scholarly journals Cousin Network Guided Sketch Recognition via Latent Attribute Warehouse

2019 ◽  
Vol 33 ◽  
pp. 9203-9210 ◽  
Author(s):  
Kaihao Zhang ◽  
Wenhan Luo ◽  
Lin Ma ◽  
Hongdong Li
Keyword(s):  
Natural Images ◽  
Classification Model ◽  
Superior Performance ◽  
Natural Image ◽  
Sketch Recognition ◽  
Image Domain ◽  
Current State ◽  
Proposed Model ◽  
Adversarial Training ◽  
Latent Attribute

We study the problem of sketch image recognition. This problem is plagued with two major challenges: 1) sketch images are often scarce in contrast to the abundance of natural images, rendering the training task difficult, and 2) the significant domain gap between sketch image and its natural image counterpart makes the task of bridging the two domains challenging. In order to overcome these challenges, in this paper we propose to transfer the knowledge of a network learned from natural images to a sketch network - a new deep net architecture which we term as cousin network. This network guides a sketch-recognition network to extract more relevant features that are close to those of natural images, via adversarial training. Moreover, to enhance the transfer ability of the classification model, a sketch-to-image attribute warehouse is constructed to approximate the transformation between the sketch domain and the real image domain. Extensive experiments conducted on the TU-Berlin dataset show that the proposed model is able to efficiently distill knowledge from natural images and achieves superior performance than the current state of the art.

scholarly journals One-shot Cluster-Based Approach for the Detection of COVID–19 from Chest X–ray Images

2021 ◽  
Author(s):  
V. N. Manjunath Aradhya ◽  
Mufti Mahmud ◽  
D. S. Guru ◽  
Basant Agarwal ◽  
M. Shamim Kaiser
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Probabilistic Neural Network ◽  
Classification Model ◽  
Superior Performance ◽  
Generalized Regression Neural Network ◽  
X Rays ◽  
X Ray ◽  
Proposed Model ◽  
Chest X Ray

AbstractCoronavirus disease (COVID-19) has infected over more than 28.3 million people around the globe and killed 913K people worldwide as on 11 September 2020. With this pandemic, to combat the spreading of COVID-19, effective testing methodologies and immediate medical treatments are much required. Chest X-rays are the widely available modalities for immediate diagnosis of COVID-19. Hence, automation of detection of COVID-19 from chest X-ray images using machine learning approaches is of greater demand. A model for detecting COVID-19 from chest X-ray images is proposed in this paper. A novel concept of cluster-based one-shot learning is introduced in this work. The introduced concept has an advantage of learning from a few samples against learning from many samples in case of deep leaning architectures. The proposed model is a multi-class classification model as it classifies images of four classes, viz., pneumonia bacterial, pneumonia virus, normal, and COVID-19. The proposed model is based on ensemble of Generalized Regression Neural Network (GRNN) and Probabilistic Neural Network (PNN) classifiers at decision level. The effectiveness of the proposed model has been demonstrated through extensive experimentation on a publicly available dataset consisting of 306 images. The proposed cluster-based one-shot learning has been found to be more effective on GRNN and PNN ensembled model to distinguish COVID-19 images from that of the other three classes. It has also been experimentally observed that the model has a superior performance over contemporary deep learning architectures. The concept of one-shot cluster-based learning is being first of its kind in literature, expected to open up several new dimensions in the field of machine learning which require further researching for various applications.

scholarly journals Microgrid Fault Detection and Classification: Machine Learning Based Approach, Comparison, and Reviews

Energies ◽  
2020 ◽  
Vol 13 (13) ◽  
pp. 3460 ◽  
Author(s):  
Shahriar Rahman Fahim ◽  
Subrata K. Sarker ◽  
S. M. Muyeen ◽  
Md. Rafiqul Islam Sheikh ◽  
Sajal K. Das
Keyword(s):  
Fault Diagnosis ◽  
Fault Detection ◽  
Classification Model ◽  
Superior Performance ◽  
Fault Classification ◽  
Support Vector ◽  
Discrete Wavelet ◽  
Fault Detection And Classification ◽  
Proposed Model ◽  
The Individual

