Conventional Methods Research Articles

Deep Variational Network Toward Blind Image Restoration.

Blind image restoration (IR) is a common yet challenging problem in computer vision. Classical model-based methods and recent deep learning (DL)-based methods represent two different methodologies for this problem, each with their own merits and drawbacks. In this paper, we propose a novel blind image restoration method, aiming to integrate both the advantages of them. Specifically, we construct a general Bayesian generative model for the blind IR, which explicitly depicts the degradation process. In this proposed model, a pixel-wise non-i.i.d. Gaussian distribution is employed to fit the image noise. It is with more flexibility than the simple i.i.d. Gaussian or Laplacian distributions as adopted in most of conventional methods, so as to handle more complicated noise types contained in the image degradation. To solve the model, we design a variational inference algorithm where all the expected posteriori distributions are parameterized as deep neural networks to increase their model capability. Notably, such an inference algorithm induces a unified framework to jointly deal with the tasks of degradation estimation and image restoration. Further, the degradation information estimated in the former task is utilized to guide the latter IR process. Experiments on two typical blind IR tasks, namely image denoising and super-resolution, demonstrate that the proposed method achieves superior performance over current state-of-the-arts.

PeriodNet: Noise-Robust Fault Diagnosis Method Under Varying Speed Conditions.

Rolling bearings are critical components in modern mechanical systems and have been extensively equipped in various rotating machinery. However, their operating conditions are becoming increasingly complex due to diverse working requirements, dramatically increasing their failure risks. Worse still, the interference of strong background noises and the modulation of varying speed conditions make intelligent fault diagnosis very challenging for conventional methods with limited feature extraction capability. To this end, this study proposes a periodic convolutional neural network (PeriodNet), which is an intelligent end-to-end framework for bearing fault diagnosis. The proposed PeriodNet is constructed by inserting a periodic convolutional module (PeriodConv) before a backbone network. PeriodConv is developed based on the generalized short-time noise resist correlation (GeSTNRC) method, which can effectively capture features from noisy vibration signals collected under varying speed conditions. In PeriodConv, GeSTNRC is extended to the weighted version through deep learning (DL) techniques, whose parameters can be optimized during training. Two open-source datasets collected under constant and varying speed conditions are adopted to assess the proposed method. Case studies demonstrate that PeriodNet has excellent generalizability and is effective under varying speed conditions. Experiments adding noise interference further reveal that PeriodNet is highly robust in noisy environments.

MagIC-Cryo-EM: Structural determination on magnetic beads for scarce macromolecules in heterogeneous samples.

Cryo-EM single-particle analyses typically require target macromolecule concentration at 0.05∼5.0 mg/ml, which is often difficult to achieve. Here, we devise Magnetic Isolation and Concentration (MagIC)-cryo-EM, a technique enabling direct structural analysis of targets captured on magnetic beads, thereby reducing the targets' concentration requirement to < 0.0005 mg/ml. Adapting MagIC-cryo-EM to a Chromatin Immunoprecipitation protocol, we characterized structural variations of the linker histone H1.8-associated nucleosomes that were isolated from interphase and metaphase chromosomes in Xenopus egg extract. Combining Du plicated S election T o E xclude R ubbish particles (DuSTER), a particle curation method that removes low signal-to-noise ratio particles, we also resolved the 3D cryo-EM structures of H1.8-bound nucleoplasmin NPM2 isolated from interphase chromosomes and revealed distinct open and closed structural variants. Our study demonstrates the utility of MagIC-cryo-EM for structural analysis of scarce macromolecules in heterogeneous samples and provides structural insights into the cell cycle-regulation of H1.8 association to nucleosomes.

Effective Active Learning Method for Spiking Neural Networks.

