Search results for: linear drives

Authors: Teesta Dey

Abstract:

Integrated Transport development with proper traffic management leads to sustainable growth of any urban sphere. Appropriate mass transport planning is essential for the populous cities in third world countries like India. The exponential growth of motor vehicles with unplanned road network is now the common feature of major urban centres in India. Kolkata, the third largest mega city in India, is not an exception of it. The imbalance between demand and supply of unplanned transport services in this city is manifested in the high economic and environmental costs borne by the associated society. With the passage of time, the growth and extent of passenger demand for rapid urban transport has outstripped proper infrastructural planning and causes severe transport problems in the overall urban realm. Hence Kolkata stands out in the world as one of the most crisis-ridden metropolises. The urban transport crisis of this city involves severe traffic congestion, the disparity in mass transport services on changing peripheral land uses, route overlapping, lowering of travel speed and faulty implementation of governmental plans as mostly induced by rapid growth of private vehicles on limited road space with huge carbon footprint. Therefore the paper will critically analyze the extant road network pattern for improving regional connectivity and accessibility, assess the degree of congestion, identify the deviation from demand and supply balance and finally evaluate the emerging alternate transport options as promoted by the government. For this purpose, linear, nodal and spatial transport network have been assessed based on certain selected indices viz. Road Degree, Traffic Volume, Shimbel Index, Direct Bus Connectivity, Average Travel and Waiting Tine Indices, Route Variety, Service Frequency, Bus Intensity, Concentration Analysis, Delay Rate, Quality of Traffic Transmission, Lane Length Duration Index and Modal Mix. Total 20 Traffic Intersection Points (TIPs) have been selected for the measurement of nodal accessibility. Critical Congestion Zones (CCZs) are delineated based on one km buffer zones of each TIP for congestion pattern analysis. A total of 480 bus routes are assessed for identifying the deficiency in network planning. Apart from bus services, the combined effects of other mass and para transit modes, containing metro rail, auto, cab and ferry services, are also analyzed. Based on systematic random sampling method, a total of 1500 daily urban passengers’ perceptions were studied for checking the ground realities. The outcome of this research identifies the spatial disparity among the 15 boroughs of the city with severe route overlapping and congestion problem. North and Central Kolkata-based mass transport services exceed the transport strength of south and peripheral Kolkata. Faulty infrastructural condition, service inadequacy, economic loss and workers’ inefficiency are the most dominant reasons behind the defective mass transport network plan. Hence there is an urgent need to revive the extant road based mass transport system of this city by implementing a holistic management approach by upgrading traffic infrastructure, designing new roads, better cooperation among different mass transport agencies, better coordination of transport and changing land use policies, large increase in funding and finally general passengers’ awareness.

Keywords: carbon footprint, critical congestion zones, direct bus connectivity, integrated transport development

Procedia PDF Downloads 272

Authors: Francois Brambati, Daniele Ruscio, Federica Biassoni, Rebecca Hueting, Alessandra Tedeschi

Abstract:

