دانلود و نمایش مقالات مرتبط با forecasting::صفحه 1
دانلود بهترین مقالات isi همراه با ترجمه فارسی 2

با سلام خدمت کاربران در صورتی که با خطای سیستم پرداخت بانکی مواجه شدید از طریق کارت به کارت (6037997535328901 بانک ملی ناصر خنجری ) مقاله خود را دریافت کنید (تا مشکل رفع گردد). 

نتیجه جستجو - forecasting

تعداد مقالات یافته شده: 206
ردیف عنوان نوع
1 A combined real-time intelligent fire detection and forecasting approach through cameras based on computer vision method
یک رویکرد تشخیص و پیش‌بینی حریق هوشمند ترکیبی در زمان واقعی از طریق دوربین‌ها بر اساس روش بینایی کامپیوتری-2022
Fire is one of the most common hazards in the process industry. Until today, most fire alarms have had very limited functionality. Normally, only a simple alarm is triggered without any specific information about the fire circumstances provided, not to mention fire forecasting. In this paper, a combined real-time intelligent fire detection and forecasting approach through cameras is discussed with extracting and predicting fire development characteristics. Three parameters (fire spread position, fire spread speed and flame width) are used to charac- terize the fire development. Two neural networks are established, i.e., the Region-Convolutional Neural Network (RCNN) for fire characteristic extraction through fire detection and the Residual Network (ResNet) for fire forecasting. By designing 12 sets of cable fire experiments with different fire developing conditions, the accu- racies of fire parameters extraction and forecasting are evaluated. Results show that the mean relative error (MRE) of extraction by RCNN for the three parameters are around 4–13%, 6–20% and 11–37%, respectively. Meanwhile, the MRE of forecasting by ResNet for the three parameters are around 4–13%, 11–33% and 12–48%, respectively. It confirms that the proposed approach can provide a feasible solution for quantifying fire devel- opment and improve industrial fire safety, e.g., forecasting the fire development trends, assessing the severity of accidents, estimating the accident losses in real time and guiding the fire fighting and rescue tactics.
keywords: ایمنی آتش سوزی صنعتی | تشخیص حریق | پیش بینی آتش سوزی | تجزیه و تحلیل آتش سوزی | هوش مصنوعی | Industrial fire safety | Fire detection | Fire forecasting | Fire analysis | Artificial intelligence
مقاله انگلیسی
2 A deep learning-based cow behavior recognition scheme for improving cattle behavior modeling in smart farming
طرح شناخت رفتار گاو مبتنی بر یادگیری عمیق برای بهبود مدل‌سازی رفتار گاو در کشاورزی هوشمند-2022
Farming and animal husbandry applications are improvised with the implication of machine learning and artificial intelligence in recent years. The precise estimation, recommendations, and performances are the prime reason for the technology implication. Owing to the modern agri- cultural and animal cultures, this article introduces an innovative Behavior Recognition and Computation Scheme (BRCS) for predicting cow behaviors. The information from the swallowed microchip is processed based on the observed animal action that is used for the forecast. Considering the information to be rectilinear, the distractions and distribution patterns (data) are augmented in identifying and forecasting its behavior. The proposed scheme identifies the pat- terns using a deep recurrent learning paradigm recurrently. This pattern is distinguished for idle and non-idle observations for improving the prediction accuracy. Distinguished data patterns are mapped for the consecutive time and observation data in classifying abnormalities. The proposed scheme’s performance is validated using the metrics accuracy, precision, computing time, and mean error.
keywords: رفتار گاو | تحلیل داده ها | یادگیری عمیق | تشخیص الگو | Cow behavior | Data analysis | Deep learning | Pattern recognition
مقاله انگلیسی
3 Federated learning with hyperparameter-based clustering for electrical load forecasting
یادگیری فدرال با خوشه‌بندی مبتنی بر فراپارامتر برای پیش‌بینی بار الکتریکی-2022
Electrical load prediction has become an integral part of power system operation. Deep learning models have found popularity for this purpose. However, to achieve a desired prediction accuracy, they require huge amounts of data for training. Sharing electricity consumption data of individual households for load prediction may compromise user privacy and can be expensive in terms of communication resources. Therefore, edge computing methods, such as federated learning, are gaining more importance for this purpose. These methods can take advantage of the data without centrally storing it. This paper evaluates the performance of federated learning for short-term forecasting of individual house loads as well as the aggregate load. It discusses the advantages and disadvantages of this method by comparing it to centralized and local learning schemes. Moreover, a new client clustering method is proposed to reduce the convergence time of federated learning. The results show that federated learning has a good performance with a minimum root mean squared error (RMSE) of 0.117 kWh for individual load forecasting.
