Search results for: observer nodes

Authors: Mohammadreza Kashizadeh, Mohammadamin Hashemi

Abstract:

Solymorph, a kinetic building facade designed for optimal energy capture and architectural expression, is explored in this paper. The system integrates photovoltaic panels with soft robotic actuators for precise solar tracking, resulting in enhanced electricity generation compared to static facades. Driven by the growing interest in dynamic building envelopes, the exploration of novel facade systems is necessitated. Increased energy generation and regulation of energy flow within buildings are potential benefits offered by integrating photovoltaic (PV) panels as kinetic elements. However, incorporating these technologies into mainstream architecture presents challenges due to the complexity of coordinating multiple systems. To address this, Solymorph leverages soft robotic actuators, known for their compliance, resilience, and ease of integration. Additionally, the project investigates the potential for employing Large Language Models (LLMs) to streamline the design process. The research methodology involved design development, material selection, component fabrication, and system assembly. Grasshopper (GH) was employed within the digital design environment for parametric modeling and scripting logic, and an LLM was experimented with to generate Python code for the creation of a random surface with user-defined parameters. Various techniques, including casting, 3D printing, and laser cutting, were utilized to fabricate the physical components. Finally, a modular assembly approach was adopted to facilitate installation and maintenance. A case study focusing on the application of Solymorph to an existing library building at Politecnico di Milano is presented. The facade system is divided into sub-frames to optimize solar exposure while maintaining a visually appealing aesthetic. Preliminary structural analyses were conducted using Karamba3D to assess deflection behavior and axial loads within the cable net structure. Additionally, Finite Element (FE) simulations were performed in Abaqus to evaluate the mechanical response of the soft robotic actuators under pneumatic pressure. To validate the design, a physical prototype was created using a mold adapted for a 3D printer's limitations. Casting Silicone Rubber Sil 15 was used for its flexibility and durability. The 3D-printed mold components were assembled, filled with the silicone mixture, and cured. After demolding, nodes and cables were 3D-printed and connected to form the structure, demonstrating the feasibility of the design. Solymorph demonstrates the potential of soft robotics and Artificial Intelligence (AI) for advancements in sustainable building design and construction. The project successfully integrates these technologies to create a dynamic facade system that optimizes energy generation and architectural expression. While limitations exist, Solymorph paves the way for future advancements in energy-efficient facade design. Continued research efforts will focus on cost reduction, improved system performance, and broader applicability.

Keywords: artificial intelligence, energy efficiency, kinetic photovoltaics, pneumatic control, soft robotics, sustainable building

Procedia PDF Downloads 24

Authors: A. Peyvan, D. Li, J. Komperda, F. Mashayek

Abstract:

Turbulence can be observed in a variety fluid motions in nature and industrial applications. Recent investment in high-speed aircraft and propulsion systems has revitalized fundamental research on turbulent flows. In these systems, capturing chaotic fluid structures with different length and time scales is accomplished through the Direct Numerical Simulation (DNS) approach since it accurately simulates flows down to smallest dissipative scales, i.e., Kolmogorov’s scales. The discontinuous spectral element method (DSEM) is a high-order technique that uses spectral functions for approximating the solution. The DSEM code has been developed by our research group over the course of more than two decades. Recently, the code has been improved to run large cases in the order of billions of solution points. Running big simulations requires a considerable amount of RAM. Therefore, the DSEM code must be highly parallelized and able to start on multiple computational nodes on an HPC cluster with distributed memory. However, some pre-processing procedures, such as determining global element information, creating a global face list, and assigning global partitioning and element connection information of the domain for communication, must be done sequentially with a single processing core. A separate code has been written to perform the pre-processing procedures on a local machine. It stores the minimum amount of information that is required for the DSEM code to start in parallel, extracted from the mesh file, into text files (pre-files). It packs integer type information with a Stream Binary format in pre-files that are portable between machines. The files are generated to ensure fast read performance on different file-systems, such as Lustre and General Parallel File System (GPFS). A new subroutine has been added to the DSEM code to read the startup files using parallel MPI I/O, for Lustre, in a way that each MPI rank acquires its information from the file in parallel. In case of GPFS, in each computational node, a single MPI rank reads data from the file, which is specifically generated for the computational node, and send them to other ranks on the node using point to point non-blocking MPI communication. This way, communication takes place locally on each node and signals do not cross the switches of the cluster. The read subroutine has been tested on Argonne National Laboratory’s Mira (GPFS), National Center for Supercomputing Application’s Blue Waters (Lustre), San Diego Supercomputer Center’s Comet (Lustre), and UIC’s Extreme (Lustre). The tests showed that one file per node is suited for GPFS and parallel MPI I/O is the best choice for Lustre file system. The DSEM code relies on heavily optimized linear algebra operation such as matrix-matrix and matrix-vector products for calculation of the solution in every time-step. For this, the code can either make use of its matrix math library, BLAS, Intel MKL, or ATLAS. This fact and the discontinuous nature of the method makes the DSEM code run efficiently in parallel. The results of weak scaling tests performed on Blue Waters showed a scalable and efficient performance of the code in parallel computing.