This research, in the frame of social acceptance of renewable energies and community-based production and consumption models, aims at (1) supporting a data-driven approachable to dealing with climate change and (2) identifying & quantifying the psycho-sociological dimensions and factors that could support the transition from a technology-driven approach to a consumer-driven approach throughout the emerging “prosumer business models.” In addition to the existing Social Acceptance dimensions, this research tries to identify a purely individual psychological fourth dimension to understand processes and factors underling individual acceptance and adoption of renewable energy business models, realizing a Prosumer Acceptance Index. Questionnaire data collection has been performed throughout an online survey platform, combining standardized and ad-hoc questions adapted for the research purposes. To identify the main factors (individual/social) influencing the relation with renewable energy technology (RET) adoption, a Factorial Analysis has been conducted to identify the latent variables that are related to each other, revealing 5 latent psychological factors: Factor 1. Concern about environmental issues: global environmental issues awareness, strong beliefs and pro-environmental attitudes rising concern on environmental issues. Factor 2. Interest in energy sharing: attentiveness to solutions for local community’s collective consumption, to reduce individual environmental impact, sustainably improve the local community, and sell extra energy to the general electricity grid. Factor 3. Concern on climate change: environmental issues consequences on climate change awareness, especially on a global scale level, developing pro-environmental attitudes on global climate change course and sensitivity about behaviours aimed at mitigating such human impact. Factor 4. Social influence: social support seeking from peers. With RET, advice from significant others is looked for internalizing common perceived social norms of the national/geographical region. Factor 5. Impact on bill cost: inclination to adopt a RET when economic incentives from the behaviour perception affect the decision-making process could result in less expensive or unvaried bills. Linear regression has been conducted to identify and quantify the factors that could better predict behavioural intention to become a prosumer. An overall scale measuring “acceptance of a renewable energy solution” was used as the dependent variable, allowing us to quantify the five factors that contribute to measuring: awareness of environmental issues and climate change; environmental attitudes; social influence; and environmental risk perception. Three variables can significantly measure and predict the scores of the “Acceptance in becoming a prosumer” ad hoc scale. Variable 1. Attitude: the agreement to specific environmental issues and global climate change issues of concerns and evaluations towards a behavioural intention. Variable 2. Economic incentive: the perceived behavioural control and its related environmental risk perception, in terms of perceived short-term benefits and long-term costs, both part of the decision-making process as expected outcomes of the behaviour itself. Variable 3. Age: despite fewer economic possibilities, younger adults seem to be more sensitive to environmental dimensions and issues as opposed to older adults. This research can facilitate policymakers and relevant stakeholders to better understand which relevant psycho-sociological factors are intervening in these processes and what and how specifically target when proposing change towards sustainable energy production and consumption.

Keywords: behavioural intention, environmental risk perception, prosumer, renewable energy technology, social acceptance

Procedia PDF Downloads 129

Authors: Carlotta D’Alessandro, Giuseppe Ioppolo, Katarzyna Szopik-Depczyńska

Abstract:

— The growing scarcity of resources and the mounting pressures of climate change, water pollution, and chemical contamination have prompted societies, governments, and businesses to seek ways to minimize their environmental impact. To combat climate change, and foster sustainability, Industrial Symbiosis (IS) offers a powerful approach, facilitating the shift toward a circular economic model. IS has gained prominence in the European Union's policy framework as crucial enabler of resource efficiency and circular economy practices. The essence of IS lies in the collaborative sharing of resources such as energy, material by-products, waste, and water, thanks to geographic proximity. It can be exemplified by eco-industrial parks (EIPs), which are natural environments for boosting cooperation and resource sharing between businesses. EIPs are characterized by group of businesses situated in proximity, connected by a network of both cooperative and competitive interactions. They represent a sustainable industrial model aimed at reducing resource use, waste, and environmental impact while fostering economic and social wellbeing. IS, combined with Artificial Intelligence (AI)-driven technologies, can further optimize resource sharing and efficiency within EIPs. This research, supported by the “CE_IPs” project, aims to analyze the potential for IS and AI, in advancing circularity and sustainability at Fosso Imperatore. The Fosso Imperatore Industrial Park in Nocera Inferiore, Italy, specializes in agriculture and the industrial transformation of agricultural products, particularly tomatoes, tobacco, and textile fibers. This unique industrial cluster, centered around tomato cultivation and processing, also includes mechanical engineering enterprises and agricultural packaging firms. To stimulate the shift from a traditional to a circular economic model, an AI-powered Local Development Plan (LDP) is developed for Fosso Imperatore. It can leverage data analytics, predictive modeling, and stakeholder engagement to optimize resource utilization, reduce waste, and promote sustainable industrial practices. A comprehensive SWOT analysis of the AI-powered LDP revealed several key factors influencing its potential success and challenges. Among the notable strengths and opportunities arising from AI implementation are reduced processing times, fewer human errors, and increased revenue generation. Furthermore, predictive analytics minimize downtime, bolster productivity, and elevate quality while mitigating workplace hazards. However, the integration of AI also presents potential weaknesses and threats, including significant financial investment, since implementing and maintaining AI systems can be costly. The widespread adoption of AI could lead to job losses in certain sectors. Lastly, AI systems are susceptible to cyberattacks, posing risks to data security and operational continuity. Moreover, an Analytic Hierarchy Process (AHP) analysis was employed to yield a prioritized ranking of the outlined AI-driven LDP practices based on the stakeholder input, ensuring a more comprehensive and representative understanding of their relative significance for achieving sustainability in Fosso Imperatore Industrial Park. While this study provides valuable insights into the potential of AIpowered LDP at the Fosso Imperatore, it is important to note that the findings may not be directly applicable to all industrial parks, particularly those with different sizes, geographic locations, or industry compositions. Additional study is necessary to scrutinize the generalizability of these results and to identify best practices for implementing AI-driven LDP in diverse contexts.

