Traditional Architecture Research Articles

Enhancing stock market prediction accuracy with recurrent deep learning models: A case study on the CAC40 index

This paper explores the application of Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks for stock price prediction over a 10-day horizon. The study aims to compare the predictive performance of these two deep learning architectures within the context of financial forecasting. Utilizing historical stock data from the CAC40 dataset, which represents a capitalization-weighted measure of the 40 most significant stocks on the Euronext Paris, we train and evaluate RNN and LSTM models to forecast future stock prices. Our results demonstrate the superior performance of LSTM networks in capturing the intricate temporal dependencies inherent in stock price data. Compared to standard RNNs, LSTM models exhibit higher accuracy and provide more reliable forecasts over the 10-day prediction period. The specialized memory cells and gating mechanisms in LSTM networks enable them to effectively identify both short-term changes and long-term patterns in stock prices, thus outperforming traditional RNN architectures. This enhanced ability to model the complex dynamics of stock market data underscores the potential of LSTM networks to improve investment decision-making, risk management, and the overall efficiency of financial markets. The insights gained from this study contribute to the growing body of knowledge on the application of deep learning in finance and investment, offering valuable guidance for practitioners and researchers seeking to harness the power of advanced algorithms for stock market prediction and optimization.

MobileAmcT: A Lightweight Mobile Automatic Modulation Classification Transformer in Drone Communication Systems

With the rapid advancement of wireless communication technology, automatic modulation classification (AMC) plays a crucial role in drone communication systems, ensuring reliable and efficient communication in various non-cooperative environments. Deep learning technology has demonstrated significant advantages in the field of AMC, effectively and accurately extracting and classifying modulation signal features. However, existing deep learning models often have high computational costs, making them difficult to deploy on resource-constrained drone communication devices. To address this issue, this study proposes a lightweight Mobile Automatic Modulation Classification Transformer (MobileAmcT). This model combines the advantages of lightweight convolutional neural networks and efficient Transformer modules, incorporating the Token and Channel Conv (TCC) module and the EfficientShuffleFormer module to enhance the accuracy and efficiency of the automatic modulation classification task. The TCC module, based on the MetaFormer architecture, integrates lightweight convolution and channel attention mechanisms, significantly improving local feature extraction efficiency. Additionally, the proposed EfficientShuffleFormer innovatively improves the traditional Transformer architecture by adopting Efficient Additive Attention and a novel ShuffleConvMLP feedforward network, effectively enhancing the global feature representation and fusion capabilities of the model. Experimental results on the RadioML2016.10a dataset show that compared to MobileNet-V2 (CNN-based) and MobileViT-XS (ViT-based), MobileAmcT reduces the parameter count by 74% and 65%, respectively, and improves classification accuracy by 1.7% and 1.09% under different SNR conditions, achieving an accuracy of 62.93%. This indicates that MobileAmcT can maintain high classification accuracy while significantly reducing the parameter count and computational complexity, clearly outperforming existing state-of-the-art AMC methods and other lightweight deep learning models.

Software-Defined Named Data Networking in Literature: A Review

This paper presents an in-depth review of software-defined named data networking (SD-NDN), a transformative approach in network architectures poised to deliver substantial benefits. By addressing the limitations inherent in traditional host-centric network architectures, SD-NDN offers improvements in network performance, scalability, and efficiency. The paper commences with an overview of named data networking (NDN) and software-defined networking (SDN), the two fundamental building blocks of SD-NDN. It then explores the specifics of integrating NDN with SDN, illustrating examples of various SD-NDN models. These models are designed to leverage SDN for NDN routing, caching, and forwarding. The paper concludes by proposing potential strategies for further integration of SDN and NDN and some open research questions. These proposed strategies aim to stimulate further exploration and innovation in the field of SD-NDN.

Attention-Based Neural Network for Cardiac MRI Segmentation: Application to Strain and Volume Computation

ContextDeep learning algorithms have been widely used for cardiac image segmentation. However, most of these architectures rely on convolutions that hardly model long-range dependencies, limiting their ability to extract contextual information. Moreover, the traditional U-net architecture suffers from the difference of semantic information between feature maps of the encoder and decoder (also known as the semantic gap). Material and methodTo address this issue, a new network architecture relying on attention mechanism was introduced. Swin Filtering Blocks (SFB), that use Swin Transformer blocks in a cross-attention manner, were added between the encoder and the decoder to filter information coming from the encoder based on the feature map from the decoder. Attention was also employed at the lowest resolution in the form of a transformer layer to increase the receptive field of the network.We conducted experiments to assess both generalization capability and to evaluate how training on all frames of the cardiac cycle rather than only the end-diastole and end-systole impacts strain and segmentation performances. Results and conclusionVisual inspection of feature maps suggested that Swin Filtering Blocks contribute to the reduction of the semantic gap. Performing attention between all patches using a transformer layer brought higher performance than convolutions. Training the model with all phases of the cardiac cycle resulted in slightly more accurate segmentations while leading to a more noticeable improvement for strain estimation. A limited decrease in performance was observed when testing on out-of-distribution data, but the gap widens for the most apical slices.

