106 research outputs found
Epigenetic variation in lingonberries
No full textEpigenetic variation plays a role in developmental gene regulation, response to the environment,
and in natural variation of gene expression levels. The purpose of the study is to investigate
cytosine methylation and secondary compounds of lingonberry (Vaccinium vitis-idaea) among
cutting-propagated cultivar Erntedank (ED) and its tissue-culture plants (NC, LC). This was
analyzed by using Methylation Sensitive Amplified Polymorphism (MSAP) where the primers
were cleaved in cytosine residues at 5'-CCGG-3' sites in CpG-islands. In leaf regenerants (LC1),
we observed highest methylated sites from all primer combinations (108 bands), with their highest
variation in secondary metabolites. We measured that tissue-cultured plants showed higher
methylation bands than maternal plants. For instance, we identified the mother plant ED exhibited
79 bands of methylation, which is comparatively low. On the other hand, we observed the highest
total phenolic content in (NC3) but LC1 represents low phenolic content. Our study showed more
methylation in micropropagated plants (NC1, NC2, NC3 and LC1) than those derived from ED
cutting cultivar where methylation was not present. On the contrary, we observed higher
secondary metabolites in cutting cultivar ED but comparatively less in micropropagated plants
(NC1, NC2, NC3 LC1). Hence, our study confirmed that higher methylation sites observed in
micropropagated plants and less amount of secondary metabolites appears.Includes bibliographical references (pages 69-91)
Interweaving Insights: High-Order Feature Interaction for Fine-Grained Visual Recognition
Get PDFThis paper presents a novel approach for Fine-Grained Visual Classification (FGVC) by exploring Graph Neural Networks (GNNs) to facilitate high-order feature interactions, with a specific focus on constructing both inter- and intra-region graphs. Unlike previous FGVC techniques that often isolate global and local features, our method combines both features seamlessly during learning via graphs. Inter-region graphs capture long-range dependencies to recognize global patterns, while intra-region graphs delve into finer details within specific regions of an object by exploring high-dimensional convolutional features. A key innovation is the use of shared GNNs with an attention mechanism coupled with the Approximate Personalized Propagation of Neural Predictions (APPNP) message-passing algorithm, enhancing information propagation efficiency for better discriminability and simplifying the model architecture for computational efficiency. Additionally, the introduction of residual connections improves performance and training stability. Comprehensive experiments showcase state-of-the-art results on benchmark FGVC datasets, affirming the efficacy of our approach. This work underscores the potential of GNN in modeling high-level feature interactions, distinguishing it from previous FGVC methods that typically focus on singular aspects of feature representation. Our source code is available at https://github.com/Arindam-1991/I2-HOFI
Multi-level Threat Analysis in Anomalous Crowd Videos
No full textCrowd anomaly detection is a challenging problem in the field of computer vision. An abnormal event in a crowd scene can be labeled as threat in a video. Several existing solutions in this area have marked video frames either normal or abnormal event. Such categorization of frames can be referred as two-class threat labeling problem. However, this notion of two-class threat labeling is not well defined in literature. An event can have multiple aspects as it can be treated as anomalous or non-anomalous based on the situation of occurrence. Based on this argument, we propose a new paradigm of extending this two class threat labeling problem to multi-class labeling. As a solution to this multi-class labeling problem, we cluster frames with low, medium and high threat. We also propose a new feature known as pseudo-entropy for better clustering of threats. Our framework consists of two main components, namely, Earth mover distance (EMD) based anomaly detection system and multi-level threat analysis. As an outcome frame-wise and segment-wise threat representation are also presented to facilitate real time video search for relevant events. Exhaustive internal comparison and statistical analysis over benchmark UCSD and UMN dataset clearly indicates the merit of the proposed framework.</p
An Ellipse Fitted Training-Less Model for Pedestrian Detection