Keywords: artificial intelligence, climate change, Fosso Imperatore, industrial park, industrial symbiosis

Procedia PDF Downloads 23

Authors: Faruk Ozdemir, Roy Kalawsky, Peter Hubbard

Abstract:

Accurate estimation of RUL provides a basis for effective predictive maintenance, reducing unexpected downtime for industrial equipment. However, while models such as the Random Forest have effective predictive capabilities, they are the so-called ‘black box’ models, where interpretability is at a threshold to make critical diagnostic decisions involved in industries related to aviation. The purpose of this work is to present a prognostic framework that embeds Explainable Artificial Intelligence (XAI) techniques in order to provide essential transparency in Machine Learning methods' decision-making mechanisms based on sensor data, with the objective of procuring actionable insights for the aviation industry. Sensor readings have been gathered from critical equipment such as turbofan jet engine and landing gear, and the prediction of the RUL is done by a Random Forest model. It involves steps such as data gathering, feature engineering, model training, and evaluation. These critical components’ datasets are independently trained and evaluated by the models. While suitable predictions are served, their performance metrics are reasonably good; such complex models, however obscure reasoning for the predictions made by them and may even undermine the confidence of the decision-maker or the maintenance teams. This is followed by global explanations using SHAP and local explanations using LIME in the second phase to bridge the gap in reliability within industrial contexts. These tools analyze model decisions, highlighting feature importance and explaining how each input variable affects the output. This dual approach offers a general comprehension of the overall model behavior and detailed insight into specific predictions. The proposed framework, in its third component, incorporates the techniques of causal analysis in the form of Granger causality tests in order to move beyond correlation toward causation. This will not only allow the model to predict failures but also present reasons, from the key sensor features linked to possible failure mechanisms to relevant personnel. The causality between sensor behaviors and equipment failures creates much value for maintenance teams due to better root cause identification and effective preventive measures. This step contributes to the system being more explainable. Surrogate Several simple models, including Decision Trees and Linear Models, can be used in yet another stage to approximately represent the complex Random Forest model. These simpler models act as backups, replicating important jobs of the original model's behavior. If the feature explanations obtained from the surrogate model are cross-validated with the primary model, the insights derived would be more reliable and provide an intuitive sense of how the input variables affect the predictions. We then create an iterative explainable feedback loop, where the knowledge learned from the explainability methods feeds back into the training of the models. This feeds into a cycle of continuous improvement both in model accuracy and interpretability over time. By systematically integrating new findings, the model is expected to adapt to changed conditions and further develop its prognosis capability. These components are then presented to the decision-makers through the development of a fully transparent condition monitoring and alert system. The system provides a holistic tool for maintenance operations by leveraging RUL predictions, feature importance scores, persistent sensor threshold values, and autonomous alert mechanisms. Since the system will provide explanations for the predictions given, along with active alerts, the maintenance personnel can make informed decisions on their end regarding correct interventions to extend the life of the critical machinery.

