Efficient Management Research Articles

LEVERAGING ARTIFICIAL INTELLIGENCE (AI) IN PUBLIC SECTOR FINANCIAL RISK MANAGEMENT: INNOVATIONS, CHALLENGES, AND FUTURE DIRECTIONS

This paper examines the transformative role of Artificial Intelligence (AI) in enhancing financial risk management practices within the public sector in different context. With the increasing complexity of financial markets and the growing demand for transparency and efficiency in public finance management, traditional methods of risk identification and mitigation are proving to be inadequate. AI and machine learning technologies offer a promising alternative, with their ability to process vast amounts of data, recognize patterns, and predict future trends with a high degree of accuracy. We delve into the application of predictive models for identifying various financial risks, including credit, market, liquidity, and operational risks, and explore how AI algorithms can optimize decision-making processes through scenario analysis, resource allocation, and policy impact analysis. The paper also addresses the challenges associated with integrating AI into public financial management systems, such as data privacy concerns, the need for skilled personnel, and the importance of developing regulatory frameworks that ensure ethical use and transparency. By presenting case studies and real-world applications, this study highlights both the successes and failures of AI implementations in the public sector, providing valuable lessons learned and best practices. As AI technologies continue to evolve, this paper underscores the need for ongoing research and adaptation to fully realize their potential in making public sector financial risk management more proactive, efficient, and resilient.

Causality-inspired crop pest recognition based on Decoupled Feature Learning.

Ensuring the efficient recognition and management of crop pests is crucial for maintaining the balance in global agricultural ecosystems and ecological harmony. Deep learning-based methods have shown promise in crop pest recognition. However, prevailing methods often fail to address a critical issue: biased pest training dataset distribution stemming from the tendency to collect images primarily in certain environmental contexts, such as paddy fields. This oversight hampers recognition accuracy when encountering pest images dissimilar to training samples, highlighting the need for a novel approach to overcome this limitation. We introduce the Decoupled Feature Learning (DFL) framework, leveraging causal inference techniques to handle training dataset bias. DFL manipulates the training data based on classification confidence to construct different training domains and employs center triplet loss for learning class-core features. The proposed DFL framework significantly boosts existing baseline models, attaining unprecedented recognition accuracies of 95.33%, 92.59%, and 74.86% on the Li, DFSPD, and IP102 datasets, respectively. Extensive testing on three pest datasets using standard baseline models demonstrates the superiority of DFL in pest recognition. The visualization results show that DFL encourages the baseline models to capture the class-core features. The proposed DFL marks a pivotal step in mitigating the issue of data distribution bias, enhancing the reliability of deep learning in agriculture. © 2024 Society of Chemical Industry.

Heuristic power management of hybrid source electric vehicle based on PV-battery-PEMFC

Renewable energy sources are now being focused on for usage in electric vehicles. Although majority of electric vehicles run solely on batteries, they have eliminated local emissions but not pollution. To tackle this issue, this research looks into the performance and power management aspects of an electric vehicle's hybrid power system, with a particular emphasis on the interactions between fuel cells, batteries, and photovoltaic (PV) cells. Stable operation is ensured via a bi-directional buck-boost converter, which maintains the voltage from all sources around reference 430 V. Initially, the fuel cell supplies electricity under low light conditions. The PV system and battery take over when the irradiance surpasses 100 W/m2, with the battery first draining and then charging in tandem with the increase in irradiance. 1750 RPM is the constant motor speed that is reached after making the required torque adjustments. A model full electric vehicle with multiple sources has been proposed with an efficient power management algorithm. When the battery is in stationary mode and the state of charge (SOC) is less than 100%, extra solar power is used to charge the battery. The model also takes into consideration using the car for entertainment or gadget charging when the ignition is off. The biogas output can be regulated using an inferential control technique using artificial neural network (ANN) based on the fuel demand or consumption. The system also includes anaerobic digestion of organic waste to provide hydrogen for the fuel cell sustainably from biogas. Power, current, SOC profiles, motor performance graphs, and other validations show that the extensive simulations exhibit efficient power management and a strong model for hybrid electric car power systems. The model has been simulated in the MATLAB Simulink environment and has been tested under realistic conditions.

