Specific Architecture Research Articles

Towards 6G Technology: Insights into Resource Management for Cloud RAN Deployment

Rapid advancements in the development of smart terminals and infrastructure, coupled with a wide range of applications with complex requirements, are creating traffic demands that current networks may not be able to fully handle. Accordingly, the study of 6G networks deserves attention from both industry and academia. Artificial intelligence (AI) has emerged for application in the optimization and design process of new 6G networks. The developmental trend of 6G is towards effective resource management, along with the architectural improvement of the current network and hardware specifications. Cloud RAN (CRAN) is considered one of the major concepts in sixth- and fifth-generation wireless networks, being able to improve latency, capacity, and connectivity to huge numbers of devices. Besides bettering the current set-up in terms of setting the carriers’ network architecture and hardware specifications, among other potential enablers, the developmental trend of 6G also means that there must be effective resource management. As a result, this study covers a thorough analysis of resource management plans in CRAN, optimization, and AI taxonomy, and how AI integration might enhance existing resource management.

Machine learning-based prediction approach for ranging resolution enhancement of FMCW LiDAR system with LSTM networks

Ranging resolution is one of the most important factors of frequency-modulated continuous wave (FMCW) light detection and ranging (LiDAR) systems, which is determined by the effective sweep bandwidth and observation time of the ranging signal used for Fourier transform. Conventional methods for resolution enhancement either require expensive devices or complicated operation with human intervention, which is high-cost and inefficient. For the first time, a machine learning-based prediction approach is proposed for resolution improvement. A long short-term memory (LSTM) network with a special architecture, which is driven by a theoretical model of FMCW ranging signals, is established for signal prediction. A resampling-based preprocessing block is then designed to denoise the original ranging data and enhance its feature. Finally, multi-step prediction of the input time-series signal is performed using the well-trained LSTM network to increase effective data length so as to enhance the resolution. The effectiveness of the proposed method is verified through several experiments. The results show that the proposed method not only has the advantages of low-cost and high-efficiency, but also enables the FMCW LiDAR system to possess larger equivalent bandwidth, better ranging resolution, and higher signal-to-noise ratio (SNR), enlightening the development of machine learning in high-precision ranging systems.

Methodology for Severe Convective Cloud Identification Using Lightweight Neural Network Model Ensembling

This study introduces an advanced ensemble methodology employing lightweight neural network models for identifying severe convective clouds from FY-4B geostationary meteorological satellite imagery. We have constructed a FY-4B based severe convective cloud dataset by a combination of algorithms and expert judgment. Through the ablation study of a model ensembling combination of multiple specialized lightweight architectures—ENet, ESPNet, Fast-SCNN, ICNet, and MobileNetV2—the optimal EFNet (ENet- and Fast-SCNN-based network) not only achieves real-time processing capabilities but also ensures high accuracy in severe weather detection. EFNet consistently outperformed traditional, heavier models across several key performance indicators: achieving an accuracy of 0.9941, precision of 0.9391, recall of 0.9201, F1 score of 0.9295, and computing time of 18.65 s over the test dataset of 300 images (~0.06 s per 512 × 512 pic). ENet shows high precision but misses subtle clouds, while Fast-SCNN has high sensitivity but lower precision, leading to misclassifications. EFNet’s ensemble approach balances these traits, enhancing overall predictive accuracy. The ensemble method of lightweight models effectively aggregates the diverse strengths of the individual models, optimizing both speed and predictive performance.

Spatio‐Temporal Machine Learning for Regional to Continental Scale Terrestrial Hydrology

AbstractIntegrated hydrologic models can simulate coupled surface and subsurface processes but are computationally expensive to run at high resolutions over large domains. Here we develop a novel deep learning model to emulate subsurface flows simulated by the integrated ParFlow‐CLM model across the contiguous US. We compare convolutional neural networks like ResNet and UNet run autoregressively against our novel architecture called the Forced SpatioTemporal RNN (FSTR). The FSTR model incorporates separate encoding of initial conditions, static parameters, and meteorological forcings, which are fused in a recurrent loop to produce spatiotemporal predictions of groundwater. We evaluate the model architectures on their ability to reproduce 4D pressure heads, water table depths, and surface soil moisture over the contiguous US at 1 km resolution and daily time steps over the course of a full water year. The FSTR model shows superior performance to the baseline models, producing stable simulations that capture both seasonal and event‐scale dynamics across a wide array of hydroclimatic regimes. The emulators provide over 1,000× speedup compared to the original physical model, which will enable new capabilities like uncertainty quantification and data assimilation for integrated hydrologic modeling that were not previously possible. Our results demonstrate the promise of using specialized deep learning architectures like FSTR for emulating complex process‐based models without sacrificing fidelity.