Keywords: predictive maintenance, explainable artificial intelligence, prognostic, RUL, machine learning, turbofan engines, C-MAPSS dataset

Procedia PDF Downloads 4

Authors: Elhadi Nasr, Ibrahim Ramadan

Abstract:

Biostratigraphical analyses of well sections from the Maragh Low in the Eastern Sirt Basin has allowed high resolution correlations to be undertaken. Full integration of this data with available palaeoenvironmental, lithological, gravity, seismic, aeromagnetic, igneous, radiometric and wireline log information and a geochemical analysis of source rock quality and distribution has led to a more detailed understanding of the geological and the structural history of this area. Pre Sirt Unconformity two superimposed rifting cycles have been identified. The oldest is represented by the Amal Group of sediments and is of Late Carboniferous, Kasimovian / Gzelian to Middle Triassic, Anisian age. Unconformably overlying is a younger rift cycle which is represented the Sarir Group of sediments and is of Early Cretaceous, late Neocomian to Aptian in age. Overlying the Sirt Unconformity is the marine Late Cretaceous section. An assessment of pyrolysis results and a palynofacies analysis has allowed hydrocarbon source facies and quality to be determined. There are a number of hydrocarbon source rock horizons in the Maragh Low, these are sometimes vertically stacked and they are of fair to excellent quality. The oldest identified source rock is the Triassic Shale, this unit is unconformably overlain by sandstones belonging to the Sarir Group and conformably overlies a Triassic Siltstone unit. Palynological dating of the Triassic Shale unit indicates a Middle Triassic, Anisian age. The Triassic Shale is interpreted to have been deposited in a lacustrine palaeoenvironment. This particularly is evidenced by the dark, fine grained, organic rich nature of the sediment and is supported by palynofacies analysis and by the recovery of fish fossils. Geochemical analysis of the Triassic Shale indicates total organic carbon varying between 1.37 and 3.53. S2 pyrolysate yields vary between 2.15 mg/g and 6.61 mg/g and hydrogen indices vary between 156.91 and 278.91. The source quality of the Triassic Shale varies from being of fair to very good / rich. Linked to thermal maturity it is now a very good source for light oil and gas. It was once a very good to rich oil source. The Early Barremian Shale was also deposited in a lacustrine palaeoenvironment. Recovered palynomorphs indicate an Early Cretaceous, late Neocomian to early Barremian age. The Early Barremian Shale is conformably underlain and overlain by sandstone units belonging to the Sarir Group of sediments which are also of Early Cretaceous age. Geochemical analysis of the Early Barremian Shale indicates that it is a good oil source and was originally very good. Total organic carbon varies between 3.59% and 7%. S2 varies between 6.30 mg/g and 10.39 mg/g and the hydrogen indices vary between 148.4 and 175.5. A Late Barremian Shale unit of this age has also been identified in the central Maragh Low. Geochemical analyses indicate that total organic carbon varies between 1.05 and 2.38%, S2 pyrolysate between 1.6 and 5.34 mg/g and the hydrogen index between 152.4 and 224.4. It is a good oil source rock which is now mature. In addition to the non marine hydrocarbon source rocks pre Sirt Unconformity, three formations in the overlying Late Cretaceous section also provide hydrocarbon quality source rocks. Interbedded shales within the Rachmat Formation of Late Cretaceous, early Campanian age have total organic carbon ranging between, 0.7 and 1.47%, S2 pyrolysate varying between 1.37 and 4.00 mg/g and hydrogen indices varying between 195.7 and 272.1. The indication is that this unit would provide a fair gas source to a good oil source. Geochemical analyses of the overlying Tagrifet Limestone indicate that total organic carbon varies between 0.26% and 1.01%. S2 pyrolysate varies between 1.21 and 2.16 mg/g and hydrogen indices vary between 195.7 and 465.4. For the overlying Sirt Shale Formation of Late Cretaceous, late Campanian age, total organic carbon varies between 1.04% and 1.51%, S2 pyrolysate varies between 4.65 mg/g and 6.99 mg/g and the hydrogen indices vary between 151 and 462.9. The study has proven that both the Sirt Shale Formation and the Tagrifet Limestone are good to very good and rich sources for oil in the Maragh Low. High resolution biostratigraphical interpretations have been integrated and calibrated with thermal maturity determinations (Vitrinite Reflectance (%Ro), Spore Colour Index (SCI) and Tmax (ºC) and the determined present day geothermal gradient of 25ºC / Km for the Maragh Low. Interpretation of generated basin modelling profiles allows a detailed prediction of timing of maturation development of these source horizons and leads to a determination of amounts of missing section at major unconformities. From the results the top of the oil window (0.72% Ro) is picked as high as 10,700’ and the base of the oil window (1.35% Ro) assuming a linear trend and by projection is picked as low as 18,000’ in the Maragh Low. For the Triassic Shale the early phase of oil generation was in the Late Palaeocene / Early to Middle Eocene and the main phase of oil generation was in the Middle to Late Eocene. The Early Barremian Shale reached the main phase of oil generation in the Early Oligocene with late generation being reached in the Middle Miocene. For the Rakb Group section (Rachmat Formation, Tagrifet Limestone and Sirt Shale Formation) the early phase of oil generation started in the Late Eocene with the main phase of generation being between the Early Oligocene and the Early Miocene. From studying maturity profiles and from regional considerations it can be predicted that up to 500’ of sediment may have been deposited and eroded by the Sirt Unconformity in the central Maragh Low while up to 2000’ of sediment may have been deposited and then eroded to the south of the trough.

