General Architecture Research Articles

Human Action Recognition: A Taxonomy-Based Survey, Updates, and Opportunities.

Human action recognition systems use data collected from a wide range of sensors to accurately identify and interpret human actions. One of the most challenging issues for computer vision is the automatic and precise identification of human activities. A significant increase in feature learning-based representations for action recognition has emerged in recent years, due to the widespread use of deep learning-based features. This study presents an in-depth analysis of human activity recognition that investigates recent developments in computer vision. Augmented reality, human-computer interaction, cybersecurity, home monitoring, and surveillance cameras are all examples of computer vision applications that often go in conjunction with human action detection. We give a taxonomy-based, rigorous study of human activity recognition techniques, discussing the best ways to acquire human action features, derived using RGB and depth data, as well as the latest research on deep learning and hand-crafted techniques. We also explain a generic architecture to recognize human actions in the real world and its current prominent research topic. At long last, we are able to offer some study analysis concepts and proposals for academics. In-depth researchers of human action recognition will find this review an effective tool.

Cutting-Edge Assets for Trust in 5G and Beyond: Requirements, State of the Art, Trends, and Challenges

In 5G and beyond, the figure of cross-operator/domain connections and relationships grows exponentially among stakeholders, resources, and services, with reputation-based trust models being one of the capital technologies leveraged for trustworthy decision-making. This work studies novel 5G assets on which trust can be used to overcome unsuitable decision-making and address current requirements. First, it introduces a background and general architecture of reputation-based trust models. Then, it analyzes pivotal 5G assets on which trust can enhance their performance. In addition, this article performs a comprehensive review of the current reputation models applied to 5G assets and compares their properties, features, techniques, and results. Finally, it provides current trends and future challenges to conducting forthcoming research in the area.

Security in Wireless Communication Networks

Over the last decade, wireless networks have experienced significant growth due to the proliferation of mobile devices and new development of radio technologies. Since the very beginning, security for wireless communication networks has always been regarded as a critical issue. In recent research frenzy on 5G and V2X communications, security plays a pivotal role as wireless Internet access serves as critical infrastructures to facilitate the digital transcations. This book timely provides a comprehensive introduction to the security in wireless communication networks, with respect to not only general concepts, but also practical principles and cases in specific wireless communication systems. This book covers a wide range starting from the general wireless communication network architecture and basic concepts of network security to the mathematical background and practical techniques, and further to the specific security issues in different wireless networks, such as WLAN, LTE, 5G, etc. Comprehensively covering the security issues, security mechanisms, design principles, and techniques in wireless communication networks. The book intends to be a self-contained and one semester textbook on wireless security for either undergraduate senior level or graduate level courses. This book can also serve as a reference for practitioners and researchers in the field to get an idea of the current and future research focus in the emerging wireless security area.

GAAF: Searching Activation Functions for Binary Neural Networks Through Genetic Algorithm

Binary neural networks (BNNs) show promising utilization in cost and power-restricted domains such as edge devices and mobile systems. This is due to its significantly less computation and storage demand, but at the cost of degraded performance. To close the accuracy gap, in this paper we propose to add a complementary activation function (AF) ahead of the sign based binarization, and rely on the genetic algorithm (GA) to automatically search for the ideal AFs. These AFs can help extract extra information from the input data in the forward pass, while allowing improved gradient approximation in the backward pass. Fifteen novel AFs are identified through our GA-based search, while most of them show improved performance (up to 2.54% on ImageNet) when testing on different datasets and network models. Interestingly, periodic functions are identified as a key component for most of the discovered AFs, which rarely exist in human designed AFs. Our method offers a novel approach for designing general and application-specific BNN architecture. GAAF will be released on GitHub.

Characterization of immunoglobulin loci in the gigantic genome of Ambystoma mexicanum.

