Time Series Graphs Research Articles

Implementing the Color Wheel System in an Inclusive Middle School Setting

The Color Wheel System (CWS), a class-wide, rule-based behavioral management strategy, is a successful intervention to reduce off-task behaviors for elementary school students. However, this intervention has rarely been investigated in the middle school setting. The current study implemented the CWS within three sixth-grade general education inclusionary classrooms in a middle school in the United States. A multiple-baseline across classrooms design evaluated the effects of the CWS on class-wide inappropriate vocalizations. Partial-interval time-sampling recorded intervals when any student in the class displayed inappropriate vocalizations. Visual analysis of time-series graphs and effect size measures indicated that the CWS created large, immediate, and sustained decreases in inappropriate vocalizations across all classrooms. Implications for using the CWS as a class-wide behavioral management strategy within the middle school setting and directions for future research are discussed.

Assessment of agroclimatic resources in agricultural landscapes of the Turkestan region of the Republic of Kazakhstan Askha

The article presents the scientific results of a study assessing agroclimatic resources in agricultural landscapes located in various natural zones of the Turkestan region of the RK (Republic of Kazakhstan). The research methods included classical and modern methods of mathematical statistics using digital technology and time series graphs to develop a mathematical model for climatic and hydrological indicators. Assessment of changes in indicators of agroclimatic resources in agricultural landscapes for 1941–2020 showed that the sum of air temperature, evaporation from the water surface and radiation balance of the daytime surface, characterising the energy resources of landscapes, increased by 10–15%, which contributes to increase in the total water consumption of agricultural land by 10–12%. Meanwhile, the decreasing tendency of the amount of precipitation by 5–10% in all natural climatic zones of the region has become one of the factors leading to a decrease in the natural moisture supply of the soil and vegetation cover of landscapes by 10–15%, acting as important environment-forming and ecological functions. The combined impact of these environment-forming factors has become the key reason for the increase in the deficit of agricultural land water consumption by 15–20%, the reduction of solar energy costs for the soil-forming process by 10–15% and the increase of the climate aridisation, and has become a signal for the need in the safety of agricultural activities, requiring the development of a set of adaptive measures to mitigate this process in the region.

Stock Returns and Volatility: Comparative Investigation from SAARC Countries

This research article analyses the stock return and volatility of three selected SAARC countries (Pakistan, India, and Bangladesh), focusing on the role of natural resources in influencing market performance. This study aims to determine the robustness of the performance, considering the economic significance of these countries' natural resources. The daily data from the PSX 100 index (Pakistan Stock Exchange), BSE index (Bombay Stock Exchange), and DSE index (Dhaka Stock Exchange) for the years 2019 to 2021 has been obtained from their websites. The data is treated in MS Excel to compute the daily Geometric Returns for BSE, PSX, and DSE indices. Furthermore, the data were analyzed using the specialized package EViews for Time Series Graph, Descriptive Statistics, Unit Root Test, and GARCH Model. The findings of this research show that the BSE index has the highest return value of 6.78 percent compared with 4.56 percent and 3.75 percent for DSE and PSX, respectively. The Half-life model has been applied to calculate the volatility observed by the indices. The result shows that BSE is the most volatile and takes the highest time of 45 days to revert to its mean position, followed by PSX and DSE, which take 19 and 10 days, respectively. Therefore, investing in the BSE index is better for risk-lover investors. At the same time, DSE has the fastest mean reversion compared to the other two indices. Therefore, it is feasible for risk-averse investors.

