Basic Architecture Research Articles

A Survey on Recommender Systems Using Graph Neural Network

The expansion of the Internet has resulted in a change in the flow of information. With the vast amount of digital information generated online, it is easy for users to feel overwhelmed. Finding the specific information can be a challenge, and it can be difficult to distinguish credible sources from unreliable ones. This has made recommender system (RS) an integral part of the information services framework. These systems alleviate users from information overload by analyzing users’ past preferences and directing only desirable information toward users. Traditional RSs use approaches like collaborative and content-based filtering to generate recommendations. Recently, these systems have evolved to a whole new level, intuitively optimizing recommendations using deep network models. graph neural networks (GNNs) have become one of the most widely used approaches in RSs, capturing complex relationships between users and items using graphs. In this survey, we provide a literature review of the latest research efforts done on GNN-based RSs. We present an overview of RS, discuss its generalized pipeline and evolution with changing learning approaches. Furthermore, we explore basic GNN architecture and its variants used in RSs, their applications, and some critical challenges for future research.

Adaptive human–machine theorem proving system

This paper presents a novel approach to constructing human–machine theorem proving systems. These systems integrate machine learning capabilities, human expert knowledge, and rigorous logical control for the effective construction and verification of proofs. The innovation of this approach lies in its openness: the user is given a tool for building such systems. Users can create theorem proving systems by selecting existing logical inference strategies or adding new ones in accordance with the provided interfaces or relationship agreements. The systems being built have a significant human--machine adaptive nature. During their operation, a meta-strategy is developed and trained based on the foundational elements of the existing strategies. The system is designed as a universal framework for managing various strategies, with the provision of a basic architecture and a library of strategies with the possibility of adding new ones. During the learning process, a system of structural characteristics is also accumulated and trained, on the basis of which a decision is made on the use of specific strategy elements at the next step. The presentation is conducted for the sequential calculus of minimal positive predicate logic as the most suitable for the deductive synthesis of programs and algorithms, for which it is proposed to use this approach.

Measurement of intelligent computing via Levenberg Marquardt algorithm (LMA) for accurate prediction of fluid forces in a transient non-Newtonian thermal flow

Predicting precise results for the quantities of interest in time-dependent Computational Fluid Dynamics (CFD) simulations requires a significant investment of computational resources and time. To get around these issues, CFD simulations have been joined with Artificial Neural Networks (ANN). An optimally configured artificial neural network (ANN) is given the training and validation data sets produced by computational fluid dynamics (CFD). The flow around a cylinder, which is a well-known benchmark problem for incompressible flows, has been taken into consideration by the hybrid-CFD system. The mathematical model is based on the non-stationary Navier-Stokes and energy equations with viscosity. The basic architecture of the ANN model consists of 10 hidden layers, three output levels, and five input layers. Fast second-order LMA, a top-tier approach, was used to train the network. Both the Mean Square Error (MSE) and the coefficient of determination (R) provide statistical evidence that the ANN projected values for the drag and lift coefficients and average Nusselt number obtained from the finite element analysis are accurate. This analysis suggests that ANNs have the potential to significantly cut down on the amount of time and energy needed to run time-dependent simulations.

Remote laboratory development for online learning of modern physics experiments: initial development

This study aims to design, develop, and test the quality of the remote laboratory system for online physics experimental learning on modern physics. The research used the ADDIE development model (Analysis, Design, Development, Implementation, Evaluation). The analysis was carried out by studying the literature on curriculum texts and recommendations from the Physics Education Association regarding laboratory learning. The product was designed by adopting the basic architecture of remote laboratory systems developed in science. Product development was undertaken to produce laboratory equipment, a graphical user interface with LabVIEW, and an e-learning system with Moodle. A remote laboratory system of data acquisition and e-learning tools on modern physics topics has been successfully developed with good-quality results. It is suitable for use in supporting online learning of modern physics experiments. The implications of this research show that the developed remote laboratory system can be an effective solution to support online learning of modern physics experiments, offering a high-quality alternative for physics teaching in the digital age.

