scispace - formally typeset
Search or ask a question

Showing papers on "Architecture published in 2022"


Journal ArticleDOI
TL;DR: The International Seminar on Urban Form (ISUF) as mentioned in this paper was founded by three schools of urban morphology, in England, Italy and France, following seminal work by two morphologists, M.R. Conzen and Saverio Muratori.
Abstract: The forces and events leading to the formation of the International Seminar on Urban Form (ISUF) are identified. ISUF is expanding the field of urban morphology beyond its original confines in geography, particularly into the domains of architecture and planning. Three schools of urban morphology, in England, Italy and France, are coming together, following seminal work by two morphologists, M.R.G. Conzen and Saverio Muratori. The bringing together of these schools provides the basis for an interdisciplinary field and the opportunity to establish common theoretical foundations for the growing number of urban morphologists in many parts of the world. ISUF's ambitious mission is to address real and timely issues concerning city building by providing a forum for thought and action which includes related disciplines and professions in different cultures. The potential of an interdisciplinary urban morphology to contribute to the understanding and management of urban development in a period of unprecedented change is discussed.

302 citations


Book
01 Feb 2022
TL;DR: The power of design here today, gone tomorrow is the power of designing for a safer future towards the spiritual in design sensing a dwelling the biotechnology of communities the lessons of vernacular architecture form follows fun is convenience the enemy? sharing not buying generations to come the best designers in the world making the future work.
Abstract: The power of design here today, gone tomorrow? designing for a safer future towards the spiritual in design sensing a dwelling the biotechnology of communities the lessons of vernacular architecture form follows fun is convenience the enemy? sharing not buying generations to come the best designers in the world making the future work.

177 citations


Journal ArticleDOI
TL;DR: The Robot Operating System (ROS) as discussed by the authors was designed from the ground up to meet the challenges set forth by modern robotic systems in new and exploratory domains at all scales.
Abstract: The next chapter of the robotics revolution is well underway with the deployment of robots for a broad range of commercial use cases. Even in a myriad of applications and environments, there exists a common vocabulary of components that robots share—the need for a modular, scalable, and reliable architecture; sensing; planning; mobility; and autonomy. The Robot Operating System (ROS) was an integral part of the last chapter, demonstrably expediting robotics research with freely available components and a modular framework. However, ROS 1 was not designed with many necessary production-grade features and algorithms. ROS 2 and its related projects have been redesigned from the ground up to meet the challenges set forth by modern robotic systems in new and exploratory domains at all scales. In this Review, we highlight the philosophical and architectural changes of ROS 2 powering this new chapter in the robotics revolution. We also show through case studies the influence ROS 2 and its adoption has had on accelerating real robot systems to reliable deployment in an assortment of challenging environments. Description This Review describes ROS 2’s design, features, and performance with four case studies on land, air, sea, and even space.

150 citations


Book
01 Jan 2022
TL;DR: In this article, the need for change what teachers need to know and be able to do the need of new assessments in teaching new assessment strategies in teaching an architecture for a licensing system developing prototype assessments for licensing the internship implementation concerns.
Abstract: Licensing teachers - the need for change what teachers need to know and be able to do the need for new assessments in teaching new assessment strategies in teaching an architecture for a licensing system developing prototype assessments for licensing the internship implementation concerns.

101 citations


Journal ArticleDOI
TL;DR: In this paper , a new integration of an Internet of Things (IoT) architecture with deep learning against cyberattacks for online monitoring of the power transformer status is introduced for fault diagnosis of power transformers and cyberattacks.