APPLICATION OF ARTIFICIAL INTELLIGENCE MODELS IN 5G AND 6G COMMUNICATION NETWORKS FOR NETWORK TRAFFIC CLASSIFICATION

An overview of artificial intelligence and machine learning models that can be adapted or used for traffic classification in 5G and 6G networks is provided. Emphasis is placed on convolutional neural networks, designed to handle data with a constant network topology. Given this feature, the need to transform traffic data into formats suitable for convolutional neural networks is outlined. Models capable of traffic classification, such as LeNet-5, AlexNet, VGGNet, ResNet, 1D CNN, Inception (GoogleNet), MobileNet, and Capsule Networks are proposed. Their features, advantages, and disadvantages are summarized. The structure of 6G networks is proposed. A description of the levels of 6G networks is given, and the tasks to be solved by artificial intelligence at each level are outlined. Specific neural network architectures and existing algorithms for 6G networks are listed, including authors, year of creation, and main articles on the topic, with features. The conceptual place of artificial intelligence in 6G networks is described, considering the type of centralization. Positive and negative consequences from the implementation of artificial intelligence in 6G networks are highlighted.

ICTSurF: Implicit Continuous-Time Survival Functions with neural networks

Background and objective:Recently, the rise of models based on deep neural networks (DNNs) has demonstrated enhanced effectiveness in survival analysis. However, deep learning dealing with survival analysis usually required specific architecture or strict discretization scheme limiting the temporal precision of input and output values. Methods:This research introduces the Implicit Continuous-Time Survival Function (ICTSurF), built on a continuous-time survival model, and constructs survival distribution through implicit representation. As a result, our method is capable of accepting inputs in continuous-time space and producing survival probabilities in continuous-time space, independent of neural network architecture. Results:Comparative evaluations against existing methods underscore the remarkable competitiveness of our proposed approach. Furthermore, we highlight the advantages of a flexible discretization scheme, showing improved performance with a lower number of discretizations compared to a rigid scheme. Conclusion:Our model exhibits competitive performance compared to existing methods, enhancing the flexibility of input data.

Intelligent deep learning supports biomedical image detection and classification of oral cancer.

Oral cancer is a malignant tumor that usually occurs within the tissues of the mouth. This type of cancer mainly includes tumors in the lining of the mouth, tongue, lips, buccal mucosa and gums. Oral cancer is on the rise globally, especially in some specific risk groups. The early stage of oral cancer is usually asymptomatic, while the late stage may present with ulcers, lumps, bleeding, etc. The objective of this paper is to propose an effective and accurate method for the identification and classification of oral cancer. We applied two deep learning methods, CNN and Transformers. First, we propose a new CANet classification model for oral cancer, which uses attention mechanisms combined with neglected location information to explore the complex combination of attention mechanisms and deep networks, and fully tap the potential of attention mechanisms. Secondly, we design a classification model based on Swim transform. The image is segmented into a series of two-dimensional image blocks, which are then processed by multiple layers of conversion blocks. The proposed classification model was trained and predicted on Kaggle Oral Cancer Images Dataset, and satisfactory results were obtained. The average accuracy, sensitivity, specificity and F1-Socre of Swin transformer architecture are 94.95%, 95.37%, 95.52% and 94.66%, respectively. The average accuracy, sensitivity, specificity and F1-Score of CANet model were 97.00%, 97.82%, 97.82% and 96.61%, respectively. We studied different deep learning algorithms for oral cancer classification, including convolutional neural networks, converters, etc. Our Attention module in CANet leverages the benefits of channel attention to model the relationships between channels while encoding precise location information that captures the long-term dependencies of the network. The model achieves a high classification effect with an accuracy of 97.00%, which can be used in the automatic recognition and classification of oral cancer.

