context of a centralized political-administrative system. A structural equation model (SEM) is employed to encode multiple dimensions of the collaborative process, perceived outcomes, as well as their relationships. The empirical finding indicates that joint decision making and implementation positively affect the perceived outcomes significantly. The empirical results indicate that joint decision making and joint implementation affect perceived outcomes significantly. Instead, resource sharing and trust building do not affect the outcomes positively as expected. Additionally, compromised autonomy negatively affects the collaborative outcomes. We also discuss the institutional advantages for achieving successful outcomes in emergency management in China by reducing the degree of compromised autonomy. Our findings provide insight that can improve efforts to build and maintain a collaborative process to respond to emergencies.
38
Smolyanskaya, Alexandra, Douglas A. Ruff, and Richard T. Born. "Joint tuning for direction of motion and binocular disparity in macaque MT is largely separable." Journal of Neurophysiology 110, no. 12 (December 15, 2013): 2806–16. http://dx.doi.org/10.1152/jn.00573.2013.
Full textAbstract:
Neurons in sensory cortical areas are tuned to multiple dimensions, or features, of their sensory space. Understanding how single neurons represent multiple features is of great interest for determining the informative dimensions of the neurons' response, the decoding algorithms appropriate for extracting this information from the neuronal population, and for determining where specific transformations occur along the visual hierarchy. Despite the established role of cortical area MT in judgments of motion and depth, it is not known how individual neurons jointly encode the two dimensions. We investigated the joint tuning of individual MT neurons for two visual features: direction of motion and binocular disparity, an important depth cue. We found that a separable, multiplicative combination of tuning for the two features can account for more than 90% of the variance in the joint tuning function for over 91% of MT neurons. These results suggest 1) that each feature can be read out independently from MT by simply averaging across the population without regard to the other feature and 2) that the inseparable representations seen in subsequent areas, such as MST, must be computed beyond MT. Intriguingly, we found that the remaining nonseparable component of the joint tuning function often manifested as small but systematic changes in the neurons' preferences for one feature as the other one was varied. We believe this reflects the local columnar organization of tuning for direction and binocular disparity in MT, indicating that joint tuning may provide a new tool with which to probe functional architecture.
39
Kim, Yeonggwang, Giwon Ku, Chulseung Yang, Jeonggi Lee, and Jinsul Kim. "Lightweight Three-Dimensional Pose and Joint Center Estimation Model for Rehabilitation Therapy." Electronics 12, no. 20 (October 16, 2023): 4273. http://dx.doi.org/10.3390/electronics12204273.
Full textAbstract:
In this study, we proposed a novel transformer-based model with independent tokens for estimating three-dimensional (3D) human pose and shape from monocular videos, specifically focusing on its application in rehabilitation therapy. The main objective is to recover pixel-aligned rehabilitation-customized 3D human poses and body shapes directly from monocular images or videos, which is a challenging task owing to inherent ambiguity. Existing human pose estimation methods heavily rely on the initialized mean pose and shape as prior estimates and employ parameter regression with iterative error feedback. However, video-based approaches face difficulties capturing joint-level rotational motion and ensuring local temporal consistency despite enhancing single-frame features by modeling the overall changes in the image-level features. To address these limitations, we introduce two types of characterization tokens specifically designed for rehabilitation therapy: joint rotation and camera tokens. These tokens progressively interact with the image features through the transformer layers and encode prior knowledge of human 3D joint rotations (i.e., position information derived from large-scale data). By updating these tokens, we can estimate the SMPL parameters for a given image. Furthermore, we incorporate a temporal model that effectively captures the rotational temporal information of each joint, thereby reducing jitters in local parts. The performance of our method is comparable with those of the current best-performing models. In addition, we present the structural differences among the models to create a pose classification model for rehabilitation. We leveraged ResNet-50 and transformer architectures to achieve a remarkable PA-MPJPE of 49.0 mm for the 3DPW dataset.