Keywords: computational fluid dynamics, direct numerical simulation, spectral element, turbulent flow

Procedia PDF Downloads 107

Authors: Carolyn Hatch, Laurent Simon

Abstract:

Urban mobility and the transportation industry are undergoing a transformation, shifting from an auto production-consumption model that has dominated since the early 20th century towards new forms of personal and shared multi-modality [1]. This is shaped by key forces such as climate change, which has induced a shift in production and consumption patterns and efforts to decarbonize and improve transport services through, for instance, the integration of vehicle automation, electrification and mobility sharing [2]. Advanced innovation practices and platforms for experimentation and validation of new mobility products and services that are increasingly complex and multi-stakeholder-oriented are shaping this new world of mobility. Transportation hubs – such as airports - are emblematic of these disruptive forces playing out in the mobility industry. Airports are emerging as the core of innovation ecosystems on and around contemporary mobility issues, and increasingly recognized as complex public/private nodes operating in many societal dimensions [3,4]. These include urban development, sustainability transitions, digital experimentation, customer experience, infrastructure development and data exploitation (for instance, airports generate massive and often untapped data flows, with significant potential for use, commercialization and social benefit). Yet airport innovation practices have not been well documented in the innovation literature. This paper addresses this gap by proposing a model of airport innovation that aims to equip airport stakeholders to respond to these new and complex innovation needs in practice. The methodology involves: 1 – a literature review bringing together key research and theory on airport innovation management, open innovation and innovation ecosystems in order to evaluate airport practices through an innovation lens; 2 – an international benchmarking of leading airports and their innovation practices, including such examples as Aéroports de Paris, Schipol in Amsterdam, Changi in Singapore, and others; and 3 – semi-structured interviews with airport managers on key aspects of organizational practice, facilitated through a close partnership with the Airport Council International (ACI), a major stakeholder in this research project. Preliminary results find that the most successful airports are those that have shifted to a multi-stakeholder, platform ecosystem model of innovation. The recent entrance of new actors in airports (Google, Amazon, Accor, Vinci, Airbnb and others) have forced the opening of organizational boundaries to share and exchange knowledge with a broader set of ecosystem players. This has also led to new forms of governance and intermediation by airport actors to connect complex, highly distributed knowledge, along with new kinds of inter-organizational collaboration, co-creation and collective ideation processes. Leading airports in the case study have demonstrated a unique capacity to force traditionally siloed activities to “think together”, “explore together” and “act together”, to share data, contribute expertise and pioneer new governance approaches and collaborative practices. In so doing, they have successfully integrated these many disruptive change pathways and forced their implementation and coordination towards innovative mobility outcomes, with positive societal, environmental and economic impacts. This research has implications for: 1 - innovation theory, 2 - urban and transport policy, and 3 - organizational practice - within the mobility industry and across the economy.