A large quantity of labeled data is required to train high-performance deep spiking neural networks (SNNs), but obtaining labeled data is expensive. Active learning is proposed to reduce the quantity of labeled data required by deep learning models. However, conventional active learning methods in SNNs are not as effective as that in conventional artificial neural networks (ANNs) because of the difference in feature representation and information transmission. To address this issue, we propose an effective active learning method for a deep SNN model in this article. Specifically, a loss prediction module ActiveLossNet is proposed to extract features and select valuable samples for deep SNNs. Then, we derive the corresponding active learning algorithm for deep SNN models. Comprehensive experiments are conducted on CIFAR-10, MNIST, Fashion-MNIST, and SVHN on different SNN frameworks, including seven-layer CIFARNet and 20-layer ResNet-18. The comparison results demonstrate that the proposed active learning algorithm outperforms random selection and conventional ANN active learning methods. In addition, our method converges faster than conventional active learning methods.

Genetic and mechanistic evaluation of an individual with para-Bombay phenotype associated with a compound heterozygote comprising two novel FUT1 variants.

As is well documented, the para-Bombay phenotype is typically characterized by the reduction or absence of ABH antigens on red blood cells but the presence of corresponding antigens in saliva. Herein, the underlying molecular mechanism of an individual with para-Bombay AB phenotype combined with two novel variants of the FUT1 gene was investigated. ABH antigens and antibodies were detected in the serum of the proband using conventional serological methods. The coding region nucleotides of the ABO, FUT1, and FUT2 genes were directly sequenced by polymerase chain reaction. Moreover, the FUT1 haploid type in the proband was analyzed by TA clone sequencing. The 3D structure of wild-type and mutant fucosyltransferases were simulated and analyzed using Phyre2 and Pymol software. Lastly, the effect of missense substitution on the function of fucosyltransferase was predicted by the Polymorphism Phenotyping algorithm (PolyPhen-2) and MutationTaster. ABH antigens were noted to be absent on the surface of red blood cells of the proband. The ABO genotype was ABO*A1.02/ABO*B.01, while the FUT2 genotype was FUT2*01/FUT2*c.357T. Interestingly, two novel missense variants (c.289G>A, p.Ala97Thr and c.575G>C, p.Arg192Pro) and one synonymous SNP (c.840G>A) were identified in the FUT1 gene. Furthermore, c.289G>A was detected in one haploid type, whereas c.575G>C and c.840G>A were discovered in another haploid type. Meanwhile, in silico analysis revealed that amino acid substitution caused by missense variants altered the partial spatial structure of the α-helices where residues 97 and 298 were located using 3D homology modeling software. Finally, both missense variants were defined as probably damaging based on PolyPhen-2 prediction. Two novel FUT1 variants were identified in a Chinese individual with para-Bombay AB phenotype, which can expand our understanding of the molecular mechanism underlying the para-Bombay phenotype and contribute to improving the safety of blood transfusion.

Synthesis and Characterization of Baicalein-loaded Aquasomes: An In vitro and In silico Perspective for Diabetes Mellitus.

Millions of individuals worldwide suffer from metabolic abnormalities induced by diabetes. Baicalein, a flavonoid, has shown several properties in various treatments with potential properties, including anti-inflammatory, antioxidant, and anti-diabetic properties. Practically, its application is hindered due to low solubility in aqueous media. Overcoming this challenge, aquasomes can offer an effective approach for delivering drugs and bioactive molecules to target various diseases. The study aimed to develop and evaluate baicalein-loaded aquasomes for improving solubility and comparing their antidiabetic properties to acarbose through in silico docking. Baicalein-loaded aquasomes were prepared through a three-step process: core preparation, lactose coating, and drug loading. The evaluation included assessing particle size, drug-excipient interactions, drug entrapment efficiency, loading capacity, in vitro drug release, and the kinetics of drug release. In silico docking and in vitro α-amylase inhibition activity was evaluated to assess the anti-diabetic potential of baicalein. The baicalein-loaded aquasomes were spherical with sizes ranging from 300-400 nm. FTIR analysis indicated no interaction between the components. The formulation exhibited drug entrapment efficiency of 94.04±0 4.01% and drug loading of 17.60 ± 01.03%. Drug release study showed sustained and complete (97.30 ± 02.06%) release, following first-order kinetics. Docking analysis revealed comparable binding affinity to acarbose, while the α-amylase inhibition assay showed greater inhibition potential of the aquasomes compared to the baicalein solution. Aquasomes offer an alternative approach to conventional delivery methods. The selfassembling characteristics of aquasomes greatly simplify their preparation process, adding to their appeal as a drug delivery system.

