- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Machine learning for improved data analysis of biological aerosol using the WIBS
摘要： Primary biological aerosol including bacteria, fungal spores and pollen have important implications for public health and the environment. Such particles may have different concentrations of chemical fluorophores and will respond differently in the presence of ultraviolet light, potentially allowing for different types of biological aerosol to be discriminated. Development of ultraviolet light induced fluorescence (UV-LIF) instruments such as the Wideband Integrated Bioaerosol Sensor (WIBS) has allowed for size, morphology and fluorescence measurements to be collected in real-time. However, it is unclear without studying instrument responses in the laboratory, the extent to which different types of particles can be discriminated. Collection of laboratory data is vital to validate any approach used to analyse data and ensure that the data available is utilized as effectively as possible.
关键词： biological aerosol,UV-LIF,WIBS,clustering,machine learning
更新于2025-09-23 15:21:21
-
[Lecture Notes in Computer Science] Intelligence Science and Big Data Engineering Volume 11266 (8th International Conference, IScIDE 2018, Lanzhou, China, August 18–19, 2018, Revised Selected Papers) || An Improved Spectral Clustering Algorithm Based on Dynamic Tissue-Like Membrane System
摘要： With vast amount of data generated, it is becoming a main aspect to mine useful information from such data. Clustering research is an important task of data mining. Traditional clustering algorithms such as K-means algorithm are too old to propose high-dimensional data, so an ef?cient clustering algorithm, spectral clustering is generated. In recent years, more and more scholars has been ?rmly committing to studying spectral clustering algorithm for its solid theoretical foundation and excellent clustering results. In this paper we propose an improved spectral clustering algorithm based on Dynamic Tissue-like P System abbreviated as ISC-DTP. ISC-DTP algorithm takes use of the advantages of maximal parallelism in tissue-like membrane system. Experiment is conducted on an arti?cial data set and four UCI data sets. And we compare the ISC-DTP algorithm with original spectral clustering algorithm and K-means algorithm. The experiments demonstrate the effectiveness and robustness of the proposed algorithm.
关键词： Spectral clustering algorithm,Tissue-like membrane system,Data mining,ISC-DTP algorithm
更新于2025-09-23 15:21:21
-
Cluster-based Resource Allocation and User Association in mmWave Femtocell Networks
摘要： In millimeter wave(mmW) dense femto-networks, major challenges are overcoming the performance loss imposed by channel and managing the co-channel interference. The former is due to mmW susceptibility to pathloss and shadowing and the latter is due to density of the network. We cope with both challenges by a clustering method designed for mmW environment. In our approach, the femto access points (FAP) and femto users (FU) are clustered based on having the most line of sight connectivity. We modify this binary optimization problem into a continuous problem using deductive penalty functions and solve it by difference of two convex functions (D.C.) programming. Our clustering algorithm achieves higher data rate compared to the foremost clustering method. We also propose a technique to assign FUs to FAPs in each cluster which has near-optimal performance and polynomial time complexity. We solve mixed integer nonlinear programming of power and sub-channel allocation by D.C. programming. Instead of using the deductive penalty terms in D.C. programming, we penalize the objective function in a multiplicative manner. Thus, the penalty term depends on both constraint violation and objective function. Our scheme achieves around 10% higher data rate compared to the method using deductive penalty terms.