Integrating Kalman filter noise residue into U-Net for robust image denoising: the KU-Net model

In low-level image processing, where the main goal is to reconstruct a clean image from a noise-corrupted version, image denoising continues to be a critical challenge. Although recent developments have led to the introduction of complex architectures to improve denoising performance, these models frequently have more parameters and higher computational demands. Here, we propose a new, simplified architecture called KU-Net, which is intended to achieve better denoising performance while requiring less complexity. KU-Net is an extension of the basic U-Net architecture that incorporates gradient information and noise residue from a Kalman filter. The network’s ability to learn is improved by this deliberate incorporation, which also helps it better preserve minute details in the denoised images. Without using Image augmentation, the proposed model is trained on a limited dataset to show its resilience in restricted training settings. Three essential inputs are processed by the architecture: gradient estimations, the predicted noisy image, and the original noisy grey image. These inputs work together to steer the U-Net’s encoding and decoding stages to generate high-quality denoised outputs. According to our experimental results, KU-Net performs better than traditional models, as demonstrated by its superiority on common metrics like the Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR). KU-Net notably attains a PSNR of 26.60 dB at a noise level of 50, highlighting its efficacy and potential for more widespread use in image denoising.

Enhancement of Near‐Infrared Photovoltaic Response of Si/Au Schottky‐Junction Structure by Band‐Bending Approaches

A combined approach of band bending is employed to enhance the near‐infrared (NIR) photovoltaic (PV) response of a Si/Au Schottky junction (SHJ) device. As a reference, the basic architecture of the SHJ device consists of textured n‐Si and gold nanoparticles (Au NPs). Its photoelectric conversion efficiency at 1319 nm wavelength is 0.0302%. A series of band‐bending approaches are then applied to the reference device in sequence, aiming to minimize the electric loss of the structure by strengthening built‐in electric field. These approaches include introductions of an Al2O3 layer for front field passivation, a p+‐Si layer to form a p+n‐like junction at the front of the device and a SiO2 layer for rear field passivation. With these modifications, under 1319 nm illumination, the open‐circuit voltage eventually increases by 14%, the short‐circuit current increases by 18% and the photoelectric conversion efficiency of the device increases by 66% to reach 0.0501%. The results of this work propose a strategy to minimize the electric loss in an NIR PV device.

The Conquest, Governance and basic Architecture of Martand Temple built by Lalitaditya Muktapida Rule (724-761 A.D.).

The Conquest, Governance and basic Architecture of Martand Temple built by Lalitaditya Muktapida Rule (724-761 A.D.).

Lightweight omni-dimensional dynamic convolution with spatial-spectral self-attention network for hyperspectral image classification

ABSTRACT Omni-dimensional dynamic convolution can adjust spatial sizes, the amount of input/output channels, and kernel size based on the characteristics of the input, thus improving the capacity to extract characteristics through convolution, resulting in increased computation and model complexity. As a result, it is challenging to deploy these models on resource-limited airborne high-spectral testing systems. This paper proposes a lightweight omni-dimensional dynamic convolution network as a possible solution to this issue. In this network, the LS2CM module is used for spatial-spectral information extraction, and the pyramidal residual network is the basic architecture for extracting features from shallow to deep layers, and lightweight omni-dimensional dynamic convolution is adopted in the convolution module. Overcoming the pyramidal structure can only extract local information, we proposed a new simple spatial-spectral self-attention mechanism to extract global information from hyperspectral. Besides, the Huber function as an activation function. The IP, WHU-Hi-LongKou, SA, and PU datasets were used to verify the accuracy of the suggested network model. The results show that the proposed lightweight network maintains an appropriate equilibrium among model complexity as well as accuracy.

Analysis of Key Technologies for Data Security Protection Based on Cloud Computing

With the rapid development of cloud computing, more and more enterprises and institutions are migrating their data and business operations to the cloud. However, this shift has brought data security issues in cloud environments to the forefront. This paper primarily investigates the key technologies for data security protection in cloud computing environments. It begins by introducing the basic concepts and architecture of cloud computing and analyzing the fundamental concepts and threats related to data security protection. The paper then delves into critical technologies such as data encryption, access control, data storage and backup security, and data privacy protection, detailing the algorithmic principles and implementation methods of these technologies. Additionally, the paper explores the challenges faced by current cloud computing data security protection technologies and their corresponding solutions, analyzing the effectiveness of these technologies through practical case studies. Finally, the paper forecasts the future development trends of cloud computing data security technologies, particularly the potential impact of emerging technologies on data security protection. This research aims to provide theoretical and technical support for data security protection in cloud computing environments.