Lagrangian relaxation-based approaches for cooperative location and assignment of emergency responders

Efficient fire response and the coordination of various fire vehicles are paramount for delivering optimal services and conducting effective rescue operations. This study explores the challenges of cooperative station location and vehicle assignment, focusing on the synergistic dispatch of fire vehicles from multiple stations. It highlights that the response time of the last arriving vehicle, crucial for forming a complete and effective response unit, is a critical determinant in the overall success of fire rescue operations. The primary objective of the model is to minimize the total system cost, encompassing both the capital investment in fire stations and the potential losses from fire incidents. By employing a Lagrangian relaxation technique, the model effectively simplifies the optimization challenge into more manageable sub-problems, thereby enhancing solution accuracy. The robustness and flexibility of the model were tested through simulations in a hypothetical network and a real-world scenario, using data from urban fire services. The results demonstrate the model’s scalability and adaptability to different network configurations and operational constraints, showcasing its potential to substantially enhance emergency response efficiency and decision-making in urban fire management. This research makes a significant contribution to emergency response management by providing a validated framework that improves the coordination and effectiveness of fire rescue operations, thereby reducing fire damage and enhancing public safety.

Optimization of Manning's roughness coefficient using 1-dimensional hydrodynamic modelling in the perennial river system: A case of lower Narmada Basin, India.

This research bears significant implications for river management, flood forecasting, and ecosystem preservation in the Lower Narmada Basin. A more precise estimation of Manning's Roughness Coefficeint (n) will enhance the accuracy of hydraulic models and facilitate informed decision-making regarding flood risk management, water resource allocation, and environmental conservation efforts. Ultimately, this study aspires to contribute to the sustainable management of perennial river systems in India and beyond by offering a robust methodology for optimizing Manning's n tailored to the complex hydrological dynamics of the Lower Narmada Basin. Through a synthesis of empirical evidence and computational modelling, it seeks to empower stakeholders with actionable insights toward preserving and enhancing these invaluable natural resources. Using the new HEC-RAS v 6.0, a one-dimensional hydrodynamic model was developed to predict overbank discharge at different points along the basin. The study analyzes water levels, stream discharges, and river stage, optimizing Manning's n and required flood risk management. The model predicted a strong output agreement with R2, NSE, and RMSE for the 2020 eventas 0.83, 0.81, and 0.36, respectively, with an optimum Manning's n of 0.03. The lower Narmada Basin part near the coastal zone (validation point) appears inundated frequently. The paper aims to provide insights into optimizing Manning's coefficient, which can ultimately lead to better water flow predictions and more efficient water management in the region.

Cultural rice fields in the wave of climate change: a multilateral evolutionary game framework for adaptive management of agricultural heritage systems

Agricultural Heritage Systems (AHS) are pivotal in preserving rich agricultural production experience and traditional culture, as well as in maintaining biodiversity and promoting sustainable development in agriculture and rural economies. However, climate change poses significant threats to these systems, such as ecological degradation, biodiversity loss, and shifts in agricultural production patterns. This study, grounded in theories of information asymmetry and bounded rationality, constructs evolutionary game models for adaptive management of AHS under market mechanisms and government guidance. By employing stability analysis and numerical simulation with Delay Differential Equations (DDE) that consider historical delays, and through sensitivity analysis, this research delves into the strategic evolutionary outcomes of stakeholders under various scenarios. It aims to provide theoretical insights and policy recommendations for the dynamic protection and adaptive management of AHS in the face of climate change. The findings indicate that the public goods nature of AHS, alongside externalities and information asymmetry, leads to market failure. Sole reliance on autonomous actions by farmers and meteorological departments is insufficient for optimal resource allocation and effective protection. Government intervention, through regulatory and incentive measures, can effectively mitigate market failures and steer adaptive management of AHS towards efficiency and sustainability. Moreover, the study identifies key factors for adaptive management, such as enhancing stakeholders’ initial willingness to participate, reducing the costs of adapting to climate change, optimizing cooperative benefit distribution mechanisms, and increasing the profitability of resource cooperation. Sensitivity analysis of government subsidies and penalty mechanisms further reveals the complex and critical role these policy tools play in fostering stakeholder engagement. Based on these findings, the study recommends enhancing initial participation willingness, controlling transformation costs to alleviate economic burdens, optimizing benefit distribution mechanisms to boost cooperative resource profitability, and establishing dynamic subsidy and penalty mechanisms for optimal resource allocation. The theoretical and practical contributions of this research lie in applying theories of information asymmetry and bounded rationality to the adaptive management of AHS under climate change, enriching the theoretical framework in this field, and providing scientific decision-making support for policymakers. By demonstrating an effective path for AHS protection through combined government and market mechanisms in the context of global climate change, this research holds significant theoretical and practical implications for enhancing the efficiency of adaptive management of AHS, protecting, and inheriting valuable agricultural cultural heritage.