A complete dynamical analysis of discrete electric lattice coupled with modified Zakharov–Kuznetsov equation

The behavior of nonlinear waves within a modified Zakharov–Kuznetsov equation and their interactions with discrete electric lattice structures are examined in this study. The ϕ6−model expansion method is utilized to acquire substantial knowledge into the complex dynamics of the system under consideration, particularly with regard to the discrete electric lattice and analytical electrical solitons. By incorporating higher-order effects and improving accuracy in representing specific physical conditions, the study achieves a more realistic portrayal of nonlinear wave dynamics. The investigation also sheds light on the relationship between non-linearity, discreteness, and equation dynamics by exploring the conditions that lead to the formation of solitons and other nonlinear structures. In addition, a unique set of electrical solitons is defined to explore dynamic behaviors such as chaotic, quasi-periodic, and periodic motions under various parameterized conditions, including an external damping force. Phase plane analysis is visualized by using dynamic structure 3D and 2D phase plots, is used for bifurcation and sensitivity inspections. Finally, time series graphs are offered as mathematical depictions of solitary waves, and Lyapunov exponents with real and complex eigenvalues are used to study the stability and chaotic behaviors of the system.

Studying the Relationship between Satellite-Derived Evapotranspiration and Crop Yield: A Case Study of the Cauvery River Basin

Satellite-derived evapotranspiration (ETa) products serve global applications, including drought monitoring and food security assessment. This study examines the applicability of ETa data from two distinct sources, aiming to analyze its correlation with crop yield (rice, maize, barley, soybean). Given the critical role of crop yield in economic and food security contexts, monthly and yearly satellite-derived ETa data were assessed for decision-makers, particularly in drought-prone and food-insecure regions. Utilizing QGIS, zonal statistics operations and time series graphs were employed to compare ETa with crop yield and ET anomaly. Data processing involved converting NRSC daily data to monthly and extracting single-pixel ET data using R Studio. Results reveal USGSFEWS as a more reliable ETa source, offering better accuracy and data continuity, especially during monsoon seasons. However, the correlation between crop yield and ETa ranged from 12% to 35%, while with ET anomaly, it ranged from 35% to 55%. Enhanced collection of satellite-based ETa and crop-yield data is imperative for informed decision-making in these regions. Despite limitations, ETa can moderately guide decisions regarding crop-yield management.

Design of Nonlinear Autoregressive Neuro-Computing Structure for Bioconvective Micropolar Nanofluidic Model

In the present arena, the tools of artificial intelligence (AI) play a significant role in research across various fields by enabling advanced data analysis, pattern recognition and decision-making. This research work presents the numerical investigation of bioconvective micropolar nanofluidic model (BCMNFM) by employing the knacks of AI-based nonlinear autoregressive (NAR) approach with a combination of backpropagated Levenberg–Marquardt neural networks (BLMNNs) represented as NAR-BLMNNs. This research work investigates the flow design to highlight the attributes of mass and heat exchange. A dataset for BCMNFM is created by applying the Adam numerical procedure by variation of unsteadiness parameter ([Formula: see text], magnetic field parameter ([Formula: see text] thermophoresis parameter (Nt), Brownian motion parameter (Nb), bioconvection Peclet number (Pe) and spin gradient viscosity parameter ([Formula: see text] The skills of AI-based NAR-BLMNNs technique is then utilized on the dataset created for BCMNFM to investigate the approximate solutions. The achieved and impactful values of performance consistently range between [Formula: see text] and [Formula: see text] across all scenarios of BCMNFM. The precision and the validation of predicted approach NAR-BLMNNs is exceptionally established by the graphical demonstration for all scenarios of MSE, regression metrics, error histograms and time series graphs. The numerical calculations attained through AI-based NAR-BLMNNs technique further rationalize the precision of the proposed methodology for solving the BCMNFM effectively and efficiently.

A fault diagnosis method of hot spots for photovoltaic clusters based on model parameters

AbstractUtilizing the direct current‐side electrical data resources of the photovoltaic power generation system on the FusionSolar platform, this study investigates the impact of hot spot faults on the output characteristics of photovoltaic strings and proposes a hot spot fault diagnosis method based on time series waveform characteristics. By analyzing the mechanisms of hot spot generation and evolution, as well as the characteristic differences in I–V curves and time series compared to other types of faults, the waveform variation patterns of hot spots in current and voltage time series are obtained. A function form suitable for hot spot fault waveform characteristics in time series graphs is constructed, and fault diagnosis feature vectors are extracted. Combining field operation and maintenance experience, a fuzzy reasoning fault diagnosis system is established to determine the causes and estimate the severity of hot spot faults. Experimental results indicate that hot spot faults have unique and corresponding variations in the current/voltage time series waveforms of the string output. The constructed function form can clearly represent the waveform variation patterns, and the established fuzzy reasoning system can achieve effective and reliable diagnosis of hot spot faults.