67 citations


Proceedings ArticleDOI
01 Jun 2022
TL;DR: Zhang et al. as mentioned in this paper proposed a spatial pooling operator to conduct only basic token mixing, which achieved state-of-the-art performance on ImageNet-1K, achieving 82.1 % top-1 accuracy.
Abstract: Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in transformers can be replaced by spatial MLPs and the resulted models still perform quite well. Based on this observation, we hypothesize that the general architecture of the transformers, instead of the specific token mixer module, is more essential to the model's performance. To verify this, we deliberately replace the attention module in transformers with an embarrassingly simple spatial pooling operator to conduct only basic token mixing. Surprisingly, we observe that the derived model, termed as PoolFormer, achieves competitive performance on multiple computer vision tasks. For example, on ImageNet-1K, PoolFormer achieves 82.1 % top-1 accuracy, surpassing well-tuned vision transformer/MLP-like baselines DeiT-B/ResMLP-B24 by 0.3%/1.1% accuracy with 35%/52% fewer parameters and 49%/61% fewer MACs. The effectiveness of Pool-Former verifies our hypothesis and urges us to initiate the concept of “MetaFormer”, a general architecture abstracted from transformers without specifying the token mixer. Based on the extensive experiments, we argue that MetaFormer is the key player in achieving superior results for recent transformer and MLP-like models on vision tasks. This work calls for more future research dedicated to improving MetaFormer instead of focusing on the token mixer modules. Additionally, our proposed PoolFormer could serve as a starting baseline for future MetaFormer architecture design.

59 citations


Journal ArticleDOI
TL;DR: Recently, a dizzying number of X-former models have been proposed as mentioned in this paper , which improve upon the original Transformer architecture, many of which make improvements around computational and memory efficiency.
Abstract: Transformer model architectures have garnered immense interest lately due to their effectiveness across a range of domains like language, vision, and reinforcement learning. In the field of natural language processing for example, Transformers have become an indispensable staple in the modern deep learning stack. Recently, a dizzying number of “X-former” models have been proposed—Reformer, Linformer, Performer, Longformer, to name a few—which improve upon the original Transformer architecture, many of which make improvements around computational and memory efficiency . With the aim of helping the avid researcher navigate this flurry, this article characterizes a large and thoughtful selection of recent efficiency-flavored “X-former” models, providing an organized and comprehensive overview of existing work and models across multiple domains.

57 citations


Proceedings ArticleDOI
17 Jul 2022
TL;DR: In this paper , a transformer-based Siamese network architecture (abbreviated by ChangeFormer) is proposed for change detection from a pair of co-registered remote sensing images.
Abstract: This paper presents a transformer-based Siamese network architecture (abbreviated by ChangeFormer) for Change Detection (CD) from a pair of co-registered remote sensing images. Different from recent CD frameworks, which are based on fully convolutional networks (ConvNets), the proposed method unifies hierarchically structured transformer encoder with Multi-Layer Perception (MLP) decoder in a Siamese network architecture to efficiently render multi-scale long-range details required for accurate CD. Experiments on two CD datasets show that the proposed end-to-end trainable ChangeFormer architecture achieves better CD performance than previous counterparts. Our code and pre-trained models are available at github.com/wgcban/ChangeFormer.

56 citations


Journal ArticleDOI
01 May 2022
TL;DR: In this paper , a black phosphorus-polydopamine (BP-MXene) nanohybrid was synthesized to enhance the flame-retardant properties of thermoplastic polyurethane elastomer.
Abstract: • A black phosphorus-MXene@polydopamine nanohybrid was synthesized. • The TPU/BP-MXene@PDA nanocomposite simultaneously showed reinforcing and toughening effects towards TPU. • The TPU/BP-MXene@PDA nanocomposite could be achieved excellent thermal stability, mechanical properties and flame retardancy. • A synergistic flame-retardant mechanism between black phosphorus and MXene in the TPU were discussed and clarified. Black phosphorus (BP), as one of the most promising fillers for flame retarding polymer, has been seriously limited in practical application, due to the agglomeration and poor structural stability challenges. Here, the BP was modified by MXene and polydopamine (PDA) via ultrasonication and dopamine modification strategy to improve the structural stability and dispersibility in the matrix. Then, the obtained (BP-MXene@PDA) nanohybrid was employed to promote the mechanical performance, thermal stability, and flame retardancy of thermoplastic polyurethane elastomer (TPU). The resultant TPU composite containing 2 wt.% of BP1-MXene2@PDA showed a 19.2% improvement in the tensile strength and a 13.8% increase in the elongation at break compared to those of the pure TPU. The thermogravimetric analysis suggested that BP-MXene@PDA clearly enhances the thermal stability of TPU composites. Furthermore, the introduction of the BP-MXene@PDA nanohybrids could considerably improve the flame retardancy of TPU composite, i.e., 64.2% and 27.3% decrease in peak heat release rate and total heat release, respectively. The flame-retardant mechanisms of TPU/BP-MXene@PDA in the gas phase and condensed phase were investigated systematically. This work provides a novel strategy to simultaneously enhance the fire safety and mechanical properties of TPU, thus expanding its industrial applications.

