We present a novel approach to crystallographic ligand density interpretation based on Zernike shape descriptors. Electron density for a bound ligand is expanded in an orthogonal polynomial series (3D Zernike polynomi...
详细信息
ISBN:
(纸本)9783642040306
We present a novel approach to crystallographic ligand density interpretation based on Zernike shape descriptors. Electron density for a bound ligand is expanded in an orthogonal polynomial series (3D Zernike polynomials) and the coefficients from this expansion are employed to construct rotation-invariant descriptors. these descriptors can be compared highly efficiently against large databases of descriptors computed front other molecules. In this manuscript we describe this process and show initial results from an electron density interpretation study oil a dataset containing over a hundred OMIT maps. We could identify the correct ligand as the first hit in about 30% of the cases, within the top five in a further 30% of the cases, and giving rise to an 80% probability of getting the correct ligand within the top ten matches. In all but a few examples, the top hit was highly similar to the correct ligand in both shape and chemistry. Further extensions and intrinsic limitations of the method are discussed.
Disabled forelimb has been a main obstacle for people to communicate with computer by keyboard. To achieve the interface with computer, most of them have to use voice commands to interact with it. But this kind of int...
详细信息
ISBN:
(纸本)9781665424257
Disabled forelimb has been a main obstacle for people to communicate with computer by keyboard. To achieve the interface with computer, most of them have to use voice commands to interact with it. But this kind of interface has many inconveniences, such as the inability of using it in both noisy and quiet places as well as inadequate provision of commands compared to keyboard. Surface electromyography (sEMG)is a kind of signal that is created when muscles start to contract or the brain produces nerve impulses for muscle contraction. Also the existence of sEMG signals does not depend on the integrity of hands. this project aims to explore the possibility of exploiting sEMG signals to realize that the disabled can interact withthe computer through the keyboard. We designed a series of hand movements (sEMG signals) and made them correspond one-to-one with specific strings. By detecting and recognizing the sEMG signals of muscles, the disabled can use the virtual keyboard to interact withthe computer normally. In addition, we also designed a signal processing method based on multi-class support vector machine (SVM) with error-correcting output code (ECOC) and label-threshold pre-process. It helps patients in need create their own sEMG signal recognition model. Traditional signal processing method with floating window can accurately identify each action, but it will output the classification results of each action several times, which will cause great inconvenience to the use of the virtual keyboard. this new signal processing method with ECOC and pre-process greatly avoids this problem.
this paper studies the characteristics of denoised partial discharge (PD) signals and then puts forward a new method to extract features from distribution of PD energy against relevant phase position. the analysis res...
详细信息
ISBN:
(纸本)7506251159
this paper studies the characteristics of denoised partial discharge (PD) signals and then puts forward a new method to extract features from distribution of PD energy against relevant phase position. the analysis results to field measured data shows the efficiency and practicability of the new method.
this paper describes the various aspects of the BEDMOND AAL Joint Programme project, which aims at the development of an ICT-based system for the early detection of Alzheimer's disease and other neurodegenerative ...
详细信息
A new approach to facial expression recognition is constructed by combining the Local Binary pattern and Laplacian Eigenmaps. Firstly, each image is transformed by an LBP operator and then divided into 3x5 non-overlap...
详细信息
ISBN:
(纸本)9783642040696
A new approach to facial expression recognition is constructed by combining the Local Binary pattern and Laplacian Eigenmaps. Firstly, each image is transformed by an LBP operator and then divided into 3x5 non-overlapping blocks. the features of facial expression images are formed by concatenating the LBP histogram of each block. Secondly, linear graph embedding framework is used as a platform, and then Laplacian Eigenmaps is developed under this framework and applied for feature dimensionality reduction. Finally, Support Vector Machine is used to classify the seven expressions (anger, disgust, fear, happiness, neutral, sadness and Surprise) on JAFFE database. the maximum facial expression recognition rate of the proposed algorithm reaches to 70.48% for person-independent recognition, which is much better than that of LBP+PCA and LBP+LDA algorithms. the experiment results prove that the facial expression recognition with local binary pattern and Laplacian Eigenmaps is an effective and feasible algorithm.
An important problem for blind people during their navigation in the outdoor environment is the need for external help while reaching a specific place. In order to reduce this dependence, a smart mobile system capable...