Enhanced thermally integrated Carnot battery using low-GWP working fluid pair: Multi-aspect analysis and multi-scale optimization

Thermally integrated Carnot battery (TICB) emerges as a promising technology for long-duration energy storage. This study aims to improve its multi-dimensional performance from the optimization design level, thereby promoting its competitiveness. Firstly, a refined system architecture is developed, integrating subsystem layout modification and advanced thermal integration mode. Sixteen potential working fluid pairs are formed by screening low-GWP refrigerants as drop-in substitutes for R245fa. Then, a comprehensive evaluation framework is established to characterize this technology from energy, exergy, and economic perspectives, and a collaborative optimization method is introduced to facilitate integrated optimization. Finally, a whole cycle cumulative exergy analysis is conducted to explore directions for further improvement. Results indicate that, compared to the basic architecture, the round-trip efficiency (RTE) of the proposed system is elevated by over 30%. The use of different alternative refrigerants in the charging and discharging cycles makes the TICB not only sustainable but also more efficient. The thermodynamic dilemma of determining the heat pump evaporation temperature disappears with a closed-type heat source. To maximize overall thermo-economics, sufficient heat pump subcooling and evaporator internal superheat are necessary, and the ideal storage temperature span and pinch point temperature difference of heat exchangers must be identified. The collaborative optimization displays that the first-rank working fluid pair is R1234ze(Z)-R1224yd(Z), with an RTE of 85.2%, a volumetric energy density of 3.10 kWh/m3, and a levelized cost of storage of 0.303 $/kWh, respectively. Furthermore, the RTE is highly sensitive to the insulation quality of storage tanks. A mere 2.5% performance degradation can lead to a 10% points decline in RTE. Internal exergy destruction is primarily caused by poor heat transfer matching, while external exergy loss mainly results from underutilized heat sources during non-charging periods. Therefore, we recommend the district heating network as the target heat source for the dual-period TICB. These achievements offer a valuable reference for the research and development of efficient, affordable, and sustainable TICB.

Inhibitory circuits generate rhythms for leg movements during Drosophila grooming.

Limbs execute diverse actions coordinated by the nervous system through multiple motor programs. The basic architecture of motor neurons that activate muscles that articulate joints for antagonistic flexion and extension movements is conserved from flies to vertebrates. While excitatory premotor circuits are expected to establish sets of leg motor neurons that work together, our study uncovered a new instructive role for inhibitory circuits: their ability to generate rhythmic leg movements. Using electron microscopy data for the Drosophila nerve cord, we categorized ~120 GABAergic inhibitory neurons from the 13A and 13B hemi-lineages into classes based on similarities in morphology and connectivity. By mapping their synaptic partners, we uncovered pathways for inhibiting specific groups of motor neurons, disinhibiting antagonistic counterparts, and inducing alternation between flexion and extension. We tested the function of specific inhibitory neurons through optogenetic activation and silencing, using an in-depth ethological analysis of leg movements during grooming. We combined anatomy and behavior analysis findings to construct a computational model that can reproduce major aspects of the observed behavior, confirming the sufficiency of these premotor inhibitory circuits to generate rhythms.

Efficient fruit disease diagnosis on resource-constrained agriculture devices

Climate change in recent years has caught the attention of researchers worldwide, with drastic effects on many economic sectors, especially agriculture and livestock. Due to global warming and declining water levels, food security is becoming an increasingly urgent concern. The situation is more challenging in underdeveloped nations such as Pakistan, where little attention has been paid to improving the processes to produce effective seeds and herbicides. The problem has been exacerbated due to financial constraints and a lack of technology to monitor crops. It has been observed that even a noncritical disease can ruin the crop if timely inspections aren’t performed. Although many solutions have been proposed recently, most are based on heavy mobile applications and cloud-based solutions, which results in considerable computational cost, power consumption, and latency. This work proposes a Deep Neural Networks (DNNs)-based light-weight solution for diagnosing and classifying apple crop diseases for farmers working in rural places (where the internet is not accessible). With the increasing need for efficient and robust Machine Learning (ML) applications on edge devices, such as mobile phones, Raspberry Pi, and Jetson Nano-based devices, there has been a demand for more efficient Deep Neural Networks (DNN) models. To meet this demand, various DNN-based models have been experimented with, including Basic CNN Architecture, AlexNet, and EfficientNet Lite to measure performance After a thorough examination and evaluation of each model’s performance, efficiency, and resource usage, the most optimal model was picked and developed applications for classifying apple crop disease. Using a transfer learning strategy on a specially developed EfficientNet DNN architecture, achieving 85% test accuracy.