Implementasi Kebijakan Kepegawaian Melalui Aplikasi Analisis Beban Kerja (E-ABK) Pada Kantor Kecamatan Bubutan Kota Surabaya

This study aims to analyze the implementation of personnel policies through Workload Analysis (E-ABK) at the Bubutan District office, Surabaya City. The research method used is qualitative descriptive with data collection through interviews, observations, and documentation. The results of the study show that there are several obstacles in the implementation of E-ABK, including the lack of effective communication between the Bubutan District office of Surabaya and the Organization Section of the Regional Secretariat of Surabaya, limited resources that there are still employees who have difficulty filling in supporting data, especially elderly employees, so there is a need for a mentoring role given to users of the E-ABK application, as well as the attitude and disposition of employees showing dissatisfaction in the use of the E-ABK application. In addition, the complex bureaucratic structure is also an obstacle in filling out E-ABK. To overcome these obstacles, it is recommended to increase communication and socialization regarding E-ABK, provide adequate resource support, provide motivation and appreciation to employees, simplify bureaucratic structure, and develop E-ABK. Better implementation is expected to increase the efficiency and effectiveness of employee workload management and achieve organizational goals more optimally.

Management of drug supply chain information based on “artificial intelligence + vendor managed inventory” in China: perspective based on a case study

ObjectivesTo employ a drug supply chain information system to optimize drug management practices, reducing costs and improving efficiency in financial and asset management.MethodsA digital artificial intelligence + vendor managed inventory (AI+VMI)-based system for drug supply chain information management in hospitals has been established. The system enables digitalization and intelligentization of purchasing plans, reconciliations, and consumption settlements while generating purchase, sales, inventory reports as well as various query reports. The indicators for evaluating the effectiveness before and after project implementation encompass drug loss reporting, inventory discrepancies, inter-hospital medication retrieval frequency, drug expenditure, and cloud pharmacy service utilization.ResultsThe successful implementation of this system has reduced the hospital inventory rate to approximately 20% and decreased the average annual inventory error rate from 0.425‰ to 0.025‰, significantly boosting drug supply chain efficiency by 42.4%. It has also minimized errors in drug application, allocation, and distribution while increasing adverse reaction reports. Drug management across multiple hospital districts has been standardized, leading to improved access to medicines and enhanced patient satisfaction.ConclusionThe AI+VMI system improves drug supply chain management by ensuring security, reducing costs, enhancing efficiency and safety of drug management, and elevating the professional competence and service level of pharmaceutical personnel.

Site Specific Nutrient Management (SSNM): Principles, Key Features and its Potential Role in Soil, Crop Ecosystem and Climate Resilience Farming

As the world population expands, farming practices have intensified to meet increased food demand. Modern crop varieties now require higher levels of fertilization compared to traditional organic methods, which are insufficient to meet these new demands. However, inefficient nutrient management and imbalances in field nutrient levels have led to various crop issues. To achieve higher agricultural output and productivity, there has been a notable increase in the application of chemical fertilizers, which unfortunately contributes to soil and water pollution, degradation of soil fertility, and nutrient imbalances. In response, modern technologies are being leveraged to promote sustainable food production and foster balanced agricultural development. Site specific nutrient management (SSNM) aims to empower farmers to adjust fertilizer application dynamically to meet the nutrient requirements of high-yielding crops, bridging the gap between natural nutrient sources like soil, crop residues, manure, and irrigation water. It is based on the principles of 4Rs: right product, right dose, right time and right place. Modern technologies like Optical sensors, Crop Manager, Remote Sensing, Nutrient Expert®, fertility mapping, Active Canopy Sensors, Variable rate technologies etc. are used to enhance the potential of SSNM to higher level. The focus is on optimizing nutrient application timing and rates to maximize crop yield and nutrient efficiency, thereby enhancing the economic value of harvest per unit of fertilizer used, rather than simply increasing or decreasing fertilizer use.

