The aim of this study is to identify types and grades of Chinese liquors. For this, a hand-held electronic nose (e-nose) system is designed and a triangular difference-based binary coding (TDBC) recognition method is ...
详细信息
The aim of this study is to identify types and grades of Chinese liquors. For this, a hand-held electronic nose (e-nose) system is designed and a triangular difference-based binary coding (TDBC) recognition method is proposed. For a test sample of liquors, features extracted from five gas sensors of the e-nose are converted into binary codes (0 and 1) for each liquor category. Specifically, for each liquor category, if a feature value of a test sample is within the feature value range of all training samples, we mark it as 1, otherwise 0. Subsequently, for each liquor category, the sum of binary codes of the test sample is calculated, and the category corresponding to the maximum sum value is determined as the predicted label of the test sample. Using the e-nose-based TDBC method, average recognition accuracies of 97.5% and 99.0% for liquor-type identification and grade evaluation were achieved, which were considerably higher than those obtained using four traditional recognition methods. These results indicate that as a novel approach, the e-nose-based TDBC method allows the recognition of Chinese liquors accurately and quickly, which is of great significance for liquor detection and industrial quality assurance methods.
The traditional pointer instrument recognition scheme is implemented in three steps, which is cumbersome and inefficient. So it is difficult to apply to the industrial production of real-time monitoring. Based on the ...
详细信息
The traditional pointer instrument recognition scheme is implemented in three steps, which is cumbersome and inefficient. So it is difficult to apply to the industrial production of real-time monitoring. Based on the improvement of the CSL coding method and the setting of the pre-cache mechanism, an intelligent reading recognition technology of the YOLOv5 pointer instrument is proposed in this paper, which realizes the rapid positioning and reading recognition of the pointer instrument. The problem of angle interaction in rotating target detection is eliminated, the complexity of image preprocessing is avoided, and the problems of poor adaptability of Hough detection are solved in this strategy. The experimental results show that compared with the traditional algorithm, the algorithm in this paper can effectively identify the angle of the pointer instrument, has high detection efficiency and strong adaptability, and has broad application prospects.
Traditional network embedding primarily focuses on learning a continuous vector representation for each node, preserving network structure and/or node content information, such that off-the-shelf machine learning algo...
详细信息
Traditional network embedding primarily focuses on learning a continuous vector representation for each node, preserving network structure and/or node content information, such that off-the-shelf machine learning algorithms can be easily applied to the vector-format node representations for network analysis. However, the learned continuous vector representations are inefficient for large-scale similarity search, which often involves finding nearest neighbors measured by distance or similarity in a continuous vector space. In this article, we propose a search efficient binary network embedding algorithm called binaryNE to learn a binary code for each node, by simultaneously modeling node context relations and node attribute relations through a three-layer neural network. binaryNE learns binary node representations using a stochastic gradient descent-based online learning algorithm. The learned binary encoding not only reduces memory usage to represent each node, but also allows fast bit-wise comparisons to support faster node similarity search than using Euclidean or other distance measures. Extensive experiments and comparisons demonstrate that binaryNE not only delivers more than 25 times faster search speed, but also provides comparable or better search quality than traditional continuous vector based network embedding methods. The binary codes learned by binaryNE also render competitive performance on node classification and node clustering tasks. The source code of the binaryNE algorithm is available at https://***/daokunzhang/binaryNE.
BackgroundLocal communities in the South Eastern Lowveld of Zimbabwe have adopted the feeding of livestock with Neorautanenia brachypus (Harms) C.A. tuber to mitigate against climate change. Differences within Neoraut...
详细信息
BackgroundLocal communities in the South Eastern Lowveld of Zimbabwe have adopted the feeding of livestock with Neorautanenia brachypus (Harms) C.A. tuber to mitigate against climate change. Differences within Neorautanenia brachypus (Harms) tuber flesh colour and preferences by cattle have been observed, suggesting possible diversity within the N. brachypus plant community. This study aimed at distinguishing the N. brachypus wild plant species through phenotypic and genetic characterization using morphological descriptors and random amplified polymorphic (RAPD) markers respectively. Leaf samples were selected using judgmental sampling techniques from wards 11-15 in Sengwe (Chiredzi district) for leaf morphology and molecular characterization. RAPD-PCR analysis was done using 18-screened random decamer primers to confirm the diversity in the plant population. The similarity of the biotypes was evaluated using binary coding on the basis of the presence or absence of a morphological indicator as well as distinct DNA amplicon fragments. Primer 7.0.13 was used to estimate morphological and genetic similarities using the unweighted pair group method with arithmetic average (UPGMA). The cluster number was estimated using the Elbow method part of the R ***, 14 biotype groups were identified from 96 accessions visually characterized basing of leaf characteristics. All the leaf biotypes displayed arcuate venation with differences observed for leaf shape, tip shape and leaf margins. The 14 biotypes clustered into six groups based on the binary data of the morphological characteristics. RAPD primers generated three hundred and sixty eight distinct amplicons with 77.5% being polymorphic from the 14 biotypes. The number of bands produced per primer ranged from four (OPF-02) to 44 (UBC-746). The PIC value ranged from 0.1327 to 0.1873 for the RAPD primers. Use of molecular markers collapsed the biotypes into five clusters. Both the leaf descriptors and RAPD ma
We are considering the capabilities and the technical features of the fast digital detection and demodulation algorithms for the signals of various modulation formats as they are realized in programmable logic devices...