40
Xu, Zhe, Ivan Gavran, Yousef Ahmad, Rupak Majumdar, Daniel Neider, Ufuk Topcu, and Bo Wu. "Joint Inference of Reward Machines and Policies for Reinforcement Learning." Proceedings of the International Conference on Automated Planning and Scheduling 30 (June 1, 2020): 590–98. http://dx.doi.org/10.1609/icaps.v30i1.6756.
Full textAbstract:
Incorporating high-level knowledge is an effective way to expedite reinforcement learning (RL), especially for complex tasks with sparse rewards. We investigate an RL problem where the high-level knowledge is in the form of reward machines, a type of Mealy machines that encode non-Markovian reward functions. We focus on a setting in which this knowledge is a priori not available to the learning agent. We develop an iterative algorithm that performs joint inference of reward machines and policies for RL (more specifically, q-learning). In each iteration, the algorithm maintains a hypothesis reward machine and a sample of RL episodes. It uses a separate q-function defined for each state of the current hypothesis reward machine to determine the policy and performs RL to update the q-functions. While performing RL, the algorithm updates the sample by adding RL episodes along which the obtained rewards are inconsistent with the rewards based on the current hypothesis reward machine. In the next iteration, the algorithm infers a new hypothesis reward machine from the updated sample. Based on an equivalence relation between states of reward machines, we transfer the q-functions between the hypothesis reward machines in consecutive iterations. We prove that the proposed algorithm converges almost surely to an optimal policy in the limit. The experiments show that learning high-level knowledge in the form of reward machines leads to fast convergence to optimal policies in RL, while the baseline RL methods fail to converge to optimal policies after a substantial number of training steps.
41
Ben Tamou, Abdelouahid, Lahoucine Ballihi, and Driss Aboutajdine. "Automatic Learning of Articulated Skeletons Based on Mean of 3D Joints for Efficient Action Recognition." International Journal of Pattern Recognition and Artificial Intelligence 31, no. 04 (February 2, 2017): 1750008. http://dx.doi.org/10.1142/s0218001417500082.
Full textAbstract:
In this paper, we present a new approach for human action recognition using [Formula: see text] skeleton joints recovered from RGB-D cameras. We propose a descriptor based on differences of skeleton joints. This descriptor combines two characteristics including static posture and overall dynamics that encode spatial and temporal aspects. Then, we apply the mean function on these characteristics in order to form the feature vector, used as an input to Random Forest classifier for action classification. The experimental results on both datasets: MSR Action 3D dataset and MSR Daily Activity 3D dataset demonstrate that our approach is efficient and gives promising results compared to state-of-the-art approaches.
42
Jones, Heath G., Andrew D. Brown, Kanthaiah Koka, Jennifer L. Thornton, and Daniel J. Tollin. "Sound frequency-invariant neural coding of a frequency-dependent cue to sound source location." Journal of Neurophysiology 114, no. 1 (July 2015): 531–39. http://dx.doi.org/10.1152/jn.00062.2015.
Full textAbstract:
The century-old duplex theory of sound localization posits that low- and high-frequency sounds are localized with two different acoustical cues, interaural time and level differences (ITDs and ILDs), respectively. While behavioral studies in humans and behavioral and neurophysiological studies in a variety of animal models have largely supported the duplex theory, behavioral sensitivity to ILD is curiously invariant across the audible spectrum. Here we demonstrate that auditory midbrain neurons in the chinchilla ( Chinchilla lanigera) also encode ILDs in a frequency-invariant manner, efficiently representing the full range of acoustical ILDs experienced as a joint function of sound source frequency, azimuth, and distance. We further show, using Fisher information, that nominal “low-frequency” and “high-frequency” ILD-sensitive neural populations can discriminate ILD with similar acuity, yielding neural ILD discrimination thresholds for near-midline sources comparable to behavioral discrimination thresholds estimated for chinchillas. These findings thus suggest a revision to the duplex theory and reinforce ecological and efficiency principles that hold that neural systems have evolved to encode the spectrum of biologically relevant sensory signals to which they are naturally exposed.