Keywords: Geochemical analysis of the source rocks from wells in Eastern Sirt Basin.

Procedia PDF Downloads 406

Authors: Fani Sakellariadou

Abstract:

The Blue Economy includes all marine-based and marine-related activities. They correspond to established, emerging as well as unborn ocean-based industries. Seabed mining is an emerging marine-based activity; its operations depend particularly on cutting-edge science and technology. The 21st century will face a crisis in resources as a consequence of the world’s population growth and the rising standard of living. The natural capital stored in the global ocean is decisive for it to provide a wide range of sustainable ecosystem services. Seabed mineral deposits were identified as having a high potential for critical elements and base metals. They have a crucial role in the fast evolution of green technologies. The major categories of marine mineral deposits are deep-sea deposits, including cobalt-rich ferromanganese crusts, polymetallic nodules, phosphorites, and deep-sea muds, as well as shallow-water deposits including marine placers. Seabed mining operations may take place within continental shelf areas of nation-states. In international waters, the International Seabed Authority (ISA) has entered into 15-year contracts for deep-seabed exploration with 21 contractors. These contracts are for polymetallic nodules (18 contracts), polymetallic sulfides (7 contracts), and cobalt-rich ferromanganese crusts (5 contracts). Exploration areas are located in the Clarion-Clipperton Zone, the Indian Ocean, the Mid Atlantic Ridge, the South Atlantic Ocean, and the Pacific Ocean. Potential environmental impacts of deep-sea mining include habitat alteration, sediment disturbance, plume discharge, toxic compounds release, light and noise generation, and air emissions. They could cause burial and smothering of benthic species, health problems for marine species, biodiversity loss, reduced photosynthetic mechanism, behavior change and masking acoustic communication for mammals and fish, heavy metals bioaccumulation up the food web, decrease of the content of dissolved oxygen, and climate change. An important concern related to deep-sea mining is our knowledge gap regarding deep-sea bio-communities. The ecological consequences that will be caused in the remote, unique, fragile, and little-understood deep-sea ecosystems and inhabitants are still largely unknown. The blue economy conceptualizes oceans as developing spaces supplying socio-economic benefits for current and future generations but also protecting, supporting, and restoring biodiversity and ecological productivity. In that sense, people should apply holistic management and make an assessment of marine mining impacts on ecosystem services, including the categories of provisioning, regulating, supporting, and cultural services. The variety in environmental parameters, the range in sea depth, the diversity in the characteristics of marine species, and the possible proximity to other existing maritime industries cause a span of marine mining impact the ability of ecosystems to support people and nature. In conclusion, the use of the untapped potential of the global ocean demands a liable and sustainable attitude. Moreover, there is a need to change our lifestyle and move beyond the philosophy of single-use. Living in a throw-away society based on a linear approach to resource consumption, humans are putting too much pressure on the natural environment. Applying modern, sustainable and eco-friendly approaches according to the principle of circular economy, a substantial amount of natural resource savings will be achieved. Acknowledgement: This work is part of the MAREE project, financially supported by the Division VI of IUPAC. This work has been partly supported by the University of Piraeus Research Center.

