Central Computer Research Articles

A Hybrid IoT-Enabled Transfer Learning Model for Accurate Diagnosis of Coronary Heart Disease

Coronary heart disease (CHD) is the top cause of death in the world, which shows how important it is to get a correct evaluation as soon as possible. The Internet of Things (IoT) opens up new ways to improve healthcare, and transfer learning has shown promise in making machine learning models work better, especially when it comes to medical analysis. IoT-Enabled Transfer Learning Model (HIETLM), which is new, is proposed in this study as a way to accurately diagnose congenital heart disease. Wearable IoT devices are used by the HIETLM to continuously collect vital data from patients, such as their heart rate, blood pressure, and level of exercise. These pieces of information are sent to a central computer to be processed and analyzed. The suggested model has two main parts: a base model that was learned on a big external dataset, and a transfer learning part that was fine-tuned using data from a single patient. The base model has already been trained on a big set of general health data to learn general trends and traits that are useful for diagnosing CHD. This training helps the model understand complicated patterns and connections that are hard to learn from a small collection. The transfer learning part then tweaks the base model using the patient-specific data to make it fit the unique traits of each patient. To test how well the HIETLM worked, we did tests with a group of patients who were thought to have congenital heart disease. From the data, we can see that the HIETLM is more accurate, sensitive, and detailed than other models. The suggested model could help make CHD diagnoses more accurate and faster, which would improve patient results and lower healthcare costs.

Fugitive Location Identification System Using Photo Matching Across Distributed Surveillance Networks

Abstract: Using image matching algorithms from distributed CCTV surveillance networks, this research suggests a criminal identification method. This method aims to increase the effectiveness and efficiency of identifying and apprehending criminals by using the capabilities of networked surveillance cameras. The distributed CCTV network and the matching algorithm make up the two primary parts of the suggested system. The vast array of security cameras that make up the distributed CCTV network are positioned in different areas, including streets, buildings, and public areas. These cameras provide data to a central computer by taking pictures of people in real time.

A Hybrid IoT-Enabled Transfer Learning Model for Accurate Diagnosis of Coronary Heart Disease

Coronary heart disease (CHD) is the top cause of death in the world, which shows how important it is to get a correct evaluation as soon as possible. The Internet of Things (IoT) opens up new ways to improve healthcare, and transfer learning has shown promise in making machine learning models work better, especially when it comes to medical analysis. IoT-Enabled Transfer Learning Model (HIETLM), which is new, is proposed in this study as a way to accurately diagnose congenital heart disease. Wearable IoT devices are used by the HIETLM to continuously collect vital data from patients, such as their heart rate, blood pressure, and level of exercise. These pieces of information are sent to a central computer to be processed and analyzed. The suggested model has two main parts: a base model that was learned on a big external dataset, and a transfer learning part that was fine-tuned using data from a single patient. The base model has already been trained on a big set of general health data to learn general trends and traits that are useful for diagnosing CHD. This training helps the model understand complicated patterns and connections that are hard to learn from a small collection. The transfer learning part then tweaks the base model using the patient-specific data to make it fit the unique traits of each patient. To test how well the HIETLM worked, we did tests with a group of patients who were thought to have congenital heart disease. From the data, we can see that the HIETLM is more accurate, sensitive, and detailed than other models. The suggested model could help make CHD diagnoses more accurate and faster, which would improve patient results and lower healthcare costs.

Predicting Heart Diseases in IoT-Based Electronic Health Records: A Federated Learning Approach

Predicting heart diseases is important for finding them early and treating them effectively. We present a shared learning method for predicting heart diseases using IoT-based electronic health records (EHRs) in this work. Federated learning lets many autonomous IoT devices work together to train a model, while protecting the safety and security of the data. Proposed method uses the fact that IoT devices are spread out to train a global model for predicting heart disease without putting private EHR data in one place. With the EHR data, each IoT device learns a model locally and only sends model changes to a central computer. The computer takes all of these changes and improves the world model. This model is then sent back to the IoT devices to be improved even more. This looping process makes sure that the world model keeps getting better while keeping data private. The proposed method tested by using a real-world collection of EHRs from IoT devices in trials. We looked at how well our shared learning method worked compared to more standard centralized learning methods. Our results show that the pooled learning method makes predictions that are as good as or better than the other methods while protecting data privacy. It also looked at how different IoT device properties, like the amount of data they send and receive and their processing power, affect the shared learning process. It is discovered that devices with more processing power and more data add more to the improvement of the global model. This shows how important it is to choose the right devices in shared learning systems. The paper study shows that pooled learning can be used to predict heart diseases in IoT-based EHRs and that it works well. Our method uses the ability of IoT devices to work together to make accurate predictions while protecting data privacy. This makes it suitable for use in real-life healthcare situations.