Optimizing sparse general matrix–matrix multiplication for DCUs

Sparse general matrix–matrix multiplication (SpGEMM) is a crucial and complex computational task in many practical applications. Improving the performance of SpGEMM on SIMT processors like modern GPUs is challenging due to the unpredictable sparsity of sparse matrices. Although existing GPU solutions have made progress in improving performance through advanced algorithm design, they ignore some optimizations related to specific processor architectures. This can result in a partially inefficient implementation of their algorithms. This paper focuses on optimizing four inefficient parts of the NSparse algorithm on DCU (a GPU-like accelerator). The optimizations include: 1) setting parameters to improve the load balance of the second matrix by extracting maximum row information at runtime; 2) reducing overhead of binning operations by making full use of registers and shared memory effectively; 3) improving numerical SpGEMM performance by adjusting its calculation mode; and 4) enhancing global load balance through finer-grained grouping and kernel configurations. Experiment results demonstrate that when compared to five state-of-the-art SpGEMM algorithms (bhSparse, KokkosKernels, NSparse, rocSparse, and spECK), our optimized method achieves an average of 7.99x (up to 18.2x), 8.01x (up to 20.83x), 2.37x (up to 6.16x), 1.82x (up to 4.20x), and 1.63x (up to 5.01x) speedups on 29 sparse matrices with different sparse structures, respectively.

Quantum 3.0: Quantum Learning, Quantum Heuristics and Beyond

Quantum learning paradigms address the question of how best to harness conceptual elements of quantum mechanics and information processing to improve operability and functionality of a computing system for specific tasks through experience. It is one of the fastest evolving framework, which lies at the intersection of physics, statistics and information processing, and is the next frontier for data sciences, machine learning and artificial intelligence. Progress in quantum learning paradigms is driven by multiple factors: need for more efficient data storage and computational speed, development of novel algorithms as well as structural resonances between specific physical systems and learning architectures. Given the demand for better computation methods for data-intensive processes in areas such as advanced scientific analysis and commerce as well as for facilitating more data-driven decision-making in education, energy, marketing, pharmaceuticals and healthcare, finance and industry.

Quantum 3.0: Quantum Learning, Quantum Heuristics and Beyond

Quantum learning paradigms address the question of how best to harness conceptual elements of quantum mechanics and information processing to improve operability and functionality of a computing system for specific tasks through experience. It is one of the fastest evolving framework, which lies at the intersection of physics, statistics and information processing, and is the next frontier for data sciences, machine learning and artificial intelligence. Progress in quantum learning paradigms is driven by multiple factors: need for more efficient data storage and computational speed, development of novel algorithms as well as structural resonances between specific physical systems and learning architectures. Given the demand for better computation methods for data-intensive processes in areas such as advanced scientific analysis and commerce as well as for facilitating more data-driven decision-making in education, energy, marketing, pharmaceuticals and healthcare, finance and industry.

Efficient calcium sulfite oxidation treatment by a highly active iron-manganese bimetallic metal-organic frameworks (MOFs)

Calcium sulfite (CaSO3) oxidation is the key step in the resource utilization of flue gas desulfurization (FGD) ash waste. However, under natural conditions the oxidation rate of CaSO3 is very low, limiting its conversion into calcium sulfate, an acceptable product for construction material. This study was devoted to the investigation of the synthesis and performance of a bimetallic MOFs with potential catalytic activity, namely, Fe/Mn(BDC)(DMF,F) catalysts. A combination of techniques including SEM, EDS, XRD, FT-IR, etc. were used to characterize the catalysts. The excellent catalytic performance examined in a gas-liquid-solid three-phase oxidation system are due to the special flexible respiratory architecture and homogeneous distribution of active sites, which allows the reactants to fully contact with the catalyst. Mn incorporated in the backbone of the metal-organic framework significantly enriches the catalytic active species that participate in a radical chain reaction with activated SO32- as ·SO3-, which in turn generates the key radical ·SO5- that reacts with SO32- to form SO42-. In the presence of Fe/Mn(BDC)(DMF, F)-13, the oxidation ratio of CaSO3 could reach 90.71%, which is more than 30-fold compared to non-catalytic oxidation and almost 5 times the effects of the single metal Fe(BDC)(DMF, F) catalyst. In addition, the study of kinetics shows that the oxidation rate of Fe/Mn(BDC)(DMF,F)-13 can reach 0.042 mmol·L-1·s-1 with an apparent activation energy of 10.86 kJ/mol. The oxidation rate is mainly affected by reaction temperature, pH value, catalyst concentration, and air flow rate. This study provides a potentially sustainable way for utilization of CaSO3-containing desulfurization ash.