Keywords: blue economy, deep-sea mining, ecosystem services, environmental impacts

Procedia PDF Downloads 82

Authors: Katerina Zaharieva, Katya Milenova, Zara Cherkezova-Zheleva, Alexander Eliyas, Boris Kunev, Ivan Mitov

Abstract:

The synthesized nanosized manganese ferrite-type of samples have been tested as photocatalysts in the reaction of oxidative degradation of model contaminant Reactive Black 5 (RB5) dye in aqueous solutions under UV irradiation. As it is known this azo dye is applied in the textile-coloring industry and it is discharged into the waterways causing pollution. The co-precipitation procedure has been used for the synthesis of manganese ferrite-type of materials: Sample 1 - Mn0.25Fe2.75O4, Sample 2 - Mn0.5Fe2.5O4 and Sample 3 - MnFe2O4 from 0.03M aqueous solutions of MnCl2•4H2O, FeCl2•4H2O and/or FeCl3•6H2O and 0.3M NaOH in appropriate amounts. The mechanochemical activation of co-precipitated ferrite-type of samples has been performed in argon (Samples 1 and 2) or in air atmosphere (Sample 3) for 2 hours at a milling speed of 500 rpm. The mechano-chemical treatment has been carried out in a high energy planetary ball mill type PM 100, Retsch, Germany. The mass ratio between balls and powder was 30:1. As a result mechanochemically activated Sample 4 - Mn0.25Fe2.75O4, Sample 5 - Mn0.5Fe2.5O4 and Sample 6 - MnFe2O4 have been obtained. The synthesized manganese ferrite-type photocatalysts have been characterized by X-ray diffraction method and Moessbauer spectroscopy. The registered X-ray diffraction patterns and Moessbauer spectra of co-precipitated ferrite-type of materials show the presence of manganese ferrite and additional akaganeite phase. The presence of manganese ferrite and small amounts of iron phases is established in the mechanochemically treated samples. The calculated average crystallite size of manganese ferrites varies within the range 7 – 13 nm. This result is confirmed by Moessbauer study. The registered spectra show superparamagnetic behavior of the prepared materials at room temperature. The photocatalytic investigations have been made using polychromatic UV-A light lamp (Sylvania BLB, 18 W) illumination with wavelength maximum at 365 nm. The intensity of light irradiation upon the manganese ferrite-type photocatalysts was 0.66 mW.cm-2. The photocatalytic reaction of oxidative degradation of RB5 dye was carried out in a semi-batch slurry photocatalytic reactor with 0.15 g of ferrite-type powder, 150 ml of 20 ppm dye aqueous solution under magnetic stirring at rate 400 rpm and continuously feeding air flow. The samples achieved adsorption-desorption equilibrium in the dark period for 30 min and then the UV-light was turned on. After regular time intervals aliquot parts from the suspension were taken out and centrifuged to separate the powder from solution. The residual concentrations of dye were established by a UV-Vis absorbance single beam spectrophotometer CamSpec M501 (UK) measuring in the wavelength region from 190 to 800 nm. The photocatalytic measurements determined that the apparent pseudo-first-order rate constants calculated by linear slopes approximating to first order kinetic equation, increase in following order: Sample 3 (1.1х10-3 min-1) < Sample 1 (2.2х10-3 min-1) < Sample 2 (3.3 х10-3 min-1) < Sample 4 (3.8х10-3 min-1) < Sample 6 (11х10-3 min-1) < Sample 5 (15.2х10-3 min-1). The mechanochemically activated manganese ferrite-type of photocatalyst samples show significantly higher degree of oxidative degradation of RB5 dye after 120 minutes of UV light illumination in comparison with co-precipitated ferrite-type samples: Sample 5 (92%) > Sample 6 (91%) > Sample 4 (63%) > Sample 2 (53%) > Sample 1 (42%) > Sample 3 (15%). Summarizing the obtained results we conclude that the mechanochemical activation leads to a significant enhancement of the degree of oxidative degradation of the RB5 dye and photocatalytic activity of tested manganese ferrite-type of catalyst samples under our experimental conditions. The mechanochemically activated Mn0.5Fe2.5O4 ferrite-type of material displays the highest photocatalytic activity (15.2х10-3 min-1) and degree of oxidative degradation of the RB5 dye (92%) compared to the other synthesized samples. Especially a significant improvement in the degree of oxidative degradation of RB5 dye (91%) has been determined for mechanochemically treated MnFe2O4 ferrite-type of sample with the highest extent of substitution of iron ions by manganese ions than in the case of the co-precipitated MnFe2O4 sample (15%). The mechanochemically activated manganese ferrite-type of samples show good photocatalytic properties in the reaction of oxidative degradation of RB5 azo dye in aqueous solutions and it could find potential application for dye removal from wastewaters originating from textile industry.