Keywords: airport management, ecosystem, innovation, mobility, platform, transport hubs

Procedia PDF Downloads 153

Authors: Stefan K. Behfar

Abstract:

The rapid growth of the Ethereum network has brought forth the urgent need for scalable analysis methods to handle the increasing volume of blockchain data. In this research, we propose efficient methodologies for making Ethereum network analysis scalable. Our approach leverages a combination of graph-based data representation, probabilistic sampling, and parallel processing techniques to achieve unprecedented scalability while preserving critical network insights. Data Representation: We develop a graph-based data representation that captures the underlying structure of the Ethereum network. Each block transaction is represented as a node in the graph, while the edges signify temporal relationships. This representation ensures efficient querying and traversal of the blockchain data. Probabilistic Sampling: To cope with the vastness of the Ethereum blockchain, we introduce a probabilistic sampling technique. This method strategically selects a representative subset of transactions and blocks, allowing for concise yet statistically significant analysis. The sampling approach maintains the integrity of the network properties while significantly reducing the computational burden. Graph Convolutional Networks (GCNs): We incorporate GCNs to process the graph-based data representation efficiently. The GCN architecture enables the extraction of complex spatial and temporal patterns from the sampled data. This combination of graph representation and GCNs facilitates parallel processing and scalable analysis. Distributed Computing: To further enhance scalability, we adopt distributed computing frameworks such as Apache Hadoop and Apache Spark. By distributing computation across multiple nodes, we achieve a significant reduction in processing time and enhanced memory utilization. Our methodology harnesses the power of parallelism, making it well-suited for large-scale Ethereum network analysis. Evaluation and Results: We extensively evaluate our methodology on real-world Ethereum datasets covering diverse time periods and transaction volumes. The results demonstrate its superior scalability, outperforming traditional analysis methods. Our approach successfully handles the ever-growing Ethereum data, empowering researchers and developers with actionable insights from the blockchain. Case Studies: We apply our methodology to real-world Ethereum use cases, including detecting transaction patterns, analyzing smart contract interactions, and predicting network congestion. The results showcase the accuracy and efficiency of our approach, emphasizing its practical applicability in real-world scenarios. Security and Robustness: To ensure the reliability of our methodology, we conduct thorough security and robustness evaluations. Our approach demonstrates high resilience against adversarial attacks and perturbations, reaffirming its suitability for security-critical blockchain applications. Conclusion: By integrating graph-based data representation, GCNs, probabilistic sampling, and distributed computing, we achieve network scalability without compromising analytical precision. This approach addresses the pressing challenges posed by the expanding Ethereum network, opening new avenues for research and enabling real-time insights into decentralized ecosystems. Our work contributes to the development of scalable blockchain analytics, laying the foundation for sustainable growth and advancement in the domain of blockchain research and application.

Keywords: Ethereum, scalable network, GCN, probabilistic sampling, distributed computing

Procedia PDF Downloads 39

Authors: George Charkoftakis, Panagiotis Liosatos, Nicolas-Alexander Tatlas, Dimitrios Goustouridis, Stelios M. Potirakis

Abstract:

E-maintenance is a relatively new concept, generally referring to maintenance management by monitoring assets over the Internet. One of the key links in the chain of an e-maintenance system is data acquisition and transmission. Specifically for the case of a fleet of heavy-duty vehicles, where the main challenge is the diversity of the vehicles and vehicle-embedded self-diagnostic/reporting technologies, the design of the data acquisition and transmission unit is a demanding task. This clear if one takes into account that a heavy-vehicles fleet assortment may range from vehicles with only a limited number of analog sensors monitored by dashboard light indicators and gauges to vehicles with plethora of sensors monitored by a vehicle computer producing digital reporting. The present work proposes an adaptable internet of things (IoT) sensor node that is capable of addressing this challenge. The proposed sensor node architecture is based on the increasingly popular single-board computer – expansion boards approach. In the proposed solution, the expansion boards undertake the tasks of position identification by means of a global navigation satellite system (GNSS), cellular connectivity by means of 3G/long-term evolution (LTE) modem, connectivity to on-board diagnostics (OBD), and connectivity to analog and digital sensors by means of a novel design of expansion board. Specifically, the later provides eight analog plus three digital sensor channels, as well as one on-board temperature / relative humidity sensor. The specific device offers a number of adaptability features based on appropriate zero-ohm resistor placement and appropriate value selection for limited number of passive components. For example, although in the standard configuration four voltage analog channels with constant voltage sources for the power supply of the corresponding sensors are available, up to two of these voltage channels can be converted to provide power to the connected sensors by means of corresponding constant current source circuits, whereas all parameters of analog sensor power supply and matching circuits are fully configurable offering the advantage of covering a wide variety of industrial sensors. Note that a key feature of the proposed sensor node, ensuring the reliable operation of the connected sensors, is the appropriate supply of external power to the connected sensors and their proper matching to the IoT sensor node. In standard mode, the IoT sensor node communicates to the data center through 3G/LTE, transmitting all digital/digitized sensor data, IoT device identity, and position. Moreover, the proposed IoT sensor node offers WiFi connectivity to mobile devices (smartphones, tablets) equipped with an appropriate application for the manual registration of vehicle- and driver-specific information, and these data are also forwarded to the data center. All control and communication tasks of the IoT sensor node are performed by dedicated firmware. It is programmed with a high-level language (Python) on top of a modern operating system (Linux). Acknowledgment: This research has been co-financed by the European Union and Greek national funds through the Operational Program Competitiveness, Entrepreneurship, and Innovation, under the call RESEARCH—CREATE—INNOVATE (project code: T1EDK- 01359, IntelligentLogger).

