Trends In Historical Data Research Articles

Implementing Loss Prevention by Identifying Trends and Insights to Help Policyholders Mitigate Risks and Reduce Claims

Loss prevention is a critical focus for both insurers and policyholders, as rising claim volumes lead to increased premiums and financial losses. This paper explores the implementation of loss prevention strategies through the identification of trends and insights derived from historical data, predictive analytics, and emerging technologies. By leveraging these insights, insurers can recommend proactive risk mitigation measures to policyholders, reducing the occurrence of claims and overall risks. The study begins by analyzing historical data trends across various sectors such as auto, property, and health insurance, identifying key factors that drive claims. Predictive analytics is then applied to forecast future risks, allowing insurers to develop personalized strategies for mitigating those risks. Emerging technologies like Internet of Things (IoT) devices and artificial intelligence (AI) are highlighted for their role in providing real-time data and early warning systems, which help to prevent incidents before they escalate into claims. This paper also outlines practical loss prevention strategies for policyholders, such as installing smart home devices to monitor potential hazards, encouraging safe driving habits through telematics, and promoting health and wellness programs to lower medical claims. These risk mitigation strategies are shown to provide significant return on investment (ROI) for policyholders by reducing claims frequency and severity. Through case studies and data analysis, the paper demonstrates that proactive loss prevention not only benefits policyholders by lowering their risk exposure but also helps insurers reduce claims costs and enhance profitability. In conclusion, this research highlights the importance of trend identification, predictive analytics, and emerging technologies in the future of loss prevention, offering a path forward for insurers and policyholders to work collaboratively in mitigating risks.

Climate change adaptation strategies among smallholder farmers in Senegal’s semi-arid zone: role of socio-economic factors and institutional supports

In dryland agricultural systems, developing appropriate climate-smart technology (CST) options is important to adapt agriculture to climate change and transition toward sustainability, as well as increasing productivity and incomes. This study examines the impact of socio-economic and institutional support on community responses to climate change and the impact of changes in three selected regions of Senegal (Meouane, Thiel, and Daga Birame), which fall within different rainfall gradients. It captures community perceptions of climate change, compares them to long-term meteorological data, and identifies site-specific response strategies. Communities are randomly selected from a list of communities within the target sites. We used a two-stage stratified sampling method to select sample households. First, purposive sampling was conducted to select at least six (6) villages as a cluster within each rainfall gradient. Likewise, the selection of households in each cluster was based on the main value chains of crops grown in the study area, namely groundnut, millet, black pea, and livestock. A total of 145 households participated in this study. Data from surveys conducted during the 2022 post-harvest season were analyzed using descriptive statistics and logit models. The analysis found that smallholders have a comprehensive understanding of climate indicators, including annual rainfall, shortened crop seasons, and rising temperatures, compared to historical data trends. Additionally, the results highlight how farmers view the negative impacts of seasonal rainfall deficiencies (72%), delayed start of the growing season (88%), frequent dry spells (68%), and longer dry spells (76%), which ultimately lead to decreased grain and fodder yields. The logit model also highlights the importance of socio-economic and institutional factors such as access to credit, extension services, agricultural experience, frequency of interaction with extension workers, and access to government subsidies. These factors play a crucial role in farmers’ decision to adopt CST. Given the specificity of community contexts, these insights have important implications for guiding policymakers and making it easier to reduce climate risk among smallholder farmers.

SHAKF-PU: Sage-Husa Adaptive Kalman Filtering-Based Pedestrian Characteristic Parameter Update Mechanism for Enhancing Step Length Estimation in Pedestrian Dead Reckoning.

Step length estimation (SLE) is the core process for pedestrian dead reckoning (PDR) for indoor positioning. Original SLE requires accurate estimations of pedestrian characteristic parameter (PCP) by the linear update, which may cause large distance errors. To enhance SLE, this paper proposes the Sage-Husa adaptive Kalman filtering-based PCP update (SHAKF-PU) mechanism for enhancing SLE in PDR. SHAKF has the characteristic of predicting the trend of historical data; the estimated PCP is closer to the true value than the linear update. Since different kinds of pedestrians can influence the PCP estimation, adaptive PCP estimation is required. Compared with the classical Kalman filter, SHAKF updates its Q and R parameters in each update period so the estimated PCP can be more accurate than other existing methods. The experimental results show that SHAKF-PU reduces the error by 24.86% compared to the linear update, and thus, the SHAKF-PU enhances the indoor positioning accuracy for PDR.

