Joint Deep Learning and Clustering Algorithm for Liquid Particle Detection of Pharmaceutical Injection

AbstractSingle-cell RNA sequencing (scRNA-seq) is a recent technology that enables fine-grained discovery of cellular subtypes and specific cell states. It routinely uses machine learning methods, such as feature learning, clustering, and classification, to assist in uncovering novel information from scRNA-seq data. However, current methods are not well suited to deal with the substantial amounts of noise that is created by the experiments or the variation that occurs due to differences in the cells of the same type. Here, we develop a new hybrid approach, Deep Unsupervised Single-cell Clustering (DUSC), that integrates feature generation based on a deep learning architecture with a model-based clustering algorithm, to find a compact and informative representation of the single-cell transcriptomic data generating robust clusters. We also include a technique to estimate an efficient number of latent features in the deep learning model. Our method outperforms both classical and state-of-the-art feature learning and clustering methods, approaching the accuracy of supervised learning. The method is freely available to the community and will hopefully facilitate our understanding of the cellular atlas of living organisms as well as provide the means to improve patient diagnostics and treatment.

Download Full-text

Gradient clustering algorithm based on deep learning aerial image detection

Pattern Recognition Letters ◽

10.1016/j.patrec.2020.09.032 ◽

2021 ◽

Vol 141 ◽

pp. 37-44

Author(s):

Ning Liu ◽

Bin Guo ◽

Xinju Li ◽

Xiangyu Min

Keyword(s):

Deep Learning ◽

Clustering Algorithm ◽

Aerial Image ◽

Image Detection

Download Full-text

Deep Learning for Fingerprint Localization in Indoor and Outdoor Environments

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi9040267 ◽

2020 ◽

Vol 9 (4) ◽

pp. 267 ◽

Cited By ~ 2

Author(s):

Da Li ◽

Yingke Lei ◽

Xin Li ◽

Haichuan Zhang

Keyword(s):

Magnetic Field ◽

Deep Learning ◽

Clustering Algorithm ◽

Fingerprint Image ◽

Density Peak ◽

Localization Accuracy ◽

Localization System ◽

Outdoor Environments ◽

Indoor And Outdoor Environments ◽

Indoor And Outdoor

Wi-Fi and magnetic field fingerprinting-based localization have gained increased attention owing to their satisfactory accuracy and global availability. The common signal-based fingerprint localization deteriorates due to well-known signal fluctuations. In this paper, we proposed a Wi-Fi and magnetic field-based localization system based on deep learning. Owing to the low discernibility of magnetic field strength (MFS) in large areas, the unsupervised learning density peak clustering algorithm based on the comparison distance (CDPC) algorithm is first used to pick up several center points of MFS as the geotagged features to assist localization. Considering the state-of-the-art application of deep learning in image classification, we design a location fingerprint image using Wi-Fi and magnetic field fingerprints for localization. Localization is casted in a proposed deep residual network (Resnet) that is capable of learning key features from a massive fingerprint image database. To further enhance localization accuracy, by leveraging the prior information of the pre-trained Resnet coarse localizer, an MLP-based transfer learning fine localizer is introduced to fine-tune the coarse localizer. Additionally, we dynamically adjusted the learning rate (LR) and adopted several data enhancement methods to increase the robustness of our localization system. Experimental results show that the proposed system leads to satisfactory localization performance both in indoor and outdoor environments.

Download Full-text

Deep Learning Particle Detection for Probabilistic Tracking in Fluorescence Microscopy Images

2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI) ◽

10.1109/isbi45749.2020.9098598 ◽

2020 ◽

Author(s):

C. Ritter ◽

T. Wollmann ◽

J.-Y. Lee ◽

R. Bartenschlager ◽

K. Rohr

Keyword(s):

Deep Learning ◽

Fluorescence Microscopy ◽

Particle Detection ◽

Probabilistic Tracking ◽

Microscopy Images

Download Full-text

Combining DBN and FCM for Fault Diagnosis of Roller Element Bearings without Using Data Labels

Shock and Vibration ◽

10.1155/2018/3059230 ◽

2018 ◽

Vol 2018 ◽

pp. 1-12 ◽

Cited By ~ 2

Author(s):

Fan Xu ◽

Yan jun Fang ◽

Dong Wang ◽

Jia qi Liang ◽

Kwok Leung Tsui

Keyword(s):