The axolotl, Ambystoma mexicanum is a unique biological model for complete tissue regeneration. Is a neotenic endangered species and is highly susceptible to environmental stress, including infectious disease. In contrast to other amphibians, the axolotl is particularly vulnerable to certain viral infections. Like other salamanders, the axolotl genome is one of the largest (32 Gb) and the impact of genome size on Ig loci architecture is unknown. To better understand the immune response in axolotl, we aimed to characterize the immunoglobulin loci of A. mexicanum and compare it with other model vertebrates. The most recently published genome sequence of A. mexicanum (V6) was used for alignment-based annotation and manual curation using previously described axolotl Ig sequences or reference sequences from other vertebrates. Gene models were further curated using A. mexicanum spleen RNA-seq data. Human, Xenopus tropicalis, Danio rerio (zebrafish), and eight tetrapod reference genomes were used for comparison. Canonical A. mexicanum heavy chain (IGH), lambda (IGL), sigma (IGS), and the putative surrogate light chain (SLC) loci were identified. No kappa locus was found. More than half of the IGHV genes and the IGHF gene are pseudogenes and there is no clan I IGHV genes. Although the IGH locus size is proportional to genome size, we found local size restriction in the IGHM gene and the V gene intergenic distances. In addition, there were V genes with abnormally large V-intron sizes, which correlated with loss of gene functionality. The A. mexicanum immunoglobulin loci share the same general genome architecture as most studied tetrapods. Consistent with its large genome, Ig loci are larger; however, local size restrictions indicate evolutionary constraints likely to be imposed by high transcriptional demand of certain Ig genes, as well as the V(D)J recombination over very long genomic distance ranges. The A. mexicanum has undergone an extensive process of Ig gene loss which partially explains a reduced potential repertoire diversity that may contribute to its impaired antibody response.

Digital Platform for Supercomputer Mathematical Modeling of Spraying Processes

The work presents a digital platform for supercomputer modeling the problems of spraying the particles on substrates. The purpose of this work is to discuss the general architecture, technology stack and implementation features of the platform's user interface. The platform is based on web technologies for access and management of calculations, which allow implementing a user system for conducting a full cycle of a computational experiment, including the configuration of applied applications, their launch on remote computing resources, monitoring the completion of tasks, analysis and interactive visualization of results. User interaction with computing resources is implemented through the graphical interface that does not require the client computer to have any additional software, except actual version of a modern web browser. An important advantage of the platform is the ability to make large-scale computer research in a multi-user mode that is based on the natural principles of building client-server applications. The presented digital web platform was successfully tested on computing clusters of the KIAM RAS in solving a number of the topical mathematical problems of nanotechnology. Also, with its help, for the last 3 years, group training of MIPT students in modern information technologies has been carried out.

An integrated supervision framework to safeguard the urban river water quality supported by ICT and models

Models and information and communication technology (ICT) can assist in the effective supervision of urban receiving water bodies and drainage systems. Single model-based decision tools, e.g., water quality models and the pollution source identification (PSI) method, have been widely reported in this field. However, a systematic pathway for environmental decision support system (EDSS) construction by integrating advanced single techniques has rarely been reported, impeding engineering applications. This paper presents an integrated supervision framework (UrbanWQEWIS) involving monitoring-early warning-source identification-emergency disposal to safeguard the urban water quality, where the data, model, equipment and knowledge are smoothly and logically linked. The generic architecture, all-in-one equipment and three key model components are introduced. A pilot EDSS is developed and deployed in the Maozhou River, China, with the assistance of environmental Internet of Things (IoT) technology. These key model components are successfully validated via in situ monitoring data and dye tracing experiments. In particular, fluorescence fingerprint-based qualitative PSI and Bayesian-based quantitative PSI methods are effectively coupled, which can largely reduce system costs and enhance flexibility. The presented supervision framework delivers a state-of-the-art management tool in the digital water era. The proposed technical pathway of EDSS development provides a valuable reference for other regions.