ROBOTIC EQUIPMENT OF THEATER STAGES

Background. The topic of the article is timely. Many interesting and technically quite feasible ideas in equipping the stage were not implemented in the theater due to the lack of direct groundwork and limited time resources. Problem statement. Generalization of the latest experience in the field of theatrical machinery requires raising the issue to the level of an interdisciplinary scientific direction based on mechanics, mechatronics and robotics. Purpose. The need to implement the increasingly complex ideas of performance directors in a modern theater requires the improvement of demonstration equipment, primarily theatrical machinery based on new scientific achievements and modern technical means of mechanization and automation. Research methods. Special stage robots can have a very different appearance, for example, they can be zoomorphic or anthropomorphic, but while maintaining the style of constructivism, they can have a man-made appearance. Such robots can perform complex movements, while they usually have numerous moving parts with independent drives. To provide flexible motion control capabilities with a focus on spectator perception, it is required to use microprocessor control with coordination from central control computers. Results. When setting requirements for such a technique, the orientation towards visual perception is specific, which is also used in demonstration robotics. Based on the scientific generalization of previous and new experience in creating technical equipment for theatrical productions of large theaters, the paper describes and characterizes typical tasks of creating and working out a scientific base for creating modern and promising equipment for theatrical productions based on general principles and practical methods of mechanics, mechatronics and robotics.

К истории математического моделирования в Южном федеральном университете

The article is devoted to the history of mathematical modeling at Rostov State University (RSU), now Southern Federal University (SFU). The authors have been describing it since 1950. As elsewhere in the world, its begin-nings are associated with problems of mechanics. At the Rostov State University, its founders are considered to be I.I. Vorovich and N.N. Moiseev, future academicians of the Russian Academy of Sciences. The flourishing of work on mathematical modeling is associated with the opening of a computer center at the Rostov State University (1958), and then a research institute of mechanics and applied mathematics (1971), where a simulation model of the Sea of Azov was created, for which its developers were awarded the USSR State Prize. The article examines not only the history of mathematical modeling as a scientific direction, but also the history of its formation as an academic subject at the Faculty of Mechanics and Mathematics (now the I.I. Vorovich Institute of Mathematics, Mechanics and Computer Science of the SFedU).

Research and development of a predictive system for fall armyworm early warning on maize crop

The rapid increase in fall armyworms (FAW, Spodoptera frugiperda) in recent years has posed major challenges to maize growers around the globe. To keep larval density below the economic threshold, we need interdisciplinary agricultural solutions like plant protection epidemiology, the Internet of Things, and scientific data techniques for early detection, monitoring, forecasting, and making informed decisions. Pest control should be planned ahead of time to prevent indiscriminate pesticide spraying, waste, and a negative effect on the environment. In this study, the authors plan to create a comprehensive iFAWcast software system that will automatically predict, alert, and gather research data on fall armyworms on maize crops in Vietnam. The system is comprised of three major components: (i) An automatic forecasting and alerting tool for fall armyworm outbreaks on the web platform; (ii) An agriculture reporting, forecasting, alerting, and user management tool on the web platform; and (iii) A mobile app that provides forecasting and alerting services on fall armyworms to farmers based on their geographical location. The iFAWcast system includes a central computation that dynamically updates weather forecasts from the Visual Crossing API and the OpenWeatherMap API, as well as a formula for the effective cumulative temperature based on the characteristics of fall armyworms on maize crops in Vietnam. The developed system was tested using data collected straight from the field, yielding extremely accurate and dependable results.

MultiSum: A Multi-Facet Approach for Extractive Social Summarization Utilizing Semantic and Sociological Relationships

Social summarization aims to provide summaries for a large number of social texts (called posts) about a single topic. To extract a summary, both the representation of post and summary selection method are crucial. Previous methods introduce social relation to enhance post embedding to mitigate the sparse representation due to its brief and informal expression. However, they ignore that there are multiple relations between posts. Besides, existing graph-based centrality calculation approaches tend to select posts from one aspect. This leads to facet bias especially when there are multiple viewpoints. In this paper, we propose a model named MultiSum to improve social summarization. Specifically, 1) We use graph convolutional networks to fuse text content with social and semantic relations to improve post representation; 2) The similarity between the summary and all aspects is incorporated into the centrality score during the selection phase, encouraging the model to pay attention to different facets. Experimental results on English and Chinese corpora support the effectiveness of this model. Furthermore, external evaluations by human experts and large language models demonstrate the validity of MultiSum in facet coverage and redundancy reduction.