Deep Learning ◽

Fault Diagnosis ◽

Clustering Algorithm ◽

Principal Component ◽

Belief Networks ◽

Deep Belief Networks ◽

Vibration Signals ◽

Fuzzy C Means ◽

Roller Bearings ◽

Mode Decomposition

Because deep belief networks (DBNs) in deep learning have a powerful ability to extract useful information from the raw data without prior knowledge, DBNs are used to extract the useful feature from the roller bearings vibration signals. Unlike classification methods, the clustering method can classify the different fault types without data label. Therefore, a method based on deep belief networks (DBNs) in deep learning (DL) and fuzzy C-means (FCM) clustering algorithm for roller bearings fault diagnosis without a data label is presented in this paper. Firstly, the roller bearings vibration signals are extracted by using DBN, and then principal component analysis (PCA) is used to reduce the dimension of the vibration signal features. Secondly, the first two principal components (PCs) are selected as the input of fuzzy C-means (FCM) for roller bearings fault identification. Finally, the experimental results show that the fault diagnosis of the method presented is better than that of other combination models, such as variation mode decomposition- (VMD-) singular value decomposition- (SVD-) FCM, and ensemble empirical mode decomposition- (EEMD-) fuzzy entropy- (FE-) PCA-FCM.

Download Full-text

Wood Defect Detection Based on Depth Extreme Learning Machine

Applied Sciences ◽

10.3390/app10217488 ◽

2020 ◽

Vol 10 (21) ◽

pp. 7488

Author(s):

Yutu Yang ◽

Xiaolin Zhou ◽

Ying Liu ◽

Zhongkang Hu ◽

Fenglong Ding

Keyword(s):

Deep Learning ◽

Extreme Learning Machine ◽

Defect Detection ◽

Clustering Algorithm ◽

Classification Performance ◽

Image Features ◽

Test Time ◽

Machine Model ◽

Feature Extraction Method ◽

Learning Machine

The deep learning feature extraction method and extreme learning machine (ELM) classification method are combined to establish a depth extreme learning machine model for wood image defect detection. The convolution neural network (CNN) algorithm alone tends to provide inaccurate defect locations, incomplete defect contour and boundary information, and inaccurate recognition of defect types. The nonsubsampled shearlet transform (NSST) is used here to preprocess the wood images, which reduces the complexity and computation of the image processing. CNN is then applied to manage the deep algorithm design of the wood images. The simple linear iterative clustering algorithm is used to improve the initial model; the obtained image features are used as ELM classification inputs. ELM has faster training speed and stronger generalization ability than other similar neural networks, but the random selection of input weights and thresholds degrades the classification accuracy. A genetic algorithm is used here to optimize the initial parameters of the ELM to stabilize the network classification performance. The depth extreme learning machine can extract high-level abstract information from the data, does not require iterative adjustment of the network weights, has high calculation efficiency, and allows CNN to effectively extract the wood defect contour. The distributed input data feature is automatically expressed in layer form by deep learning pre-training. The wood defect recognition accuracy reached 96.72% in a test time of only 187 ms.

Download Full-text

A High-Order CFS Algorithm for Clustering Big Data

Mobile Information Systems ◽

10.1155/2016/4356127 ◽

2016 ◽

Vol 2016 ◽

pp. 1-8 ◽

Cited By ~ 4

Author(s):

Fanyu Bu ◽

Zhikui Chen ◽

Peng Li ◽

Tong Tang ◽

Ying Zhang

Keyword(s):

Big Data ◽

Deep Learning ◽

Clustering Algorithm ◽

Big Data Analytics ◽

Learning Model ◽

Heterogeneous Data ◽

High Order ◽

Tensor Model ◽

Industrial Internet ◽

Deep Learning Model

With the development of Internet of Everything such as Internet of Things, Internet of People, and Industrial Internet, big data is being generated. Clustering is a widely used technique for big data analytics and mining. However, most of current algorithms are not effective to cluster heterogeneous data which is prevalent in big data. In this paper, we propose a high-order CFS algorithm (HOCFS) to cluster heterogeneous data by combining the CFS clustering algorithm and the dropout deep learning model, whose functionality rests on three pillars: (i) an adaptive dropout deep learning model to learn features from each type of data, (ii) a feature tensor model to capture the correlations of heterogeneous data, and (iii) a tensor distance-based high-order CFS algorithm to cluster heterogeneous data. Furthermore, we verify our proposed algorithm on different datasets, by comparison with other two clustering schemes, that is, HOPCM and CFS. Results confirm the effectiveness of the proposed algorithm in clustering heterogeneous data.