51 citations


Journal ArticleDOI
TL;DR: In this paper , the authors examine multiple platform sponsors from an industrial manufacturing context and demarcate three platform archetypes: product platform, supply chain platform, and platform ecosystem, and find that each platform archetype is characterized by a specific innovation mechanism that contributes to the platform service discovery and expands the platform value.

46 citations


Journal ArticleDOI
TL;DR: In this article , an analysis of the cutting-edge applications of AR and VR in Architecture Engineering Construction (AEC) projects and prevailing trends in their usage is presented. But their use requires additional refinement for them to be integrated into the BIM process.

Journal ArticleDOI
TL;DR: Recently, the emergence of pre-training models has brought uni-modal fields such as computer vision (CV) and natural language processing (NLP) to a new era as discussed by the authors .
Abstract: Abstract In the past few years, the emergence of pre-training models has brought uni-modal fields such as computer vision (CV) and natural language processing (NLP) to a new era. Substantial works have shown that they are beneficial for downstream uni-modal tasks and avoid training a new model from scratch. So can such pre-trained models be applied to multi-modal tasks? Researchers have explored this problem and made significant progress. This paper surveys recent advances and new frontiers in vision-language pre-training (VLP), including image-text and video-text pre-training. To give readers a better overall grasp of VLP, we first review its recent advances in five aspects: feature extraction, model architecture, pre-training objectives, pre-training datasets, and downstream tasks. Then, we summarize the specific VLP models in detail. Finally, we discuss the new frontiers in VLP. To the best of our knowledge, this is the first survey focused on VLP. We hope that this survey can shed light on future research in the VLP field.

Journal ArticleDOI
TL;DR: To improve the efficiency of deep learning research, this review focuses on three aspects: quantized/binarized models, optimized architectures, and resource-constrained systems.
Abstract: Over the past decade, deep-learning-based representations have demonstrated remarkable performance in academia and industry. The learning capability of convolutional neural networks (CNNs) originates from a combination of various feature extraction layers that fully utilize a large amount of data. However, they often require substantial computation and memory resources while replacing traditional hand-engineered features in existing systems. In this review, to improve the efficiency of deep learning research, we focus on three aspects: quantized/binarized models, optimized architectures, and resource-constrained systems. Recent advances in light-weight deep learning models and network architecture search (NAS) algorithms are reviewed, starting with simplified layers and efficient convolution and including new architectural design and optimization. In addition, several practical applications of efficient CNNs have been investigated using various types of hardware architectures and platforms.