No full textThe problem of pedestrian detection has gained much popularity in the computer vision community in recent times. We have noted that the existing solutions to this problem are mostly supervised in nature. However, it is difficult to guarantee availability of labelled training data in all situations. In this paper, we propose a training-less solution of pedestrian detection. Some of the additional challenges for pedestrian detection are proper handling of viewpoint dependencies, background clutter, illumination variation and occlusion. We design an ellipse fitting model, as a part of our training-less solution, for accurate pedestrian detection. In this model, we fit an ellipse to each competing bounding box (proposal). An area and entropy based quality factor is introduced for every such (fitted) ellipse to discriminate among the proposals. We filter out proposals with low quality factors. Performance comparisons with some well-known supervised pedestrian detection approaches on publicly available PETS2009 dataset demonstrate that our solution is highly promising.</p
Your turn: At home turning angle estimation for Parkinson’s disease severity assessment
Get PDFPeople with Parkinson’s Disease (PD) often experience progressively worsening gait, including changes in how they turn around, as the disease progresses. Existing clinical rating tools are not capable of capturing hour-by-hour variations of PD symptoms, as they are confined to brief assessments within clinic settings, leaving gait performance outside these controlled environments unaccounted for. Measuring turning angles continuously and passively is a component step towards using gait characteristics as sensitive indicators of disease progression in PD. This paper presents a deep learning-based approach to automatically quantify turning angles by extracting 3D skeletons from videos and calculating the rotation of hip and knee joints. We utilise advanced human pose estimation models, Fastpose and Strided Transformer, on a total of 1386 turning video clips from 24 subjects (12 people with PD and 12 healthy control volunteers), trimmed from a PD dataset of unscripted free-living videos in a home-like setting (Turn-REMAP). We also curate a turning video dataset, Turn-H3.6M, from the public Human3.6M human pose benchmark with 3D groundtruth, to further validate our method. Previous gait research has primarily taken place in clinics or laboratories evaluating scripted gait outcomes, but this work focuses on free-living home settings where complexities exist, such as baggy clothing and poor lighting. Due to difficulties in obtaining accurate groundtruth data in a free-living setting, we quantise the angle into the nearest bin 45° based on the manual labelling of expert clinicians. Our method achieves a turning calculation accuracy of 41.6%, a Mean Absolute Error (MAE) of 34.7°, and a weighted precision (WPrec) of 68.3% for Turn-REMAP. On Turn-H3.6M, it achieves an accuracy of 73.5%, an MAE of 18.5°, and a WPrec of 86.2%. This is the first work to explore the use of single monocular camera data to quantify turns by PD patients in a home setting. All data and models are publicly available, providing a baseline for turning parameter measurement to promote future PD gait research
Roy et al. 2023 Supplemental Information for "Sediment-encased pressure–temperature maturation experiments elucidate the impact of diagenesis on melanin-based fossil color and its paleobiological implications."
No full textSupplemental Information for
Sediment-encased pressure–temperature maturation experiments elucidate the impact of diagenesis on melanin-based fossil color and its paleobiological implications.
Arindam Roy* (https://orcid.org/0000-0002-4890-6851)
Michael Pittman* (https://orcid.org/0000-0002-6149-3078)
Thomas G. Kaye (https://orcid.org/0000-0001-7996-618X)
Evan T. Saitta (https://orcid.org/0000-0002-9306-9060)
*Corresponding author(s)
Email: [email protected] ; [email protected]
The Dataset contains two files, (1) Supporting Information and (2) Supporting Data PCA worksheet.
The first contains Supplementary tables and figures (.docx file) while the structural organisation of the second (.xlsx file) is provided below:
Authors:
Arindam Roy* (https://orcid.org/0000-0002-4890-6851)
Michael Pittman* (https://orcid.org/0000-0002-6149-3078)
Thomas G. Kaye (https://orcid.org/0000-0001-7996-618X)
Evan T. Saitta (https://orcid.org/0000-0002-9306-9060)
*Corresponding author(s)
README:
We received ToF-SIMS data (Samples 1–30, 36–51) pertaining to purified melanosome extracts of modern bird feathers (both fresh and capsule-matured) from Caitlin Colleary (Associate Curator of Vertebrate Paleontology, Cleveland Museum of Natural History), based on their previous work (Colleary et al. 2015). Citation below:
Colleary, C., A. Dolocan, J. Gardner, S. Singh, M. Wuttke, R. Rabenstein, J. Habersetzer, S. Schaal, M. Feseha, M. Clemens, B. F. Jacobs, E. D. Currano, L. L. Jacobs, R. L. Sylvestersen, S. E. Gabbott, and J. Vinther. 2015. Chemical, experimental, and morphological evidence for diagenetically altered melanin in exceptionally preserved fossils. Proceedings of the National Academy of Sciences USA 112(41):12592-7. doi: https://doi.org/10.1073/pnas.1509831112
We further augmented this data set by adding ToF-SIMS spectra from our own samples (31-34, 52-79) pertaining to sediment encased maturation experiments (190ºC to 300ºC) and fossilised feathers of paravian dinosaurs housed at the Shandong Tianyu Museum of Natural History, Linyi Shi, Shandong, China.