Predicting Groundwater Level using Temporal Attention Enhanced Graph Neural Network

A revolutionary approach for groundwater management is essential. To predicting the water levels using for integrating IoT sensors, cloud computing, and advanced data analysis methods. IoT sensors are employed for real-time measurement of groundwater levels, creating a robust dataset. The paper focuses on predicting future groundwater levels, a crucial aspect of sustainable resource management. To enhance predictive accuracy, a preprocessing algorithm, such as Min-Max normalization, is introduced to clean and normalize the collected data, ensuring its reliability. Additionally, a feature extraction algorithm, such as Principal Component Analysis (PCA), is implemented to identify relevant patterns and trends within the dataset, enhancing the efficiency of subsequent analysis. A novel classification algorithm, Spatial-Temporal Graph Convolutional Network, is introduced, enabling the identification of potential groundwater recharge areas. This classification algorithm leverages historical data and extracted features to categorize regions based on their suitability for groundwater renewal. Finally, this research uses a Temporal attention-enhanced graph Neural Network machine learning algorithm to predict groundwater levels in the next few years. This algorithm utilizes the preprocessed data and extracted features, identifying intricate patterns and trends in historical data to generate precise predictions for groundwater levels in the upcoming years.

Web Server Based Data Monitoring System of PV Panels Using S7-1200 PLC

This This paper presents the design and implementation of a solar panel data monitoring system using a Web Server as a real-time operating system. The system is built via the Siemens S7-1200 Programmable Logic Controller (PLC) and programmed using TIA (Totally Integrated Automation) Portal V17 software. This approach enables real-time data collection and visualization of essential parameters such as voltage, current, power output, temperature, irradiance, and environmental conditions. The S7-1200 PLC serves as the central control unit, interfacing with the PV panels and gathering data. The acquired data is then transmitted to a web server, which hosts a user-friendly interface accessible through web browsers. Users can remotely monitor the performance of PV panels, track historical data trends, and receive alerts in case of anomalies. This web server-based system offers a convenient and efficient solution for effective PV panel management, enabling users to optimize energy production, detect issues promptly, and make informed decisions for maintenance and operational improvements.

A Comprehensive and Practical Method for Transformer Fault Analysis With Historical Data Trend Using Fuzzy Logic

Dissolved Gas Analysis (DGA) of transformer oil is an important tool to identify incipient faults of transformer. The challenge with the existing research on DGA is that only a single sample is used for the analysis which might lead to inaccurate results. In this paper a comprehensive three stages fuzzy logic approach is proposed to emulate best practices in the industry for transformer health analysis using the current as well as historical data from previous samples. In the first stage, a fuzzy logic is developed for an oil sampling pre-check for better lab acceptance rate which helps to save time and cost. In the second stage fuzzy, the latest IEEE Std C57.104 – 2019 is used to determine the status of transformer health by considering the gas formation rate from past samples and observing the trend. Finally, the third stage fuzzy is used to identify the transformer fault type and determine the corresponding down time. The proposed approach is tested on real data from the industry and the results demonstrate accurate transformer health identification with additional advantages of saving time and cost.

Crop Price Prediction

Abstract: In developing nations like India, where more than 33% of the population is in need, ensuring food profitability is a major problem. Estimates of crop yields for a given season are indisputably regarded as making a substantial contribution to investigating food accounting data and yield deficits. There is no structure in place to advise farmers on the best crops to cultivate, which would help with cost estimation. So, in this paper, we make an effort to forecast crop prices that a farmer can get from his field by looking at trends in historical data. For our analysis, we are taking a few crops like wheat, ragi, bajra, and barley. We are using a variety of information, including rainfall, previous crop yields, etc. We have implemented supervised machine learning algorithms (Decision Tree) to analyze and predict data.