Application of SDN-IP hybrid network multicast architecture in Commercial Aerospace Data Center

Abstract The increasing amount of massive data generated by commercial spacecraft in orbit puts forward higher and higher requirements for the stability, reliability, and computing power of computer systems for commercial aerospace data center. Data center computer systems are gradually transforming from X86 architecture and IP network model to a platform model with cloud computing and software-defined network (SDN) technology. This article proposes a new network architecture based on a unicast/multicast protocol for data interaction between the SDN and IP network. There are three main contributions of this article. The first is that the architecture proposed in this article aims to reduce end-to-end transmission latency and packet loss. The second is to improve the flexibility of system configuration and precise control when the SND controller state changes. The third is to verify the feasibility of deploying network architecture in a real data center environment.

Artificial intelligence of imaging and clinical neurological data for predictive, preventive and personalized (P3) medicine for Parkinson Disease: The NeuroArtP3 protocol for a multi-center research study.

The burden of Parkinson Disease (PD) represents a key public health issue and it is essential to develop innovative and cost-effective approaches to promote sustainable diagnostic and therapeutic interventions. In this perspective the adoption of a P3 (predictive, preventive and personalized) medicine approach seems to be pivotal. The NeuroArtP3 (NET-2018-12366666) is a four-year multi-site project co-funded by the Italian Ministry of Health, bringing together clinical and computational centers operating in the field of neurology, including PD. The core objectives of the project are: i) to harmonize the collection of data across the participating centers, ii) to structure standardized disease-specific datasets and iii) to advance knowledge on disease's trajectories through machine learning analysis. The 4-years study combines two consecutive research components: i) a multi-center retrospective observational phase; ii) a multi-center prospective observational phase. The retrospective phase aims at collecting data of the patients admitted at the participating clinical centers. Whereas the prospective phase aims at collecting the same variables of the retrospective study in newly diagnosed patients who will be enrolled at the same centers. The participating clinical centers are the Provincial Health Services (APSS) of Trento (Italy) as the center responsible for the PD study and the IRCCS San Martino Hospital of Genoa (Italy) as the promoter center of the NeuroartP3 project. The computational centers responsible for data analysis are the Bruno Kessler Foundation of Trento (Italy) with TrentinoSalute4.0 -Competence Center for Digital Health of the Province of Trento (Italy) and the LISCOMPlab University of Genoa (Italy). The work behind this observational study protocol shows how it is possible and viable to systematize data collection procedures in order to feed research and to advance the implementation of a P3 approach into the clinical practice through the use of AI models.

On polytope intersection by half-spaces and hyperplanes for unsplit geometric volume of fluid methods on arbitrary grids

Several tools with improved accuracy and computational efficiency, along with added capabilities, are presented for performing analytic and geometric operations involving intersections between half-spaces or hyperplanes and 2- or 3-polytopes (polygons or polyhedra, either convex or non-convex) that typically arise in advanced volume of fluid (VOF) methods on arbitrary grids. In particular, tools for the intersection between a polyhedron and a half-space, and for the computation of the interface position to cut off a given area/volume fraction from an arbitrary polygonal/polyhedral grid cell in PLIC (piecewise linear interface calculation) reconstruction have been improved in terms of accuracy and computational efficiency. In addition, specific tools are also proposed for (1) the intersection in 3D between a planar polygon and a half-space, and the computation of the resulting intersected area, which can be useful for unsplit methods based on wetted-area time-integration advection (WATIA) schemes, and for (2) the efficient computation of the geometric center of the set of clipped vertices and volume resulting from the intersection between an arbitrary polyhedron and a half-space, which can be useful for, respectively, several PLIC reconstruction methods and unsplit methods based on fluid-volume intersection advection (FVIA) schemes. Finally, a convenient strategy to perform the recursive intersections required during the advection step in advanced geometric VOF methods based on FVIA schemes is also proposed. To assess the performance and accuracy of the proposed tools, different tests were carried out for several convex and non-convex polytopes. Speedups of ×5 and improvements in accuracy of up to 5 orders of magnitude over previous tools have been achieved for certain geometries and operations. The proposed tools have been included in two advection methods (an FVIA method and a new WATIA method proposed in this work) and in a PLIC reconstruction method to demonstrate their improved performance and capabilities on structured and unstructured grids.