Empowering communication strategy for safe cyberspace: insights from trust-based quality information

Purpose The recent trends of managing how to achieve communication in a safe cyberspace have attracted the particular attention from scholars worldwide. The strategic initiative of having an active organization of communication pathways is required for further scholarly elaboration to enable a subsisting safe community in cyberspace. An example of the challenges is the issue of trust in information or questionable issues denoting lack of detail and clarity. Thus, this obviously refers to a dubious circumstance that needs to explain the situation on addressing the critical issue of trust-based quality information. To respond to such an apparent situation, this paper aims to critically explore the insightful value of trust in information as essential element of quality assurance. Such arranged strategy would enable individual capacity and accountability in achieving the efficient communication management for a safe cyberspace. Design/methodology/approach The study attempted a critical review of recent literature by analysing peer-reviewed articles from journals, books, proceedings and book chapters related to theme of communication management for safe cyberspace. Findings The finding reveals that the strategic approach of enabling effective communication management for safe cyberspace is actualized through advancing trust-based quality information. Originality/value This paper aims to contribute towards enhancing communication management for safe cyberspace by addressing issues relating to trust that would lead to the quality of information.

Understanding Carbon Footprint in Sustainable Land-Based Marine Aquaculture: Exploring Production Techniques

In aquaculture, it is crucial to understand and mitigate the carbon footprint for sustainable production. As demand for seafood increases, various production techniques compete for an eco-friendly status. This review examines the carbon footprint of various land-based marine aquaculture systems, highlighting their environmental impact. Through exploring innovations and best practices, it navigates the complexities of reducing emissions and promoting carbon sequestration. Some proposals for this purpose are based on diversification through low-trophic-level species, the preservation of high-carbon sequestration sites, polyculture, organic aquaculture and improvements in nutrition, feeding, waste and energy management. In this sense, some land-based aquaculture systems are progressively adapting and updating their zootechnical procedures. Recirculating Aquaculture Systems (RASs) offer interesting advantages such as water conservation, pollution reduction and biosecurity. Integrated Multi-Trophic Aquaculture systems (IMTAs) aim to address two major issues in aquaculture: efficient water usage and the environmental impact of effluents, which are rich in organic particles and dissolved nutrients from undigested food and feces; hence, these systems involve cultivating multiple species (polyculture). Biofloc Technology (BFT) is based on the formation of bioflocs in a culture medium. These systems can enhance feeding efficiency and waste management, thus optimizing nutrient utilization and minimizing environmental impact, achieved through reduced water and fertilizer usage. Traditional (extensive) aquaculture systems operate with minimal input of feed and chemicals, relying heavily on the natural productivity of the ecosystems; thus, the need for manufactured feed, the environmental impact associated with feed production and the transportation and overall costs are significantly reduced. Overall, while RASs, BFT and extensive systems in general offer significant sustainability benefits, IMTA’s holistic approach to ecosystem management and nutrient recycling makes it, in our estimation, the most effective method in terms of ecological footprint in aquaculture. However, its quantitative evaluation is extremely complex, and there is currently a lack of references about its global carbon footprint. Therefore, further research and development are required, as well as collaboration and knowledge-sharing among stakeholders.

Developing a smart forest protection mini program with Spring Boot: Integrating big data and image recognition technologies

Forests are essential for ecological stability yet pose significant management challenges due to their expansive and remote nature. Despite advancements in data acquisition, there is a lack of tools that effectively combine image recognition with big data analytics for real-time monitoring. This study introduces a "Smart Forest Protection" mini program, developed using Spring Boot, which integrates these technologies to facilitate immediate and efficient forest management. The program features intelligent plant recognition, user-driven incident reporting, waste recycling point displays, and a platform for disseminating forest conservation knowledge. Additionally, a big data visualization platform illustrates the spatiotemporal distribution of forests in Zhuhai, aiding governmental and environmental agencies in making informed decisions that enhance forest conservation and promote sustainable practices.

A systematic review on the role of nature-based solutions (NbS) in housing delivery in Africa

Purpose The study aims to examine the potential benefits of integrating nature-based solutions (NbS) in the housing sector. Design/methodology/approach The approach adopted was a systematic literature review aided by the Preferred Reporting Items for Systematic Reviews criteria and the VOSviewer software. Abductive reasoning was used to analyze the collected data, which was then subjected to content analysis through an iterative read-and-review procedure. Findings The study identified green walls, indoor greenery, porous pavement and landscaping, rainwater harvesting and water purification and green roofs as elements of buildings where NbS should be incorporated. Although nature-based research on integrated greenery facades and roof applications was noted, rainwater harvesting and water purification-oriented research remained dominant. These findings demonstrate the advantages of implementing NbS in the housing sector, including energy efficiency, environmental development, flood prevention and sustainable water management. Integrating NbS into housing designs can considerably contribute to the creation of more resilient, eco-friendly and comfortable living environments. However, the adoption of NbS faces hurdles, including a lack of awareness, limited policy support and economic constraints. Practical implications This study recommends that NbS be mainstreamed into housing development and knowledge exchange opportunities between sub-Saharan Africa and Europe, as well as other regions, to promote the adoption of NbS through research and collaborations. Also, it contributes to the discourse of sustainable affordable housing in the Global South while addressing United Nations Sustainable Development Goals 11, 12, 13 and 15. This study offers valuable guidance to stakeholders, thereby fostering the development of more sustainable and resilient housing practices and policies. Originality/value The study used VOSviewer software visualization to identify structural patterns and track prominent research frontiers, allowing for a more thorough yet concise mapping and capture of a scientific knowledge domain.