Active Clustering Ensemble With Self-Paced Learning.

A clustering ensemble provides an elegant framework to learn a consensus result from multiple prespecified clustering partitions. Though conventional clustering ensemble methods achieve promising performance in various applications, we observe that they may usually be misled by some unreliable instances due to the absence of labels. To tackle this issue, we propose a novel active clustering ensemble method, which selects the uncertain or unreliable data for querying the annotations in the process of the ensemble. To fulfill this idea, we seamlessly integrate the active clustering ensemble method into a self-paced learning framework, leading to a novel self-paced active clustering ensemble (SPACE) method. The proposed SPACE can jointly select unreliable data to label via automatically evaluating their difficulty and applying easy data to ensemble the clusterings. In this way, these two tasks can be boosted by each other, with the aim to achieve better clustering performance. The experimental results on benchmark datasets demonstrate the significant effectiveness of our method. The codes of this article are released in https://Doctor-Nobody.github.io/codes/space.zip.

Aptamer-guided Selective Delivery of Therapeutics to Breast Cancer Cells Expressing Specific Biomarkers

Abstract: Cancer biomarkers or tumor-associated antigens (TAA) are the focus area of current research in cancer biology for diagnosis, prognosis, screening, and targeted treatments. Breast cancer is the second most common type of cancer, affecting women more than men. Conventional methods and antibody-targeted therapies are less effective and suffer systemic cytotoxicity, poor tissue sensitivity, low penetration capacity, and reduced accumulation of the drug in tumor cells that limit its application and sometimes result in treatment failure. Opting for aptamer-mediated targeted delivery of various anti-cancer agents (drugs, siRNA, miRNA, shRNA and peptides) could possibly overcome these limitations by utilizing aptamer as a targeting ligand. The purpose of this article is to review the novel indicative biomarkers of breast cancer and also describe current applications of aptamer-guided active targeting systems in breast cancer therapy in vivo and in vitro.

Analytical and clinical validation of an LC-MS/MS method for carbamazepine, lamotrigine and levetiracetam in dried blood spots

ObjectivesTherapeutic drug monitoring is performed routinely in patients on anti-epileptic drugs (AEDs) for optimisation and individualisation of therapy. The dried blood spot (DBS) sampling technique is a suitable, more patient-friendly...

Formation of cell spheroids using Standing Surface Acoustic Wave (SSAW).

3D bioprinting becomes one of the popular approaches in the tissue engineering. In this emerging application, bioink is crucial for fabrication and functionality of constructed tissue. The use of cell spheroids as bioink can enhance the cell-cell interaction and subsequently the growth and differentiation of cells in the 3D printed construct with the minimum amount of other biomaterials. However, the conventional methods of preparing the cell spheroids have several limitations, such as long culture time, low-throughput, and medium modification. In this study, the formation of cell spheroids by SSAW was evaluated both numerically and experimentally in order to overcome the aforementioned limitations. The effects of excitation frequencies on the cell accumulation time, diameter of the formed cell spheroids, and subsequently, the growth and viability of cell spheroids in the culture medium over time were studied. Using the high-frequency (23.8 MHz) excitation, cell accumulation time to the pressure nodes could be reduced in comparison to that of the low-frequency (10.4 MHz) excitation, but in a smaller spheroid size. SSAW excitation at both frequencies does not affect the cell viability up to 7 days, > 90% with no statistical difference compared with the control group. In summary, SSAW can effectively prepare the cell spheroids as bioink for the future 3D bioprinting and various biotechnology applications (e.g., pharmaceutical drug screening and tissue engineering).

Non-Rigid Registration Via Intelligent Adaptive Feedback Control.