Effective strategy for alleviation of oil contamination in marine via the superhydrophobic biochar: Performances, mechanisms and environmental recalcitrance

The performance of layered double hydroxides (LDH)-biochar composite on alleviating oil spill pollution is poorly understood. A superhydrophobic biochar (NCY) was synthesized from the pristine wood chips biochar (WCB) after the surface deposition of NiCo-LDH (NCB) and hydrophobic modification with stearate. The oil removal potential of the designed biochars was investigated via the diesel oil/crude oil adsorption experiments and the environmental recalcitrance evaluation. The compared characterization results revealed that NiCo-LDH was successfully deposited onto biochar matrix via the electrostatic attraction and pore filling effect, which facilitated a special flower-like hierarchical architecture rough surface for biochar and hinder the multi-layer stacking of LDH. Benefit from the constructed hierarchical architecture, the occupancy of oxygen-containing functional groups and hydrophobic modification of stearate, the water contact angle of NCY (156°) was remarkably larger than NCB (117°) and WCB (50.1°), which exhibit a superhydrophobic. The maximum diesel oil sorption capacities of biochars increased from 3.28 g/g in WCB to 5.64 g/g in NCB and 11.6 g/g in NCY, as well as the maximum crude oil sorption capacities of biochars showed a similar trend (WCB: 4.64 g/g, NCB: 8.74 g/g, NCY: 18.6 g/g). Accordingly, NCY showed higher oil adsorption capacity than NCB and WCB mainly due to the enhanced hydrophobic forces and the π-π electron donor-acceptor interaction resulted from lower amount of O-containing functional groups and superhydrophobic surface wettability. Furthermore, the application of LDH remarkably improved the environmental recalcitrance of biochar (resist to the chemical oxidation and thermal decomposition in marine) due to the coating of NiCo-LDH could enhance the bulk stability of biochar and increase the liable carbon content in biochar. This study proved that the application of NiCo-LDH and stearate could be an effective approach for improve the oil pollution remediation capacity and the environmental recalcitrance of biochar.

Developing CBTC system safety requirement hierarchy through STPA methodology

Safety-critical systems, such as the railway signal system, are subject to potentially high costs from failures, including loss of life and property damage. The use of new technology, including communication-based train control (CBTC) systems with software and computers, has changed the types of accidents that occur. Software-related issues and dysfunctional interactions between system components controlled by the software are increasingly the cause of incidents. Developing a “safe” safety-critical system requires accurate and complete safety requirements, which are the foundation of system development. Traditional hazard analysis techniques are insufficient for identifying the causes of accidents in modern railway signaling systems. Systems-Theoretic Process Analysis (STPA) is a powerful new hazard analysis method designed to address these limitations. Building upon this foundation, a hierarchical approach to safety requirement development has been further developed. This approach combines STPA analysis with a hierarchical modeling approach to establish traceability links from safety requirements to specific architectures, refine and allocate system-level safety requirements to relevant subsystems, and abstract safety requirements at higher hierarchical levels to enable easy changes to lower-level implementations. This paper employs the aforementioned methodology within the context of the CBTC system, thereby enhancing risk management and hazard analysis, enabling early insights, and facilitating the generation of safety requirements of CBTC System.