Keywords: IoT sensor nodes, e-maintenance, single-board computers, sensor expansion boards, on-board diagnostics

Procedia PDF Downloads 125

Authors: Wissam Saliba, Mandy Nicholson

Abstract:

Secretory carcinoma (SC) is a rare type of salivary gland cancer. It was first realized as a distinct type of malignancy in 2010and wasinitially termed “mammary analogue secretory carcinoma” because of similarities with secretory breast cancer. The name was later changed to SC. Most SCs originate in parotid glands, and most harbour a rare gene mutation: ETV6-NTRK3. This mutation is rare in common cancers and common in rare cancers; it is present in most secretory carcinomas. Disease outcomes for SC are usually described as favourable as many cases of SC are lowgrade (LG), and cancer growth is slow. In early stages, localized therapy is usually indicated (surgery and/or radiation). Despitea favourable prognosis, a sub-set of casescan be much more aggressive.These cases tend to be of high-grade(HG).HG casesare associated with a poorer prognosis.Management of such cases can be challenging due to limited evidence for effective systemic therapy options. This case report describes the clinical management of a 46-year-oldmale patient with a unique case of SC. He was initially diagnosed with a low/intermediate grade carcinoma of the left parotid gland in 2009; he was treated with surgery and adjuvant radiation. Surgical pathology favoured primary salivary adenocarcinoma, and 2 lymph nodes were positive for malignancy. SC was not yet realized as a distinct type of cancerat the time of diagnosis, and the pathology reportvalidated this gap by stating that the specimen lacked features of the defined types of salivary carcinoma.Slow-growing pulmonary nodules were identified in 2017. In 2020, approximately 11 years after the initial diagnosis, the patient presented with malignant pleural effusion. Pathology from a pleural biopsy was consistent with metastatic poorly differentiated cancer of likely parotid origin, likely mammary analogue secretory carcinoma. The specimen was sent for Next Generation Sequencing (NGS); ETV6-NTRK3 gene fusion was confirmed, and systemic therapy was initiated.One cycle ofcarboplatin/paclitaxel was given in June 2020. He was switched to Larotrectinib (NTRK inhibitor (NTRKi)) later that month. Larotrectinib continued for approximately 9 months, with discontinuation in March 2021 due to disease progression. A second-generation NTRKi (Selitrectinib) was accessed and prescribedthrough a single patient study. Selitrectinib was well tolerated. The patient experienced a complete radiological response within~4 months. Disease progression occurred once again in October 2021. Progression was slow, and Selitrectinib continuedwhile the medical team performed a thorough search for additional treatment options. In January 2022, a liver lesion biopsy was performed, and NGS showed an NTRKG623R solvent-front resistance mutation. Various treatment pathways were considered. The patient pursuedanother investigational NTRKi through a clinical trial, and Selitrectinib was discontinued in July 2022. Excellent performance status was maintained throughout the entire course of treatment.It can be concluded that NTRK inhibitors provided satisfactory treatment efficacy and tolerance for this patient with high-grade transformation and NTRK gene fusion cancer. In the future, more clinical research is needed on systemic treatment options for high-grade transformations in NTRK gene fusion SCs.