A comparative study to examine principal component analysis and kernel principal component analysis-based weighting layer for convolutional neural networks

ABSTRACT In the recent decay, the focus on processing signal data processing such as time series, images, and videos increased. The purpose of this processing is mainly forecasting, classification, and regression. The development of machine learning methods, on the other hand, caused the introduction of novel machine learning-based signal processor models. Convolutional neural networks (CNNs) are the best-known models widely used for signal processing. This work introduces a novel approach by combining PCA with CNNs for signal processing, offering the potential for improved performance in tasks like forecasting, classification, and regression. A comparative analysis of traditional architectures will be crucial in evaluating the effectiveness of the proposed model.

The Parthian Manor House of Sarab-e Murt in the Context of the Iranian Architectural Tradition

The Parthian Manor House of Sarab-e Murt in the Context of the Iranian Architectural Tradition

Acculturation Phenomenon in Vernacular Architecture between Vietnamese and Chams in the Kingdom of Cochin-China (16th–18th)–Southeast Asia

ABSTRACT This paper presents in general the remaining vernacular houses in the middle region of Vietnam, known as the Kingdom of Cochin-china (16th−18th). Accordingly, there are three common types of vernacular houses. Those are the “Nha Ruong” popular in the north-middle region, the “Nha La Mai” popular in the central and south-middle regions, and the “Nha Roi” popular in both the north and south-middle regions of Vietnam. This study mainly focused on the viewpoint of architectural typology and construction techniques through site investigations, comparative study, and analysis of the remaining vernacular houses. With the approach of indigenous culture, residential planning, spatial arrangement, carpenter’s tools, design methods, and construction techniques, the similarities and differences between the vernacular houses have been determined. In addition, this study also defined the acculturation phenomenon in architecture between the middle region Vietnamese emigrants and the indigenous Chams in the past. The study results are expected to help architects and students to create new architectural products that can be sustainable in the harsh climatic conditions such as the middle region of Vietnam, refining and inheriting the quintessence of traditional architecture to enrich the cultural identity of Vietnam in particular and of Southeast Asia in general.

Narrowing the semantic gaps in U-Net with learnable skip connections: The case of medical image segmentation

Current state-of-the-art medical image segmentation techniques predominantly employ the encoder–decoder architecture. Despite its widespread use, this U-shaped framework exhibits limitations in effectively capturing multi-scale features through simple skip connections. In this study, we made a thorough analysis to investigate the potential weaknesses of connections across various segmentation tasks, and suggest two key aspects of potential semantic gaps crucial to be considered: the semantic gap among multi-scale features in different encoding stages and the semantic gap between the encoder and the decoder. To bridge these semantic gaps, we introduce a novel segmentation framework, which incorporates a Dual Attention Transformer module for capturing channel-wise and spatial-wise relationships, and a Decoder-guided Recalibration Attention module for fusing DAT tokens and decoder features. These modules establish a principle of learnable connection that resolves the semantic gaps, leading to a high-performance segmentation model for medical images. Furthermore, it provides a new paradigm for effectively incorporating the attention mechanism into the traditional convolution-based architecture. Comprehensive experimental results demonstrate that our model achieves consistent, significant gains and outperforms state-of-the-art methods with relatively fewer parameters. This study contributes to the advancement of medical image segmentation by offering a more effective and efficient framework for addressing the limitations of current encoder–decoder architectures. Code: https://github.com/McGregorWwww/UDTransNet.

Bioclimatic Design Strategies For Housing in Areas Affected by Natural Events

Objective: The objective of this study was a housing design with bioclimatic criteria and construction technology with traditional materials to propose an appropriate solution for families that suffered damage from the 2017 earthquakes in Oaxaca, Mexico. Method: A climatic characterization of the site was carried out to obtain bioclimatic strategies for the housing design. Analysis methods were used to validate these strategies such as comfort triangles and Mahoney tables. The housing was designed considering the resulting strategies and prioritized passive ones. Results and conclusions: It was obtained that for the study area the main strategies for the housing design are natural cross ventilation, thermal inertia in walls and ceilings and solar radiation during the cold months. The study highlights the importance of implementing bioclimatic design strategies according to the climatic context that promote the improvement of the habitability level of housing. Implications of the research: The research contributes to the design of a sustainable housing model for families affected in their patrimony by the action of earthquakes in the study area considering the environmental conditions, in addition to promoting the conservation of traditional architecture and construction systems. Originality/value: In the area of sustainability and the environment, a housing design was proposed that adopts practices that minimize the environmental impact and ensures that the new houses are energy efficient and environmentally friendly and adapt to climate change.