Keywords: Federated learning | Electricity load forecasting | Edge computing | LSTM | Decentralized learning
مقاله انگلیسی
4 The importance of accounting-integrated information systems for realising productivity and sustainability in the agricultural sector
اهمیت سیستم های اطلاعاتی حسابداری یکپارچه برای تحقق بهره وری و پایداری در بخش کشاورزی-2021
Agricultural information systems are an integral part of modern farming and are helping to make a significant contribution to improved farm productivity and profitability. To date, however, there has been a failure to integrate accounting information systems with onfarm data, despite today’s farmers facing unprecedented and interconnected economic and resource pressures. This study explores this problem in more detail, defines the objectives of the solution and develops a model of integrated accounting and agricultural information systems, drawing on a ‘fads and fashions’ framework and advancing our understanding of bundled innovations. Using data from a participatory case study in Australian potato farming, the study integrates accounting data with soil moisture and climate data to track, alert and inform irrigation decisions. Development of preliminary digital software based on the model demonstrates how cost-informed tracking, alerts and forecasting can be supported by bundling accounting information systems and sensing technology. In doing so, the model extends the fads and fashions framework for agricultural information systems and demonstrates how accounting information can be the key for improved water productivity, profitability and agricultural sustainability.
keywords: تصمیم گیری کشاورزی | سیستم های حسابداری یکپارچه | نوآوری های همراه | سنسور | اطلاعات دیجیتال | ایستگاه های آب و هوا | تصویربرداری ماهواره ای | Agricultural decision-making | Integrated accounting systems | Bundled innovations | Sensors | Digital information | Weather stations | Satellite imagery
مقاله انگلیسی
5 Cultural consensus knowledge of rice farmers for climate risk management in the Philippines
دانش اجماع فرهنگی کشاورزان برنج برای مدیریت ریسک آب و هوایی در فیلیپین-2021
Despite efforts and investments to integrate weather and climate knowledges, often dichotomized into the scientific and the local, a top-down practice of science communication that tends to ignore cultural consensus knowledge still prevails. This paper presents an empirical application of cultural consensus analysis for climate risk management. It uses mixed methods such as focus groups, freelisting, pilesorting, and rapid ethnographic assessment to understand farmers’ knowledge of weather and climate conditions in Barangay Biga, Oriental Mindoro, Philippines. Multi-dimensional scaling and aggregate proximity matrix of items are generated to assess the similarity among the different locally perceived weather and climate conditions. Farmers’ knowledge is then qualitatively compared with the technical classification from the government’s weather bureau. There is cultural agreement among farmers that the weather and climate con- ditions can be generally grouped into wet, dry, and unpredictable weather (Maria Loka). Damaging hazards belong into two subgroups on the opposite ends of the wet and dry scale, that is, tropical cyclone is grouped together with La Ni˜na, rainy season, and flooding season, while farmers perceive no significant difference between El Ni˜no, drought, and dry spells. Ethnographic information reveals that compared to the technocrats’ reductive knowledge, farmers imagine weather and climate conditions (panahon) as an event or a phenomenon they are actively experiencing by observing bioindicators, making sense of the interactions between the sky and the landscape, and the agroecology of pest and diseases, while being subjected to agricultural regulations on irrigation, price volatility, and control of power on subsidies and technologies. This situated local knowledge is also being informed by forecasts and advisories from the weather bureau illustrating a hybrid of technical science, both from the technocrats and the farmers, and personal experiences amidst agricultural precarities. Speaking about the hybridity of knowledge rather than localizing the scientific obliges technocrats and scientists to productively engage with different ways of knowing and the tensions that mediate farmers’ knowledge as a societal experience.