IoT Technology for Monitoring and Control of Smart Greenhouses

A greenhouse is a covered structured area which protect the plants from extreme weather condition, providing a controlled environment for their growth and cultivation. The innovative Internet of Things (IoT) technology uses a series of sensors connected to a central computer to control the greenhouse environment. Greenhouse sensor systems include elements that monitor and control temperature, humidity, soil moisture, lighting, and external weather conditions. The research aims to design a greenhouse monitoring and control system based on the Internet of Things (IoT). In smart greenhouses, IoT involves sensors, devices, and information and communication infrastructure for real-time monitoring, data collection, and processing to control the environment inside the greenhouse unit. Controlled greenhouses, supported by computer technology, can enhance quality and increase crop yields. This research involves three greenhouses that are independently monitored and controlled through an Internet of Things (IoT) cloud platform. Cloud monitoring facilitates better integration of devices across different geographical locations.

The 'Courant Hilton': building the mathematical sciences at New York University.

This essay explores how mid-twentieth-century mathematicians at New York University envisioned their discipline, cultural identities and social roles, and how these self-constructed identities materialized in the planning of their new academic building, Warren Weaver Hall. These mathematicians considered their research to be a 'living part of the stream of science', requiring a mathematics research library which they equated to a scientific laboratory and a complex of computing rooms which served as an interdisciplinary research centre. Identifying as 'scientists', they understood their societal value to be that of researchers, outputting mathematics research valuable to the natural sciences, the emerging field of computer science and the United States government and military, as well as educators. When the building opened in 1965, it was touted by the university administration as an 'example of excellence'; it later, in 1970, became the site of heated negotiations when university student and faculty protestors staged a sit-in rebuking the Atomic Energy Commission's Computing Center housed on the second floor. A close study of the correspondence between the mathematicians and their peers in the university's administration, private foundations, government agencies and an architectural firm not only illuminates the day-to-day work practices of this eminent group of mathematicians, but also sheds light on their own self-constructed academic and social identities within their contemporaneous Cold War culture.

The fabrication and testing drifting buoys of marine data collection

This paper presents the primary contents of successfully researching, designing and manufacturing drifting buoys to collect marine data to measure temperature, salinity, and ocean currents in surface layers. The paper presents the basic information about the structure, specifications, the buoys working as the laboratory results, and field tests of drift buoys at sea. The drifting buoy test results at the sea of Van Don - Quang Ninh area met the criteria of water-tightness, buoyancy, and balance; the ability to collect temperature and salinity data of the sensors; the ability to transmit and receive information from drifting buoy at sea to the central computer via a web server; operability of the parachute and the travel of the buoy. The buoy database management software is on the website at http://vnsea.vn. It manages the collected data in real-time, showing the parameters and their variables in space and time, the buoy's tracking on the Google map.

Quadratic Optimization Models for Balancing Preferential Access and Fairness: Formulations and Optimality Conditions

Typically, within facility location problems, fairness is defined in terms of accessibility of users. However, for facilities perceived as undesirable by communities hosting them, fairness between the usage of facilities becomes especially important. Limited research exists on this notion of fairness. To close this gap, we develop a series of optimization models for the allocation of populations of users to facilities such that access for users is balanced with a fair utilization of facilities. The optimality conditions of the underlying nonconvex quadratic models state the precise balance between accessibility and fairness. We define new classes of fairness and a metric to quantify the extent to which fairness is achieved in both optimal and suboptimal allocations. We show that a continuous relaxation of our central model is sufficient to achieve a perfect extent of fairness, while a special case reduces to the classical notion of proportional fairness. Our work is motivated by pervasive ecological challenges faced by the waste management community as policymakers seek to reduce the number of recycling centers in the last few years. As a computational case study, applying our models on data for the state of Bavaria in Germany, we find that even after the closure of a moderate number of recycling centers, large degrees of access can be ensured, provided that the closures are conducted optimally. Fairness, however, is impacted more, with facilities in rural regions shouldering larger loads of visiting populations than those in urban regions. History: Accepted by Pascal Van Hentenryck, Area Editor for Computational Modeling: Methods & Analysis. Funding: Computer resources and support provided by the Erlangen Regional Computing Center are gratefully acknowledged. B. Singh was partially financially supported by the Bavarian State Ministry for Science and Art (Bayerisches Staatsministerium für Wissenschaft und Kunst) under the Competence Network for Scientific High Performance Computing in Bavaria. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0308 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2022.0308 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