43
Zhai, Hao, Xin Pan, You Yang, Jinyuan Jiang, and Qing Li. "Two-Stage Focus Measurement Network with Joint Boundary Refinement for Multifocus Image Fusion." International Journal of Intelligent Systems 2023 (August 31, 2023): 1–16. http://dx.doi.org/10.1155/2023/4155948.
Full textAbstract:
Focus measurement, one of the key tasks in multifocus image fusion (MFIF) frameworks, identifies the clearer parts of multifocus images pairs. Most of the existing methods aim to achieve disposable pixel-level focus measurement. However, the lack of sufficient accuracy often gives rise to misjudgments in the results. To this end, a novel two-stage focus measurement with joint boundary refinement network is proposed for MFIF. In this work, we adopt a coarse-to-fine strategy to gradually achieve block-level and pixel-level focus measurement for producing more fine-grained focus probability maps, instead of directly predicting at the pixel level. In addition, the joint boundary refinement optimizes the performance on the focused/defocused boundary component (FDB) during the focus measurement. To improve feature extraction capability, both CNN and transformer are employed to, respectively, encode local patterns and capture long-range dependencies. Then, the features from two input branches are legitimately aggregated by modeling the spatial complementary relationship in each pair of multifocus images. Extensive experiments demonstrate that the proposed model achieves state-of-the-art performance in both subjective perception and objective assessment.
44
Arnoux, Léo, Sebastien Fromentin, Dario Farotto, Mathieu Beraneck, Joseph McIntyre, and Michele Tagliabue. "The visual encoding of purely proprioceptive intermanual tasks is due to the need of transforming joint signals, not to their interhemispheric transfer." Journal of Neurophysiology 118, no. 3 (September 1, 2017): 1598–608. http://dx.doi.org/10.1152/jn.00140.2017.
Full textAbstract:
To perform goal-oriented hand movement, humans combine multiple sensory signals (e.g., vision and proprioception) that can be encoded in various reference frames (body centered and/or exo-centered). In a previous study (Tagliabue M, McIntyre J. PLoS One 8: e68438, 2013), we showed that, when aligning a hand to a remembered target orientation, the brain encodes both target and response in visual space when the target is sensed by one hand and the response is performed by the other, even though both are sensed only through proprioception. Here we ask whether such visual encoding is due 1) to the necessity of transferring sensory information across the brain hemispheres, or 2) to the necessity, due to the arms’ anatomical mirror symmetry, of transforming the joint signals of one limb into the reference frame of the other. To answer this question, we asked subjects to perform purely proprioceptive tasks in different conditions: Intra, the same arm sensing the target and performing the movement; Inter/Parallel, one arm sensing the target and the other reproducing its orientation; and Inter/Mirror, one arm sensing the target and the other mirroring its orientation. Performance was very similar between Intra and Inter/Mirror (conditions not requiring joint-signal transformations), while both differed from Inter/Parallel. Manipulation of the visual scene in a virtual reality paradigm showed visual encoding of proprioceptive information only in the latter condition. These results suggest that the visual encoding of purely proprioceptive tasks is not due to interhemispheric transfer of the proprioceptive information per se, but to the necessity of transforming joint signals between mirror-symmetric limbs. NEW & NOTEWORTHY Why does the brain encode goal-oriented, intermanual tasks in a visual space, even in the absence of visual feedback about the target and the hand? We show that the visual encoding is not due to the transfer of proprioceptive signals between brain hemispheres per se, but to the need, due to the mirror symmetry of the two limbs, of transforming joint angle signals of one arm in different joint signals of the other.
45
Geigle, Gregor, Jonas Pfeiffer, Nils Reimers, Ivan Vulić, and Iryna Gurevych. "Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval." Transactions of the Association for Computational Linguistics 10 (2022): 503–21. http://dx.doi.org/10.1162/tacl_a_00473.