Geophysical controls on metabolic cycling in three Patagonian fjords

Biogeochemical cycling in fjords underpins crucial environmental and economic functions including carbon sequestration and food security, and a fundamental understanding of the controls on these cycles is essential for sustainable management of fjords that are facing increasing climate and anthropogenic stressors. However, the interaction of external forcing and local geomorphology in fjords leads to complex coupling that is challenging to measure using traditional methods, particularly in a connected coastal system like the Chiloe Inland Sea (CIS) in northern Patagonia. This study resolves key functional differences between the three major fjords (Reloncaví, Comau and Reñihue) in the CIS using high-resolution sampling of surface waters integrated with regional oceanographic and meteorological observations, models and historic data. The dominant geophysical control varied among the three fjords: river input in Reloncaví Fjord, synoptic winds in Comau Fjord and tidal forcing in Reñihue Fjord. Variable geomorphic characteristics, e.g., orientation and the location of the riverine input, resulted in contrasting physical-metabolic responses between fjords to otherwise similar meteorological and oceanic forcing conditions. Each fjord’s relative location and degree of connectivity to the CIS influenced its internal metabolic balance over synoptic to seasonal scales. In Comau Fjord, the salt fingering form of double diffusive mixing was linked to vertical density structure and wind forcing in the northern CIS; consistent trends in historical data suggest that salt fingering may be an important mechanism for delivery of nutrients to the euphotic zone. The highest metabolic rates in the study region occurred in Reñihue Fjord and were linked to vertical mixing of nutrient-rich waters to the surface in the central CIS. Climate change is predicted to result in decreasing river discharge and weakening zonal winds in northern Patagonia. Therefore, the functional relationships observed in this study imply-two key impacts of these altered forcing conditions in coming decades: 1) a lateral shift in the transfer of planktonic carbon to coastal sediments, i.e., moving landward from the CIS into fjords, and 2) greater biogeochemical variability in fjord surface waters, which will present greater management challenges for aquaculture.

Autoencoding Conditional GAN for Portfolio Allocation Diversification

Over the decades, the Markowitz framework has been used extensively in portfolio analysis though it puts too much emphasis on the analysis of the market uncertainty rather than on the trend prediction. While generative adversarial network (GAN) and conditional GAN (CGAN) have been explored to generate financial time series and extract features that can help portfolio analysis. The limitation of the CGAN framework stands in putting too much emphasis on generating series rather than keeping features that can help this generator. In this paper, we introduce an autoencoding CGAN (ACGAN) based on deep generative models that learns the internal trend of historical data while modeling market uncertainty and future trends. We evaluate the model on several real-world datasets from both the US and Europe markets, and show that the proposed ACGAN model leads to better portfolio allocation and generates series that are closer to true data compared to the existing Markowitz and CGAN approaches.

Parameter Identification in Power Transmission Systems Based on Graph Convolution Network

Parameter Identification plays an important role in electric power transmission systems. Existing approaches for parameter identification tasks typically have two limitations: (1) They generally ignored development trend of historical data, and did not mine characteristics of corresponding power grid branches. (2) They did not consider the constraints of power grid topology, and treated different branches independently. Therefore, they could not characterize correlations between the center node and its neighborhoods. To overcome these limitations, this work proposes a multi-task graph convolutional neural network (MT-GCN) which utilizes the graph convolutional network (GCN) and the fully convolutional network (FCN) as building blocks for parameter identification. Specially, GCN can extract the structure information to enhance local feature extraction. FCN is a decoding module following GCN module, and it is used to identify the parameters of each branch according to its characteristics. Compared with previous methods, the proposed method is significantly improved in accuracy. Besides, this method is robust to measurement noise and errors, and can cope with multiple conditions in real power transmission systems.

Simulation of future climate scenarios and the impact on the water availability in southern Brazil

Water is an essential natural resource that is being impacted by climate change. Thus, knowledge of future water availability conditions around the globe becomes necessary. Based on that, this study aimed to simulate future climate scenarios and evaluate the impact on water balance in southern Brazil. Daily data of rainfall and air temperature (maximum and minimum) were used. The meteorological data were collected in 28 locations over 30 years (1980-2009). For the data simulation, we used the climate data stochastic generator PGECLIMA_R. It was considered two scenarios of the fifth report of the Intergovernmental Panel on Climate Change (IPCC) and a scenario with the historical data trend. The water balance estimates were performed for the current data and the simulated data, through the methodology of Thornthwaite and Mather (1955). The moisture indexes were spatialized by the kriging method. These indexes were chosen as the parameters to represent the water conditions in different situations. The region assessed presented a high variability in water availability among locations; however, it did not present high water deficiency values, even with climate change. Overall, it was observed a reduction of moisture index in most sites and in all scenarios assessed, especially in the northern region when compared to the other regions. The second scenario of the IPCC (the worst situation) promoting higher reductions and dry conditions for the 2099 year. The impacts of climate change on water availability, identified in this study, can affect the general society, therefore, they must be considered in the planning and management of water resources, especially in the regional context

Research on the Fastest Detection Method for Weak Trends under Noise Interference.

