Representative Algorithms Research Articles

Bladder Volume Estimation Using 3-D Electrical Impedance Tomography Based on Fringe Field Sensing

Clinically, dynamic monitoring of bladder volume is of great significance for patients with bladder diseases. This paper proposes a method for the continuous monitoring of bladder volume by 3D electrical impedance tomography (EIT). To facilitate convenient installation and maintenance for patients, a single-layer half-circle EIT sensor is proposed and designed to be attached at the top of full bladder for 3D imaging, based on fringe field sensing. By incorporating the simple prior knowledge of the approximate position and maximum extension region of a full bladder in abdomen, a dedicated sparse representation algorithm was proposed to alleviate the ill-posedness of 3D reconstruction and improve the image quality. Bladder volume is finally estimated based on the 3D image with improved accuracy. Effectiveness of the proposed method is verified by simulation and human trials. Results show that this method is able to reconstruct 3D image of bladder, and the estimation errors of volume are less than 8% in the human trials, which is accurate enough for patients nursing. This provides a promising alternative for the dynamic monitoring of bladder volume.

Retracted: BRFP: An Efficient and Universal Sentence Embedding Learning Model Method Supporting Fused Syntax Combined with Graph Embedding Representation Algorithm

Retracted: BRFP: An Efficient and Universal Sentence Embedding Learning Model Method Supporting Fused Syntax Combined with Graph Embedding Representation Algorithm

Design of a Visual Training System for Software Engineering Education Based on Knowledge Graphs

With the increase of the content and difficulty of software engineering education courses, software engineering education visual training system came into being, but the technology is not mature at present, and the representation learning algorithm part of the visual training system needs to be optimized. In order to solve this problem, the research proposes to optimize the take model by using the trans representation algorithm, and embed the optimized knowledge map into the new software engineering education visual training system. The performance of TEKEE model is verified by comparing TEKEE model with Trans E model, Trans D model and TEKED model. The experimental results show that the MR value of the optimized TEKEE model is 62, Hits@10 The value is 0.92, which is better than the other three representation learning models. In terms of the bearing capacity test of the visual training system, the response time of the business operation of the research and design training system is 1.22 seconds, and the CPU occupancy of the application server is 12.5%, all of which are normal. The experimental results show that the performance of the optimized TEKEE model has indeed been greatly improved, and the visual training system composed of the optimized knowledge map has a very good carrying capacity, which can provide a new idea for the software engineering education and training system.

Secuer: Ultrafast, scalable and accurate clustering of single-cell RNA-seq data.

Identifying cell clusters is a critical step for single-cell transcriptomics study. Despite the numerous clustering tools developed recently, the rapid growth of scRNA-seq volumes prompts for a more (computationally) efficient clustering method. Here, we introduce Secuer, a Scalable and Efficient speCtral clUstERing algorithm for scRNA-seq data. By employing an anchor-based bipartite graph representation algorithm, Secuer enjoys reduced runtime and memory usage over one order of magnitude for datasets with more than 1 million cells. Meanwhile, Secuer also achieves better or comparable accuracy than competing methods in small and moderate benchmark datasets. Furthermore, we showcase that Secuer can also serve as a building block for a new consensus clustering method, Secuer-consensus, which again improves the runtime and scalability of state-of-the-art consensus clustering methods while also maintaining the accuracy. Overall, Secuer is a versatile, accurate, and scalable clustering framework suitable for small to ultra-large single-cell clustering tasks.

The New Generation Brain-Inspired Sparse Learning: A Comprehensive Survey

In recent years, the enormous demand for computing resources resulting from massive data and complex network models has become the limitation of deep learning. In the large-scale problems with massive samples and ultrahigh feature dimensions, sparsity has gradually drawn much attention from academia and the industrial field. In this article, the new generation of brain-inspired sparse learning is reviewed comprehensively. First, sparse cognition learning is introduced from the visual biology mechanism to modeling for the natural image. Second, the sparse representation algorithms are summarized to sort out the research progress of sparse learning. Third, the relevant research on sparse feature selection learning is reviewed. Then, the sparse deep networks and applications are summed up. Last but not least, ten public issues and challenges of sparse learning are discussed. By investigating the development process of sparse learning, this article summarizes the advantages, disadvantages, limitations, and future research directions of the algorithm, which can help readers conduct further study.

