Robust Embedded Deep K-means Clustering

Background/Objectives: This paper proposes a new type of regularization for deep learning neural networks that is capable of explicit separation of the lower dimensional hidden layer input pattern representation into two components: class information component and transform component. Methods: Currently, researchers involved in pattern recognition problems are actively searching for the replacement of deterministic feature extraction algorithms by unsupervised methods capable of generating optimal domain-specific image features during the training process of auto-associative multilayer neural networks. The result of the training process of the deep neural network with a “bottleneck” hidden layer is the task-oriented encoder capable of efficient input signal dimensionality reduction. Findings: Many important useful properties of the encoder including the degree of invariance of the feature extraction to input signal transformations (perturbations) greatly depend on the particular form of the regularization applied. In addition to the regular weight decay smoothing component the suggested regularization has two additional components: the first one minimizes the spread of the class-describing features under different pattern transforms and the other component minimizes the spread of the transformation description features for the objects with same perturbations but from the different classes. Class-membership information from the training sequence is used along with the introduced estimator of the similarity of pattern transform to compute the regularization terms. The research reveals that a private case of the suggested regularization corresponds to the well-known Frobenius norm of Jacobian matrix of the encoder activations, therefore the contribution of this paper can be seen as a non-local extension of the encoder Jacobian-based family of deep neural network regularizers embedding invariance to non-local input pattern transformations into the deep neural network feature extraction pipeline. Experiments carried out on the synthetic and real pattern datasets show promising results and encourage further investigation of the proposed approach. Improvements/Applications: This method can be used for areal images recognition invariant to lighting, weather and orientation, for example for the recognition of vehicles and other landmarks in the images obtained by the unmanned aerial vehicles (UAV).

Feature mapping using far-field microphones for distant speech recognition

Learning ability is the basic characteristic of human intelligence. The July 1, 2005 issue of Science published a list of 125 important questions in science. Among them, the question 94 “What are the limits of learning by machines?”. The annotation “Computers can already beat the world’s best chess players, and they have a wealth of information on the Web to draw on. But abstract reasoning is still beyond any machine”. In recent artificial intelligence has made great progresses. In 1997, the rise of the man-machine war, IBM Supercomputer Deep Blue defeated the chess master Garry Kasparov. On February 14, 2011, IBM’s Watson supercomputer won a practice round against Jeopardy champions Ken Jennings and Brad Rutter. In March 2016, Google DeepMind’s AlphaGo sealed a 4-1 victory over a South Korean Go grandmaster Lee Se-dol. This paper focuses on the machine learning methods of AlphaGo, including reinforcement learning, deep learning, deep reinforcement learning, analysis of the existing problems and the latest research progress. Deep reinforcement learning is the combination of deep learning and reinforcement learning, which can realize the learning algorithm from the perception to action. Simply said, this is the same as human behavior, input sensing information such as vision, and then, direct output action through the deep neural network. Deep reinforcement learning has the potential to learn a variety of skills for the robot to achieve full autonomy. Even though reinforcement learning is practiced successfully, but feature states need to manually set, for complex scene is a difficult thing, especially easy to cause the dimension disaster, and expression is not good. In 2010, Sascha Lange and Martin Riedmiller proposed deep auto-encoder neural networks in reinforcement learning to extract feature, which is used to control the visual correlation. In 2013, DeepMind proposed deep Q-network (DQN) in NIPS 2013, using convolution neural network to extract features, and then applied in reinforcement learning. They continue to improve and published an improved version of DQN on Nature in 2015, which has aroused widespread concern. In order to break through the limits of learning by machines, cognitive machine learning is proposed, which is the combination of machine learning and brain cognition, so that the machine intelligence is constantly evolving, and gradually reaches the human level of artificial intelligence. A cognitive model entitled Consciousness And Memory (CAM) is proposed by author, which consists of memory, consciousness, high-level cognitive functions, perception and motor. High-level cognitive functions of the brain include learning, language, thinking, decision making, emotion, and so on. Learning is a course to accept the stimulus through the nervous system and obtain new behavior, habits and accumulation experience. According to the current research progress of brain science and cognitive science, cognitive machine learning may be interested in learning emergence, procedural memory knowledge learning, learning evolution and so on. For intelligence, so-called evolution is refers to the learning of learning and the structure also follows the change. It is important to record the learning result by structure changing and improve the learning method.