Keywords: secretory carcinoma, high-grade transformations, NTRK gene fusion, NTRK inhibitor

Procedia PDF Downloads 87

Authors: Leo Byrne, Neil Watts

Abstract:

In the complex and evolving landscape of global trade, maritime sanctions emerge as a critical tool wielded by the international community to curb illegal activities and alter the behavior of non-compliant states and entities. These sanctions, designed to restrict or prohibit trade by sea with sanctioned jurisdictions, entities, or individuals, face continuous challenges due to the sophisticated evasion tactics employed by countries like North Korea. As the Democratic People's Republic of Korea (DPRK) diverts significant resources to circumvent these measures, understanding the nuances of their methodologies becomes imperative for maintaining the integrity of global trade systems. The DPRK, one of the most sanctioned nations globally, has developed an intricate network to facilitate its trade in illicit goods, ensuring the flow of revenue from designated activities continues unabated. Given its geographic and economic conditions, North Korea predominantly relies on maritime routes, utilizing foreign ports to route its illicit trade. This reliance on the sea is exploited through various sophisticated methods, including the use of front companies, falsification of documentation, commingling of bulk cargos, and physical alterations to vessels. These tactics enable the DPRK to navigate through the gaps in regulatory frameworks and lax oversight, effectively undermining international sanctions regimes Maritime sanctions carry significant implications for global trade, imposing heightened risks in the maritime domain. The deceptive practices employed not only by the DPRK but also by other high-risk jurisdictions, necessitate a comprehensive understanding of UN targeted sanctions. For stakeholders in the maritime sector—including maritime authorities, vessel owners, shipping companies, flag registries, and financial institutions serving the shipping industry—awareness and compliance are paramount. Violations can lead to severe consequences, including reputational damage, sanctions, hefty fines, and even imprisonment. To mitigate risks associated with these deceptive practices, it is crucial for maritime sector stakeholders to employ rigorous due diligence and regulatory compliance screening measures. Effective sanctions compliance serves as a protective shield against legal, financial, and reputational risks, preventing exploitation by international bad actors. This requires not only a deep understanding of the sanctions landscape but also the capability to identify and manage risks through informed decision-making and proactive risk management practices. As the DPRK and other sanctioned entities continue to evolve their sanctions evasion tactics, the international community must enhance its collective efforts to demystify and counter these practices. By leveraging more stringent compliance measures, stakeholders can safeguard against the illicit use of the maritime domain, reinforcing the effectiveness of maritime sanctions as a tool for global security. This paper seeks to dissect North Korea's adaptive strategies in the face of maritime sanctions. By examining up-to-date, geographically, and temporally relevant case studies, it aims to shed light on the primary nodes through which Pyongyang evades sanctions and smuggles goods via third-party ports. The goal is to propose multi-level interaction strategies, ranging from governmental interventions to localized enforcement mechanisms, to counteract these evasion tactics.

Keywords: maritime, maritime sanctions, international sanctions, compliance, risk

Procedia PDF Downloads 26

Authors: Claudio Clemente, Valentina Gargiulo, Alessio Occhicone, Giovanni Piero Pepe, Giovanni Ausanio, Michela Alfè

Abstract:

Volatile organic compound (VOC) emissions represent a serious risk to human health and the integrity of the ecosystems, especially at high concentrations. For this reason, it is very important to continuously monitor environmental quality and develop fast and reliable portable sensors to allow analysis on site. Chemiresistors have become promising candidates for VOC sensing as their ease of fabrication, variety of suitable sensitive materials, and simple sensing data. A chemoresistive gas sensor is a transducer that allows to measure the concentration of an analyte in the gas phase because the changes in resistance are proportional to the amount of the analyte present. The selection of the sensitive material, which interacts with the target analyte, is very important for the sensor performance. The most used VOC detection materials are metal oxides (MOx) for their rapid recovery, high sensitivity to various gas molecules, easy fabrication. Their sensing performance can be improved in terms of operating temperature, selectivity, and detection limit. Metal-organic frameworks (MOFs) have attracted a lot of attention also in the field of gas sensing due to their high porosity, high surface area, tunable morphologies, structural variety. MOFs are generated by the self-assembly of multidentate organic ligands connecting with adjacent multivalent metal nodes via strong coordination interactions, producing stable and highly ordered crystalline porous materials with well-designed structures. However, most MOFs intrinsically exhibit low electrical conductivity. To improve this property, MOFs can be combined with organic and inorganic materials in a hybrid fashion to produce composite materials or can be transformed into more stable structures. MOFs, indeed, can be employed as the precursors of metal oxides with well-designed architectures via the calcination method. The MOF-derived MOx partially preserved the original structure with high surface area and intrinsic open pores, which act as trapping centers for gas molecules, and showed a higher electrical conductivity. Core-shell heterostructures, in which the surface of a metal oxide core is completely coated by a MOF shell, forming a junction at the core-shell heterointerface, can also be synthesized. Also, nanocomposite in which MOF structures are intercalated with graphene related materials can also be produced, and the conductivity increases thanks to the high mobility of electrons of carbon materials. As MOF structures, zinc-based MOFs belonging to the ZIF family were selected in this work. Several Zn-based materials based and/or derived from MOFs were produced, structurally characterized, and arranged in a chemo resistive architecture, also exploring the potentiality of different approaches of sensing layer deposition based on PLD (pulsed laser deposition) and, in case of thermally labile materials, MAPLE (Matrix Assisted Pulsed Laser Evaporation) to enhance the adhesion to the support. The sensors were tested in a controlled humidity chamber, allowing for the possibility of varying the concentration of ethanol, a typical analyte chosen among the VOCs for a first survey. The effect of heating the chemiresistor to improve sensing performances was also explored. Future research will focus on exploring new manufacturing processes for MOF-based gas sensors with the aim to improve sensitivity, selectivity and reduce operating temperatures.

Keywords: chemiresistors, gas sensors, graphene related materials, laser deposition, MAPLE, metal-organic frameworks, metal oxides, nanocomposites, sensing performance, transduction mechanism, volatile organic compounds

Procedia PDF Downloads 22

Authors: Pablo Reche

Abstract:

Since 1980’s aquaculture has become the biggest economic activity in southern Chile, being Salmo salar and Oncorhynchus mykiss the main finfish species. High fish density makes both species prone to contract diseases, what drives the industry to big losses, affecting greatly the local economy. Three are the most concerning infective agents, the infectious salmon anemia virus (ISAv), the bacteria Piscirickettsia salmonis and the copepod Caligus rogercresseyi. To regulate the industry the government arranged the salmon farms within management areas named as barrios, which coordinate the fallowing periods and antibiotics treatments of their salmon farms. In turn, barrios are gathered into larger management areas, named as macrozonas whose purpose is to minimize the risk of disease transmission between them and to enclose the outbreaks within their boundaries. However, disease outbreaks still happen and transmission to neighbor sites enlarges the initial event. Salmon disease agents are mostly transported passively by local currents. Thus, to understand how transmission occurs it must be firstly studied the physical environment. In Chile, salmon farming takes place in the inner seas of the southernmost regions of western Patagonia, between 41.5ºS-55ºS. This coastal marine system is characterised by western winds, latitudinally modulated by the position of the South-Eats Pacific high-pressure centre, high precipitation rates and freshwater inflows from the numerous glaciers (including the largest ice cap out of Antarctic and Greenland). All of these forcings meet in a complex bathymetry and coastline system - deep fjords, shallow sills, narrow straits, channels, archipelagos, inlets, and isolated inner seas- driving an estuarine circulation (fast outflows westwards on surface and slow deeper inflows eastwards). Such a complex system is modelled on the numerical model MIKE3, upon whose 3D current fields particle-track-biological models (one for each infective agent) are decoupled. Each agent biology is parameterized by functions for maturation and mortality (reproduction not included). Such parameterizations are depending upon environmental factors, like temperature and salinity, so their lifespan will depend upon the environmental conditions those virtual agents encounter on their way while passively transported. CLIC (Connectivity-Langrangian–IFOP-Chile) is a service platform that supports the graphical visualization of the connectivity matrices calculated from the particle trajectories files resultant of the particle-track-biological models. On CLIC users can select, from a high-resolution grid (~1km), the areas the connectivity will be calculated between them. These areas can be barrios and macrozonas. Users also can select what nodes of these areas are allowed to release and scatter particles from, depth and frequency of the initial particle release, climatic scenario (winter/summer) and type of particle (ISAv, Piscirickettsia salmonis, Caligus rogercresseyi plus an option for lifeless particles). Results include probabilities downstream (where the particles go) and upstream (where the particles come from), particle age and vertical distribution, all of them aiming to understand how currently connectivity works to eventually propose a minimum risk zonation for aquaculture purpose. Preliminary results in Chiloe inner sea shows that the risk depends not only upon dynamic conditions but upon barrios location with respect to their neighbors.