Cell2Grid: an efficient, spatial, and convolutional neural network-ready representation of cell segmentation data.

Cell segmentation algorithms are commonly used to analyze large histologic images as they facilitate interpretation, but on the other hand they complicate hypothesis-free spatial analysis. Therefore, many applications train convolutional neural networks (CNNs) on high-resolution images that resolve individual cells instead, but their practical application is severely limited by computational resources. In this work, we propose and investigate an alternative spatial data representation based on cell segmentation data for direct training of CNNs. We introduce and analyze the properties of Cell2Grid, an algorithm that generates compact images from cell segmentation data by placing individual cells into a low-resolution grid and resolves possible cell conflicts. For evaluation, we present a case study on colorectal cancer relapse prediction using fluorescent multiplex immunohistochemistry images. We could generate Cell2Grid images at resolution that were 100 times smaller than the original ones. Cell features, such as phenotype counts and nearest-neighbor cell distances, remain similar to those of original cell segmentation tables ( ). These images could be directly fed to a CNN for predicting colon cancer relapse. Our experiments showed that test set error rate was reduced by 25% compared with CNNs trained on images rescaled to with bilinear interpolation. Compared with images at resolution (bilinear rescaling), our method reduced CNN training time by 85%. Cell2Grid is an efficient spatial data representation algorithm that enables the use of conventional CNNs on cell segmentation data. Its cell-based representation additionally opens a door for simplified model interpretation and synthetic image generation.

DNA/RNA sequence feature representation algorithms for predicting methylation-modified sites

<p indent="0mm">Methylation is an important epigenetic modification that plays a key role in regulating gene expression and the occurrence and development of cancers. Accurately identifying DNA/RNA methylation modified sites is the basis for studying the biological functions of methylation. The rapid development of high-throughput sequencing technology has led to the accumulation of DNA/RNA sequence data. Thus, machine learning has become an important method of predicting methylation sites. Feature-encoding algorithms of DNA/RNA sequences extract and encode sequence information into numerical features with strong categorical information for building a machine learning model to predict methylation sites. Therefore, the feature-encoding algorithms of DNA/RNA sequences become the key factor for training a good-performing machine learning model. This study systematically surveyed the 40 feature-encoding algorithms commonly used in the available literatures of the DNA/RNA methylation site prediction models and grouped them into seven categories based on the principles used in calculation. These 40 feature-encoding algorithms were investigated and compared on the benchmark and independent datasets of RNA m⁶A modification in three species, including <italic>S</italic>.<italic> cerevisiae</italic>, <italic>H</italic>.<italic> sapiens</italic>, and Mouse, and on the DNA 4mC modification dataset of <italic>A</italic>.<italic> thaliana</italic>. Finally, the future development of DNA/RNA sequence feature-encoding algorithms is proposed, as well as machine learning models for predicting biological sites.

Deep Learning-Based Community Detection Approach on Bitcoin Network

Community detection is essential in P2P network analysis as it helps identify connectivity structure, undesired centralization, and influential nodes. Existing methods primarily utilize topological data and neglect the rich content data. This paper proposes a technique combining topological and content data to detect communities inside the Bitcoin network using a deep feature representation algorithm and Deep Feedforward Autoencoders. Our results show that the Bitcoin network has a higher clustering coefficient, assortativity coefficient, and community structure than expected from a random P2P network. In the Bitcoin network, nodes prefer to connect to other nodes that share the same characteristics.