Concept for a generic modular software architecture for the integration of quality relevant data and sample implementation for a laser sintering system

Additive manufacturing (AM) processes, such as laser sintering (LS), are complex in parameter dependencies and process flow. To be able to analyse and potentially predict the quality of the manufactured parts, the monitoring of multiple process parameters along the process chain is necessary. Currently, there are standards defined for data exchange but there is no framework to store and analyse these data or enhance a system with additional sensors. Therefore, a generic software concept is required that allows a consistent process monitoring. In this publication, a generic workflow for AM including pre- and post-processing steps is presented and relevant communication interfaces as e.g. OPC-UA, and relevant data types to be collected are identified. The concept allows the use of different communication protocols, storing and evaluating process data and by its modularity the enhancement of a system with its hardware. The stored values can be analysed by further scripts. The architecture is applicated on LS and partial aspects are prototypically implemented as well as practically validated. Therefore, a generic modular software concept, based on a hardware independent Docker based architecture, is presented. A practical feasibility test shows that machine and image data can be decentralized tapped and recorded, cloud-based analysed and web-based visualized.

Proposal of a module-driven architecture for building simulation models devoted to container terminals: dilemmas in applying generic, flexible, and modular principles

Container terminals are complex systems where containerized cargo undergoes a set of processing and handling operations to be delivered to their outgoing modes. A pool of decision support methods and simulation models has been developed to assist planners and managers in making decisions about daily operations. Nevertheless, most are designed for a particular terminal and not generic types. Indeed, a generic model serves as a conceptual factory to create specific models which greatly reduces the time and efforts of development; however, building such a model is no mean feat. To this aim, the paper on hand discusses the complexity of applying genericity, flexibility, and modularity in system modeling and proposes a generic architecture to build modular and flexible simulation models for container terminals. This architecture is split into a set of smaller, manageable, well-connected, and generic modules that facilitate the creation of highly parametrized specific models. An illustrative example of the architecture usage is presented in a case study, the new container terminal of Stockholm, and the resulting models were validated by subject matter experts. Finally, to prove its efficiency, a numerical study fed with real data is conducted to investigate the handling capacity of the studied system under different handling and flow scenarios. The obtained results show that the terminal handling capacity can be increased by around 50% if three to four more straddle carriers are added to the existing fleet.

Employing Machine Learning and IoT for Earthquake Early Warning System in Smart Cities

An earthquake early warning system (EEWS) should be included in smart cities to preserve human lives by providing a reliable and efficient disaster management system. This system can alter how different entities communicate with one another using an Internet of Things (IoT) network where observed data are handled based on machine learning (ML) technology. On one hand, IoT is employed in observing the different measures of EEWS entities. On the other hand, ML can be exploited to analyze these measures to reach the best action to be taken for disaster management and risk mitigation in smart cities. This paper provides a survey on the different aspects required for that EEWS. First, the IoT system is generally discussed to provide the role it can play for EEWS. Second, ML models are classified into linear and non-linear ones. Third, the evaluation metrics of ML models are addressed by focusing on seismology. Fourth, this paper exhibits a taxonomy that includes the emerging ML and IoT efforts for EEWS. Fifth, it proposes a generic EEWS architecture based on IoT and ML. Finally, the paper addresses the application of ML for earthquake parameters’ observations leading to an efficient EEWS.

Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection.