Which urban and landscape qualities make Arctic villages attractive? The Torne River villages in Sweden

ABSTRACT Throughout history, small village communities in the Arctic have developed several strategies to ensure their survival. Along the Torne River, some fishing communities have produced specific architectures, landscapes, and social strategies to support their communities and survive for centuries. However, depopulation, aging, climate change, and the expansion of the extraction industry are threatening these villages. The hypothesis is that traditional fishing villages situated alongside rivers possess architectural, urban, and social attributes that can enhance outdoor activities linked to water and green spaces and enable the long-term social sustainability of Arctic villages. The innovative approach of the paper involves combining a mapping methodology of green and blue infrastructure with the architectural, urban, social and historical values of a place to identify design strategies for improving attractiveness demonstrating its efficacy, particularly in small, local-scale villages. The paper investigates the villages of Kukkola and Korpikylä taken as emblematic examples and explores the architectural and landscape value in relation to the green–blue infrastructure.

Ag-Incorporated Cr-Doped BaTiO3 Aerogel toward Enhanced Photocatalytic Degradation of Methyl Orange.

A novel Cr-doped BaTiO3 aerogel was successfully synthesized using a co-gelation technique that involves two metallic alkoxides and a supercritical drying method. This freshly prepared aerogel has a high specific surface area of over 100 m2/g and exhibits improved responsiveness to the simulated sunlight spectrum. Methyl orange (MO) was chosen as the simulated pollutant, and the results reveal that the Cr-doped BaTiO3 aerogel, when modified with the noble metal silver (Ag), achieves a pollutant removal rate approximately 3.2 times higher than that of the commercially available P25, reaching up to 92% within 60 min. The excellent photocatalytic performance of the Ag-modified Cr-doped BaTiO3 aerogel can be primarily attributed to its extensive specific surface area and three-dimensional porous architecture. Furthermore, the incorporation of Ag nanoparticles effectively suppresses the recombination of photo-generated electrons and holes. Stability and reusability tests have confirmed the reliability of the Ag-modified Cr-doped BaTiO3 aerogel. Therefore, this material emerges as a highly promising candidate for the treatment of textile wastewater.

Surface functionalized biochar for the effective capacitive deionization of lead ions

Biochar has emerged as a promising alternative to activated carbon for capacitive deionization (CDI) due to its special architecture and functionalities. However, the selective purification of trace toxic ions is always limited by the number of specific functionalities. Herein, a thiosemicarbazide-modified biochar (BC-S) was developed for removing trace Pb2+ from water. The cotton stalk derived biochar (BC) is prepared by one-step activation with CO2, which has a high mesoporous ratio and is favorable for ion transport. It was then chemically modified with thiosemicarbazide to add additional Pb2+ adsorption sites. BC as anode and BC-S as cathode formed an asymmetric device for testing, and it exhibited a Pb2+ adsorption capacity of 68.5 mg g−1, much higher than that of the symmetric BC electrode (15.9 mg g−1). More importantly, BC-S still performs excellent Pb2+ selectivity in the presence of various cations such as Ca2+ and Mg2+. The ex-situ XPS and SEM revealed that Pb2+ is adsorbed by −C-S, −C = S, −SOx-, and −N- functional groups on the electrode surface, where electrosorption and chemisorption co-occur. This work shows that biochar can be engineered and explored broadly as an inexpensive sustainable electrode material for the separation and recovery of heavy metals and salt ions from water.

Hybrid Intelligent Control System for Adaptive Microgrid Optimization: Integration of Rule-Based Control and Deep Learning Techniques

Microgrids (MGs) have evolved as critical components of modern energy distribution networks, providing increased dependability, efficiency, and sustainability. Effective control strategies are essential for optimizing MG operation and maintaining stability in the face of changing environmental and load conditions. Traditional rule-based control systems are extensively used due to their interpretability and simplicity. However, these strategies frequently lack the flexibility for complex and changing system dynamics. This paper provides a novel method called hybrid intelligent control for adaptive MG that integrates basic rule-based control and deep learning techniques, including gated recurrent units (GRUs), basic recurrent neural networks (RNNs), and long short-term memory (LSTM). The main target of this hybrid approach is to improve MG management performance by combining the strengths of basic rule-based systems and deep learning techniques. These deep learning techniques readily enhance and adapt control decisions based on historical data and domain-specific rules, leading to increasing system efficiency, stability, and resilience in adaptive MG. Our results show that the proposed method optimizes MG operation, especially under demanding conditions such as variable renewable energy supply and unanticipated load fluctuations. This study investigates special RNN architectures and hyperparameter optimization techniques with the aim of predicting power consumption and generation within the adaptive MG system. Our promising results show the highest-performing models indicating high accuracy and efficiency in power prediction. The finest-performing model accomplishes an R2 value close to 1, representing a strong correlation between predicted and actual power values. Specifically, the best model achieved an R2 value of 0.999809, an MSE of 0.000002, and an MAE of 0.000831.