Download Full-text

Soybean Yield Preharvest Prediction Based on Bean Pods and Leaves Image Recognition Using Deep Learning Neural Network Combined With GRNN

Frontiers in Plant Science ◽

10.3389/fpls.2021.791256 ◽

2022 ◽

Vol 12 ◽

Author(s):

Wei Lu ◽

Rongting Du ◽

Pengshuai Niu ◽

Guangnan Xing ◽

Hui Luo ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Image Recognition ◽

Clustering Algorithm ◽

Prediction Models ◽

Soybean Seed ◽

Soybean Plant ◽

Single Shot ◽

Yield Prediction ◽

Soybean Yield

Soybean yield is a highly complex trait determined by multiple factors such as genotype, environment, and their interactions. The earlier the prediction during the growing season the better. Accurate soybean yield prediction is important for germplasm innovation and planting environment factor improvement. But until now, soybean yield has been determined by weight measurement manually after soybean plant harvest which is time-consuming, has high cost and low precision. This paper proposed a soybean yield in-field prediction method based on bean pods and leaves image recognition using a deep learning algorithm combined with a generalized regression neural network (GRNN). A faster region-convolutional neural network (Faster R-CNN), feature pyramid network (FPN), single shot multibox detector (SSD), and You Only Look Once (YOLOv3) were employed for bean pods recognition in which recognition precision and speed were 86.2, 89.8, 80.1, 87.4%, and 13 frames per second (FPS), 7 FPS, 24 FPS, and 39 FPS, respectively. Therefore, YOLOv3 was selected considering both recognition precision and speed. For enhancing detection performance, YOLOv3 was improved by changing IoU loss function, using the anchor frame clustering algorithm, and utilizing the partial neural network structure with which recognition precision increased to 90.3%. In order to improve soybean yield prediction precision, leaves were identified and counted, moreover, pods were further classified as single, double, treble, four, and five seeds types by improved YOLOv3 because each type seed weight varies. In addition, soybean seed number prediction models of each soybean planter were built using PLSR, BP, and GRNN with the input of different type pod numbers and leaf numbers with which prediction results were 96.24, 96.97, and 97.5%, respectively. Finally, the soybean yield of each planter was obtained by accumulating the weight of all soybean pod types and the average accuracy was up to 97.43%. The results show that it is feasible to predict the soybean yield of plants in situ with high precision by fusing the number of leaves and different type soybean pods recognized by a deep neural network combined with GRNN which can speed up germplasm innovation and planting environmental factor optimization.

Download Full-text

DeepDBSCAN: Deep Density-Based Clustering for Geo-Tagged Photos

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi10080548 ◽

2021 ◽

Vol 10 (8) ◽

pp. 548

Author(s):

Jang-You Park ◽

Dong-June Ryu ◽

Kwang-Woo Nam ◽

Insung Jang ◽

Minseok Jang ◽

...

Keyword(s):

Deep Learning ◽

Clustering Algorithm ◽

Nearest Neighbor ◽

Spatial Clustering ◽

Clustering Algorithms ◽

Learning Technology ◽

Neighbor Graph ◽

Density Based Clustering ◽

Real Objects ◽

Nearest Neighbor Graph

Density-based clustering algorithms have been the most commonly used algorithms for discovering regions and points of interest in cities using global positioning system (GPS) information in geo-tagged photos. However, users sometimes find more specific areas of interest using real objects captured in pictures. Recent advances in deep learning technology make it possible to recognize these objects in photos. However, since deep learning detection is a very time-consuming task, simply combining deep learning detection with density-based clustering is very costly. In this paper, we propose a novel algorithm supporting deep content and density-based clustering, called deep density-based spatial clustering of applications with noise (DeepDBSCAN). DeepDBSCAN incorporates object detection by deep learning into the density clustering algorithm using the nearest neighbor graph technique. Additionally, this supports a graph-based reduction algorithm that reduces the number of deep detections. We performed experiments with pictures shared by users on Flickr and compared the performance of multiple algorithms to demonstrate the excellence of the proposed algorithm.

Download Full-text