Trend anomaly detection is the practice of comparing and analyzing current and historical data trends to detect real-time abnormalities in online industrial data-streams. It has the advantages of tracking a concept drift automatically and predicting trend changes in the shortest time, making it important both for algorithmic research and industry. However, industrial data streams contain considerable noise that interferes with detecting weak anomalies. In this paper, the fastest detection algorithm “sliding nesting” is adopted. It is based on calculating the data weight in each window by applying variable weights, while maintaining the method of trend-effective integration accumulation. The new algorithm changes the traditional calculation method of the trend anomaly detection score, which calculates the score in a short window. This algorithm, SNWFD–DS, can detect weak trend abnormalities in the presence of noise interference. Compared with other methods, it has significant advantages. An on-site oil drilling data test shows that this method can significantly reduce delays compared with other methods and can improve the detection accuracy of weak trend anomalies under noise interference.

Predicting Rainfall from Historical Data Trends

Weather forecasting is and has been an attempt by meteorologists to predict the weather conditions with previous data trends recorded from the past.The weather forecasting is very important in countries like India where majority of the economy is dependent on agriculture. Rainfall prediction is the main factor we are studying and implementing here. Few algorithms used for rainfall prediction are LSTM, Genetic Algorithms and GRU, these are computer aided rule-based algorithms. In this paper, we performed qualitative analysis using GRU (Gated Recurrent Unit) algorithm.The GRU is the newer generation of Recurrent Neural networks and is pretty similar to an LSTM. GRU is also known to give accurate results and it is also good for processing sequence data for predictions.

Demand Forecasting Approaches Based on Associated Relationships for Multiple Products

As product variety is an important feature for modern enterprises, multi-product demand forecasting is essential to support order decision-making and inventory management. However, these well-established forecasting approaches for multi-dimensional time series, such as Vector Autoregression (VAR) or dynamic factor model (DFM), all cannot deal very well with time series with high or ultra-high dimensionality, especially when the time series are short. Considering that besides the demand trends in historical data, that of associated products (including highly correlated ones or ones having significantly causality) can also provide rich information for prediction, we propose new forecasting approaches for multiple products in this study. The demand of associated products is treated as predictors to add in AR model to improve its prediction accuracy. If there are many time series associated with the object, we introduce two schemes to simplify variables to avoid over-fitting. Then procurement data from a grid company in China is applied to test forecasting performance of the proposed approaches. The empirical results reveal that compared with four conventional models, namely single exponential smoothing (SES), autoregression (AR), VAR and DFM respectively, the new approaches perform better in terms of forecasting errors and inventory simulation performance. They can provide more effective guidance for actual operational activities.

Ensemble forecast and parameter inference of childhood diarrhea in Chobe District, Botswana

Diarrheal disease is the second largest cause of mortality in children younger than 5, yet our ability to anticipate and prepare for outbreaks remains limited. Here, we develop and test an epidemiological forecast model for childhood diarrheal disease in Chobe District, Botswana. Our prediction system uses a compartmental susceptible-infected-recovered-susceptible (SIRS) model coupled with Bayesian data assimilation to infer relevant epidemiological parameter values and generate retrospective forecasts. Our model inferred two system parameters and accurately simulated weekly observed diarrhea cases from 2007-2017. Accurate retrospective forecasts for diarrhea outbreaks were generated up to six weeks before the predicted peak of the outbreak, and accuracy increased over the progression of the outbreak. Many forecasts generated by our model system were more accurate than predictions made using only historical data trends. Accurate real-time forecasts have the potential to increase local preparedness for coming outbreaks through improved resource allocation and healthcare worker distribution.

Research of Building the Monitoring System of Cleaning in Place Applying MCGS

Cleaning In-place (CIP) system is a set of technical systems including cleaning main unit and software technology. The paper is introduced with the technical scheme of real-time process monitoring system using for CIP; designed by the hardware configuration of signal acquisition, signal transformation and data control in monitoring system; used MCGS to realize with the monitoring and controlling configuration design of central computer, real-time database build and peripheral device driver, monitoring parameters scale transforming, data acquisition module design, and cleaning process control program design, then ,the man-machine interface is achieved, real-time process animation is displayed, automatic and real-time monitoring the CIP process, real-time data browsing and preservation, as well as real-time and historical data trend is displayed and report output functions.