关键词： D.C. programming,Resource allocation,Multiplicative penalty function,User association,Clustering,mmWave,Femto cell
更新于2025-09-23 15:21:21
-
Day-ahead photovoltaic power production forecasting methodology based on machine learning and statistical post-processing
摘要： A main challenge towards ensuring large-scale and seamless integration of photovoltaic systems is to improve the accuracy of energy yield forecasts, especially in grid areas of high photovoltaic shares. The scope of this paper is to address this issue by presenting a uni?ed methodology for hourly-averaged day-ahead photovoltaic power forecasts with improved accuracy, based on data-driven machine learning techniques and statistical post-processing. More speci?cally, the proposed forecasting methodology framework comprised of a data quality stage, data-driven power output machine learning model development (arti?cial neural networks), weather clustering assessment (K-means clustering), post-processing output optimisation (linear regressive correction method) and the ?nal performance accuracy evaluation. The results showed that the application of linear regression coe?cients to the forecasted outputs of the developed day-ahead photovoltaic power production neural network improved the performance accuracy by further correcting solar irradiance forecasting biases. The resulting optimised model provided a mean absolute percentage error of 4.7% when applied to historical system datasets. Finally, the model was validated both, at a hot as well as a cold semi-arid climatic location, and the obtained results demonstrated close agreement by yielding forecasting accuracies of mean absolute percentage error of 4.7% and 6.3%, respectively. The validation analysis provides evidence that the proposed model exhibits high performance in both forecasting accuracy and stability.
关键词： Performance,Forecasting,Machine learning,Photovoltaic,Arti?cial neural networks,Clustering
更新于2025-09-23 15:21:01
-
[IEEE 2019 Compound Semiconductor Week (CSW) - Nara, Japan (2019.5.19-2019.5.23)] 2019 Compound Semiconductor Week (CSW) - $\mathbf{1545}\ \mu \mathbf{m}$ Quantum Dot Vertical Cavity Surface Emitting Laser with low threshold
摘要： Approximate Nearest Neighbor (ANN) search has become a popular approach for performing fast and efficient retrieval on very large-scale datasets in recent years, as the size and dimension of data grow continuously. In this paper, we propose a novel vector quantization method for ANN search which enables faster and more accurate retrieval on publicly available datasets. We define vector quantization as a multiple affine subspace learning problem and explore the quantization centroids on multiple affine subspaces. We propose an iterative approach to minimize the quantization error in order to create a novel quantization scheme, which outperforms the state-of-the-art algorithms. The computational cost of our method is also comparable to that of the competing methods.
关键词： vector quantization,Approximate nearest neighbor search,subspace clustering,large-scale retrieval,binary codes
更新于2025-09-23 15:21:01
-
Argon clustering in silicon under low-energy irradiation: Molecular dynamics simulation with different Ar–Si potentials
摘要： In this paper, the authors carried out a molecular dynamics simulation of crystal and amorphous silicon sputtering by low-energy (200 eV) Ar ions at normal incidence. The gradual damage of silicon caused by the ion bombardment was taken into account in order to study the dynamics of argon accumulation and clustering. For describing interatomic Ar–Si interaction, they used three different potentials: two binary screened Coulomb potentials (Molière and Ziegler–Biersack–Littmark) and the potential developed on the basis of density functional theory. The obtained results demonstrated the substantial influence of the chosen Ar–Si potential on calculated sputtering yields and on the processes of argon accumulation and clustering.
关键词： silicon sputtering,molecular dynamics simulation,Ar–Si potentials,argon clustering,low-energy irradiation
更新于2025-09-23 15:21:01
-
[Advances in Intelligent Systems and Computing] Recent Findings in Intelligent Computing Techniques Volume 709 (Proceedings of the 5th ICACNI 2017, Volume 3) || Detection and Analysis of Oil Spill in Ocean for Reduced Complexity in Extraction Using Image Processing
摘要： Oil spills occurring in oceans are difficult to detect and require sophisticated measures to obtain and analyze the images. In this chapter, both color image using high-resolution cameras and Synthetic Aperture Radar (SAR) images are analyzed and certain useful results are obtained to reduce the complexity in extracting the oil spills. The recognition and examination of the oil spill images are done using image processing technique. Furthermore, if the oil spill is scattered as patches, the algorithm classifies the patches into smaller patches and larger ones by using k-means clustering. Hence, the patches depending on the size or intensity can be extracted on a simpler basis.