Characterizing parameter variations for enhanced performance and adaptability in 3 nm MBCFET technology

With the continuous scaling down of semiconductor devices, traditional transistor architectures face significant challenges in maintaining performance and power efficiency. Multi-bridge channel field-effect transistors (MBCFETs) are promising candidates for next-generation of transistors, enabling significant size reduction while preserving high performance. This paper investigates both n-type and p-type 3-nm MBCFETs with a focus on their behavior under diverse operating conditions. The study examines the influence of doping concentration, sheet thickness, temperature, device width, and the number of sheets, on the device's functionality aiming for high-performance applications. Doping concentrations of acceptors and donors ranging from 1 × 10 15 cm−3 - 9 × 10 17 cm−3 and 1 × 10 17 cm−3 - 9 × 10 19 cm−3, respectively, to observe their impact on device performance. Similarly, sheet thicknesses from 1 nm to 2 nm and device widths from 3 nm to 30 nm are analyzed to understand the scaling effects. The temperature varies from 273.15 K to 573.15 K to simulate different operational environments, while the number of sheets, ranging from 1 to 7, is adjusted to evaluate structural effects on device behavior. By extracting the subthreshold swing (SS), threshold voltage (Vth), ON-current (ION), OFF-current (IOFF), and the ION/IOFF ratio, the study offers valuable insights into the suitability and potential applications of N-MBCFET and P-MBCFET devices at the ultra-scaled 3 nm dimension. At room temperatures, the SS achieves 60 mV dec⁻1 for n-type and 64 mV dec⁻1 for p-type which indicates proper switching speed, with corresponding ON/OFF ratios of 2 × 106 and 1 × 105 for n-type and p-type, respectively. This study makes notable contributions to the field of nanoscale transistor technology, aiding in the design and optimization of future electronic devices.

An In-Memory-Computing Structure with Quantum-Dot Transistor Toward Neural Network Applications: From Analog Circuits to Memory Arrays

The rapid advancements in artificial intelligence (AI) have demonstrated great success in various applications, such as cloud computing, deep learning, and neural networks, among others. However, the majority of these applications rely on fast computation and large storage, which poses significant challenges to the hardware platform. Thus, there is a growing interest in exploring new computation architectures to address these challenges. Compute-in-memory (CIM) has emerged as a promising solution to overcome the challenges posed by traditional computer architecture in terms of data transfer frequency and energy consumption. Non-volatile memory, such as Quantum-dot transistors, has been widely used in CIM to provide high-speed processing, low power consumption, and large storage capacity. Matrix-vector multiplication (MVM) or dot product operation is a primary computational kernel in neural networks. CIM offers an effective way to optimize the performance of the dot product operation by performing it through an intertwining of processing and memory elements. In this paper, we present a novel design and analysis of a Quantum-dot transistor (QDT) based CIM that offers efficient MVM or dot product operation by performing computations inside the memory array itself. Our proposed approach offers energy-efficient and high-speed data processing capabilities that are critical for implementing AI applications on resource-limited platforms such as portable devices.

ADAPTATION OF TRADITIONAL MINAHASA ARCHITECTURE IN MALANG CITY

Geographically and climatically, Minahasa and Malang are similar, being in the highlands and having a two-season climate, but Minahasa is more likely to experience seismicity than Malang. Culturally, the Minahasa tribe upholds mapalus to strengthen kinship. From these conditions, there is an adaptation that adjusts to the new environment which aims for comfort in occupying. This research aims to determine the results of geographical, climatic, and cultural adaptation of traditional Minahasa architecture in Malang City. The research method is descriptive qualitative and interviews by analyzing data in the form of comparing aspects of venustas, firmity, and utility. The findings of this research are that the meaning of the three vertical and horisontal spaces has changed slightly, such as the use of the lower space and placement of stairways into the pores. The knockdown system applied can be identified in the connection between the column and the beams, as well as the concrete column that adapts to the environmental conditions. Some have changed in terms of space, structure, and facade as a result of adaptation to the new environment. However, it does not change the main characteristics of Minahasa architecture so that traditional Minahasa architecture can be accepted in Malang.

In-Sensor Tactile Fusion and Logic for Accurate Intention Recognition.