Keywords: nanostructured manganese ferrite-type materials, photocatalytic activity, Reactive Black 5, water treatment

Procedia PDF Downloads 346

Authors: Reza Nematirad, Anil Pahwa, Balasubramaniam Natarajan

Abstract:

Time series data consist of successive data points collected over a period of time. Accurate prediction of future values is essential for informed decision-making in several real-world applications, including electricity load demand forecasting, lifetime estimation of industrial machinery, traffic planning, weather prediction, and the stock market. Due to their critical relevance and wide application, there has been considerable interest in time series forecasting in recent years. However, the proliferation of sensors and IoT devices, real-time monitoring systems, and high-frequency trading data introduce significant intricate temporal variations, rapid changes, noise, and non-linearities, making time series forecasting more challenging. Classical methods such as Autoregressive integrated moving average (ARIMA) and Exponential Smoothing aim to extract pre-defined temporal variations, such as trends and seasonality. While these methods are effective for capturing well-defined seasonal patterns and trends, they often struggle with more complex, non-linear patterns present in real-world time series data. In recent years, deep learning has made significant contributions to time series forecasting. Recurrent Neural Networks (RNNs) and their variants, such as Long short-term memory (LSTMs) and Gated Recurrent Units (GRUs), have been widely adopted for modeling sequential data. However, they often suffer from the locality, making it difficult to capture local trends and rapid fluctuations. Convolutional Neural Networks (CNNs), particularly Temporal Convolutional Networks (TCNs), leverage convolutional layers to capture temporal dependencies by applying convolutional filters along the temporal dimension. Despite their advantages, TCNs struggle with capturing relationships between distant time points due to the locality of one-dimensional convolution kernels. Transformers have revolutionized time series forecasting with their powerful attention mechanisms, effectively capturing long-term dependencies and relationships between distant time points. However, the attention mechanism may struggle to discern dependencies directly from scattered time points due to intricate temporal patterns. Lastly, Multi-Layer Perceptrons (MLPs) have also been employed, with models like N-BEATS and LightTS demonstrating success. Despite this, MLPs often face high volatility and computational complexity challenges in long-horizon forecasting. To address intricate temporal variations in time series data, this study introduces Times2D, a novel framework that parallelly integrates 2D spectrogram and derivative heatmap techniques. The spectrogram focuses on the frequency domain, capturing periodicity, while the derivative patterns emphasize the time domain, highlighting sharp fluctuations and turning points. This 2D transformation enables the utilization of powerful computer vision techniques to capture various intricate temporal variations. To evaluate the performance of Times2D, extensive experiments were conducted on standard time series datasets and compared with various state-of-the-art algorithms, including DLinear (2023), TimesNet (2023), Non-stationary Transformer (2022), PatchTST (2023), N-HiTS (2023), Crossformer (2023), MICN (2023), LightTS (2022), FEDformer (2022), FiLM (2022), SCINet (2022a), Autoformer (2021), and Informer (2021) under the same modeling conditions. The initial results demonstrated that Times2D achieves consistent state-of-the-art performance in both short-term and long-term forecasting tasks. Furthermore, the generality of the Times2D framework allows it to be applied to various tasks such as time series imputation, clustering, classification, and anomaly detection, offering potential benefits in any domain that involves sequential data analysis.

Keywords: derivative patterns, spectrogram, time series forecasting, times2D, 2D representation

Procedia PDF Downloads 41