- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[Lecture Notes in Networks and Systems] Data Analytics and Learning Volume 43 (Proceedings of DAL 2018) || Automated Parameter-Less Optical Mark Recognition
摘要： Innovation and development of computer vision algorithms finds real-time application in automated evaluation of optical mark sheets. Most of the existing methods are template specific and requires parameter tuning based on the given template. Developing robust and low-cost solutions for optical mark recognition (OMR) is still a challenging problem. The need for parameter less and computationally efficient method that works in real time adds on to the existing challenges. To address these problems, robust and computationally efficient parameter-less OMR method is proposed. The main contributions of this paper are dynamic localization of optical mark region that makes the algorithm generic and independent of templates. Accuracy is improved by implementing some of the heuristics approaches which identifies marking regions that are missed during preprocessing. Marked regions are accurately detected by computing local threshold instead of global classification margin. The algorithm is evaluated on various OMR templates obtained from different scanners and smartphones. Experimental results depict the efficiency of the proposed method with the error rate less than 2% by processing 150 sheets per minute.
关键词： Document analysis,Multiple choice questions,Optical mark recognition
更新于2025-09-23 15:21:01
-
Formation of Functional Cyclooctadiene Derivatives by Supramolecularly-Controlled Topochemical Reactions and Their Use as Highly Selective Fluorescent Biomolecule Probes
摘要： Controlling the regio- and stereochemistry of the photoproducts in solution is far more challenging for polyenes than for monoalkenes. Herein, a supramolecularly-controlled topochemical reaction of conjugated dienes in homogeneous system is developed, ultimately providing two cyclooctadiene-cored tetraimidazolium molecular receptors exclusively. These cyclooctadiene derivatives exhibited highly sensitive and selective fluorescence sensing for thymine relative to other biologically relevant species in aqueous solution at physiological pH. Both the cyclooctadiene moieties and imidazolium units play important roles in the selective recognition observed. The presented supramolecularly-controlled method allows the simple yet rare selective photoconversion of flexible cyclooctadiene derivatives in solution. This study offers a new synthetic strategy for the preparation of functional molecules with potential for use in biological applications.
关键词： thymine recognition,fluorescent biomolecule probes,supramolecularly-controlled topochemical reaction,cyclooctadiene derivatives
更新于2025-09-23 15:19:57
-
[IEEE 2019 IEEE International Symposium on Phased Array System & Technology (PAST) - Waltham, MA, USA (2019.10.15-2019.10.18)] 2019 IEEE International Symposium on Phased Array System & Technology (PAST) - Dual-Polarized 28-GHz Air-Filled SIW Phased Antenna Array for Next-Generation Cellular Systems
摘要： Biometric template aging is defined as an increase in recognition error rate with increased time since enrollment. It is believed that template aging does not occur for iris recognition. Several research groups, however, have recently reported experimental results showing that iris template aging does occur. This template aging effect manifests as a shift in the authentic distribution, resulting in an increased false non-match rate. Analyzing results from a three-year time-lapse data set, we find ～ 150% increase in the false non-match rate at a decision threshold representing a one in two million false match rate. We summarize several known elements of eye aging that could contribute to template aging, including age-related change in pupil dilation. Finally, we discuss various steps that can control the template aging effect in typical identity verification applications.
关键词： iris recognition,Biometrics,error probability,false non-match rate,template aging
更新于2025-09-23 15:19:57
-
[IEEE 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Chicago, IL, USA (2019.6.16-2019.6.21)] 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Economically sustainable growth of small-scale perovskite manufacturing in alternative PV markets
摘要： This paper proposes a new computational method for retrieving shapes under unpredictable conditions such as when occlusion, geometric distortion, and differences in image resolution occur simultaneously. The human visual system retrieves shapes from incomplete information in the real world, and it has inspired a lot of computational methods of retrieving shapes. In order to retrieve shapes, the observed shapes are decided to be alike or unlike remembered shapes in memory after the comparison of these shapes. To compare the observed and remembered shapes, they must first be appropriately represented so that the points on each shape can be mapped and compared. For this reason, the shape retrieval process needs an appropriate shape representation and shape mapping methods. Moreover, the shape representations should be normalized before the mapping process. However, a normalization process for representations under unpredictable conditions has not yet been established. In this paper, we describe a shape retrieval method that enables us to retrieve shapes under unpredictable conditions with a suitable normalization process. Using curvature partition and angle-length profile, our shape retrieval method normalizes the shape representation before it does the mapping. As a result, unlike the previously proposed methods, it can be used under unpredictable conditions such as when occlusion, geometric distortion, and differences in image resolution occur simultaneously.