Touch control intention recognition is an important direction for the future development of human-machine interactions (HMIs). However, the implementation of parallel-sensing functional modules generally requires a combination of different logical blocks and control circuits, which results in regional redundancy, redundant data, and low efficiency. Here, a location-and-pressure intelligent tactile sensor (LPI tactile sensor) unprecedentedly combined with sensing, computing, and logic is proposed, enabling efficient and ultrahigh-resolution action-intention interaction. The LPI tactile sensor eliminates the need for data transfer among the functional units through the core integration design of the layered structure. It actuates in-sensor perception through feature transmission, fusion, and differentiation, thereby revolutionizing the traditional von Neumann architecture. While greatly simplifying the data dimensionality, the LPI tactile sensor achieves outstanding resolution sensing in both location (<400µm) and pressure (75Pa). Synchronous feature fusion and decoding support the high-fidelity recognition of action and combinatorial logic intentions. Benefiting from location and pressure synergy, the LPI tactile sensor demonstrates robust privacy as an encrypted password device and interaction intelligence through pressure enhancement. It can recognize continuous touch actions in real time, map real intentions to target events, and promote accurate and efficient intention-driven HMIs.

Hardware Implementation of Next Generation Reservoir Computing with RRAM‐Based Hybrid Digital‐Analog System

Reservoir computing (RC) possesses a simple architecture and high energy efficiency for time‐series data analysis through machine learning algorithms. To date, RC has evolved into several innovative variants. The next generation reservoir computing (NGRC) variant, founded on nonlinear vector autoregression (NVAR) distinguishes itself due to its fewer hyperparameters and independence from physical random connection matrices, while yielding comparable results. However, NGRC networks struggle with massive Kronecker product calculations and matrix‐vector multiplications within the read out layer, leading to substantial efficiency challenges for traditional von Neumann architectures. In this work, a hybrid digital‐analog hardware system tailored for NGRC is developed. The digital part is a Kronecker product calculation unit with data filtering, which realizes transformation of nonlinear vector of the input linear vector. For matrix‐vector multiplication, a computing‐in‐memory architecture based on resistive random access memory array offers an energy‐efficient hardware solution, which markedly reduces data transfer and greatly improve computational parallelism and energy efficiency. The predictive capabilities of this hybrid NGRC system are validated through the Lorenz63 model, achieving a normalized root mean square error (NRMSE) of 0.00098 and an energy efficiency of 19.42TOPS W−1.

Architectural Heritage Buildings and Tourism Sustainability in Karangasem Bali

Objective: This study aims to explore and understand the interrelationships between cultural tourism and architectural heritage sites through tourist image and perception. These interrelationships must balance community needs, available resources, executive efforts and regional planning while protecting the environment. Theoretical Framework: Historic buildings are considered important elements in cultural heritage, and architecture is further considered to be one of the most important aspects that attract tourists. As a significant part of cultural heritage and tourism resources, architectural heritage is the most important commemorative, secondary architectural buildings and its natural and artificial environments in ancient areas and characteristic villages. Method: This study's method is based on mixed-method research, which is known as triangulation. This approach entailed gathering initial data, conducting interviews and surveys, and creating house maps. Traditional architectural documentation tools, such as drawings, plans, sections, elevations, and photographs, are required in all three process stages. Results and Discussion: Bali has a diversity of forms and varieties of traditional architecture. East Bali, part of the Karangasem kingdom called puri during the Mindle era of Bali, has preserved several unique architectural masterpieces. In this context, architectural heritage is critical in increasing property values. Preserving architectural heritage is considered environmentally friendly for cultural tourism. Research Implications: This study explores to what extent heritage architecture can be utilized as cultural heritage ideally and efficiently. This can be achieved by building sustainable restoration of archaeological and heritage sites to achieve sustainable heritage tourism. Originality/Value: This research utilizes experiments in countries with cultural heritage to obtain lessons, values and concepts that contribute to achieving an efficient program for sustainable tourism development based on the preservation of heritage areas.