Accurate fault classification and detection for the microgrid (MG) becomes a concern among the researchers from the state-of-art of fault diagnosis as it increases the chance to increase the transient response. The MG frequently experiences a number of shunt faults during the distribution of power from the generation end to user premises, which affects the system reliability, damages the load, and increases the fault line restoration cost. Therefore, a noise-immune and precise fault diagnosis model is required to perform the fast recovery of the unhealthy phases. This paper presents a review on the MG fault diagnosis techniques with their limitations and proposes a novel discrete-wavelet transform (DWT) based probabilistic generative model to explore the precise solution for fault diagnosis of MG. The proposed model is made of multiple layers with a restricted Boltzmann machine (RBM), which enables the model to make the probability reconstruction over its inputs. The individual RBM layer is trained with an unsupervised learning approach where an artificial neural network (ANN) algorithm tunes the model for minimizing the error between the true and predicted class. The effectiveness of the proposed model is studied by varying the input signal and sampling frequencies. A level of considered noise is added with the sample data to test the robustness of the studied model. Results prove that the proposed fault detection and classification model has the ability to perform the precise diagnosis of MG faults. A comparative study among the proposed, kernel extreme learning machine (KELM), multi KELM, and support vector machine (SVM) approaches is studied to confirm the robust superior performance of the proposed model.

Drug Target Group Prediction with Multiple Drug Networks

2020 ◽  
Vol 23 (4) ◽  
pp. 274-284 ◽  
Author(s):  
Jingang Che ◽  
Lei Chen ◽  
Zi-Han Guo ◽  
Shuaiqun Wang ◽  
Aorigele
Keyword(s):  
Drug Target ◽  
Low Cost ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
Support Vector ◽  
Multiple Drug ◽  
Property A ◽  
Multiple Networks ◽  
Proposed Model ◽  
The One

Background: Identification of drug-target interaction is essential in drug discovery. It is beneficial to predict unexpected therapeutic or adverse side effects of drugs. To date, several computational methods have been proposed to predict drug-target interactions because they are prompt and low-cost compared with traditional wet experiments. Methods: In this study, we investigated this problem in a different way. According to KEGG, drugs were classified into several groups based on their target proteins. A multi-label classification model was presented to assign drugs into correct target groups. To make full use of the known drug properties, five networks were constructed, each of which represented drug associations in one property. A powerful network embedding method, Mashup, was adopted to extract drug features from above-mentioned networks, based on which several machine learning algorithms, including RAndom k-labELsets (RAKEL) algorithm, Label Powerset (LP) algorithm and Support Vector Machine (SVM), were used to build the classification model. Results and Conclusion: Tenfold cross-validation yielded the accuracy of 0.839, exact match of 0.816 and hamming loss of 0.037, indicating good performance of the model. The contribution of each network was also analyzed. Furthermore, the network model with multiple networks was found to be superior to the one with a single network and classic model, indicating the superiority of the proposed model.

scholarly journals A Review of Algorithms and Hardware Implementations for Spiking Neural Networks

2021 ◽  
Vol 11 (2) ◽  
pp. 23
Author(s):  
Duy-Anh Nguyen ◽  
Xuan-Tu Tran ◽  
Francesca Iacopi
Keyword(s):  
Neural Networks ◽  
Computational Cost ◽  
Superior Performance ◽  
Training Algorithms ◽  
Current State ◽  
Hardware Implementations ◽  
Neuromorphic Hardware ◽  
High Level ◽  
Event Based ◽  
Hardware Platforms

Deep Learning (DL) has contributed to the success of many applications in recent years. The applications range from simple ones such as recognizing tiny images or simple speech patterns to ones with a high level of complexity such as playing the game of Go. However, this superior performance comes at a high computational cost, which made porting DL applications to conventional hardware platforms a challenging task. Many approaches have been investigated, and Spiking Neural Network (SNN) is one of the promising candidates. SNN is the third generation of Artificial Neural Networks (ANNs), where each neuron in the network uses discrete spikes to communicate in an event-based manner. SNNs have the potential advantage of achieving better energy efficiency than their ANN counterparts. While generally there will be a loss of accuracy on SNN models, new algorithms have helped to close the accuracy gap. For hardware implementations, SNNs have attracted much attention in the neuromorphic hardware research community. In this work, we review the basic background of SNNs, the current state and challenges of the training algorithms for SNNs and the current implementations of SNNs on various hardware platforms.

A Hybrid Inpainting Model Combining Diffusion and Enhanced Exemplar Methods

2021 ◽  
Vol 13 (3) ◽  
pp. 1-19
Author(s):  
Sreelakshmy I. J. ◽  
Binsu C. Kovoor
Keyword(s):  
Patch Size ◽  
Image Inpainting ◽  
Qualitative Evaluation ◽  
Natural Images ◽  
External Information ◽  
Image Editing ◽  
Model Combining ◽  
Proposed Model ◽  
The World