关键词： occlusion,Shape recognition,shape retrieval,curvature partition,geometric parameter
更新于2025-09-23 15:19:57
-
[IEEE 2019 IEEE International Conference on Sensors and Nanotechnology (SENSORS & NANO) - Penang, Malaysia (2019.7.24-2019.7.25)] 2019 IEEE International Conference on Sensors and Nanotechnology - Fabrication and Characterization of Back-Gate Controlled Silicon Nanowire based Field-effect pH Sensor
摘要： Acoustic metrics extracted from speech have the potential to serve as novel biomarkers for a variety of neurological and neurodevelopmental conditions, as is evidenced by the rapidly growing corpus of research articles studying the links between brain impairments and speech. In this paper, we discuss the advantages and the disadvantages of speech biomarkers and the various challenges in the design and the implementation of portable speech-based diagnostic and assessment tools. Furthermore, we provide a case study, presenting our experiences in developing an assessment tool for the detection of mild traumatic brain injuries (concussions) and discuss the challenges in obtaining and analyzing large sets of speech recordings that can be used to study the impact of brain injuries on vocal features.
关键词： vocal features,speech recognition,concussions,mild traumatic brain injuries,Speech analysis
更新于2025-09-23 15:19:57
-
[IEEE 2019 21st International Conference on Transparent Optical Networks (ICTON) - Angers, France (2019.7.9-2019.7.13)] 2019 21st International Conference on Transparent Optical Networks (ICTON) - Si and Si-Rich Silicon-Nitride Waveguides for Optical Transmissions and Nonlinear Applications Around 2 ??m
摘要： Grasping and manipulating everyday objects in a goal-directed manner is an important ability of a service robot. The robot needs to reason about task requirements and ground these in the sensorimotor information. Grasping and interaction with objects are challenging in real-world scenarios, where sensorimotor uncertainty is prevalent. This paper presents a probabilistic framework for the representation and modeling of robot-grasping tasks. The framework consists of Gaussian mixture models for generic data discretization, and discrete Bayesian networks for encoding the probabilistic relations among various task-relevant variables, including object and action features as well as task constraints. We evaluate the framework using a grasp database generated in a simulated environment including a human and two robot hand models. The generative modeling approach allows the prediction of grasping tasks given uncertain sensory data, as well as object and grasp selection in a task-oriented manner. Furthermore, the graphical model framework provides insights into dependencies between variables and features relevant for object grasping.
关键词： grasping,Cognitive human–robot interaction,recognition,learning and adaptive systems,probabilistic graphical models
更新于2025-09-23 15:19:57
-
Efficiency Maximization for UAV-Enabled Mobile Relaying Systems with Laser Charging
摘要： One particular challenge in biomedical named entity recognition (NER) and normalization is the identification and resolution of composite named entities, where a single span refers to more than one concept (e.g., BRCA1/2). Previous NER and normalization studies have either ignored composite mentions, used simple ad hoc rules, or only handled coordination ellipsis, making a robust approach for handling multitype composite mentions greatly needed. To this end, we propose a hybrid method integrating a machine-learning model with a pattern identification strategy to identify the individual components of each composite mention. Our method, which we have named SimConcept, is the first to systematically handle many types of composite mentions. The technique achieves high performance in identifying and resolving composite mentions for three key biological entities: genes (90.42% in F-measure), diseases (86.47% in F-measure), and chemicals (86.05% in F-measure). Furthermore, our results show that using our SimConcept method can subsequently improve the performance of gene and disease concept recognition and normalization. SimConcept is available for download at: http://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/SimConcept/
关键词： composite mentions,text mining,coordination ellipsis,bioNLP,named entity recognition
更新于2025-09-23 15:19:57
-
[IEEE 2019 21st International Conference on Transparent Optical Networks (ICTON) - Angers, France (2019.7.9-2019.7.13)] 2019 21st International Conference on Transparent Optical Networks (ICTON) - Ultrafast and Energy-Efficient All-Optical Switching Based on Graphene-Loaded Plasmonic Waveguides
摘要： In this paper, we formulate a novel time series representation framework that captures the inherent data dependency of time series and that can be easily incorporated into existing statistical classification algorithms. The impact of the proposed data representation stage in the solution to the generic underlying problem of time series classification is investigated. The proposed framework, which we call structural generative descriptions moves the structural time series representation to the probability domain, and hence is able to combine statistical and structural pattern recognition paradigms in a novel fashion. Two algorithm instantiations based on the proposed framework are developed. The algorithms are tested and compared using different publicly available real-world benchmark data. Results reported in this paper show the potential of the proposed representation framework, which in the experiments investigated, performs better or comparable to state-of-the-art time series description techniques.
关键词： time series classification,time series representation,Statistical-structural pattern recognition,structural generative descriptions (SGDs)
更新于2025-09-23 15:19:57
-
Reply to Comment on a??Photo-Controlled Reversible Microtubule Assembly Mediated by Paclitaxel-Modified Cyclodextrina??