A real-time field bus architecture for multi-smart-motor servo system

The multi-motor servo system (MMSS) is an electro-mechanical system widely used in various fields, including electric vehicles, robotics, and industrial machinery. Depending on the application, the number of motors in the system can range from several dozens to tens of thousands, which imposes additional communication demands. Thus, ensuring synchronization and control precision of the system requires addressing the challenge of guaranteeing the performance and reliability of communication among motors in the MMSS. In this paper, we design a smart servo motor (SSM) to upgrade the system to the multi-smart-motor servo system (MSMSS) based on a distributed real-time field bus architecture, namely, Multi-Motor Bus (MMB) architecture. The proposed MMB architecture is lightweight and stable, providing real-time support for Control Area Network connections to a central user computer and inter-integrated circuit connections to SSM units. This MMB architecture facilitates the synchronization of command transmission across SSMs and ensures the consistency of motors in the MSMSS. Additionally, a serial experiments to examine 3 key system performance and reliability characteristics are conducted, including command transmission time, transmission jitters, and rotation consistency. The analysis of these characteristics demonstrates the system’s potential and feasibility to be applicable in industry.

Unraveling the crypto market: A journey into decentralized finance transaction network

The explosive growth of decentralized finance (DeFi) has revolutionized the accessibility and functionality of financial services. To gain valuable insights into this evolving ecosystem, analyzing transaction data using network analysis methodology proves to be highly effective. Network analysis allows us to uncover intricate relationships, patterns, and communities within the DeFi market by examining participant transactions. We model nodes group representing actors or wallet addresses, and edges represent transactions between wallet addresses. This study focuses on three prominent DeFi token-based Ethereum protocols: DAI, UNI, and WBTC. We analyzed 5,802,742 transaction data spanning from January 2022 to January 2023 of those three tokens. Using network topology metrics, we uncover market size, average transaction of each wallet address, market density, and reachability (diameter). We also detect the presence of transaction clusters and grouping quality using the modularity metric. At last, we employ centrality calculation to identify the most important wallet address and their role in the market. We gain insight by comparing those three tokens and reveal valuable insight into patterns and relationships, network dynamics, decentralized nature, and the presence of intermediaries in the token economy market. Our objective is to uncover hidden dynamics and trace asset flows, which can provide valuable information to market participants, regulators, and innovators seeking to optimize the DeFi infrastructure, ensure stability, and mitigate risks. Leveraging the power of network analysis offers the potential to shape the future of DeFi by enhancing efficiency, security, and accessibility, thereby fostering financial inclusion and empowering individuals and businesses globally.

Calculation of centrality in the analysis of congestion of city roads on the example of Petrozavodsk

Centrality is a numerical measure that characterizes the structural properties of a graph. In the presented work, centrality is used to analyze the load of the graph of urban roads in the city of Petrozavodsk. In the paper, we describe the method used to construct the road graph, present a modified centrality measure that takes into account the features of the transport network and the distribution of passenger traffic, and demonstrate the results of numerical simulations. For the transport graph, betweenness centralities were calculated with and without regard to the distribution of passenger traffic; a connectivity analysis was carried out to identify critical, overloaded and reserve roads, and the routes that make the greatest contribution to the centrality of the most loaded roads. The obtained results show that centrality can be used for the analysis of the structural features of the graph of urban roads, modeling sustainability and planning the development of the transport network.

Calculation of Centrality in the Analysis of Congestion of City Roads on the Example of Petrozavodsk

Calculation of Centrality in the Analysis of Congestion of City Roads on the Example of Petrozavodsk

Calculation of Centrality in the Analysis of Congestion of City Roads on the Example of Petrozavodsk

Centrality is a numerical measure that characterizes the structural properties of a graph. In the presented work, centrality is used to analyze the load of the graph of urban roads in the city of Petrozavodsk. In the paper, we describe the method used to construct the road graph, present a modified centrality measure that takes into account the features of the transport network and the distribution of passenger traffic, and demonstrate the results of numerical simulations. For the transport graph, betweenness centralities were calculated with and without regard to the distribution of passenger traffic; a connectivity analysis was performed to identify critical, overloaded and reserve roads, and the routes that make the greatest contribution to the centrality of the most loaded roads. The results show that centrality can be used for the analysis of the structural features of the graph of urban roads, modeling sustainability and planning the development of the transport network.