Full textAbstract:
Abstract Current state-of-the-art approaches to cross- modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While offering unmatched retrieval performance, such models: 1) are typically pretrained from scratch and thus less scalable, 2) suffer from huge retrieval latency and inefficiency issues, which makes them impractical in realistic applications. To address these crucial gaps towards both improved and efficient cross- modal retrieval, we propose a novel fine-tuning framework that turns any pretrained text-image multi-modal model into an efficient retrieval model. The framework is based on a cooperative retrieve-and-rerank approach that combines: 1) twin networks (i.e., a bi-encoder) to separately encode all items of a corpus, enabling efficient initial retrieval, and 2) a cross-encoder component for a more nuanced (i.e., smarter) ranking of the retrieved small set of items. We also propose to jointly fine- tune the two components with shared weights, yielding a more parameter-efficient model. Our experiments on a series of standard cross-modal retrieval benchmarks in monolingual, multilingual, and zero-shot setups, demonstrate improved accuracy and huge efficiency benefits over the state-of-the-art cross- encoders.1
46
Giarmatzis, Georgios, Evangelia I. Zacharaki, and Konstantinos Moustakas. "Real-Time Prediction of Joint Forces by Motion Capture and Machine Learning." Sensors 20, no. 23 (December 4, 2020): 6933. http://dx.doi.org/10.3390/s20236933.
Full textAbstract:
Conventional biomechanical modelling approaches involve the solution of large systems of equations that encode the complex mathematical representation of human motion and skeletal structure. To improve stability and computational speed, being a common bottleneck in current approaches, we apply machine learning to train surrogate models and to predict in near real-time, previously calculated medial and lateral knee contact forces (KCFs) of 54 young and elderly participants during treadmill walking in a speed range of 3 to 7 km/h. Predictions are obtained by fusing optical motion capture and musculoskeletal modeling-derived kinematic and force variables, into regression models using artificial neural networks (ANNs) and support vector regression (SVR). Training schemes included either data from all subjects (LeaveTrialsOut) or only from a portion of them (LeaveSubjectsOut), in combination with inclusion of ground reaction forces (GRFs) in the dataset or not. Results identify ANNs as the best-performing predictor of KCFs, both in terms of Pearson R (0.89–0.98 for LeaveTrialsOut and 0.45–0.85 for LeaveSubjectsOut) and percentage normalized root mean square error (0.67–2.35 for LeaveTrialsOut and 1.6–5.39 for LeaveSubjectsOut). When GRFs were omitted from the dataset, no substantial decrease in prediction power of both models was observed. Our findings showcase the strength of ANNs to predict simultaneously multi-component KCF during walking at different speeds—even in the absence of GRFs—particularly applicable in real-time applications that make use of knee loading conditions to guide and treat patients.
47
Xie, Cunxiang, Limin Zhang, and Zhaogen Zhong. "Entity Alignment Method Based on Joint Learning of Entity and Attribute Representations." Applied Sciences 13, no. 9 (May 6, 2023): 5748. http://dx.doi.org/10.3390/app13095748.
Full textAbstract:
Entity alignment helps discover and link entities from different knowledge graphs (KGs) that refer to the same real-world entity, making it a critical technique for KG fusion. Most entity alignment methods are based on knowledge representation learning, which uses a mapping function to project entities from different KGs into a unified vector space and align them based on calculated similarities. However, this process requires sufficient pre-aligned entity pairs. To address this problem, this study proposes an entity alignment method based on joint learning of entity and attribute representations. Structural embeddings are learned using the triples modeling method based on TransE and PTransE and extracted from the embedding vector space utilizing semantic information from direct and multi-step relation paths. Simultaneously, attribute character embeddings are learned using the N-gram-based compositional function to encode a character sequence for the attribute values, followed by TransE to model attribute triples in the embedding vector space to obtain attribute character embedding vectors. By learning the structural and attribute character embeddings simultaneously, the structural embeddings of entities from different KGs can be transferred into a unified vector space. Lastly, the similarities in the structural embedding of different entities were calculated to perform entity alignment. The experimental results showed that the proposed method performed well on the DBP15K and DWK100K datasets, and it outperformed currently available entity alignment methods by 16.8, 27.5, and 24.0% in precision, recall, and F1 measure, respectively.