On the Need for Cognitive Closure and Judgmental Trend Forecasting

The paper considers the following hypothesis: humans’ need for cognitive closure reduces the usage of historical observations in judgmental forecasts only in horizontal trends. To test this hypothesis, three studies were conducted. In each, participants forecasted the next, unknown observation using the previous time series. The analysis concentrated on trend analysis and how the trends in historical data are used as the basis for forecasting depending on psychological traits, in particular cognitive closure.

Statistical Adjustment Module Advanced Optimizer Planner and SAP Generated the Case of a Food Production Company

Objectives: An analysis of forecast system SAP-APO of a company producing food demand is made Methods/Statistical analysis: redefining the parameters of statistical models l module demand for SAP-APO, change the statistical model adaptive average seasonality and trend of historical data and categorize products according segmentation analysis to assign a different range of tolerance to each when comparing their demand forecasts with sales in recent months. Findings: After implementation the percentage improvement product to manually adjust decreased by 12.58%, compared to the previous level of attention. Application/Improvements: This decreased attention, resulting in an increase in the utility system more than 85%.

How sales manager experience and historical data trends affect decision making

Purpose– The purpose of this study is to examine how trends in historical data influence two types of predictive judgments: territory selection and salesperson hiring. Sales managers are confronted frequently with decisions that explicitly or implicitly involve forecasting with limited information. In doing so, they conceptualize how the magnitude of these trend effects may be affected by the experience managers have in making these types of judgments. Study 1 provides evidence of a curvilinear relationship between experience and reliance on the trend data whereby the sales territory selections of novice sales managers exhibited greater susceptibility to informational trends than did the evaluations of naïve and expert decision-makers. A benchmark analysis in Study 2 further revealed that the salesperson selections made by novice and expert sales managers were equally biased, albeit in opposite directions, with novices overweighting and experts underweighting historical performance trends. Implications of these findings are discussed, as are avenues for future research.Design/methodology/approach– The authors employ an online experimental design methodology of practicing managers. For Study 1, they use regression, whereas Study 2 uses a deterministic process to develop a priori predictive benchmark forecasts. Ordinary least squares is then used to estimate manager’s decisions, which are then compared to the predictive forecasts to determine accuracy.Findings– Study 1 provides evidence of a curvilinear relationship between experience and reliance on the trend data whereby the sales territory selections of novice sales managers exhibited greater susceptibility to informational trends than did the evaluations of naïve and expert decision-makers. A benchmark analysis in Study 2 further revealed that the salesperson selections made by novice and expert sales managers were equally biased, albeit in opposite directions, with novices overweighting and experts underweighting historical performance trends.Originality/value– The present inquiry is the first to provide insights into an important issue that has been the subject of equivocal findings, namely, whether experience in a judgmental domain exerts a facilitating or debilitating effect on sales manager decision-making. In this regard, some research supports the intuition that experience in making a particular type of decision can insulate managers from judgmental bias and, in doing so, improve decision quality (see Shanteau, [1992a] for a summary). In contrast, other work provides a more pessimistic view by demonstrating that the quality of decision-making is either unaffected by or can erode with additional experience (Hutchinsonet al., 2010). To help reconcile these conflicting findings, the authors presented and tested a theoretical framework conceptualizing how trends may influence predictive judgments across three levels of decision-maker experience.

Development of a Statistical Methodology for Gas Turbine Prognostics

To optimize both production and maintenance, from both a technical and an economical point of view, it would be advisable to predict the future health condition of a system and of its components, starting from field measurements taken in the past. For this purpose, this paper presents a methodology, based on the Monte Carlo statistical method, which aims to determine the future operating state of a gas turbine. The methodology allows the system future availability to be estimated, to support a prognostic process based on past historical data trends. One of the most innovative features is that the prognostic methodology can be applied to both global and local performance parameters, as, for instance, machine specific fuel consumption or local temperatures. First, the theoretical background for developing the prognostic methodology is outlined. Then, the procedure for implementing the methodology is developed and a simulation model is set up. Finally, different degradation-over-time scenarios for a gas turbine are simulated and a sensitivity analysis on methodology response is carried out, to assess the capability and the reliability of the prognostic methodology. The methodology proves robust and reliable, with a prediction error lower than 2%, for the availability associated with the next future data trend.