Preserving features or local shape characteristics of a mesh using conventional non-rigid registration methods is always difficult, as the preservation and deformation are competing with each other. The challenge is to find a balance between these two terms in the process of the registration, especially in presence of artefacts in the mesh. We present a non-rigid Iterative Closest Points (ICP) algorithm which addresses the challenge as a control problem. An adaptive feedback control scheme with global asymptotic stability is derived to control the stiffness ratio for maximum feature preservation and minimum mesh quality loss during the registration process. A cost function is formulated with the distance term and the stiffness term where the initial stiffness ratio value is defined by an Adaptive Neuro-Fuzzy Inference System (ANFIS)-based predictor regarding the source mesh and the target mesh topology, and the distance between the correspondences. During the registration process, the stiffness ratio of each vertex is continuously adjusted by the intrinsic information, represented by shape descriptors, of the surrounding surface as well as the steps in the registration process. Besides, the estimated process-dependent stiffness ratios are used as dynamic weights for establishing the correspondences in each step of the registration. Experiments on simple geometric shapes as well as 3D scanning datasets indicated that the proposed approach outperforms current methodologies, especially for the regions where features are not eminent and/or there exist interferences between/among features, due to its ability to embed the inherent properties of the surface in the process of the mesh registration.

Computer Simulation for Effective Pharmaceutical Kinetics and Dynamics: A Review.

Computer-based modelling and simulation are developing as effective tools for supplementing biological data processing and interpretation. It helps to accelerate the creation of dosage forms at a lower cost and with the less human effort required to conduct the work. This paper aims to provide a comprehensive description of the different computer simulation models for various drugs along with their outcomes. The data used are taken from different sources, including review papers from Science Direct, Elsevier, NCBI, and Web of Science from 1995-2020. Keywords like - pharmacokinetic, pharmacodynamics, computer simulation, whole-cell model, and cell simulation, were used for the search process. The use of computer simulation helps speed up the creation of new dosage forms at a lower cost and less human effort required to complete the work. It is also widely used as a technique for researching the structure and dynamics of lipids and proteins found in membranes. It also facilitates both the diagnosis and prevention of illness. Conventional data analysis methods cannot assess and comprehend the huge amount, size, and complexity of data collected by in vitro, in vivo</i>, and ex vivo</i> experiments. As a result, numerous in silico</i> computational e-resources, databases, and simulation software are employed to determine pharmacokinetic (PK) and pharmacodynamic (PD) parameters for illness management. These techniques aid in the provision of multiscale representations of biological processes, beginning with proteins and genes and progressing through cells, isolated tissues and organs, and the whole organism.

MPMNet: A Data-Driven MPM Framework for Dynamic Fluid-Solid Interaction.

High-accuracy, high-efficiency physics-based fluid-solid interaction is essential for reality modeling and computer animation in online games or real-time Virtual Reality (VR) systems. However, the large-scale simulation of incompressible fluid and its interaction with the surrounding solid environment is either time-consuming or suffering from the reduced time/space resolution due to the complicated iterative nature pertinent to numerical computations of involved Partial Differential Equations (PDEs). In recent years, we have witnessed significant growth in exploring a different, alternative data-driven approach to addressing some of the existing technical challenges in conventional model-centric graphics and animation methods. This article showcases some of our exploratory efforts in this direction. One technical concern of our research is to address the central key challenge of how to best construct the numerical solver effectively and how to best integrate spatiotemporal/dimensional neural networks with the available MPM's pressure solvers. In particular, we devise the MPMNet, a hybrid data-driven framework supporting the popular and powerful MPM, to combine the comprehensive properties of MPM in numerically handling physical behaviors ranging from fluid to deformable solids and the high efficiency of data-driven models. At the architectural level, our MPMNet comprises three primary components: A data processing module to describe the physical properties by way of the input fields; A deep neural network group to learn the spatiotemporal features; And an iterative refinement process to continue to reduce possible numerical errors. The goal of these special technical developments is to aim at involved numerical acceleration while preserving physical accuracy, realizing efficient and accurate fluid-solid interactions in a data-driven fashion. The extensive experimental results verify that our MPMNet can tremendously speed up the computation compared with the popular numerical methods as the complexity of interaction scenes increases while better retaining the numerical accuracy.

Design and Implementation of a Reconfigurable Corrective Control System Subject to Permanent Faults in the Controller.