详细信息
An important problem for blind people during their navigation in the outdoor environment is the need for external help while reaching a specific place. In order to reduce this dependence, a smart mobile system capable of simple scene descriptions and useful landmarks should be developed. this study proposes a system that provides an interpretation of real scenes through single (monocular) image analysis. the efficiency and effectiveness of the proposed system is validated using Indoor and Outdoor scenes in natural situations without any expedient to make image interpretation easier.
the objective of this study is to find an appropriate method of improving spectral image classifications. To fulfill this objective, a slightly modified k-Nearest-Neighbour strategy is proposed for the calculation of ...
详细信息
the objective of this study is to find an appropriate method of improving spectral image classifications. To fulfill this objective, a slightly modified k-Nearest-Neighbour strategy is proposed for the calculation of feature-probability densities. In addition, the method of using spatially distributed prior probabilities is reviewed and shown how it can be perfectly combined withthe proposed method. By conducting several experiments, it is found that the proposed strategy serves the purpose of accurately estimating class-areas, as well as increasing classification accuracies to the same extent as the 'pixel prior' method does.
the proceedings contain 123 papers. the special focus in this conference is on patternrecognition. the topics include: Continual Learning of Image Translation Networks Using Task-Dependent Weight Selection Masks;a Re...
ISBN:
(纸本)9783030412982
the proceedings contain 123 papers. the special focus in this conference is on patternrecognition. the topics include: Continual Learning of Image Translation Networks Using Task-Dependent Weight Selection Masks;a Real-Time Eye Tracking Method for Detecting Optokinetic Nystagmus;network Structure for Personalized Face-Pose Estimation Using Incrementally Updated Face-Shape Parameters;optimal Rejection Function Meets Character recognition Tasks;comparing the recognition Accuracy of Humans and Deep Learning on a Simple Visual Inspection Task;improved Gamma Corrected Layered Adaptive Background Model;one-Shot Learning-Based Handwritten Word recognition;first-Person View Hand Parameter Estimation Based on Fully Convolutional Neural Network;dual-Attention Graph Convolutional Network;enhancing Open-Set Face recognition by Closing It with Cluster-Inferred Gallery Augmentation;chart-Type Classification Using Convolutional Neural Network for Scholarly Figures;handwritten Digit String recognition for Indian Scripts;spatial-Temporal Graph Attention Network for Video-Based Gait recognition;supervised Interactive Co-segmentation Using Histogram Matching and Bipartite Graph Construction;Using Deep Convolutional LSTM Networks for Learning Spatiotemporal Features;two-Stage Fully Convolutional Networks for Stroke Recovery of Handwritten Chinese Character;text Like Classification of Skeletal Sequences for Human Action recognition;Background Subtraction Based on Encoder-Decoder Structured CNN;multi Facet Face Construction;Automated 2D Fetal Brain Segmentation of MR Images Using a Deep U-Net;action recognition in Untrimmed Videos with Composite Self-attention Two-Stream Framework;EEG Representations of Spatial and Temporal Features in Imagined Speech and Overt Speech;GAN-based Abnormal Detection by Recognizing Ungeneratable patterns;modality-Specific Learning Rate Control for Multimodal Classification;3D Multi-frequency Fully Correlated Causal Random Field Texture Model;meaning Guided
In this paper, a practical postal numeral segmentation and recognition system for Chinese business letters is presented. Line information for the address blocks is gained from the envelope image by projection, then th...
详细信息
We present CTC, a new approach to structural classification. It uses the predictive power of tree patterns correlating withthe class values, combining state-of-the-art tree mining with sophisticated pruning technique...
详细信息
ISBN:
(纸本)0769522785
We present CTC, a new approach to structural classification. It uses the predictive power of tree patterns correlating withthe class values, combining state-of-the-art tree mining with sophisticated pruning techniques to find the k most discriminative pattern in a dataset. In contrast to existing methods, CTC uses no heuristics and the only parameters to be chosen by the user are the maximum size of the rule set and a single, statistically well founded cut-off value. the experiments show that CTC classifiers achieve good accuracies while the induced models are smaller than those of existing approaches, facilitating comprehensibility.
暂无评论