Journal ArticleDOI
TL;DR: In this paper , the authors systematically review recent research around the application of VR in BIM and discuss the results using the PRISMA flowchart, and extend the discussion by summarizing the potential future work in this area.
Abstract: ABSTRACT The field of architecture, engineering, and construction (AEC) is continually striving to use resources efficiently and manage complex processes. Now more than ever, there is a strong need for digital transformation in AEC. The improvement in the accessibility of consumer-based head-mounted displays (HMD) is attracting different entertainment and research fields to immersive virtual reality (VR) applications. Building Information Modeling (BIM) is known as a promising technology in AEC. The full potential of BIM is not yet employed to empower this field, however, and this could be a result of some barriers still to be surmounted by BIM in both technological and management perspectives. One of these barriers is the communication and collaboration between design, construction, operation, and maintenance phases. VR can fill this gap by providing additional capabilities for BIM which either were not available before or were not possible to employ in practical ways. In this paper, we systematically review recent research around the application of VR in BIM and discuss the results using the PRISMA flowchart. We discuss the most commonly used technologies, software, and evaluation methods and the various applications of VR in the reviewed papers. Finally, we extend the discussion by summarizing the potential future work in this area.

Journal ArticleDOI
TL;DR: Wang et al. as discussed by the authors developed a blockchain-enabled IoT-BIM platform (BIBP) for off-site production management in modular construction (OPM-MC) that can overcome the shortcomings.

Journal ArticleDOI
TL;DR: Wang et al. as mentioned in this paper developed a blockchain-enabled IoT-BIM platform (BIBP) for off-site production management in modular construction (OPM-MC) that can overcome the shortcomings.

Journal ArticleDOI
TL;DR: A comprehensive survey of federated learning can be found in this paper , where the authors propose a functional architecture and a taxonomy of related techniques and present the distributed training, data communication, and security of FL systems.
Abstract: In recent years, data and computing resources are typically distributed in the devices of end users, various regions or organizations. Because of laws or regulations, the distributed data and computing resources cannot be directly shared among different regions or organizations for machine learning tasks. Federated learning emerges as an efficient approach to exploit distributed data and computing resources, so as to collaboratively train machine learning models, while obeying the laws and regulations and ensuring data security and data privacy. In this paper, we provide a comprehensive survey of existing works for federated learning. We propose a functional architecture of federated learning systems and a taxonomy of related techniques. Furthermore, we present the distributed training, data communication, and security of FL systems. Finally, we analyze their limitations and propose future research directions.

Book ChapterDOI
23 Jan 2022
TL;DR: SNASNet as mentioned in this paper proposes a Neural Architecture Search (NAS) approach for finding better SNN architectures by selecting the architecture that can represent diverse spike activation patterns across different data samples without training.
Abstract: Spiking Neural Networks (SNNs) have gained huge attention as a potential energy-efficient alternative to conventional Artificial Neural Networks (ANNs) due to their inherent high-sparsity activation. However, most prior SNN methods use ANN-like architectures (e.g., VGG-Net or ResNet), which could provide sub-optimal performance for temporal sequence processing of binary information in SNNs. To address this, in this paper, we introduce a novel Neural Architecture Search (NAS) approach for finding better SNN architectures. Inspired by recent NAS approaches that find the optimal architecture from activation patterns at initialization, we select the architecture that can represent diverse spike activation patterns across different data samples without training. Moreover, to further leverage the temporal information among the spikes, we search for feed-forward connections as well as backward connections (i.e., temporal feedback connections) between layers. Interestingly, SNASNet found by our search algorithm achieves higher performance with backward connections, demonstrating the importance of designing SNN architecture for suitably using temporal information. We conduct extensive experiments on three image recognition benchmarks where we show that SNASNet achieves state-of-the-art performance with significantly lower timesteps (5 timesteps). Code is available on Github .


Journal ArticleDOI
TL;DR: In this paper , the authors conducted a literature review to discuss biophilic design as a theoretical framework to interpret "nature" in architecture, and analyzed the benefits of such design practices in achieving sustainability.