Image inpainting is a technique in the world of image editing where missing portions of the image are estimated and filled with the help of available or external information. In the proposed model, a novel hybrid inpainting algorithm is implemented, which adds the benefits of a diffusion-based inpainting method to an enhanced exemplar algorithm. The structure part of the image is dealt with a diffusion-based method, followed by applying an adaptive patch size–based exemplar inpainting. Due to its hybrid nature, the proposed model exceeds the quality of output obtained by applying conventional methods individually. A new term, coefficient of smoothness, is introduced in the model, which is used in the computation of adaptive patch size for the enhanced exemplar method. An automatic mask generation module relieves the user from the burden of creating additional mask input. Quantitative and qualitative evaluation is performed on images from various datasets. The results provide a testimonial to the fact that the proposed model is faster in the case of smooth images. Moreover, the proposed model provides good quality results while inpainting natural images with both texture and structure regions.

scholarly journals Application of a modified Inception-v3 model in the dynasty-based classification of ancient murals

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Jianfang Cao ◽  
Minmin Yan ◽  
Yiming Jia ◽  
Xiaodong Tian ◽  
Zibang Zhang
Keyword(s):  
Transfer Learning ◽  
Adaptive Learning ◽  
Deep Level ◽  
Image Resolution ◽  
Learning Rate ◽  
Stochastic Gradient Descent ◽  
Natural Image ◽  
Historical Period ◽  
Proposed Model

AbstractIt is difficult to identify the historical period in which some ancient murals were created because of damage due to artificial and/or natural factors; similarities in content, style, and color among murals; low image resolution; and other reasons. This study proposed a transfer learning-fused Inception-v3 model for dynasty-based classification. First, the model adopted Inception-v3 with frozen fully connected and softmax layers for pretraining over ImageNet. Second, the model fused Inception-v3 with transfer learning for parameter readjustment over small datasets. Third, the corresponding bottleneck files of the mural images were generated, and the deep-level features of the images were extracted. Fourth, the cross-entropy loss function was employed to calculate the loss value at each step of the training, and an algorithm for the adaptive learning rate on the stochastic gradient descent was applied to unify the learning rate. Finally, the updated softmax classifier was utilized for the dynasty-based classification of the images. On the constructed small datasets, the accuracy rate, recall rate, and F1 value of the proposed model were 88.4%, 88.36%, and 88.32%, respectively, which exhibited noticeable increases compared with those of typical deep learning models and modified convolutional neural networks. Comparisons of the classification outcomes for the mural dataset with those for other painting datasets and natural image datasets showed that the proposed model achieved stable classification outcomes with a powerful generalization capacity. The training time of the proposed model was only 0.7 s, and overfitting seldom occurred.

scholarly journals Sales Growth Rate Forecasting Using Improved PSO and SVM

2014 ◽  
Vol 2014 ◽  
pp. 1-13 ◽  
Author(s):  
Xibin Wang ◽  
Junhao Wen ◽  
Shafiq Alam ◽  
Xiang Gao ◽  
Zhuo Jiang ◽  
...  
Keyword(s):  
Growth Rate ◽  
Decisive Role ◽  
Convergence Speed ◽  
Classification Model ◽  
Support Vector ◽  
Local Optimum ◽  
Sales Growth ◽  
Local Optima ◽  
Proposed Model ◽  
Forecasting Performance

Accurate forecast of the sales growth rate plays a decisive role in determining the amount of advertising investment. In this study, we present a preclassification and later regression based method optimized by improved particle swarm optimization (IPSO) for sales growth rate forecasting. We use support vector machine (SVM) as a classification model. The nonlinear relationship in sales growth rate forecasting is efficiently represented by SVM, while IPSO is optimizing the training parameters of SVM. IPSO addresses issues of traditional PSO, such as relapsing into local optimum, slow convergence speed, and low convergence precision in the later evolution. We performed two experiments; firstly, three classic benchmark functions are used to verify the validity of the IPSO algorithm against PSO. Having shown IPSO outperform PSO in convergence speed, precision, and escaping local optima, in our second experiment, we apply IPSO to the proposed model. The sales growth rate forecasting cases are used to testify the forecasting performance of proposed model. According to the requirements and industry knowledge, the sample data was first classified to obtain types of the test samples. Next, the values of the test samples were forecast using the SVM regression algorithm. The experimental results demonstrate that the proposed model has good forecasting performance.

scholarly journals BEHAVIORAL FUNCTIONS IMPLEMENTATION ON SPIKING NEURAL NETWORKS

2021 ◽  
Vol 20 (3) ◽  
pp. 591-622
Author(s):  
Anton Korsakov ◽  
Aleksandr Bakhshiev ◽  
Lyubov Astapova ◽  
Lev Stankevich
Keyword(s):  
Neural Networks ◽  
Conditioned Reflex ◽  
Negative Reinforcement ◽  
Input Pulse ◽  
Compartmental Models ◽  
Structural Adaptation ◽  
Spike Model ◽  
Current State ◽  
Proposed Model ◽  
Spiking Model