详细信息
ISBN:
(纸本)9781510830981
We are considering the capabilities and the technical features of the fast digital detection and demodulation algorithms for the signals of various modulation formats as they are realized in programmable logic devices. We show that simultaneous multitype signal processing devices can be implemented in real time.
binary coding of multiplexed signals and images has been studied in the context of spectroscopy with models of either purely constant or purely proportional noise, and has been shown to result in improved noise perfor...
详细信息
binary coding of multiplexed signals and images has been studied in the context of spectroscopy with models of either purely constant or purely proportional noise, and has been shown to result in improved noise performance under certain conditions. We consider the case of mixed noise in an imaging system consisting or multiple individually-controllable sources (X-ray or near-infrared, for example) shining on a single detector. We develop a mathematical model for the noise in such a system and show that the noise is dependent on the properties of the binary coding matrix and on the average number of sources used for each code. Each binary matrix has a characteristic linear relationship between the ratio of proportional-to-constant noise and the noise level in the decoded image. We introduce a criterion for noise level, which is minimized via a genetic algorithm search. The search procedure results in the discovery or matrices that outperform the Hadamard S-matrices at certain levels of mixed noise. Simulation of a seven-source radiography system demonstrates that the noise model predicts trends and rank order of performance in regions of nonuniform images and in a simple tomosynthesis reconstruction. We conclude that the model developed provides a simple framework for analysis, discovery, and optimization of binary coding patterns used in multiplexed imaging systems.
Fisher Vector (FV) has been widely used to aggregate the local descriptors of an image into a global representation in large-scale image retrieval. However, FV has limited learning capability and its parameters are mo...
详细信息
Fisher Vector (FV) has been widely used to aggregate the local descriptors of an image into a global representation in large-scale image retrieval. However, FV has limited learning capability and its parameters are mostly fixed after constructing the codebook, which is inflexible and cannot be trained jointly with deep networks. Moreover, the high dimension of FV makes it difficult to be applied in scenarios compact descriptors are needed. In this paper, we propose a novel compact image description scheme based on Fisher network with binary embedding to solve the large-scale image retrieval problem, which consists of two components: a Fisher encoder component and a binary embedding component. Concretely, the Fisher encoder is a trainable neural network functions as the traditional FV, which aggregates the local descriptors into a global representation. And the binary encoder embeds the high-dimensional FV to a binary vector, which outputs the compact global binary descriptor. To learn such a descriptor, we further introduce a novel and effective loss function, in which maximum margin criterion is exploited to minimize the distances of positive pairs, as well as maximizing the distances of negative pairs. Extensive experiments performed on MPEG-7 CDVS benchmarks and ILSVR2010 demonstrate that the proposed framework can achieve very superior performance over the state-of-the-art methods.
Genetic algorithm (GA), as a kind of important intelligence computing tool, is a wide research content in the academic circle and the application domain now. In this paper, for the mutation operation of GA, by combini...
详细信息
ISBN:
(纸本)9781424442843
Genetic algorithm (GA), as a kind of important intelligence computing tool, is a wide research content in the academic circle and the application domain now. In this paper, for the mutation operation of GA, by combining with the essential feature, we establish a genetic algorithm based on schema mutation (denoted by SM-GA, for short). Further, we discuss the global convergence of CM-GA by using the Markov chain theory, and analyze the performance of SM-GA through an example. All the results indicate that, SM-GA is higher than the ordinary binary code genetic algorithm (denoted by B2GA, for short) in convergence precision. There was no significant difference between SM-GA and B2GA in convergence time. SM-GA overcomes the problem that B2GA can not converge strongly to some extent.
暂无评论