Journal ArticleDOI
TL;DR: This work creatively proposes a unique architecture for text-to-image synthesis, dubbed T2IGAN, which is automatically searched by neural architecture search (NAS), and a lightweight transformer is applied in the search space to efficiently integrate the text features and image features.
Abstract: Despite the cross-modal text-to-imagesynthesis task has achieved great success, most of the latest works in this field are based on the network architectures proposed by predecessors, such as StackGAN, AttnGAN, etc. Since the quality for text-to-image synthesis is more and more demanding, these old and tandem architectures with simple convolution operations are no longer suitable. Therefore, a novel text-to-image synthesis network combining with the latest technologies is in urgent need of exploration. To tackle with this challenge, we creatively propose a unique architecture for text-to-image synthesis, dubbed T2IGAN, which is automatically searched by neural architecture search (NAS). In addition, considering the amazing capabilities of the popular transformer in natural language processing and computer vision, a lightweight transformer is applied in our search space to efficiently integrate the text features and image features. Ultimately, the effectiveness of our searched T2IGAN is remarkable by experimentally evaluating it on the typical text-to-image synthesis datasets. Specifically, we achieve an excellent result of IS 5.12 and FID 10.48 on CUB-200 Birds, IS 4.89 and FID 13.55 on Oxford-102 Flowers, IS 31.93 and FID 26.45 on COCO. By contrast with the state-of-the-art works, ours gets better performance on CUB-200 Birds and Oxford-102 Flowers.

Journal ArticleDOI
TL;DR: Wang et al. as discussed by the authors give a comprehensive survey of recent advances in Chinese NER, including the common datasets, tag schemes, evaluation metrics and difficulties of CNER, in which the CNER with deep learning is their focus.

Journal ArticleDOI
TL;DR: In this article, the authors proposed the connection of the digital building twin with blockchain-based smart contracts to execute performance-based digital payments, and demonstrated the feasibility of both the concept and technical architecture by integrating the Ethereum blockchain with digital building models and sensors via the Siemens building twin platform.

Journal ArticleDOI
TL;DR: This work was partially supported by the Spanish Ministry of Science and Innovation and the European Regional Development Fund (ERDF) and project FAME and excellence network RCIS.

Journal ArticleDOI
TL;DR: In this article , the authors propose the connection of the digital building twin with blockchain-based smart contracts to execute performance-based digital payments, and demonstrate the feasibility of both the concept and technical architecture by integrating the Ethereum blockchain with digital building models and sensors.

Journal ArticleDOI
TL;DR: In this paper , the authors present the findings of the research work taking off the wraps regarding vulnerabilities and their consequences on information security and reveal other prominent issues irrespective of information security issues.
Abstract: SDN changes the networking vision with an impressive thought of segregating the networking control from the data management hardware and brings new functionalities such as programmability , elasticity, flexibility, and adoption capability in the network, which are difficult to think of in traditional rigid network architecture . However, a wide range of vulnerable surfaces directly or indirectly affect the SDN-based system’s information security and launch various attacks. The paper begins with a glimpse of the advantages of SDN over the traditional network but, the findings of the research work take off the wraps regarding vulnerabilities and their consequences on information security. Consequently, the threat surfaces are exposed that exist in SDN architecture due to weak information security. In addition, the research findings also disclose other prominent issues irrespective of information security issues. The inclusion intends to ring the bell in the maximum SDN aspects and make researchers or professionals aware of current trends of SDN in the best possible way. The comprehensiveness of this work is retained by detailing every part of SDN, which helps the researchers or professionals to improve SDN structurally or functionally.

Journal ArticleDOI
TL;DR: In this paper , the authors combine federated learning (FL) and fog/edge computing to combat malicious codes and train a global optimized model based on distributed datasets of collaborators while removing the data and communication constraints.
Abstract: Due to resource constraints and working surroundings, many IIoT nodes are easily hacked and turn into zombies from which to launch attacks. It is challenging to detect such networked zombies rooted behind the Internet for any individual defender. In this article, we combine federated learning (FL) and fog/edge computing to combat malicious codes. Our protocol trains a global optimized model based on distributed datasets of collaborators while removing the data and communication constraints. The FL-based detection protocol maximizes the values of distributed data samples, resulting in an accurate model timely. On top of the protocol, we place mitigation intelligence in a distributed and collaborative manner. Our approach improves accuracy, eliminates mitigation time, and enlarges attackers’ expense within a defense alliance. Comprehensive evaluations confirm that the cost incurred is 2.7 times larger, the mitigation response time is 72% lower, and the accuracy is 47% higher on average. Besides, the protocol evaluation shows the detection accuracy is approximately 98% in the FL, which is almost the same as centralized training.