Unlocking freeform structured surface denoising with small sample learning: Enhancing performance via physics-informed loss and detail-driven data augmentation

Denoising plays a vital role in freeform structured surface metrology. Traditional techniques, such as Gaussian and partial differential equation-based diffusion filters, often involve a time-consuming calibration process, particularly for complex surfaces. The main challenge lies in automating the denoising operation while accurately preserving features for varied surface textures. To address this challenge, an automatic approach PI-DnCNN based on small sample learning is presented in this paper. Denoising convolutional neural network (DnCNN) is employed as the basic architecture of this approach, due to its effectiveness in tackling mix-level Gaussian noise and adapting to small training datasets. Acknowledging the constraints of limited datasets, a novel physics-informed denoising loss function marrying filtering techniques is proposed to improve model performance. Additionally, a hybrid data augmentation strategy is developed to enhance the recognition of complex components. The paper also reports a set of experiments to demonstrate the presented approach in terms of performance over conventional techniques, enhancements with limited sample sizes, and applicability in general image denoising. The experiment results suggest that the presented approach consistently achieves higher average scores compared to traditional filters and emerges superior compared to the conventional DnCNN loss across different dataset sizes. In addition, the proposed loss also shows effectiveness in general image denoising, which suggests the robustness and universality of the approach.

Spatial entropy as an inductive bias for vision transformers

Recent work on Vision Transformers (VTs) showed that introducing a local inductive bias in the VT architecture helps reducing the number of samples necessary for training. However, the architecture modifications lead to a loss of generality of the Transformer backbone, partially contradicting the push towards the development of uniform architectures, shared, e.g., by both the Computer Vision and the Natural Language Processing areas. In this work, we propose a different and complementary direction, in which a local bias is introduced using an auxiliary self-supervised task, performed jointly with standard supervised training. Specifically, we exploit the observation that the attention maps of VTs, when trained with self-supervision, can contain a semantic segmentation structure which does not spontaneously emerge when training is supervised. Thus, we explicitly encourage the emergence of this spatial clustering as a form of training regularization. In more detail, we exploit the assumption that, in a given image, objects usually correspond to few connected regions, and we propose a spatial formulation of the information entropy to quantify this object-based inductive bias. By minimizing the proposed spatial entropy, we include an additional self-supervised signal during training. Using extensive experiments, we show that the proposed regularization leads to equivalent or better results than other VT proposals which include a local bias by changing the basic Transformer architecture, and it can drastically boost the VT final accuracy when using small-medium training sets. The code is available at https://github.com/helia95/SAR.

Improving few-shot named entity recognition via Semantics induced Optimal Transport

Named entity recognition (NER) is to identify and categorize entities in unstructured text, which serves as a fundamental task for a variety of natural language processing (NLP) applications. In particular, emerging few-shot NER methods aim to learn model parameters well with few samples and have received considerable attention. The dominant few-shot NER methods usually employ pre-trained language models (PLMs) as their basic architecture and fine-tune model parameters with few NER samples. Since the sample size is small and there are a large number of parameters in PLMs, fine-tuning may result in the parameters of PLMs being highly biased. To address this issue, this study introduces the semantic distribution distance constraints to optimize the fine-tuning process of few-shot NER models and develops a framework named Semantic Constraints on few-shot Named Entity Recognition (SCNER). Specifically, the framework formulates the general knowledge transfer of PLMs as an optimal transport procedure with a semantic prior. And, a Semantics-induced Optimal Transport (SOT) regularizer is developed to utilize the importance and similarities of tokens within sentences. SOT builds the semantic distribution of the sentence and defines the transport costs between tokens to achieve the token-level optimal transport procedures. Finally, SOT is employed as a regularization term of few-shot NER to introduce the semantic distribution distance constraint for effectively transferring general knowledge from PLMs. The experiments on four public datasets demonstrate that the proposed method significantly improves the performance of NER models in both few-shot and fully supervised scenarios. SCNER is a common framework that can be applied to a variety of models without adding additional learning parameters, and can be used to enhance the generalization ability and adaptability of various few-shot NER models.