BackgroundMicrobes have dense linkages with human diseases. Balanced microorganisms protect human body against physiological disorders while unbalanced ones may cause diseases. Thus, identification of potential associations between microbes and diseases can contribute to the diagnosis and therapy of various complex diseases. Biological experiments for microbe–disease association (MDA) prediction are expensive, time-consuming, and labor-intensive.MethodsWe developed a computational MDA prediction method called GPUDMDA by combining graph attention autoencoder, positive-unlabeled learning, and deep neural network. First, GPUDMDA computes disease similarity and microbe similarity matrices by integrating their functional similarity and Gaussian association profile kernel similarity, respectively. Next, it learns the feature representation of each microbe–disease pair using graph attention autoencoder based on the obtained disease similarity and microbe similarity matrices. Third, it selects a few reliable negative MDAs based on positive-unlabeled learning. Finally, it takes the learned MDA features and the selected negative MDAs as inputs and designed a deep neural network to predict potential MDAs.ResultsGPUDMDA was compared with four state-of-the-art MDA identification models (i.e., MNNMDA, GATMDA, LRLSHMDA, and NTSHMDA) on the HMDAD and Disbiome databases under five-fold cross validations on microbes, diseases, and microbe-disease pairs. Under the three five-fold cross validations, GPUDMDA computed the best AUCs of 0.7121, 0.9454, and 0.9501 on the HMDAD database and 0.8372, 0.8908, and 0.8948 on the Disbiome database, respectively, outperforming the other four MDA prediction methods. Asthma is the most common chronic respiratory condition and affects ~339 million people worldwide. Inflammatory bowel disease is a class of globally chronic intestinal disease widely existed in the gut and gastrointestinal tract and extraintestinal organs of patients. Particularly, inflammatory bowel disease severely affects the growth and development of children. We used the proposed GPUDMDA method and found that Enterobacter hormaechei had potential associations with both asthma and inflammatory bowel disease and need further biological experimental validation.ConclusionThe proposed GPUDMDA demonstrated the powerful MDA prediction ability. We anticipate that GPUDMDA helps screen the therapeutic clues for microbe-related diseases.

Motivated by the development of deep convolution neural networks (DCNNs), the aircraft detection from remote sensing images has gained tremendous progress. However, due to complex background and multi-scale characteristics, it remains a challenge in remote sensing detection. In this paper, we propose a two-stage aircraft detection method based on deep neural networks, which integrates Deconvolution operation with Position Attention mechanism (DPANet). Specifically, considering that remote sensing images are taken from the top-down perspective, which leads to significant external structural characteristic, we introduce a deconvolution module to capture the external structural feature representation of aircraft during the feature map generation process. Moreover, aiming at reducing the error detections caused by complex background in remote sensing, we propose a position attention module in the second stage. By calculating the feature similarity between any two pixels of the target feature map, DPANet can extract the complicated internal structure feature representation of aircraft, which improve the ability to distinguish background and aircraft. By integrating the deconvolution and position attention modules, DPANet can provide better representation ability for the structural characteristic of aircraft in remote sensing images. Experimental results show that the proposed method can effectively reduce the error detections and improve the accuracy of the aircraft detection.

Scene text detection has attracted great interest from the computer vision and pattern recognition communities since text information plays an important role in image indexing and scene understanding. Deep neural networks have become popular for the task of scene text detection, especially for their ability to learn strong text features. However, existing deep learning based state-of-the-art scene text detection methods detect texts only from a single feature map which is unable to capture semantic information at all scales. In this paper, we propose a novel deep learning based model that leverages the pyramid structure of feature maps for accurate scene text detection. We also design a deep convolutional neural network model for non-maximum suppression. In addition, we develop a novel loss function and training method for end-to-end training. The experimental results validate that our end-to-end system is simple, fast, and achieves high accuracy on standard datasets, namely, ICDAR 2015 and MSRA-TD500. We also create a dataset for scene text detection.