Journal ArticleDOI
01 Aug 2022-Sensors
TL;DR: A novel blockchain mechanism for secure healthcare sector data management, which reduces the communicational and computational overhead costs compared to the existing bitcoin network and the lightweight blockchain architecture is introduced.
Abstract: Nowadays, in a world full of uncertainties and the threat of digital and cyber-attacks, blockchain technology is one of the major critical developments playing a vital role in the creative professional world. Along with energy, finance, governance, etc., the healthcare sector is one of the most prominent areas where blockchain technology is being used. We all are aware that data constitute our wealth and our currency; vulnerability and security become even more significant and a vital point of concern for healthcare. Recent cyberattacks have raised the questions of planning, requirement, and implementation to develop more cyber-secure models. This paper is based on a blockchain that classifies network participants into clusters and preserves a single copy of the blockchain for every cluster. The paper introduces a novel blockchain mechanism for secure healthcare sector data management, which reduces the communicational and computational overhead costs compared to the existing bitcoin network and the lightweight blockchain architecture. The paper also discusses how the proposed design can be utilized to address the recognized threats. The experimental results show that, as the number of nodes rises, the suggested architecture speeds up ledger updates by 63% and reduces network traffic by 10 times.

Journal ArticleDOI
TL;DR: Huang et al. as discussed by the authors proposed an adaptive convolutional neural network for energy-efficient human activity recognition (AHAR) which uses an output block predictor to select a portion of the baseline architecture to use during the inference phase.
Abstract: Human activity recognition (HAR) is one of the key applications of health monitoring that requires continuous use of wearable devices to track daily activities. This article proposes an adaptive convolutional neural network for energy-efficient HAR (AHAR) suitable for low-power edge devices. Unlike traditional adaptive (early-exit) architecture that makes the early-exit decision based on classification confidence, AHAR proposes a novel adaptive architecture that uses an output block predictor to select a portion of the baseline architecture to use during the inference phase. The experimental results show that traditional adaptive architecture suffer from performance loss whereas our adaptive architecture provides similar or better performance as the baseline one while being energy efficient. We validate our methodology in classifying locomotion activities from two data sets—1) Opportunity and 2) w-HAR. Compared to the fog/cloud computing approaches for the Opportunity data set, our baseline and adaptive architectures show a comparable weighted F1 score of 91.79%, and 91.57%, respectively. For the w-HAR data set, our baseline and adaptive architectures outperform the state-of-the-art works with a weighted F1 score of 97.55%, and 97.64%, respectively. Evaluation on real hardware shows that our baseline architecture is significantly energy efficient ( $422.38\times $ less) and memory-efficient ( $14.29\times $ less) compared to the works on the Opportunity data set. For the w-HAR data set, our baseline architecture requires $2.04\times $ less energy and $2.18\times $ less memory compared to the state-of-the-art work. Moreover, experimental results show that our adaptive architecture is 12.32% (Opportunity) and 11.14% (w-HAR) energy efficient than our baseline while providing similar (Opportunity) or better (w-HAR) performance with no significant memory overhead.

Journal ArticleDOI
TL;DR: In this article , the authors proposed a Deep Learning (DL) based Bidirectional-Gated Recurrent Unit-Convolutional Neural Network (Bi-GRU-CNN) model to detect the IoT malware and classify IoT malware families using Executable and Linkable Format (ELF) binary file byte sequences as an input feature.