Development of improved method for evaluation of reservoir properties of formation

The object of research in the paper is the process of fluid transfer through the pore space of the reservoir rock. The traditional method of assessing reservoir properties has a significant number of sources of uncertainty. In this article, to compensate for the shortcomings of the existing method of reservoir characterization, an algorithm of actions is proposed with an increase in the accuracy and representativeness of its results. The workflow of the pre-alpha version of the software for the existing pore space representation algorithm is presented. In this work, the step-by-step actions necessary to create an application that can reproduce the pore space and mass transfer processes in it by reading the data of the magnetic resonance imaging (MRI) of the rock were analytically determined. In particular, the use of ready-made open code is proposed, which displays the rock according to the pictures and also reproduces the fluid flow processes in the rock reservoir. Still, there is no adapted framework for the ordinary user. The use of such an application, proposed by the authors, will lead to a much lower degree of the reservoir properties uncertainty, will help to more reliably reflect the reservoir properties of the reservoir rock, and provide a more reliable impression of the reservoir operation at the design stage of its development. The proposed software, based on already existing developments in open access on the GitHub platform, will help the user to fully use the existing tools for building a three-dimensional model of a porous sample based on the data of MRI images of the rock. After finalizing the user interface with the help of the user interface design and front-end development, the engineering staff will be able to conduct research on the rock at a macroscopic level.

Learning fair representations by separating the relevance of potential information

Representation learning has recently been used to remove sensitive information from data and improve the fairness of machine learning algorithms in social applications. However, previous works that used neural networks are opaque and poorly interpretable, as it is difficult to intuitively determine the independence between representations and sensitive information. The internal correlation among data features has not been fully discussed, and it may be the key to improving the interpretability of neural networks. A novel fair representation algorithm referred to as FRC is proposed from this conjecture. It indicates how representations independent of multiple sensitive attributes can be learned by applying specific correlation constraints on representation dimensions. Specifically, dimensions of the representation and sensitive attributes are treated as statistical variables. The representation variables are divided into two parts related to and unrelated to the sensitive variables by adjusting their absolute correlation coefficient with sensitive variables. The potential impact of sensitive information on representations is concentrated in the related part. The unrelated part of the representation can be used in downstream tasks to yield fair results. FRC takes the correlation between dimensions as the key to solving the problem of fair representation. Empirical results show that our representations enhance the ability of neural networks to show fairness and achieve better fairness-accuracy tradeoffs than state-of-the-art works.

A Bibliometric Perspective on AI Research for Job-Résumé Matching.

The search for the right person for the right job, or in other words the selection of the candidate who best reflects the skills demanded by employers to perform a specific set of duties in a job appointment, is a key premise of the personnel selection pipeline of recruitment departments. This task is usually performed by human experts who examine the résumé or curriculum vitae of candidates in search of the right skills necessary to fit the vacant position. Recent advances in AI, specifically in the fields of text analytics and natural language processing, have sparked the interest of research on the application of these technologies to help recruiters accomplish this task or part of it automatically, applying algorithms for information extraction, parsing, representation, and matching of résumés and job descriptions, or sections within. In this study, we aim to better understand how the research landscape in this field has evolved. To do this, we follow a multifaceted bibliometric approach aimed at identifying trends, dynamics, structures, and visual mapping of the most relevant topics, highly cited or influential papers, authors, and universities working on these topics, based on a publication record retrieved from Scopus and Google Scholar bibliographic databases. We conclude that, unlike a traditional literature review, the bibliometric-guided approach allowed us to discover a more comprehensive picture of the evolution of research in this subject and to clearly identify paradigm shifts from the earliest stages to the most recent efforts proposed to address this problem.

Mathematical Simulation of Electron Transport in the Primary Photosynthetic Processes.