48
Li, Ziang, Wen Lu, Zhaoyang Wang, Jian Hu, Zeming Zhang, and Lihuo He. "Multi-Window Fusion Spatial-Frequency Joint Self-Attention for Remote-Sensing Image Super-Resolution." Remote Sensing 16, no. 19 (October 4, 2024): 3695. http://dx.doi.org/10.3390/rs16193695.
Full textAbstract:
Remote-sensing images typically feature large dimensions and contain repeated texture patterns. To effectively capture finer details and encode comprehensive information, feature-extraction networks with larger receptive fields are essential for remote-sensing image super-resolution tasks. However, mainstream methods based on stacked Transformer modules suffer from limited receptive fields due to fixed window sizes, impairing long-range dependency capture and fine-grained texture reconstruction. In this paper, we propose a spatial-frequency joint attention network based on multi-window fusion (MWSFA). Specifically, our approach introduces a multi-window fusion strategy, which merges windows with similar textures to allow self-attention mechanisms to capture long-range dependencies effectively, therefore expanding the receptive field of the feature extractor. Additionally, we incorporate a frequency-domain self-attention branch in parallel with the original Transformer architecture. This branch leverages the global characteristics of the frequency domain to further extend the receptive field, enabling more comprehensive self-attention calculations across different frequency bands and better utilization of consistent frequency information. Extensive experiments on both synthetic and real remote-sensing datasets demonstrate that our method achieves superior visual reconstruction effects and higher evaluation metrics compared to other super-resolution methods.
49
Kang, Yangyuxuan, Yuyang Liu, Anbang Yao, Shandong Wang, and Enhua Wu. "3D Human Pose Lifting with Grid Convolution." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 1 (June 26, 2023): 1105–13. http://dx.doi.org/10.1609/aaai.v37i1.25192.
Full textAbstract:
Existing lifting networks for regressing 3D human poses from 2D single-view poses are typically constructed with linear layers based on graph-structured representation learning. In sharp contrast to them, this paper presents Grid Convolution (GridConv), mimicking the wisdom of regular convolution operations in image space. GridConv is based on a novel Semantic Grid Transformation (SGT) which leverages a binary assignment matrix to map the irregular graph-structured human pose onto a regular weave-like grid pose representation joint by joint, enabling layer-wise feature learning with GridConv operations. We provide two ways to implement SGT, including handcrafted and learnable designs. Surprisingly, both designs turn out to achieve promising results and the learnable one is better, demonstrating the great potential of this new lifting representation learning formulation. To improve the ability of GridConv to encode contextual cues, we introduce an attention module over the convolutional kernel, making grid convolution operations input-dependent, spatial-aware and grid-specific. We show that our fully convolutional grid lifting network outperforms state-of-the-art methods with noticeable margins under (1) conventional evaluation on Human3.6M and (2) cross-evaluation on MPI-INF-3DHP. Code is available at https://github.com/OSVAI/GridConv.
50
Yao, Shengshi, Zixuan Xiao, and Kai Niu. "Rate–Distortion–Perception Optimized Neural Speech Transmission System for High-Fidelity Semantic Communications." Sensors 24, no. 10 (May 16, 2024): 3169. http://dx.doi.org/10.3390/s24103169.
Full textAbstract:
We consider the problem of learned speech transmission. Existing methods have exploited joint source–channel coding (JSCC) to encode speech directly to transmitted symbols to improve the robustness over noisy channels. However, the fundamental limit of these methods is the failure of identification of content diversity across speech frames, leading to inefficient transmission. In this paper, we propose a novel neural speech transmission framework named NST. It can be optimized for superior rate–distortion–perception (RDP) performance toward the goal of high-fidelity semantic communication. Particularly, a learned entropy model assesses latent speech features to quantify the semantic content complexity, which facilitates the adaptive transmission rate allocation. NST enables a seamless integration of the source content with channel state information through variable-length joint source–channel coding, which maximizes the coding gain. Furthermore, we present a streaming variant of NST, which adopts causal coding based on sliding windows. Experimental results verify that NST outperforms existing speech transmission methods including separation-based and JSCC solutions in terms of RDP performance. Streaming NST achieves low-latency transmission with a slight quality degradation, which is tailored for real-time speech communication.