Sustainable Human Resource Management with a Focus on Corporate Employee Recruitment

Sustainability principles are becoming an integral part of all aspects of business operations, including human resource management (HRM). Despite extensive research in the field of sustainability, there is a lack of focus on sustainable practices in the recruitment process. This article aims to identify opportunities for sustainable HRM with a focus on the recruitment of new employees in a company. The authors defined three research questions using the PICO method and subsequently applied PRISMA, bibliometric analysis, and content analysis methods to address them. The result is a proposal for a sustainable recruitment model, illustrated using the Milky Way Map framework. The model highlights the key areas of recruitment that need to be considered to achieve sustainable management of the recruitment process. The research emphasizes the importance of implementing a sustainable approach to recruitment. Information systems/information technology (IS/IT) plays a crucial role in optimizing recruitment processes and reducing negative environmental, social, and economic impacts. The implementation of the proposed model can bring benefits such as more efficient talent management, cost reduction, and enhanced sustainability.

Do government resource management policies influence green productivity? New perspectives from fintech and digital resource policy in China

Achieving sustainable development necessitates the exploration of innovative approaches towards low-carbon development and efficient resource management. By adopting the low-carbon city pilot project as a policy shock of Government Resource Management Policies (GRMP), we aim to scrutinize the nuanced impacts of GRMP on green productivity (GTFP). Using the difference-in-difference (DID) approach and panel data from 280 cities in China. Our findings reveal a significant relationship between GRMP and GTFP. In the immediate short-term, GRMP exhibits a negative effect on GTFP growth, followed by a long-term positive promoting effect. A detailed temporal analysis uncovers an “inverted N″ time-period effect of GRMP on GTFP growth. Further exploration into the mechanisms driving this influence reveals three key aspects: the reduction of natural resources consumption and the promotion of low-carbon production (LCP), low-carbon transportation (LCT), and low-carbon industries (LCI). While the regulated effect of financial technology resources on the relationship between GRMP and GTFP is positive but statistically insignificant, the regulated effect of digital resource policy emerges as positive and significant. Additionally, the regulated effect of mineral and forest resource coverage rate is positive but not statistically significant in the context of the influence of GRMP on GTFP. This comprehensive analysis contributes to our understanding of the dynamic interplay between policy interventions, resource management, and sustainable development in the Chinese urban landscape.

Project Management Anal yses in a Poul try Farm: Critical Path Anal yses Approach

Abstract: This research work explored the application of Critical Path Analysis (CPA) in the production cycle of broiler chickens, aimed at identifying bottlenecks and inefficiencies that could be mitigated to enhance productivity and profitability. Broiler chicken production, a critical component of the global agricultural sector, demands efficient management of various stages, including breeding, hatching, growing, and processing, to meet the increasing demand for poultry meat. The research utilized CPA, a time-tested project management tool traditionally applied in construction and manufacturing industries, to map out the critical and non-critical activities within the broiler production cycle. By identifying the longest path through these sequential activities, the study highlighted the minimum time required for a complete production cycle and pinpointed stages where delays could extend overall production time. This approach allowed for the precise identification of bottlenecks that impede productivity, such as the brooding phase and health management practices, which are critical for ensuring the growth and survival of broiler chickens.

Analyzing the Negative Impact of Supply Chain Regionalization

In response to increasing global trade, IKEA implemented a more efficient supply chain strategy and introduced a new policy in 2011 to localize its supply chain. The objective of this inquiry was to examine the alterations in supply chain management. Following the transition from centralized to regionalized supply chains, corporations faced adverse consequences such as decreased operational efficiency, increased operating expenses, and reduced adaptability in meeting market needs. These implications include increased complexity in supply chain management, decentralized operating models that result in repeated investments in fixed assets, and trade restrictions that create challenges in integrating information. The article proposes implementing efficient management systems, enhancing collaboration with local suppliers, and utilizing artificial intelligence to optimize the structure of the supply chain based on the observed impacts and outcomes. The objective is to offer risk management guidance for firms that have reached maximum production capacity and require a shift in their supply chain management methods.