Summarized results of investigation of regulation of electron transport and associated processes in the photosynthetic membrane using methods of mathematical and computer modeling carried out at the Department of Biophysics, Faculty of Biology, Lomonosov Moscow State University, are presented in this review. Detailed kinetic models of processes in the thylakoid membrane were developed using the apparatus of differential equations. Fitting of the model curves to the data of spectral measurements allowed us to estimate the values of parameters that were not determined directly in experiments. The probabilistic method of agent-based Monte Carlo modeling provides ample opportunities for studying dynamics of heterogeneous systems based on the rules for the behavior of individual elements of the system. Algorithms for simplified representation of Big Data make it possible to monitor changes in the photosynthetic apparatus in the course of culture growth in a photobioreactor and for the purpose of environmental monitoring. Brownian and molecular models describe movement and interaction of individual electron carrier proteins and make it possible to study electrostatic, hydrophobic, and other interactions leading to regulation of conformational changes in the reaction complexes. Direct multiparticle models explicitly simulate Brownian diffusion of the mobile protein carriers and their electrostatic interactions with multienzyme complexes both in solution and in heterogeneous interior of a biomembrane. The combined use of methods of kinetic and Brownian multiparticle and molecular modeling makes it possible to study the mechanisms of regulation of an integral system of electron transport processes in plants and algae at molecular and subcellular levels.

DiffSRL: Learning Dynamical State Representation for Deformable Object Manipulation With Differentiable Simulation

Dynamic state representation learning is essential for robot learning. Good latent space that can accurately describe dynamic transition and constraints can significantly accelerate reinforcement learning training as well as reduce motion planning complexity. However, deformable object have very complicated dynamics and is hard to be represented directly by a neural network without any prior physics information. We propose DiffSRL, an end-to-end dynamic state representation learning pipeline that uses differentiable physics engine to teach neural network how to represent high dimensional pointcloud data collected from deformable objects. Our specially designed loss function can guide neural network aware physics constraints and feasibility. We benchmark the performance of our methods as well as other state representation algorithms with multiple downstream tasks on PlasticineLab. Our model demonstrates superior performance most of the time on all tasks. We also demonstrate our model's performance in real hardware setting with two manipulation tasks on a UR-5 robot arm.

Contact Position Estimation in the Event of Simultaneous Multiple Contacts in Vision-based Tactile Sensors

Tactile sensors are used to detect physical contact or pressure. They provide feedback about the physical environment and allow more natural and intuitive interaction with machines. Tactile sensors have many applications in the fields of agriculture, space exploration, health and automotive. Capacitive, resistive, as well as vision (optical) based tactile sensors have been proposed in the literature. This paper proposes a novel approach to solving the problem of estimating the contact locations in the event of simultaneous multiple contacts in vision-based tactile sensors. The relationship between the contact force and the resulting physical deformation of the sensor material of a large-scale tactile sensor was studied with the aid of a custom-built hardware unit. Hardware architecture consists of a custom-designed flat rectangular sensor surface coupled with a mono-vision camera to capture the surface deformation. This method can capture detailed information on the resulting deformation for multiple simultaneous contacts. A software -based deformation estimation algorithm is proposed, where the grid array of marker positions was estimated with a tracking algorithm, an estimation algorithm, and a graphical representation algorithm. Moreover, separate analyses have been carried out to find the best suitable method to observe the deformation of the sensor material. In this study, the approach that was taken to find the contact position and deformation, produced results with an accuracy of more than 97%. Consequently, these results show that this method outperforms existing state-of-the-art techniques in terms of accuracy in the detection of the contact position. KEYWORDS: Vision-based tactile sensors, Surface deformation, marker-based localization, Contact point estimation

Resource Optimisation in Cloud Computing: Comparative Study of Algorithms Applied to Recommendations in a Big Data Analysis Architecture

Recommender systems (RS) have emerged as a means of providing relevant content to users, whether in social networking, health, education, or elections. Furthermore, with the rapid development of cloud computing, Big Data, and the Internet of Things (IoT), the component of all this is that elections are controlled by open and accountable, neutral, and autonomous election management bodies. The use of technology in voting procedures can make them faster, more efficient, and less susceptible to security breaches. Technology can ensure the security of every vote, better and faster automatic counting and tallying, and much greater accuracy. The election data were combined by different websites and applications. In addition, it was interpreted using many recommendation algorithms such as Machine Learning Algorithms, Vector Representation Algorithms, Latent Factor Model Algorithms, and Neighbourhood Methods and shared with the election management bodies to provide appropriate recommendations. In this paper, we conduct a comparative study of the algorithms applied in the recommendations of Big data architectures. The results show us that the K-NN model works best with an accuracy of 96%. In addition, we provided the best recommendation system is the hybrid recommendation combined by content-based filtering and collaborative filtering uses similarities between users and items.