摘要： In a Correspondence on our previous study “Photo-Controlled Reversible Microtubule Assembly Mediated by Paclitaxel-Modified Cyclodextrin” published in this journal in 2018,[1a] Thorn-Seshold comments on our results.[1b] First of all, we would like to appreciate his comments and interest in our work. The aggregation behavior of microtubules (MTs) in our work has been demonstrated from the viewpoint of macrocycle-based host–guest complexation at the supramolecular level and subsequently, the MT stabilizers based on azobenzene-modified paclitaxel (PTX) derivatives as photoswitchable small molecules have been investigated by Thorn-Seshold and co-workers in 2019.[2] In our case, the microscopy results showed that the MT morphology was dramatically affected by the photoisomeric complexation between cyclodextrin (CD) and arylazopyrazole (AAP). No fibrous assembly as free MT could be observed in the presence of free PTX-CD, PTX-AAP, or their inclusion complex in the cis/trans states. Therefore, the introduction of CD and AAP definitely influenced the self-assembling behavior between PTX and MT. Moreover, fluorescent-dye-staining assays demonstrated that the PTX-derived host and guest compounds still possessed MT-targeting ability to some extent, because MT could be co-labeled by FITC-tagged antibodies and adamantane-containing RhB. Thus, the microtubular aggregation was proposed as one of the possible assembling modes in Scheme 1 (cartoon presentation). The binding mode of MT with CD and AAP was directly deduced from our microscopy images and cellular confocal experiments. The biological effect in our work may be jointly attributed to both the PTX-dependent pathway (PTX-induced microtubular stabilization) and the PTX-independent pathway (complexation-induced multivalent supramolecular cross-linkage) at the nanometer scale.[3] Under these circumstances, one reasonable explanation is that the latter (independent) effect may become comparable to the former (dependent) one when the MT affinity is reduced by chemical modification at the 2’-OH position of PTX. Moreover, as a widely studied macrocyclic receptor in supramolecular chemistry, CD can form a diversity of supramolecular assemblies.[4] To determine the precise binding mode, in addition to the viewpoint of structural biology for evaluating the original PTX–MT interaction at the single-molecule level, many other factors and multiple supramolecular noncovalent interactions (e.g., self-inclusion, self-exclusion, amphiphilicity, extensive hydrogen bonding, and supramolecular multivalency/cooperativity) between PTX-CD and PTX-AAP should also be taken into account. For example, the multivalent inclusion complexation between multiple CD and PTX molecules may confer high stability to the nano-assembly.[5] Therefore, in our opinion, no binding mode can be exclusively confirmed at the present time until the hyperfine structures of such multicomponent CD–protein assemblies have been obtained both in solution and in the solid state (e.g., in a single crystal). Moreover, azobenzene/CD is one of the most frequently used host–guest pairs in adjusting the assembling/disassembling behavior of proteins and other biomacromolecules.[6] Meanwhile, AAP is a new type of azo compound, which possesses quite distinct photophysical behavior compared to conventional azobenzenes, such as enhanced photostability and photoconversion efficiency. The biological effect of pristine AAP on pure MT may deserve further attention, but this aspect was outside the scope of our previous study. Overall, based on NMR, TEM, UV/Vis transmittance, and confocal microscopy experiments, we clearly demonstrated in our previous study that 1) the MT self-assembling morphology can be strongly affected by the host–guest complexation between CD and AAP, and that 2) complexation-induced MT aggregation can be realized in a cellular environment. Thus, our work provides an alternative supramolecular chemistry method to modulate a biomacromolecular assembling process. Finally, we would like to thank Dr. Thorn-Seshold for his constructive suggestions and express our hope that we can improve the chemical simulation and gain further insight into the biological mechanism in further work.
关键词： molecular recognition,photo-responsiveness,cyclodextrin,supramolecular assembly,microtubules
更新于2025-09-23 15:19:57
-
[Institution of Engineering and Technology 8th Renewable Power Generation Conference (RPG 2019) - Shanghai, China (24-25 Oct. 2019)] 8th Renewable Power Generation Conference (RPG 2019) - Power grid frequency regulation participated by photovoltaic generation to adapt to different control modes of grid-side AGC
摘要： Labeling connected components and calculating the Euler number in a binary image are two fundamental processes for computer vision and pattern recognition. This paper presents an ingenious method for identifying a hole in a binary image in the first scan of connected-component labeling. Our algorithm can perform connected component labeling and Euler number computing simultaneously, and it can also calculate the connected component (object) number and the hole number efficiently. The additional cost for calculating the hole number is only O(H), where H is the hole number in the image. Our algorithm can be implemented almost in the same way as a conventional equivalent-label-set-based connected-component labeling algorithm. We prove the correctness of our algorithm and use experimental results for various kinds of images to demonstrate the power of our algorithm.
关键词： image feature,the Euler number,image analysis,the hole number,pattern recognition,Computer vision
更新于2025-09-23 15:19:57