The question of behavioral functions modeling of animals (in particular, the modeling and implementation of the conditioned reflex) is considered. The analysis of the current state of neural networks with the possibility of structural reconfiguration is carried out. The modeling is carried out by means of neural networks, which are built on the basis of a compartmental spiking model of a neuron with the possibility of structural adaptation to the input pulse pattern. The compartmental spike model of a neuron is able to change its structure (the size of the cell body, the number and length of dendrites, the number of synapses) depending on the incoming pulse pattern at its inputs. A brief description of the compartmental spiking model of a neuron is given, and its main features are noted in terms of the possibility of its structural reconfiguration. The method of structural adaptation of the compartmental spiking model of the neuron to the input pulse pattern is described. To study the work of the proposed model of a neuron in a network, the choice of a conditioned reflex as a special case of the formation of associative connections is justified as an example. The structural scheme and algorithm of formation of a conditioned reflex with both positive and negative reinforcement are described. The article presents a step-by-step description of experiments on the associative connection’s formation in general and conditioned reflex (both with positive and negative reinforcement), in particular. The conclusion is made about the prospects of using spiking compartmental models of neurons to improve the efficiency of the implementation of behavioral functions in neuromorphic control systems. Further promising directions for the development of neuromorphic systems based on spiking compartmental models of the neuron are considered.

scholarly journals Improving Multilingual Sentence Embedding using Bi-directional Dual Encoder with Additive Margin Softmax

2019 ◽  
Author(s):  
Yinfei Yang ◽  
Gustavo Hernandez Abrego ◽  
Steve Yuan ◽  
Mandy Guo ◽  
Qinlan Shen ◽  
...  
Keyword(s):  
United Nations ◽  
State Of The Art ◽  
Cosine Similarity ◽  
Retrieval Task ◽  
Parallel Corpus ◽  
Similar Performance ◽  
Second Stage ◽  
Current State ◽  
Proposed Model ◽  
Document Level

In this paper, we present an approach to learn multilingual sentence embeddings using a bi-directional dual-encoder with additive margin softmax. The embeddings are able to achieve state-of-the-art results on the United Nations (UN) parallel corpus retrieval task. In all the languages tested, the system achieves P@1 of 86% or higher. We use pairs retrieved by our approach to train NMT models that achieve similar performance to models trained on gold pairs. We explore simple document-level embeddings constructed by averaging our sentence embeddings. On the UN document-level retrieval task, document embeddings achieve around 97% on P@1 for all experimented language pairs. Lastly, we evaluate the proposed model on the BUCC mining task. The learned embeddings with raw cosine similarity scores achieve competitive results compared to current state-of-the-art models, and with a second-stage scorer we achieve a new state-of-the-art level on this task.

scholarly journals Mapping Seasonal High-Resolution PM2.5 Concentrations with Spatiotemporal Bagged-Tree Model across China

2021 ◽  
Vol 10 (10) ◽  
pp. 676
Author(s):  
Junchen He ◽  
Zhili Jin ◽  
Wei Wang ◽  
Yixiao Zhang
Keyword(s):  
Remote Sensing ◽  
Mean Squared Error ◽  
Fine Particulate Matter ◽  
Absolute Error ◽  
Superior Performance ◽  
Tree Model ◽  
Mixed Effect ◽  
Proposed Model ◽  
High Concentrations ◽  
Pm2.5 Concentration

High concentrations of fine particulate matter (PM2.5) are well known to reduce environmental quality, visibility, atmospheric radiation, and damage the human respiratory system. Satellite-based aerosol retrievals are widely used to estimate surface PM2.5 levels because satellite remote sensing can break through the spatial limitations caused by sparse observation stations. In this work, a spatiotemporal weighted bagged-tree remote sensing (STBT) model that simultaneously considers the effects of aerosol optical depth, meteorological parameters, and topographic factors was proposed to map PM2.5 concentrations across China that occurred in 2018. The proposed model shows superior performance with the determination coefficient (R2) of 0.84, mean-absolute error (MAE) of 8.77 μg/m3 and root-mean-squared error (RMSE) of 15.14 μg/m3 when compared with the traditional multiple linear regression (R2 = 0.38, MAE = 18.15 μg/m3, RMSE = 29.06 μg/m3) and linear mixed-effect (R2 = 0.52, MAE = 15.43 μg/m3, RMSE = 25.41 μg/m3) models by the 10-fold cross-validation method. The results collectively demonstrate the superiority of the STBT model to other models for PM2.5 concentration monitoring. Thus, this method may provide important data support for atmospheric environmental monitoring and epidemiological research.

Sign in / Sign up

Export Citation Format

Share Document