Diagnostic quality assessment for low-dimensional ECG representations

There have been several attempts to quantify the diagnostic distortion caused by algorithms that perform low-dimensional electrocardiogram (ECG) representation. However, there is no universally accepted quantitative measure that allows the diagnostic distortion arising from denoising, compression, and ECG beat representation algorithms to be determined. Hence, the main objective of this work was to develop a framework to enable biomedical engineers to efficiently and reliably assess diagnostic distortion resulting from ECG processing algorithms. We propose a semiautomatic framework for quantifying the diagnostic resemblance between original and denoised/reconstructed ECGs. Evaluation of the ECG must be done manually, but is kept simple and does not require medical training. In a case study, we quantified the agreement between raw and reconstructed (denoised) ECG recordings by means of kappa-based statistical tests. The proposed methodology takes into account that the observers may agree by chance alone. Consequently, for the case study, our statistical analysis reports the “true”, beyond-chance agreement in contrast to other, less robust measures, such as simple percent agreement calculations. Our framework allows efficient assessment of clinically important diagnostic distortion, a potential side effect of ECG (pre-)processing algorithms. Accurate quantification of a possible diagnostic loss is critical to any subsequent ECG signal analysis, for instance, the detection of ischemic ST episodes in long-term ECG recordings.

Fault Diagnosis of Rotating Equipment Bearing Based on EEMD and Improved Sparse Representation Algorithm

Aiming at the problem that the vibration signals of rolling bearings working in a harsh environment are mixed with many harmonic components and noise signals, while the traditional sparse representation algorithm takes a long time to calculate and has a limited accuracy, a bearing fault feature extraction method based on the ensemble empirical mode decomposition (EEMD) algorithm and improved sparse representation is proposed. Firstly, an improved orthogonal matching pursuit (adapOMP) algorithm is used to separate the harmonic components in the signal to obtain the filtered signal. The processed signal is decomposed by EEMD, and the signal with a kurtosis greater than three is reconstructed. Then, Hankel matrix transformation is carried out to construct the learning dictionary. The K-singular value decomposition (K-SVD) algorithm using the improved termination criterion makes the algorithm have a certain adaptability, and the reconstructed signal is constructed by processing the EEMD results. Through the comparative analysis of the three methods under strong noise, although the K-SVD algorithm can produce good results after being processed by the adapOMP algorithm, the effect of the algorithm is not obvious in the low-frequency range. The method proposed in this paper can effectively extract the impact component from the signal. This will have a positive effect on the extraction of rotating machinery impact features in complex noise environments.

Using dorsal surface for individual identification of dairy calves through 3D deep learning algorithms

Advances in machine learning techniques have allowed the development of computer vision systems (CVS) that can accurately predict several phenotypes of interest for livestock operations. In this context, 3D images taken from a top-down view are particularly useful for estimating body condition score, growth development, and body biometrics in cattle. Frequently, such CVS rely on identification (ID) systems, such as electronic tags, as a way to match animal ID and the predicted phenotype. However, the same 3D images used to predict body weight and other animal biometrics could be adopted for animal recognition as well. Such alternative would optimize CVS to recognize animal ID and monitor growth development simultaneously while leveraging the same hardware infrastructure. Furthermore, this strategy could be used to recognize animals with similar color patterns. Nonetheless, growing animals are continuously changing body shape, which could limit its use as an invariant feature for pattern recognition. Thus, the objectives of this study were: (1) to compare algorithms for different 3D object representations to identify individual animals; and (2) to evaluate how short-term changes in body shape due to animal growth affect the predictive performance of these algorithms. For objective 1, the algorithms were trained (n = 4,558) and tested (n = 1,139) using images from 38 Holstein calves. For objective 2, we designed three different experiments using images (n = 2,347) from five Holstein calves taken over six weeks during their growing period, always training and testing on different weeks. Each experiment evaluated how changing a different parameter of the image capturing procedure affected the predictive ability of the trained algorithms. In the first experiment, we varied the total number of images per animal in the training set; in the second experiment, we varied the number of weeks while keeping a fixed number of images in the training set; and in the third experiment, we skipped weeks between images in the training and test sets. The F1 score for objective (1) was up to 0.804 when testing with the last frames of each video, and up to 0.959 when using random frames for testing. For objective (2), the F1 score was up to 0.947 for the first experiment when using 130 images per animal; up to 0.979 for the second experiment when using all five weeks; and up to 0.917 when not skipping weeks between training and testing. These results show that deep learning algorithms can be used to identify individual animals through their dorsal area 3D surfaces, and, from our experiments using calves in their growing period, that they are robust enough to account for changes in body shape and size, making them a promising tool for animal recognition during growth.