The demand on devices and systems empowered by biometric verification and identification mechanisms has been increasing in recent years as they have become a significant part of our lives. Palm vein biometric is an emerging technology that has drawn considerable attention from researchers and scientists over the last decade. In the present work, a novel feature extraction methodology named GPWLD combing the Gabor features with positional Weber's local descriptor (PWLD) features is proposed. WLD is a highly representative micro-pattern descriptor that performs well against noise and illumination changes in images. However, it lacks the ability to capture the vein pattern features at different orientations. Moreover, its descriptor packs the local information content into a single histogram that does not take the spatial locality of micro-patterns into consideration. To solve these two issues, firstly, the palm vein image is passed through Gabor filter with different orientations to capture the salient rotational features found in the output feature maps. Secondly, the spatiality is achieved by uniformly dividing each feature map into several blocks. Next, Weber's law feature descriptor (WLD) histogram is computed for each block in every feature map. Finally, these histograms are concatenated to compose the final feature vector. Due to the high dimensionality of the final feature vector, Principal component analysis (PCA) algorithm is utilized for feature size reduction. In the classification stage, a deep neural network (DNN) comprising an optimized stacked autoencoder (SAE) with Bayesian optimization and a softmax layer is used. Optimization of the SAE is carried out by using Bayesian optimization to find the optimal SAE structure and the options of the training algorithm. The Experimental results verify the discriminative power of the extracted features and the accuracy of the proposed DNN. For both Identification and verification experiments, the proposed method attains higher identification rate and lower EER than state-of-the-art methods.

CMRFusion: A cross-domain multi-resolution fusion method for infrared and visible image fusion

Deep neural network for semi-automatic classification of term and preterm uterine recordings.

Data clustering is an important research topic in data mining and signal processing communications. In all the data clustering methods, the subspace spectral clustering methods based on self expression model, e.g., the Sparse Subspace Clustering (SSC) and the Low Rank Representation (LRR) methods, have attracted a lot of attention and shown good performance. The key step of SSC and LRR is to construct a proper affinity or similarity matrix of data for spectral clustering. Recently, Laplacian graph constraint was introduced into the basic SSC and LRR and obtained considerable improvement. However, the current graph construction methods do not well exploit and reveal the non-linear properties of the clustering data, which is common for high dimensional data. In this paper, we introduce the classic manifold learning method, the Local Linear Embedding (LLE), to learn the non-linear structure underlying the data and use the learned local geometry of manifold as a regularization for SSC and LRR, which results the proposed LLE-SSC and LLE-LRR clustering methods. Additionally, to solve the complex optimization problem involved in the proposed models, an efficient algorithm is also proposed. We test the proposed data clustering methods on several types of public databases. The experimental results show that our methods outperform typical subspace clustering methods with Laplacian graph constraint.

VLSI (Very Large-Scale Integration) testing is a crucial step in ensuring the reliability and functionality of integrated circuits. However, conventional testing methods often lack the ability to address user-specific requirements, resulting in suboptimal outcomes. Terahertz technology offers unique capabilities for non-destructive testing, yet its integration with VLSI testing methodologies remains limited. Additionally, the neglect of user preferences in testing processes poses a challenge to tailoring testing procedures to specific user needs. This research presents a novel approach for fostered power terahertz VLSI testing, integrating deep neural networks (DNNs) and user intent optimization principles. The proposed framework comprises three main components: terahertz signal processing, deep neural network-based feature extraction, and user intent optimization. Terahertz signals are analyzed using deep neural networks trained on labeled datasets, while user intent optimization algorithms dynamically adjust testing parameters based on user feedback. Comparative analysis with traditional testing methods reveals superior testing coverage and accuracy achieved through the integration of Terahertz Technology (TZT), deep neural networks, and user intent optimization. Our approach demonstrated a significant improvement in reliability, with values ranging from 92.5% to 95.8%, depending on the specific testing scenario and dataset used for evaluation. The accuracy achieved by our methodology surpassed existing technologies by a substantial margin. Across various experiments, accuracy values ranged from 87.3% to 91.6%, indicating a consistent improvement over baseline methods.

Traditional Image Processing Techniques (IPT), used for automating the detection and classification of weld defects from radiography images, have their own limitations, which can be overcome by Deep Neural Networks (DNN). DNN produces considerably good results in fields which offer big dataset for it to train. DNN trained with small datasets by conventional methods produces less accurate results. This limits the use of DNN in many fields. This study focuses to overcome this limitation, by adopting transfer learning using Pre-trained deep convolutional neural networks. By this method, a weld defect radiographic image classifier, which can classify 14 types of weld defects, was constructed. 940 Image patches of weld defects were manually collected and labelled from GDXray database. Subsequently the features of this weld defect dataset were extracted using VGG16 and ResNet50 CNNs, both pre-trained on the ImageNet database. Then machine learning models such as Logistic Regression, Support Vector Machine (SVM) and Random Forest were trained on these extracted features. The Classifier based on SVM trained on features extracted by ResNet50 outperforms the other counter parts with an accuracy of 98%. In all these cases, transfer learning improves performance and reduces the training time and computational system requirements.