Probing the limit of hydrologic predictability with the Transformer network

For a number of years since their introduction to hydrology, recurrent neural networks like long short-term memory (LSTM) networks have proven remarkably difficult to surpass in terms of daily hydrograph metrics on community-shared benchmarks. Outside of hydrology, Transformers have now become the model of choice for sequential prediction tasks, making it a curious architecture to investigate for application to hydrology. Here, we first show that a vanilla (basic) Transformer architecture is not competitive against LSTM on the widely benchmarked CAMELS streamflow dataset, and lagged especially prominently for the high-flow metrics, perhaps due to the lack of memory mechanisms. However, a recurrence-free variant of the Transformer model obtained mixed comparisons with LSTM, producing very slightly higher Kling-Gupta efficiency coefficients (KGE), along with other metrics. The lack of advantages for the vanilla Transformer network is linked to the nature of hydrologic processes. Additionally, similar to LSTM, the Transformer can also merge multiple meteorological forcing datasets to improve model performance. Therefore, the modified Transformer represents a rare competitive architecture to LSTM in rigorous benchmarks. Valuable lessons were learned: (1) the basic Transformer architecture is not suitable for hydrologic modeling; (2) the recurrence-free modification is beneficial, so future work should continue to test such modifications; and (3) the performance of state-of-the-art models may be close to the prediction limits of the dataset. As a non-recurrent model, the Transformer may bear scale advantages for learning from bigger datasets and storing knowledge. This work lays the groundwork for future explorations into pretraining models, serving as a foundational benchmark that underscores the potential benefits in hydrology.

Heavy atom-modified hemicyanine dyes as photosensitizer scaffolds combined with nitric oxide trigger the butterfly effect in tumor therapy

Hypoxia is a common feature of solid tumors and is considered to be the fatal flaw of conventional photodynamic therapy (PDT), which severely reduces the overall therapeutic efficacy. Here, we developed a series of halogenated photosensitizers to address this issue. The results showed that the introduction of heavy atoms enhanced the spin-coupling effect of the photosensitizers and effectively improved the type I PDT (non-oxygen-dependent) efficiency. The preferred iodine-substituted photosensitizer NRh–I was used as the basic architecture, and further nitrosyl modification was performed to obtain the NO small-molecule prodrug, which was finally encapsulated with DSPE-mPEG5k to obtain a biocompatible NO nanophotocontrolled prodrug. By using the enhanced permeability and retention effect (EPR), the prodrug system can precisely target the lesion site, release a high concentration of NO by photocontrol, kill the tumor cells, and at the same time, cascade with ROS released with the same “time-space” precision to generate higher cytotoxicity, ONOO−, which generates a stronger targeted synergistic therapeutic effect. This “butterfly effect” strategy maximizes the effect of PDT and broadens the idea of translational medicine.

Neural critic learning with accelerated value iteration for nonlinear model predictive control

In practical industrial processes, the receding optimization solution of nonlinear model predictive control (NMPC) is always a very knotty problem. Based on adaptive dynamic programming, the accelerated value iteration predictive control (AVI-PC) algorithm is developed in this paper. Integrating iteration learning with the receding horizon mechanism of NMPC, a novel receding optimization solution pattern is exploited to resolve the optimal control law in each prediction horizon. Besides, the basic architecture and the specific form of the AVI-PC algorithm are demonstrated, including the relationship among the iterative learning process, the prediction process, and the control process. On this basis, the convergence and admissibility conditions are established, and the relevant properties are comprehensively analyzed when the accelerated factor satisfies the established conditions. Furthermore, the accelerated value iterative function is approximated through the single critic network constructed by utilizing the multiple linear regression method. Finally, the plentiful simulation experiments are conducted from various perspectives to verify the effectiveness and progressiveness of the AVI-PC algorithm.

Design the Enterprise Architecture Model TOGAF 9.2 for PT Service Applications Management at PT. XXX

Enterprise architecture has an important role in supporting business goals in the ever-growing digital era. Research on PT service applications. XXX, where qualitative research methods are used, involves interviews with Heads of companies. This approach refers to basic architectural theory andenterprise architecture, by usingframework TOGAF for analysis. Through stagesPreliminary untilArchitecture Change Management, TOGAF ADM version 9.2 is implemented to design the relevant architecture. The research results provide architectural design of service applications and demonstrate IT creationRoadmap which becomes a recommendation based on the company architecture objectives that have been set.

An overview on deep clustering

In recent years, with the great success of deep learning and especially deep unsupervised learning, many deep architectural clustering methods, collectively known as deep clustering, have emerged. Deep clustering shows the potential to outperform traditional methods, especially in handling complex high-dimensional data, taking full advantage of deep learning. To achieve a comprehensive overview of the field of deep clustering, this review systematically explores deep clustering methods and their various applications. First, the basic network architecture of deep clustering is described in detail, including the common network frameworks, and loss functions. Subsequently, deep clustering is divided into several categories based on the network architecture, and benchmark datasets and evaluation metrics in the field are introduced. Next, the real-world applications of deep clustering are explored in depth, providing successful cases in the fields of bioinformatics, medicine, anomaly detection, and image processing, highlighting the broad applicability of deep clustering in solving real-world challenges. Finally, the paper summarizes its contributions and explores potential directions for future research in deep clustering.