We conducted Principal Components Analysis with this Data and this dataset effectively serves as a PCA worksheet. The file can be opened/edited using Microsoft 365 Excel (.xlsx) with the following organisation of sheets.
Sheets:
|----- PCA All : contains Sample ID, treatment categories, mass by charge (m/z) ratios of 55 peaks, peak identity and raw intensity counts
|-----PCA All Normalised : same data as PCA All but peak raw intensity counts normalised.
|-----PCA All Mean Centered: same data as PCA Normalised but with peak raw intensity mean centered.
|-----PCA All Loading Matrix: Loading matrix for PCA All using all 55 peaks.
|-----PCA All Eigen Vectors: Eigen vectors for PCA All.
|-----PCA All Scores: PCA scores for all 55 peaks.
|-----PCA No Lipids RAW: same data as PCA All but without peaks suspected to arise from lipids (e.g., CxH-).
|-----PCA No Lipids Normalised: same data as PCA without Lipids RAW but with peak raw intensity counts normalised.
|-----PCA No Lipids MeanCentred: same data as PCA without Lipids Norm but with peak raw intensity counts mean centered.
|-----PCA No Lipids Loading Matrix: Loading matrix for PCA All excluding peaks of lipid origin (CxH-).
|-----PCA No Lipids Eigen Vectors: Eigen vectors for PCA No Lipids Eigen Vectors.
|-----PCA No Lipids Scores: PCA scores for all peaks excluding those of lipid origin (CxH-).
The dataset can be created in Microsoft Office 365 (Excel: .xlsx file). The file can also be also be opened and edited using the following softwares.
1. Google Sheets
2. Apache Open Office
3. Libre Office
4. PAST 4 (free software for scientific data analysis, with functions for data manipulation, plotting, univariate and multivariate statistics, ecological analysis, time series and spatial analysis, morphometrics and stratigraphy).
Machining parameters optimization during machining of Al/5 wt% alumina metal matrix composite by fiber laser
No full textAn adaptive training-less framework for anomaly detection in crowd scenes
Get PDFAnomaly detection in crowd videos has become a popular area of research for the computer vision community. Several existing methods have determined anomaly as a deviation from scene normalcy learned via separate training with/without labeled information. However, owing to rare and sparse nature of anomalous events, any such learning can be misleading as there exist no hardcore segregation between anomalous and non-anomalous events. To address such challenge, we propose an adaptive training-less system capable of detecting anomaly on-the-fly. Our solution pipeline consists of three major components, namely, adaptive 3D-DCT model for multi-object detection-based association, local motion descriptor generation through an improved saliency guided optical flow, and anomaly detection based on Earth mover's distance (EMD). The proposed model, despite being training-free, is found to achieve comparable performance with several state-of-the-art methods on publicly available UCSD, UMN, CUHK-Avenue and ShanghaiTech datasets.</p
Precision measurement of the half-life of ^{110}Sn in large and small lattice environments
No full textLightweight Learning for Partial and Occluded Person Re-identification
Get PDFOccluded and partial person re-identification (re-ID) problems have emerged as challenging research topics in the area of computer vision. Existing part-based models, with complex designs, fail to properly tackle these problems. The reasons for their failures are two-fold. Firstly, individual body part appearances are not discriminative enough to distinguish between two closely appearing persons. Secondly, re-identification datasets typically lack detailed human body-part annotations. To address these challenges, we present a lightweight yet accurate solution for partial person re-identification. Our proposed approach consists of two key components, namely, design of a lightweight Unary-Binary projective Dictionary Learning (UBDL) model, and, construction of a similarity matrix for distilling knowledge from the deep Omni-scale network (OSNet) to UBDL. The unary dictionary (UD) pair encodes patches horizontally, ignoring the viewpoints. The binary dictionary (BD) pairs, on the other hand, are learned between two views, giving more weight to less occluded vertical patches for improving the correspondence across the views. We formulate appropriate convex objective functions for unary and binary cases by incorporating the above knowledge similarity matrix. Closed-form solutions are obtained for updating unary and binary dictionary components. Final matching scores are computed by fusing unary and binary matching scores with adaptive weighting of relevant cross-view patches. Extensive experiments and ablation studies on a number of occluded and partial re-identification datasets like Occluded-REID (O-REID), Partial-REID (PREID) and Partial-iLIDS (P-iLIDS), clearly showcase the merits of our proposed solution.</p
- …