keywords: دانش اجماع | پیش بینی آب و هوا | کشاورزی | خطر ابتلا به آب و هوا | Consensus knowledge | Weather forecasting | Agriculture | Climate risk
مقاله انگلیسی
6 Accounting for cross-immunity can improve forecast accuracy during influenza epidemics
حسابداری برای مصونیت متقابل می تواند دقت پیش بینی را در طول اپیدمی های آنفلوانزا بهبود بخشد-2021
Previous exposure to influenza viruses confers cross-immunity against future infections with related strains. However, this is not always accounted for explicitly in mathematical models used for forecasting during influenza outbreaks. We show that, if an influenza outbreak is due to a strain that is similar to one that has emerged previously, then accounting for cross-immunity explicitly can improve the accuracy of real-time forecasts. To do this, we consider two infectious disease outbreak forecasting models. In the first (the ‘‘1-group model’’), all individuals are assumed to be identical and cross-immunity is not accounted for. In the second (the ‘‘2-group model’’), individuals who have previously been infected by a related strain are assumed to be less likely to experience severe disease, and therefore recover more quickly, than immunologically naive individuals. We fit both models to estimated case notification data (including symptomatic individuals as well as laboratory-confirmed cases) from Japan from the 2009 H1N1 influenza pandemic, and then generate synthetic data for a future outbreak by assuming that the 2-group model represents the epidemiology of influenza infections more accurately. We use the 1-group model (as well as the 2-group model for comparison) to generate forecasts that would be obtained in real-time as the future outbreak is ongoing, using parameter values estimated from the 2009 epidemic as informative priors, motivated by the fact that without using prior information from 2009, the forecasts are highly uncertain. In the scenario that we consider, the 1-group model only produces accurate outbreak forecasts once the peak of the epidemic has passed, even when the values of important epidemiological parameters such as the lengths of the mean incubation and infectious periods are known exactly. As a result, it is necessary to use the more epidemiologically realistic 2-group model to generate accurate forecasts. Accounting for cross-immunity driven by exposures in previous outbreaks explicitly is expected to improve the accuracy of epidemiological modelling forecasts during influenza outbreaks.
keywords: مدلسازی ریاضی | پیش بینی آنفلوانزا | Real-timeForecast | مصونیت متقابل | 2009 H1N1 پاندمی | Mathematicalmodelling | Influenzaforecasting | Real-timeforecast | Cross-immunity | 2009H1N1pandemic
مقاله انگلیسی
7 Application of green supply chain management in the oil Industries: Modeling and performance analysis
کاربرد مدیریت زنجیره تامین سبز در صنایع نفت: مدل سازی و تحلیل عملکرد-2021
Environmental concerns relating to production affairs have made various organizations use green practices in different processes of supply chain, because the green supply chain management (GSCM) is considered as an important organizational philosophy to decrease environmental risks and as a preventive approach in order to increase environmental performance and achievement of competitive advantages for organizations. The purpose of the present article is to design an interactive model for the practices of GSCM and its application to clustering oil industries for analyzing their green performance. Therefore, the literature was studied and a total of fifteen practices were obtained using experts’ opinions in academic and oil industry professionals. In next, the fuzzy interpretative structural modeling (FISM) approach was utilized so as to determine the relationship between the practices through considering the linguistic ambiguities of judgments and designing the structural model. The existing relationships within the structural model were studied and tested by means of structural equation modeling (SEM). After that, the relative importance of each practice was calculated by applying fuzzy analysis network process (FANP). In the next, the oil industries were categorized in two clusters using the K-means algorithm aggregated to the particle swarm optimization algorithm. Results of the present study showed that ‘‘legal requirements and regulations”, ‘‘intra-organizational environmental management”, ‘‘green design” and ‘‘green technology” are of root and influential practices with relatively more importance than others; in addition, it was cleared that the first cluster industries have high performance whereas the second ones have medium performance from the viewpoint of considering the practices of GSCM. Finally, the discriminant function designed to forecasting environment performance of the oil industries and member- ship to clusters for each of them.© 2021 Elsevier Ltd. All rights reserved. Selection and peer-review under responsibility of the scientific committee of the Web International Conference on Accelerating Innovations in Material Science – 2020.