Energy consumption and thermal comfort of rock-cut and modern buildings

Energy consumption in the building sector justifies the necessity of knowing the thermal comfort perception of vernacular and modern architectural types, based on which a correct recognition was reached for the design of buildings suitable for the climatic conditions of each region. It should be determined that the different types of modern and traditional architecture are in the comfort level in harsh hot climate conditions and how much energy they consume to reach the comfort level. Despite consideration of energy consumption and thermal comfort in different buildings in Iran, there is no clear framework for evaluating these two parameters in different buildings and comparing them. This research aims to compare the indoor thermal comfort levels of vernacular architectural buildings and modern buildings in Iran's semi-hot and dry climate at the peak of summer heat and determine their energy consumption to reach the comfort level. This study has been accomplished by collecting field data, examining the indoor predicted mean vote (PMV) index of the buildings, and comparing them. It was found that rock-cut architecture buildings are in better thermal comfort conditions without energy consumption due to the use of groundmass temperature and low heat exchanges between the indoors and outdoors because of the thermal phase of the materials and the thickness of its layers. The indoor PMV average of rock-cut buildings in summer is −0.61; in modern buildings, it is 0.77, while these two building complexes are in the same climate and close. Also, the energy consumption to reach the comfort level in rock-cut buildings is zero, while modern buildings consume an average of 7.7 kW of electricity daily. The research results will lead to recognizing and modeling the climate design of vernacular architecture, which can be used in today's architecture to reduce energy consumption.

Analysis of thermal comfort in traditional architecture, focused on digital simulations

Analysis of thermal comfort in traditional architecture, focused on digital simulations

Research on fusion navigation framework and algorithm based on fully-connected neural network

Abstract Fusion navigation and positioning have evolved into crucial technologies and methodologies within navigation systems. Currently, the majority of combined positioning frameworks employ Kalman filtering algorithms for data fusion. To explore more efficient and high-precision fusion architectures and algorithms, we introduce a fusion navigation framework based on a fully-connected neural network (FCNN). Initially, we conducted an analysis of existing fusion positioning technology, data fusion algorithms, and the application of artificial intelligence algorithms in navigation positioning. Drawing insights from the federated Kalman filter (FKF) architecture, FCNN, and attention mechanism, we propose a fusion navigation framework centered on FCNN. Finally, fixed-point and trajectory determination experiments were carried out in both open and semi-shielded environments. The results demonstrate that, compared to the traditional FKF architecture, the FCNN fusion navigation framework, coupled with the attention mechanism fusion algorithm, effectively accommodates data, mitigates errors, and achieves superior positioning accuracy.

Robust and Privacy-Preserving Decentralized Deep Federated Learning Training: Focusing on Digital Healthcare Applications.

Federated learning of deep neural networks has emerged as an evolving paradigm for distributed machine learning, gaining widespread attention due to its ability to update parameters without collecting raw data from users, especially in digital healthcare applications. However, the traditional centralized architecture of federated learning suffers from several problems (e.g., single point of failure, communication bottlenecks, etc.), especially malicious servers inferring gradients and causing gradient leakage. To tackle the above issues, we propose a robust and privacy-preserving decentralized deep federated learning (RPDFL) training scheme. Specifically, we design a novel ring FL structure and a Ring-Allreduce-based data sharing scheme to improve the communication efficiency in RPDFL training. Furthermore, we improve the process of distributing parameters of the Chinese residual theorem to update the execution process of the threshold secret sharing, supporting healthcare edge to drop out during the training process without causing data leakage, and ensuring the robustness of the RPDFL training under the Ring-Allreduce-based data sharing scheme. Security analysis indicates that RPDFL is provable secure. Experiment results show that RPDFL is significantly superior to standard FL methods in terms of model accuracy and convergence, and is suitable for digital healthcare applications.

Cross-correlation-based convolutional neural network with velocity regularization for high-resolution velocimetry of particle images

Particle image velocimetry (PIV) stands as a pivotal experimental technique in fluid dynamics, enabling the visualization and analysis of fluid flows. Traditional methods for extracting velocity fields from particle images often rely on window-cross correlation PIV or, more recently, optical flow techniques rooted in intensity conservation principles. However, the former approach suffers from low resolution, whereas the latter is hampered by computational inefficiency and a high susceptibility to noise. Recent studies have demonstrated the effectiveness of convolutional neural networks (CNNs) in processing particle images to obtain high-resolution and high-accuracy velocity fields, though traditional CNN architectures are still not satisfying in accuracy. The present study introduces an enhanced network, En-FlowNetC, based on the cross correlation-based CNN FlowNetC, specifically designed to process PIV particle images and achieve high-accuracy, high-resolution velocity fields. It incorporates a velocity regularization and is trained and validated on canonical datasets. The results indicate that En-FlowNetC surpasses traditional CNN networks in accuracy and markedly outperforms the classic Horn–Schunck optical flow method in both complex and simple flow scenarios. Furthermore, this study confirms the beneficial impact of velocity regularization, when judiciously applied, on network accuracy. The proposed modifications compared to the original FlowNetC are also examined in the ablation experiments. Overall, En-FlowNetC provides an effective deep-learning solution for PIV analysis, paving the way for future endeavors aimed at achieving highly accurate and resolved velocimetry.