This article presents a reconfiguration strategy for the corrective controller achieving model matching control of an input/state asynchronous sequential machine (ASM). The considered controller is vulnerable to permanent faults that degenerate a subset of the controller's states. If the controller has a certain amount of redundancy in terms of its states, one can build a reconfiguration scheme in which the functionality of degenerated states is taken over by supplementary states. The proposed reconfiguration scheme is superior to conventional methods of fault tolerance with hardware redundancy since the required number of redundant states is much smaller. Hardware experiments on field-programmable gate array (FPGA) circuits are provided to validate the applicability of the proposed scheme. The present study serves as the first research report on the reconfigurable corrective controller.

Nanosuspension as a Novel Nanovehicle for Drug Delivery: A Recent Update on Patents and Therapeutic Applications

Abstract: Solubility is a critical factor for the therapeutic action of drugs and does not depend on the administration of routes. Various conventional methods are used to enhance the solubility of the drug, which show limited applicability. Nanotechnology is used to improve the solubility and bioavailability of drugs that belong to BCS classes II and IV. Nanosuspension is the dispersion of pure drug nanoparticles in aqueous with a minimum amount of surfactant, stabilizing the formula-tion. Various techniques, such as the bottom-up approach, dissocubes, nanopure, nanoedge, nano-jet process, supercritical fluid, dry co-grinding, milling media, and nanoprecipitation, have been used to formulate nanosuspension. Nanosuspension can be administered orally, inhalation, trans-dermal, ocular, injectable, topical, and pulmonary. To resolve the problem of solubility and stabil-ity, nanosuspension has received much attention because of its technical simplicity, cost-effectiveness, and ease of significant scale-up. Nanosuspension can control particle size surface charge properties and release the drug at specific sites at an optimal rate. Recently, more than 100 patents have been published on nanosuspension. This review article covers the different prepara-tion methods, formulation composition, marketed products, characterization, and recent patents on nanosuspension. The various benefits and evaluation of the parameters of nanosuspension are discussed briefly. This patent-based review will enhance the knowledge of control drug delivery and related patents on nanosuspension.

Fast Convergent Antinoise Dual Neural Network Controller With Adaptive Gain for Flexible Endoscope Robots.

Manual rigid endoscopes have defects such as a low efficiency, difficult operation, and safety risks, and the antinoise interference ability, convergence speed, and control accuracy of the neural network control technology for the existing autonomous endoscopes are often ignored. Solving these problems is important for the stable operation of endoscopes. Therefore, a new adaptive fast convergent antinoise dual neural network (AFA-DNN) controller for the visual servo control of ten-degree of freedom flexible endoscope robots (FERs) with physical constraints is proposed in this work. First, the control scheme of the FERs is formulated as a quadratic programming problem, and then, an AFA-DNN visual servo controller is designed for the FERs. The adaptive gains of the controller can accelerate the convergence, improve the antinoise ability, and increase the convergence accuracy of the controller. Then, according to the Lyapunov theory, the fast convergence of the AFA-DNN in finite time is proven for both noise-free and noisy conditions. The experimental results indicate that the FER controlled by the proposed AFA-DNN can accurately track various trajectories and that the AFA-DNN has a better antinoise interference ability, higher convergence accuracy, and faster convergence speed than conventional methods. The convergence speed of the AFA-DNN is increased by a factor of 4.22 by using the adaptive gains. Experiments also indicate that the AFA-DNN remains well functioning under various noise disturbances (such as constant, periodic, linear, and Gaussian noise).

Webly Supervised Knowledge-Embedded Model for Visual Reasoning.

Visual reasoning between visual images and natural language remains a long-standing challenge in computer vision. Conventional deep supervision methods target at finding answers to the questions relying on the datasets containing only a limited amount of images with textual ground-truth descriptions. Facing learning with limited labels, it is natural to expect to constitute a larger scale dataset consisting of several million visual data annotated with texts, but this approach is extremely time-intensive and laborious. Knowledge-based works usually treat knowledge graphs (KGs) as static flattened tables for searching the answer, but fail to take advantage of the dynamic update of KGs. To overcome these deficiencies, we propose a Webly supervised knowledge-embedded model for the task of visual reasoning. On the one hand, vitalized by the overwhelming successful Webly supervised learning, we make much use readily available images from the Web with their weakly annotated texts for an effective representation. On the other hand, we design a knowledge-embedded model, including the dynamically updated interaction mechanism between semantic representation models and KGs. Experimental results on two benchmark datasets demonstrate that our proposed model significantly achieves the most outstanding performance compared with other state-of-the-art approaches for the task of visual reasoning.