Generic Boundary Detection (GBD) aims at locating the general boundaries that divide videos into semantically coherent and taxonomy-free units, and could serve as an important pre-processing step for long-form video understanding. Previous works often separately handle these different types of generic boundaries with specific designs of deep networks from simple CNN to LSTM. Instead, in this paper, we present Temporal Perceiver, a general architecture with Transformer, offering a unified solution to the detection of arbitrary generic boundaries, ranging from shot-level, event-level, to scene-level GBDs. The core design is to introduce a small set of latent feature queries as anchors to compress the redundant video input into a fixed dimension via cross-attention blocks. Thanks to this fixed number of latent units, it greatly reduces the quadratic complexity of attention operation to a linear form of input frames. Specifically, to explicitly leverage the temporal structure of videos, we construct two types of latent feature queries: boundary queries and context queries, which handle the semantic incoherence and coherence accordingly. Moreover, to guide the learning of latent feature queries, we propose an alignment loss on the cross-attention maps to explicitly encourage the boundary queries to attend on the top boundary candidates. Finally, we present a sparse detection head on the compressed representation, and directly output the final boundary detection results without any post-processing module. We test our Temporal Perceiver on a variety of GBD benchmarks. Our method obtains the state-of-the-art results on all benchmarks with RGB single-stream features: SoccerNet-v2(81.9 percent average-mAP), Kinetics-GEBD(86.0 percent average-f1), TAPOS(73.2 percent average-f1), MovieScenes(51.9 percent AP and 53.1 percent Miou) and MovieNet(53.3 percent AP and 53.2 percent Miou), demonstrating the generalization ability of our Temporal Perceiver. To further pursue a general GBD model, we combined various tasks to train a class-agnostic Temporal perceiver and evaluate its performance across all benchmarks. Results show that the class-agnostic Perceiver achieves comparable detection accuracy and even better generalization ability compared to dataset-specific Temporal Perceiver.

DEVELOPMENT AND STUDY OF A MICROSPECTROMETER LAYOUT

The photoelectronic processes occurring in a vertically located double-barrier photode-tector under the influence of an external bias voltage are simulated depending on the char-acteristics of the penetrating waves. Under conditions of vertical illumination, to obtain the spectral dependence of the intensity of absorbed radiation, an algorithm was developed for selecting individual waves from the integral flux of the optical signal under conditions of changing the external bias voltage in steps of 1 mV. The algorithm takes into account the main cause-and-effect relationships between the absorption coefficient and design and technological parameters. It makes it possible to obtain the intensities of individual waves from the integral radiation flux in the optical range, where there is a change in the sign of the spectral characteristics and a linear dependence of the point of sign change on the ap-plied voltage. A general architecture, functional structure and remote control scheme for the monitor-ing system for hazardous substances have been developed, as well as corresponding pro-grams with the help of which the algorithm was operated in the LabVIEW environment. To run the algorithm, a prototype of a spectral analysis device was developed and prepared, in which an Arduino Mega board controlled by a microcontroller was used to analyze the output signal of the photodetector. The layout was tested using multi-colored LEDs. The spectral dependence of the inten-sity and its numerical data are obtained on the screen using a new principle. This method is novel and opens up prospects for further development of the field of micro-sized spectro-photometers. To identify mixtures by spectral analysis and estimate their quantity, the RDP (Remote Desktop) protocol of the remote system and the LABVIEW graphical programming envi-ronment were used. RDP was created by Microsoft to provide remote access to Windows servers and workstations.

Methodology for Automated Design of Quantum-Dot Cellular Automata Circuits

Quantum-dot Cellular Automata (QCA) provide very high scale integration potential, very high switching frequency, and have extremely low power demands, which make the QCA technology quite attractive for the design and implementation of large-scale, high-performance nanoelectronic circuits. However, state-of-the-art QCA circuit designs were not derived by following a set of universal design rules, as is the case of CMOS circuits, and, as a result, it is either impossible or very difficult to combine QCA circuit blocks in effective large-scale circuits. In this paper, we introduce a novel automated design methodology, which builds upon a QCA specific universal design rules set. The proposed methodology assumes the availability of a generic QCA crossbar architecture and provides the means to customize it in order to implement any given logic function. The programming principles and the flow of the proposed automated design tool for crossbar QCA circuits are described analytically and we apply the proposed automated design method for the design of both combinatorial and sequential circuits. The obtained designs demonstrate that the proposed method is functional, easy to use, and provides the desired QCA circuit design unification.