关键词： Image processing,Synthetic aperture radar (SAR) images,Machine learning,K-means clustering
更新于2025-09-23 15:21:01
-
Active cluster crystals
摘要： We study the appearance and properties of cluster crystals (solids in which the unit cell is occupied by a cluster of particles) in a two-dimensional system of self-propelled active Brownian particles with repulsive interactions. Self-propulsion deforms the clusters by depleting particle density inside, and for large speeds it melts the crystal. Continuous ?eld descriptions at several levels of approximation allow us to identify the relevant physical mechanisms.
关键词： non-equilibrium statistical mechanics,emergence of patterns,active matter,clustering,self-propelling particles
更新于2025-09-23 15:21:01
-
Decoupling mesoscale functional response in PLZT across the ferroelectric – relaxor phase transition with contact Kelvin probe force microscopy and machine learning
摘要： Relaxor ferroelectrics exhibit a range of interesting material behavior including high electromechanical response, polarization rotations as well as temperature and electric field-driven phase transitions. The origin of this unusual functional behavior remains elusive due to limited knowledge on polarization dynamics at the nanoscale. Piezoresponse force microscopy and associated switching spectroscopy provide access to local electromechanical properties on the micro- and nanoscale, which can help to address some of these gaps in our knowledge. However, these techniques are inherently prone to artefacts caused by signal contributions emanating from electrostatic interactions between tip and sample. Understanding functional behavior of complex, disordered systems like relaxor materials with unknown electromechanical properties therefore requires a technique that allows to distinguish between electromechanical and electrostatic response. Here, contact Kelvin probe force microscopy (cKPFM) is used to gain insight into the evolution of local electromechanical and capacitive properties of a representative relaxor material lead lanthanum zirconate across the phase transition from a ferroelectric to relaxor state. The obtained multidimensional data set was processed using an unsupervised machine learning algorithm to detect variations in functional response across the probed area and temperature range. Further analysis showed formation of two separate cKPFM response bands below 50°C, providing evidence for polarization switching. At higher temperatures only one band is observed, indicating an electrostatic origin of the measured response. In addition, from the cKPFM data qualitatively extracted junction potential difference, becomes independent of the temperature in the relaxor state. The combination of this multidimensional voltage spectroscopy technique and machine learning allows to identify the origin of the measured functional response and to decouple ferroelectric from electrostatic phenomena necessary to understand the functional behavior of complex, disordered systems like relaxor materials.
关键词： phase transition,machine learning,Relaxor ferroelectric,lead lanthanum zirconium titanate,piezoresponse force microscopy,k-means clustering,contact Kelvin probe force microscopy
更新于2025-09-23 15:21:01
-
Parallel K-Means Clustering for Brain Cancer Detection Using Hyperspectral Images
摘要： The precise delineation of brain cancer is a crucial task during surgery. There are several techniques employed during surgical procedures to guide neurosurgeons in the tumor resection. However, hyperspectral imaging (HSI) is a promising non-invasive and non-ionizing imaging technique that could improve and complement the currently used methods. The HypErspectraL Imaging Cancer Detection (HELICoiD) European project has addressed the development of a methodology for tumor tissue detection and delineation exploiting HSI techniques. In this approach, the K-means algorithm emerged in the delimitation of tumor borders, which is of crucial importance. The main drawback is the computational complexity of this algorithm. This paper describes the development of the K-means clustering algorithm on different parallel architectures, in order to provide real-time processing during surgical procedures. This algorithm will generate an unsupervised segmentation map that, combined with a supervised classification map, will offer guidance to the neurosurgeon during the tumor resection task. We present parallel K-means clustering based on OpenMP, CUDA and OpenCL paradigms. These algorithms have been validated through an in-vivo hyperspectral human brain image database. Experimental results show that the CUDA version can achieve a speed-up of ~150× with respect to a sequential processing. The remarkable result obtained in this paper makes possible the development of a real-time classification system.
关键词： unsupervised clustering,brain cancer detection,Graphics Processing Units (GPUs),OpenCL,CUDA,K-means,OpenMP,hyperspectral imaging
更新于2025-09-23 15:21:01