Keywords: Green Supply Chain Management | Oil industries | Fuzzy interpretative structural modeling | Kmeans | Particle swarm optimization | Clustering | Discriminant analysis
مقاله انگلیسی
8 Modelling corporate bank accounts
مدل سازی حساب های بانکی شرکت ها-2021
We discuss the modelling of corporate bank accounts using a proprietary dataset. We thus offer a principled treatment of a genuine industrial problem. The corporate bank accounts in our study constitute spare, irregularly-spaced time series that may take both positive and negative values. We thus builds on previous models where the underlying is real-valued. We describe an intra-monthly effect identified by practitioners whereby account uncertainty is typically lowest at the beginning and end of each month and highest in the middle. However, our theory also allows for the opposite effect to occur. In-sample applications demonstrate the statistical significance of the hypothesized monthly effect. Out-of-sample forecasting applications offer a 9% improvement compared to a standard SARIMA approach.
keywords: حساب های بانکی شرکت | فناوری | پیش بینی برنامه های کاربردی | یادگیری ماشین | Corporate bank accounts | Fin Tech | Forecasting applications | Machine learning
مقاله انگلیسی
9 Organic-waste-derived butyric acid-to-biodiesel supply-chain network: Strategic planning design using a deterministic snapshot model
شبکه زنجیره تامین اسید بوتیریک اسید به بیودیزل مشتق شده از مواد آلی: طراحی برنامه ریزی استراتژیک با استفاده از یک مدل عکس فوری قطعی-2021
An integrated optimization model for an organic-waste-derived butyric acid-to-butanol supply-chain network (BABSCN) is proposed to minimize the total network cost by simultaneously optimizing both strategic biodiesel production and waste management planning decisions. This model is useful for ensuring effective organic-waste provision for large-scale biodiesel production and waste management. The proposed mixed-integer linear-pro- gramming model optimizes the activities ranging from organic-waste preprocessing to butyric acid (BA), transportation of BA to biorefinery, butanol (BuOH) production and mixing with diesel to the distribution of biodiesel. This model is useful for forecasting organic-waste management biodiesel supply chains in South Korea in 2030. The case study results show that a total network cost of $US 3.16/gallon of B3 contains 3% BuOH from organic waste products combined with diesel. The biorefinery-related cost accounts for 98.3% of the total network cost, followed by the organic waste procurement cost (1.1%) and biodiesel distribution cost (0.6%). A scenario-based analysis shows that a 7%-BuOH increase in biodiesel increases the total network cost by 18.8%.
Keywords: Strategic planning | Supply chain | Organic waste | Biodiesel | Optimization | Cost
مقاله انگلیسی
10 Aggregate accounting research and development expenditures and the prediction of real gross domestic product
مجموع هزینه های تحقیق و توسعه حسابداری جمع آوری شده و پیش بینی تولید ناخالص داخلی واقعی-2021
The role of accounting information for public policy making has received increased attention in recent years. Konchitchki and Patatoukas (2014a,b) demonstrate that growth in aggregate accounting earnings can predict future growth in nominal and real Gross Domestic Product (GDP). We extend the micro to macro literature by decomposing earnings into the R&D and pre-R&D components. Using the Almon (1965) finite distributed lag model, we find that both components can predict future real GDP growth with different lead-lag structures. Importantly, this decomposition significantly increases the explanatory power of the predictive model using accounting information. Aggregate accounting R&D can predict real GDP through the personal consumption, business investment, and net export channels of GDP. Our study extends prior research on the forecasting usefulness of accounting information at the aggregate level and has practical implications for macro forecasting and for public policy making regarding innovative activities of publicly listed firms.
keywords: مجموع اعداد حسابداری | هزینه های تحقیق و توسعه | تولید ناخالص داخلی | پیش بینی کلان اقتصادی | ساختارهای تاخیری توزیع شده | Aggregate accounting numbers | Research and development expenditures | Gross domestic product | Macroeconomic forecasting | Distributed lag structures
مقاله انگلیسی
rss مقالات ترجمه شده rss مقالات انگلیسی rss کتاب های انگلیسی rss مقالات آموزشی
logo-samandehi
بازدید امروز: 3004 :::::::: بازدید دیروز: 0 :::::::: بازدید کل: 3004 :::::::: افراد آنلاین: 68