Optimization of Spacecraft Thrusters Configuration Under Fault Diagnosability and Recoverability Constraints

This paper investigates the problem of optimal placement (position and orientation) of spacecraft thrusters, under fault diagnosability and fault recoverability constraints. Avionics equipment contamination and plume impingement are also considered. The goal is to find the thrusters configuration with the minimal number of thrusters required for a given spacecraft architecture, so that it is guaranteed that it is possible to equip the control unit with a model-based fault diagnosis and fault-tolerant control solution, able to accommodate any single thruster's fault. This includes total loss of controllability of the faulty thruster. The proposed solution is a model-based solution in the sense that it is based on the spacecraft attitude and translational dynamics. With the help of the zonotope concept and its so-called H-representation, it is shown that this problem can be formulated as a nonlinear constrained optimization problem, which can be solved efficiently using hybrid optimization techniques. The proposed solution is assessed on a generic spacecraft architecture that performs a proximity maneuver.

Internet of Cultural Things: Current Research, Challenges and Opportunities

Driven by the visions of the Internet of Things (IoT), Artificial Intelligence (AI), and 5G communications, the Internet of Cultural Things (IoCT) realize the comprehensive interconnection among cultural products, cultural services, cultural resources, and cultural platforms, bringing individuals with richer humanistic experience, increasing economic benefits for the cultural sector, and promoting the development of cultural heritage protection and education. At present, IoCT has received widespread attention in both industry and academia. To explore new research opportunities and assist users in constructing suitable IoCT systems for specific applications, this survey provides a comprehensive overview of the IoCT components and key technologies. A comparison study of representative IoCT systems is presented according to their applicability. A general platform architecture of IoCT is proposed to link cultural objects with the internet and human. Finally, open issues for research challenges and future opportunities of IoCT are also studied in this paper.

HILS-based Demonstrator for Real-time Validation of Robust Control Strategies: An Electric Vehicle Application Case

This paper presents a demonstrator featuring closed-loop coupling of a robust-control-designed Power Management System (PMS) with a simulator – in the form of a mathematical model – of a multiple-storage-based microgrid, playing the role of the plant. The PMS ensures a reliability-aware coordinated control of the different energy storages, of various technologies, supplying a typically irregular load. Some usual applications are in stationary or mobile microgrids, like power supply systems on board of electric vehicles, the latter being the use case exemplified here. Being designed upon the hardware-in-the loop simulation (HILS) principle, the demonstrator allows calibration and real-time validation of the robust PMS and its pertinent closed-loop real-time tests in laboratory conditions. The rapid prototyping system dSPACETM MicroAutoBox II is employed for embedding the microgrid model, whereas the robust PMS is embedded on a TI C2000 microcontroller unit. General design requirements and architecture of the demonstrator are detailed, then its customization to the considered application case is presented. Finally, a set of illustrative real-time tests – obtained by using a standard driving cycle – are presented and discussed.

Changer: Feature Interaction is What You Need for Change Detection

Change detection is an important tool for long-term earth observation missions. It takes bi-temporal images as input and predicts “where” the change has occurred. Different from other dense prediction tasks, a meaningful consideration for change detection is the interaction between bi-temporal features. With this motivation, in this paper we propose a novel general change detection architecture, MetaChanger, which includes a series of alternative interaction layers in the feature extractor. To verify the effectiveness of MetaChanger, we propose two derived models, ChangerAD and ChangerEx with simple interaction strategies: Aggregation-Distribution (AD) and feature “exchange”. AD is abstracted from some complex interaction methods, and feature “exchange” is a completely parameter&computation-free operation by exchanging bi-temporal features. In addition, for better alignment of bi-temporal features, we propose a Flow-based Dual-Alignment Fusion (FDAF) module which allows interactive alignment and feature fusion. Crucially, we observe Changer series models achieve competitive performance on different scale change detection datasets. Further, our proposed ChangerAD and ChangerEx could serve as a starting baseline for future MetaChanger design. Code and weights are made available at https://github.com/likyoo/open-cd.