GIS-Based Analysis of Volatile Organic Compounds in Bucheon, Korea, Using Mobile Laboratory and Proton-Transfer-Reaction Time-of-Flight Mass Spectrometry Methods

Recently, volatile organic compounds (VOCs) have been shown to act as precursors of secondary organic particles that react with ultraviolet rays in the atmosphere and contribute to photochemical smog, global warming, odor, and human health risks, highlighting the importance of VOC management. In this study, we measured VOC concentrations in various contexts including industrial and residential areas of Bucheon, Korea, through mobile laboratory and proton-transfer-reaction time-of-flight mass spectrometry methods to determine winter VOC concentrations and visualized the data based on spatial information. Regional characteristics, temperature/humidity, atmospheric conditions, wind speed, traffic volume, etc., during the measurement period of the study site were comprehensively reviewed. For this purpose, global information system (GIS)-based air quality data and various environmental variables were comprehensively reviewed to assess spatial and temporal concentrations in three dimensions rather than in tables and graphs. Among VOCs, the levels of toluene, methanol, and n+i-butene were relatively high, with average concentrations of 48.3 ± 67.2, 34.4 ± 102.7, and 32.6 ± 57.7 ppb, respectively, at the end of the working day. The highest concentrations occurred near the Ojeong Industrial Complex. Mobile pollution sources are also a major driver of VOCs, highlighting the necessity of comprehensively reviewing traffic variables such as road level, estimated traffic volume, and average speed when identifying hotspots of air pollution. GIS-based visualization analysis techniques will improve the efficiency of air quality management.

Revolutionizing procurement processes in LNG operations: A synthesis of agile supply chain management using credit card facilities

Revolutionizing procurement processes in LNG operations is essential for ensuring efficient and cost-effective supply chain management. This paper presents a synthesis of agile supply chain management (SCM) principles using credit card facilities to streamline procurement processes in LNG operations. The integration of credit card facilities offers a flexible and efficient alternative to traditional procurement methods, enabling LNG companies to adapt quickly to changing market conditions and customer demands. The paper begins by discussing the challenges faced by LNG operations in traditional procurement processes, including lengthy approval processes, limited supplier options, and lack of transparency. It then introduces the concept of agile SCM and its principles, highlighting its potential to address these challenges and improve procurement efficiency. The synthesis of agile SCM principles with credit card facilities is explored in detail, focusing on how this approach can transform procurement processes in LNG operations. By utilizing credit card facilities, LNG companies can simplify the procurement process, reduce paperwork, and improve transaction speed. This approach also offers greater flexibility in supplier selection, allowing companies to quickly onboard new suppliers and respond to market changes. The paper also discusses the benefits of this approach, including cost savings, improved supplier relationships, and enhanced operational efficiency. Case studies and examples are provided to illustrate the application of agile SCM using credit card facilities in LNG operations. In conclusion, the synthesis of agile SCM principles with credit card facilities offers a transformative approach to procurement in LNG operations. By adopting this approach, LNG companies can enhance their competitive advantage, improve procurement efficiency, and drive overall operational excellence in the LNG industry. Keywords: Revolutionizing, Procurement Processes, LNG Operations, Credit Cards Facilities, Agile Supply Chain Management.

A novel optimized hybrid machine learning model to enhance the prediction accuracy of hourly building energy consumption

ABSTRACT Building energy consumption (BEC) prediction is crucial in efficient energy management. This paper proposes an optimized hybrid prediction model that combines a support vector regression (SVR), a newly evolved coati optimization algorithm (COA), and a recursive feature elimination with cross-validation (RFECV) implemented on an hourly new dataset. The SVR is selected based on the experimentations conducted in this work that outperform other models. The COA is used for optimizing the hyperparameters of SVR, and RFECV is used to optimize the dataset. The SVR COA performs better than the Harris hawk optimization and Gray wolf optimization. Later, the optimized SVR is implemented on the optimized dataset, showing better accuracy and faster prediction compared with the default SVR, SVR with feature elimination, and optimized SVR models. The error metrics MAE, MAPE, RMSE, and R2 are used for the model evaluation. The testing accuracy improved by 12.34%, 10.52%, 17.02%, and 0.09%, respectively, compared to the default model.