Deep Neural Networks (DNNs) have made significant improvements to reach the desired accuracy to be employed in a wide variety of Machine Learning (ML) applications. Recently the Google Brain's team demonstrated the ability of Capsule Networks (CapsNets) to encode and learn spatial correlations between different input features, thereby obtaining superior learning capabilities compared to traditional (i.e., non-capsule based) DNNs. However, designing CapsNets using conventional methods is a tedious job and incurs significant training effort. Recent studies have shown that powerful methods to automatically select the best/optimal DNN model configuration for a given set of applications and a training dataset are based on the Neural Architecture Search (NAS) algorithms. Moreover, due to their extreme computational and memory requirements, DNNs are employed using the specialized hardware accelerators in IoT-Edge/CPS devices. In this paper, we propose NASCaps, an automated framework for the hardware-aware NAS of different types of DNNs, covering both traditional convolutional DNNs and CapsNets. We study the efficacy of deploying a multi-objective Genetic Algorithm (e.g., based on the NSGA-II algorithm). The proposed framework can jointly optimize the network accuracy and the corresponding hardware efficiency, expressed in terms of energy, memory, and latency of a given hardware accelerator executing the DNN inference. Besides supporting the traditional DNN layers, our framework is the first to model and supports the specialized capsule layers and dynamic routing in the NAS-flow. We evaluate our framework on different datasets, generating different network configurations, and demonstrate the tradeoffs between the different output metrics. We will open-source the complete framework and configurations of the Pareto-optimal architectures at https://github.com/ehw-fit/nascaps.

e20611 Background: Predicting immunotherapy response in advanced non-small cell lung cancer (NSCLC) through non-invasive means could be a groundbreaking advancement. Deep features extracted from medical images by deep Convolutional Neural Networks (CNNs) along with radiomics have demonstrated promising results in different oncologic diseases. However, the method for extracting these deep features influences the predictive capabilities of the model. Methods: A retrospective analysis of a multicenter study was conducted in advanced NSCLC patients with high PD-L1 expression with the aim of developing an imaging features-based model for the prediction of best overall response (BOR) to a checkpoint inhibitor immunotherapy. All visible lung lesions, beyond RECIST 1.1, were manually segmented in baseline CT scans. Radiomics features were extracted at lesion-level, and various preprocessing methods and CNN architectures were tested for deep features extraction. Radiomics and deep features were harmonized using ComBat methodology. A distinctive feature signature was created for each patient by calculating the mean across all lesions. Using this data, machine learning models were trained to predict treatment response, specifically distinguishing between complete response (CR) and partial response (PR) from stable disease (SD) and progressive disease (PD). The study compared the performance of different deep features extraction methods and assessed shapley additive explanations (SHAP) values of radiomics for interpretability. Results: In the cohort of 116 patients (mean age: 67, 93% ever-smokers, 73% male), 1024 to 5475 quantitative imaging features per lesion were extracted. Among these patients, 67 patients were CR+PR, and 49 were SD+PD. The top-performing predictive model, trained with radiomics and deep features from a deep convolutional autoencoder, achieved an average AUC of 85%. SHAP values showed that impactful radiomics features were correlated with intensity changes in adjacent pixels describing the tumor heterogeneity, along with shape features potentially associated with malignancy. Ultimately, combining both features demonstrated statistical significance, leading to a performance improvement of ~2-5% compared to models exclusively using deep features. Conclusions: Diverse techniques for extracting deep features were evaluated, revealing autoencoder training as the most effective strategy for predicting immunotherapy response. Consequently, the findings suggest that employing deep learning to extract imaging features from baseline CT scans, combined with radiomics, represents a promising non-invasive approach for the predicting immunotherapy outcomes in advanced NSCLC patients.

In this paper, a high precision detection method of salient objects is presented based on deep convolutional networks with proper combinations of shallow and deep connections. In order to achieve better performance in the extraction of deep semantic features of salient objects, based on a symmetric encoder and decoder architecture, an upgrade of backbone networks is carried out with a transferable model on the ImageNet pre-trained ResNet50. Moreover, by introducing shallow and deep connections on multiple side outputs, feature maps generated from various layers of the deep neural network (DNN) model are well fused so as to describe salient objects from local and global aspects comprehensively. Afterwards, based on a holistically nested edge detector (HED) architecture, multiple fused side outputs with various sizes of receptive fields are integrated to form detection results of salient objects accordingly. A series of experiments and assessments on extensive benchmark datasets demonstrate the dominant performance of our DNN model for the detection of salient objects in accuracy, which has outperformed those of other published works.