A generic model of the information and decisional chain using Machine Learning based assistance in a manufacturing context

Nowadays, manufacturers must deal with huge international competition and continually improve their performances. In this context, several essential approaches namely CBM (Condition-based maintenance), PHM (Prognostics and Health Management), and PLM (Product Lifecycle Management) are used for manufacturing systems to maintain and increase their availability, reliability and performance. This implies that operational usage data of the manufacturing equipment must then be made available to all stakeholders concerned through efficient informational chains. However confronted with a large amount of data, the stakeholders must be assisted in their decision-making. This paper aims to propose a generic architecture that models the information and decision chain from the target system to the relevant stakeholders by assisting them in their decision-making. The proposed generic architecture is illustrated by a use case based on the LSTM (Long Short-Term Memory) algorithm in the context of energy management for a fleet of mobile robots.

НАУКОВО-ТЕОРЕТИЧНІ ЗАСАДИ ДЕРЖАВНОГО РЕГУЛЮВАННЯ ІВЕСТИЦІЙНОГО ЗАБЕЗПЕЧЕННЯ ЖИТЛОВОГО БУДІВНИЦТВА

The issue of intensifying economic transformations and accelerating the pace of socio-economic development under modern conditions cannot be resolved without adequate investment support. Construction of residential real estate is a field that is traditionally defined by a high level of dependence on investment funds. The state plays an extremely important role in this process. It is thanks to effective state mechanisms for regulating the investment attractiveness of the industry that the prerequisites for the accumulation of investment flows and assistance in solving the population's housing problem and implementing the tasks of the country's social and housing policy are formed. The modern legislative basis for regulation of investment processes in the construction of residential real estate is studied in the article. The set of institutional subjects of regulation of investment processes in the construction industry is defined here. The systematization of scientific and theoretical foundations of state regulation of investment processes of housing construction has been carried out. The methodological plane of functions, tasks and principles of state regulation of investment activity in the industry is analyzed. The methodological plane of the set of principles of state regulation by the process of attracting investment flows in the industry based on the strategic priorities of inclusiveness and sustainable housing construction has been supplemented. The author's scheme of the general architecture of the mechanism of state regulation of investment activity in the field of housing construction has been formed. The range of socio-economic and environmental bonuses from investments in the construction of residential real estate objects from the standpoint of creating new economic opportunities for the region and the national economy, ensuring the development of processes of inclusive urbanization and environmental stability in the industry is defined in the article. A brief review of the level of return on investment in residential construction is carried out here. The potential for possible future services from investing in residential real estate has been determined.

Acceleration of high-quality Raman imaging via a locality enhanced transformer network.

Raman imaging (RI) is an outstanding technique that enables molecular-level medical diagnostics and therapy assessment by providing characteristic fingerprint and morphological information about molecules. However, obtaining high-quality Raman images generally requires a long acquisition time, up to hours, which is prohibitive for RI applications of timely cytopathology and histopathology analyses. To address this issue, image super-resolution (SR) based on deep learning, including convolutional neural networks and transformers, has been widely recognized as an effective solution to reduce the time required for achieving high-quality RI. In this study, a locality enhanced transformer network (LETNet) is proposed to perform Raman image SR. Specifically, the general architecture of the transformer is adopted with the replacement of self-attention by convolution to generate high-fidelity and detailed SR images. Additionally, the convolution in the LETNet is further optimized by utilizing depth-wise convolution to improve the computational efficiency of the model. Experiments on hyperspectral Raman images of breast cancer cells and Raman images of a few channels of brain tumor tissues demonstrate that the LETNet achieves superior 2×, 4×, and 8× SR with fewer parameters compared with other SR methods. Consequently, high-quality Raman images can be obtained with a significant reduction in time, ranging from 4 to 64 times. Overall, the proposed method provides a novel, efficient, and reliable solution to expedite high-quality RI and promote its application in real-time diagnosis and therapy.