Keywords: aquaculture zonation, Caligus rogercresseyi, Chilean Patagonia, coastal oceanography, connectivity, infectious salmon anemia virus, Piscirickettsia salmonis

Procedia PDF Downloads 132

Authors: Ali Kazemi

Abstract:

Those within the volatile and interconnected international economic markets, appropriately predicting market trends, hold substantial fees for traders and financial establishments. Traditional device mastering strategies have made full-size strides in forecasting marketplace movements; however, monetary data's complicated and networked nature calls for extra sophisticated processes. This observation offers a groundbreaking method for monetary marketplace prediction that leverages the synergistic capability of Graph Convolutional Networks (GCNs) and Long Short-Term Memory (LSTM) networks. Our suggested algorithm is meticulously designed to forecast the traits of inventory market indices and cryptocurrency costs, utilizing a comprehensive dataset spanning from January 1, 2015, to December 31, 2023. This era, marked by sizable volatility and transformation in financial markets, affords a solid basis for schooling and checking out our predictive version. Our algorithm integrates diverse facts to construct a dynamic economic graph that correctly reflects market intricacies. We meticulously collect opening, closing, and high and low costs daily for key inventory marketplace indices (e.g., S&P 500, NASDAQ) and widespread cryptocurrencies (e.g., Bitcoin, Ethereum), ensuring a holistic view of marketplace traits. Daily trading volumes are also incorporated to seize marketplace pastime and liquidity, providing critical insights into the market's shopping for and selling dynamics. Furthermore, recognizing the profound influence of the monetary surroundings on financial markets, we integrate critical macroeconomic signs with hobby fees, inflation rates, GDP increase, and unemployment costs into our model. Our GCN algorithm is adept at learning the relational patterns amongst specific financial devices represented as nodes in a comprehensive market graph. Edges in this graph encapsulate the relationships based totally on co-movement styles and sentiment correlations, enabling our version to grasp the complicated community of influences governing marketplace moves. Complementing this, our LSTM algorithm is trained on sequences of the spatial-temporal illustration discovered through the GCN, enriched with historic fee and extent records. This lets the LSTM seize and expect temporal marketplace developments accurately. Inside the complete assessment of our GCN-LSTM algorithm across the inventory marketplace and cryptocurrency datasets, the version confirmed advanced predictive accuracy and profitability compared to conventional and opportunity machine learning to know benchmarks. Specifically, the model performed a Mean Absolute Error (MAE) of 0.85%, indicating high precision in predicting day-by-day charge movements. The RMSE was recorded at 1.2%, underscoring the model's effectiveness in minimizing tremendous prediction mistakes, which is vital in volatile markets. Furthermore, when assessing the model's predictive performance on directional market movements, it achieved an accuracy rate of 78%, significantly outperforming the benchmark models, averaging an accuracy of 65%. This high degree of accuracy is instrumental for techniques that predict the course of price moves. This study showcases the efficacy of mixing graph-based totally and sequential deep learning knowledge in economic marketplace prediction and highlights the fee of a comprehensive, records-pushed evaluation framework. Our findings promise to revolutionize investment techniques and hazard management practices, offering investors and economic analysts a powerful device to navigate the complexities of cutting-edge economic markets.

Keywords: financial market prediction, graph convolutional networks (GCNs), long short-term memory (LSTM), cryptocurrency forecasting

Procedia PDF Downloads 19