The PASCAL Visual Object Classes Challenge

Lack of typical fault samples remains a huge challenge for intelligent fault diagnosis of gearbox. In this paper, a novel approach named deep transfer multi-wavelet auto-encoder is presented for gearbox intelligent fault diagnosis with few training samples. Firstly, new-type deep multi-wavelet auto-encoder is designed for learning important features of the collected vibration signals of gearbox. Secondly, high-quality auxiliary samples are selected based on similarity measure to well pre-train a source model sharing similar characteristics with the target domain. Thirdly, parameter knowledge acquired from the source model is transferred to target model using very few target training samples. Transfer diagnosis cases for different fault severities and compound faults of gearbox confirm the feasibility of the proposed approach even if the working conditions have significant changes.

Deep transfer multi-wavelet auto-encoder for intelligent fault diagnosis of gearbox with few target training samples

/pdf/semantic-texton-forests-for-image-categorization-and-3so8x8hnma.pdf

Semantic Texton Forests for Image Categorization and Segmentation

Motivation An essential part of drug discovery is the accurate prediction of the binding affinity of new compound-protein pairs. Most of the standard computational methods assume that compounds or proteins of the test data are observed during the training phase. However, in real-world situations, the test and training data are sampled from different domains with different distributions. To cope with this challenge, we propose a deep learning-based approach that consists of three steps. In the first step, the training encoder network learns a novel representation of compounds and proteins. To this end, we combine convolutional layers and long-short-term memory layers so that the occurrence patterns of local substructures through a protein and a compound sequence are learned. Also, to encode the interaction strength of the protein and compound substructures, we propose a two-sided attention mechanism. In the second phase, to deal with the different distributions of the training and test domains, a feature encoder network is learned for the test domain by utilizing an adversarial domain adaptation approach. In the third phase, the learned test encoder network is applied to new compound-protein pairs to predict their binding affinity. Results To evaluate the proposed approach, we applied it to KIBA, Davis and BindingDB datasets. The results show that the proposed method learns a more reliable model for the test domain in more challenging situations. Availability and implementation https://github.com/LBBSoft/DeepCDA.

DeepCDA: Deep Cross-Domain Compound-Protein Affinity Prediction through LSTM and Convolutional Neural Networks

For the last three decades, content-based image retrieval (CBIR) has been an active research area, representing a viable solution for retrieving similar images from an image repository. In this article, we propose a novel CBIR technique based on the visual words fusion of speeded-up robust features (SURF) and fast retina keypoint (FREAK) feature descriptors. SURF is a sparse descriptor whereas FREAK is a dense descriptor. Moreover, SURF is a scale and rotation-invariant descriptor that performs better in the case of repeatability, distinctiveness, and robustness. It is robust to noise, detection errors, geometric, and photometric deformations. It also performs better at low illumination within an image as compared to the FREAK descriptor. In contrast, FREAK is a retina-inspired speedy descriptor that performs better for classification-based problems as compared to the SURF descriptor. Experimental results show that the proposed technique based on the visual words fusion of SURF-FREAK descriptors combines the features of both descriptors and resolves the aforementioned issues. The qualitative and quantitative analysis performed on three image collections, namely Corel-1000, Corel-1500, and Caltech-256, shows that proposed technique based on visual words fusion significantly improved the performance of the CBIR as compared to the feature fusion of both descriptors and state-of-the-art image retrieval techniques.

/pdf/an-effective-content-based-image-retrieval-technique-for-1f5lz1xr2l.pdf

An effective content-based image retrieval technique for image visuals representation based on the bag-of-visual-words model

Drug-target Interactions (DTIs) prediction plays a central role in drug discovery. Computational methods in DTIs prediction have gained more attention because carrying out in vitro and in vivo experiments on a large scale is costly and time-consuming. Machine learning methods, especially deep learning, are widely applied to DTIs prediction. In this study, the main goal is to provide a comprehensive overview of deep learning-based DTIs prediction approaches. Here, we investigate the existing approaches from multiple perspectives. We explore these approaches to find out which deep network architectures are utilized to extract features from drug compound and protein sequences. Also, the advantages and limitations of each architecture are analyzed and compared. Moreover, we explore the process of how to combine descriptors for drug and protein features. Likewise, a list of datasets that are commonly used in DTIs prediction is investigated. Finally, current challenges are discussed and a short future outlook of deep learning in DTI prediction is given.

Deep Learning in Drug Target Interaction Prediction: Current and Future Perspectives.

In this paper, we investigate the unsupervised domain transfer learning in which there is no label in the target samples whereas the source samples are all labeled. We use the transformation matrix to transfer both target and source samples to a common subspace where they have the same distribution and each target sample in the transformed space is constructed of a linear combination of the source samples. To preserve the local and global structure of the samples in the transferred domain, the low-rank and sparse constraints are imposed on the reconstruction coefficient matrix. In this paper, in order to consider the discriminative ability of the target and source samples, the information content of the reconstruction coefficient matrix is utilized. To capture the discriminative ability of the target samples, it is assumed that the class labels of the source samples which are linearly incorporated in constructing a target sample should be the same. Based on this assumption, it is assured that the target samples are well distributed over the transferred domain. To handle this, we utilize the linear entropy to measure the discriminant power of the target domain. This term considers the discriminative ability of the target samples without using their hidden labels. Also, to assess the discriminative ability of source samples, we use max-margin classifier where the kernel matrix is defined by using the reconstruction coefficient matrix. To evaluate the proposed approach, it is applied on MSRC, VOC 2007, CMU PIE, Office, Caltech-256, Extended Yale B and two imbalanced datasets. The experimental results show that our proposed approach outperforms its competitors.

Transfer subspace learning via low-rank and discriminative reconstruction matrix

Content-based image retrieval has attracted researcher's attention due to the rapid growing of images database. Many approaches for content based image retrieval have been proposed but completely satisfactory result has not yet been obtained. In this paper a new approach for content-based image retrieval using the bag of visual words (BoW) has been proposed. In this approach, two separate visual vocabularies are produced based on the scale invariant feature transform (SIFT) and hue descriptor. Traditional SIFT BoW model do not utilize any color information in image description. We incorporate hue descriptor in our method which adds complementary information to BoW representation of images and increase the overall performance of retrieval. The quantization in BoW model is an essential step that has a great impact on the final result but it produces loss in quantization. To overcome this unfavorable effect, soft assignment is used in our proposed approach in which each feature vector can be assigned to multiple nearest visual words based on some weighting function. Experimental results on benchmark dataset showed that the proposed approach has a superior performance with respect to other methods.

Parvin Razzaghi

Papers

DeepCDA: Deep Cross-Domain Compound-Protein Affinity Prediction through LSTM and Convolutional Neural Networks

Deep Learning in Drug Target Interaction Prediction: Current and Future Perspectives.

Transfer subspace learning via low-rank and discriminative reconstruction matrix

Bag of visual words approach for image retrieval using color information

A new fast approach to nonparametric scene parsing