Deep-Learning-Based Simulation and Inversion of Transient Electromagnetic Sounding Signals in Permafrost Monitoring Problem

Abstract —This article presents a novel approach to addressing the challenges in permafrost monitoring through the integration of deep-learning techniques with conventional electromagnetic sounding methods. Our methodology comprises a forward finite element method (FEM) solver, augmented with the Sumudu transform, and an artificial neural network (ANN) solver trained on FEM-generated data. Remarkably, the ANN solver demonstrates similar accuracy to the FEM solver but operates at a superior speed that is nearly 10,000 times faster. Furthermore, we introduce an inverse problem solution drawing on the PARS algorithm. In addition, we present an ANN-based inverse solver, where the input and output roles are inverted. The ANN inverse solver is trained on the same data, thereby offering an alternative approach to solving the inverse problem. In a computational experiment, we compare the numerical inversion results using the PARS algorithm with those obtained from the ANN forward solver, ANN inversion, and a linear combination of these solutions. This comprehensive analysis sheds light on the effectiveness of our deep-learning-based approach in permafrost monitoring, providing insights for future applications in geophysics and environmental science.

A Stochastic Recurrent Encoder Decoder Network for Multistep Probabilistic Wind Power Predictions.

In this article, a stochastic recurrent encoder decoder neural network (SREDNN), which considers latent random variables in its recurrent structures, is developed for the first time for the generative multistep probabilistic wind power predictions (MPWPPs). The SREDNN enables the stochastic recurrent model under the encoder-decoder framework to engage exogenous covariates to produce better MPWPP. The SREDNN consists of five components, the prior network, the inference network, the generative network, the encoder recurrent network, and the decoder recurrent network. The SREDNN is equipped with two critical advantages compared with conventional RNN-based methods. First, the integration over the latent random variable builds an infinite Gaussian mixture model (IGMM) as the observation model, which drastically increases the expressiveness of the wind power distribution. Secondly, hidden states of the SREDNN are updated in a stochastic way, which builds an infinite mixture of the IGMM for describing the ultimate wind power distribution and enables the SREDNN to model complex patterns across wind speed and wind power sequences. Computational experiments are conducted on a dataset of a commercial wind farm having 25 wind turbines (WTs) and two publicly assessable WT datasets to verify the advantages and effectiveness of the SREDNN for MPWPP. Experimental results show that the SREDNN achieves a lower negative form of the continuously ranked probability score (CRPS*) as well as a superior sharpness and comparable reliability of prediction intervals by comparing against considered benchmarking models. Results also show the clear benefit gained from considering latent random variables in SREDNN.

Early Detection of Colorectal Cancer: Conventional Techniques and Current Biomarkers

Abstract: Colorectal cancer (CRC) is the third most common cancer worldwide, and the incidence of CRC seems to increase gradually. The survival of CRC varies in different countries, attributed to the screening program. Generally, diagnostic approaches for CRC can be divided into visual detection methods and laboratory methods. Colonoscopy, sigmoidoscopy, and computed tomography colonography are considered visual methods widely used in cancer detection. Although visual methods provide some benefits, some disadvantages such as late detection, are present, making them useless in rapidly progressing CRC patients. On the other hand, laboratory tests are developed to compensate for the disadvantages of visual methods. More recent progression in laboratory tests makes them able to superfine detection of CRC. For instance, molecular and genetic methods based on the components of cancer cells, like nucleic acid and proteins, can prognosticate further cancer development in susceptible patients. Alongside new therapeutic approaches developed within decades, the number of CRC detection methods has increased, which aims to reduce the duration between cancer initiation and detection. This review sought to survey the CRC detection methods, including conventional and recently-developed methods, to provide better insight into CRC screening.