BRFP: An Efficient and Universal Sentence Embedding Learning Model Method Supporting Fused Syntax Combined with Graph Embedding Representation Algorithm

Due to the rapidly growing volume of data on the Internet, the methods of efficiently and accurately processing massive text information have been the focus of research. In natural language processing theory, sentence embedding representation is an important method. This paper proposes a new sentence embedding learning model called BRFP (Factorization Process with Bidirectional Restraints) that fuses syntactic information, uses matrix decomposition to learn syntactic information, and fuses and calculates with word vectors to obtain the embedded representation of sentences. In the experimental chapter, text similarity experiments are conducted to verify the rationality and effectiveness of the model and analyzed experimental results on Chinese and English texts with the current mainstream learning methods, and potential improvement directions are summarized. The experimental results on Chinese and English datasets, including STS, AFQMC, and LCQMC, show that the model proposed in this paper outperforms the CNN method in terms of accuracy and F1 value by 7.6% and 4.8. The comparison experiment with the word vector weighted model shows that when the sentence length is longer, or the corresponding syntactic structure is complex, the model’s advantages in this paper are more prominent than TF-IDF and SIF methods. Compared with the TF-IDF method, the effect improved by 14.4%. Compared with the SIF method, it has a maximum advantage of 7.9%, and the overall improvement in each comparative experimental task is between 4 and 6 percentage points. In the neural network model comparison experiment, the model in this paper compared the CNN, RNN, LSTM, ST, QT, and InferSent models, and the effect significantly improved on the 14’OnWN, 14’Tweet-news, and 15’Ans.-forum datasets. For example, in the 14’OnWN dataset, the BRFP method has a 10.9% improvement over the ST method. The 14’Tweet-news dataset has a 22.9% advantage over the LSTM method, and the 15’Ans.-forum dataset has a 24.07% improvement over the RNN method. The article also demonstrates the generality of the model, proving that the model proposed in this paper is also a universal learning framework.

Attention-wise masked graph contrastive learning for predicting molecular property.

Accurate and efficient prediction of the molecular property is one of the fundamental problems in drug research and development. Recent advancements in representation learning have been shown to greatly improve the performance of molecular property prediction. However, due to limited labeled data, supervised learning-based molecular representation algorithms can only search limited chemical space and suffer from poor generalizability. In this work, we proposed a self-supervised learning method, ATMOL, for molecular representation learning and properties prediction. We developed a novel molecular graph augmentation strategy, referred to as attention-wise graph masking, to generate challenging positive samples for contrastive learning. We adopted the graph attention network as the molecular graph encoder, and leveraged the learned attention weights as masking guidance to generate molecular augmentation graphs. By minimization of the contrastive loss between original graph and augmented graph, our model can capture important molecular structure and higher order semantic information. Extensive experiments showed that our attention-wise graph mask contrastive learning exhibited state-of-the-art performance in a couple of downstream molecular property prediction tasks. We also verified that our model pretrained on larger scale of unlabeled data improved the generalization of learned molecular representation. Moreover, visualization of the attention heatmaps showed meaningful patterns indicative of atoms and atomic groups important to specific molecular property.