WordCanvas: Text-to-Image Generation

This project investigates the novel use of stable dif- fusion techniques to generate high-quality images from detailed text descriptions. The combination of natural language under- standing and computer vision in text-to-image conversion opens up new possibilities for content creation and communication. Using cutting-edge stable diffusion models, our project builds a solid foundation for the generation process, which includes tokenization, pre-processing, specialized architecture design, and post-processing techniques. The advantages include eye-catching images, increased user engagement, content personalization, and improved accessibility. Automation of content generation has applications in marketing, education, data visualization, and creative expression. However, challenges such as model accuracy, ethical concerns, and biases need addressing. Achieving a balance between automation and human supervision is critical for the responsible application of this transformative capability. Index Terms—Stable diffusion, Text-to-image conversion, Nat- ural language understanding, Pre - processing, Post-processing techniques, Content personalization

Refined offshore wind speed prediction: Leveraging a two-layer decomposition technique, gated recurrent unit, and kernel density estimation for precise point and interval forecasts

Precise forecasting of offshore wind speeds is paramount for various applications, including offshore wind energy production, disaster prevention and mitigation, and maritime navigation. This study introduces a novel model for point and interval prediction of offshore wind speed, incorporating an innovative two-layer decomposition technique, gated recurrent unit (GRU), and kernel density estimation (KDE). Initially, the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is utilized to decompose the raw series into multiple subsequences, thus alleviating the inherent data nonstationarity. Subsequently, we employ the refined composite multiscale fuzzy entropy (RCMFE) to reconstruct the subsequences into multiple components, thereby reducing the computational complexity. Variational mode decomposition (VMD) is utilized to enhance the modeling accuracy to decompose the high-frequency component, thereby generating a set of submodels. The GRU, a specialized recurrent neural network architecture, is leveraged to forecast the remaining components and submodels, producing a series of subresults. The subresults are linearly summed to obtain the final point prediction result. Finally, based on point prediction, employing KDE to gauge the probability density distribution of prediction errors culminates in the derivation of the offshore wind speed prediction interval. The experimental results substantiate the superior predictive performance of the proposed prediction model.

Seismic data denoising with two-step prediction strategy based on Neural Network

Seismic data denoising (SDD) plays an important role in obtaining high-quality data for subsequent seismic imaging and inversion. However, traditional SDD methods still present several disadvantages such as parameter selection difficulties, high computational costs, and a strong dependence on the experience of processing personnel. Deep learning (DL)-based SDD methods can overcome these issues to a certain extent, having the advantages of high computational efficiency and negligible dependency on the experience of processing personnel. However, existing DL-based SDD methods typically adopt a specific single-network architecture, which can be further improved in terms of training efficiency and denoising quality. In this paper, we propose a two-step prediction denoising method based on the combination of two identical or different network architectures for improving the accuracy and efficiency of DL-based SDD methods. Compared with existing SDD methods, the two-step prediction denoising method is more capable of extracting feature information at multiple scales because multiple network architectures are combined in a single denoising task, thus improving the training efficiency and denoising accuracy. In this study, we implemented the two-step prediction denoising method using an improved denoising convolutional neural network (DnCNN) and a nested U-shaped fully convolutional network (U-Net++). Several synthetic numerical examples based on three different types of noise were denoised, with the results indicating that the proposed method effectively improves the accuracy and efficiency of the DL-based SDD method. Finally, a test using field data was performed to demonstrate the real-world applicability of the novel two-step prediction denoising method.