Effect of fear with saturated fear cost and harvesting on aquatic food chain model (plankton–fish model) in the presence of nanoparticles

Studying the interplay of phytoplankton–zooplankton–fish (PP–ZP–F) in an aquatic system is crucial for better understanding of nutrient cycling, assessing ecosystem health, predicting and mitigating harmful algal blooms, and managing fisheries in the water bodies. In order to investigate the effectiveness of nanoparticles (NPs), fear, and harvesting, this paper focuses on exploring the dynamics of a food chain model among PP–ZP–F species. We consider the fear of fish on zooplankton species (which reduces the reproduction rate of ZPs) with saturated fear cost in the presence of nanoparticles (NPs) and harvesting in fish. The system dynamics are studied from the viewpoint of proving positivity, boundedness, and uniqueness, followed by analysing the existence and local stability of biologically feasible equilibria. Conditions for the global stability of the interior equilibrium point are also found. Furthermore, we established the transversality conditions for the occurrence of Hopf, transcritical, and saddle–node bifurcations. To validate our theoretical results, we made numerous phase portraits, time-series graphs, tables showing the extinction of species, and bifurcation diagrams. It is numerically observed that increasing the contact rate of NPs with PPs makes the system stable from chaos, and further increase of contact rate may lead to extinction. Chaos at a low contact rate can also be managed by increasing the fear level, and the chaotic behaviour at a low fear level can again be controlled by enhancing the harvesting of fish species. Over-exploitation may result in the extinction of fish, whereas fear may promote coexistence, stability, and long-term survival of the species. Increased saturated fear cost can make the system chaotic from stable dynamics. Therefore, the theoretical as well as numerical findings of our paper may be of great interest in estimating the behaviour of aquatic systems biologically and practically.

Analisis Kondisi Atmosfer pada Kejadian Hujan ES di Kota Palembang 04 November 2023

Seasonal transitions in Indonesia are typically accompanied by extreme weather phenomena, such as hail that occurred in the city of Palembang on November 4, 2023. The analysis of atmospheric conditions is intended to understand the dynamics of the atmosphere during the occurrence of the hailstorm phenomenon. The data used in this study include satellite imagery from Himawari-9 channels 8, 11, 13, 15, GSM data, ECMWF modelling data, and SST anomaly data. The research results indicate that anomalies in sea surface temperature and vertical convergence profiles, as well as relative humidity (RH), strengthen the potential for convective activity leading to extreme weather conditions. Based on Himawari-9 satellite imagery, the time series graph shows the lowest peak cloud temperature at around -80°C, with the Atmospheric Stability Index based on the GSM method indicating a labile atmospheric condition. Furthermore, using the RGB 24 Hour Microphysics and CCO methods, Cumulonimbus clouds were observed to begin growing at 07:20 UTC, entering the mature stage at 09:20 UTC, and starting to decay at 10:20 UTC.

Predicting ICU Interventions: A Transparent Decision Support Model Based on Multivariate Time Series Graph Convolutional Neural Network.

In this study, we present a novel approach for predicting interventions for patients in the intensive care unit using a multivariate time series graph convolutional neural network. Our method addresses two critical challenges: the need for timely and accurate decisions based on changing physiological signals, drug administration information, and static characteristics; and the need for interpretability in the decision-making process. Drawing on real-world ICU records from the MIMIC-III dataset, we demonstrate that our approach significantly improves upon existing machine learning and deep learning methods for predicting two targeted interventions, mechanical ventilation and vasopressors. Our model achieved an accuracy improvement from 81.6% to 91.9% and a F1 score improvement from 0.524 to 0.606 for predicting mechanical ventilation interventions. For predicting vasopressor interventions, our model achieved an accuracy improvement from 76.3% to 82.7% and a F1 score improvement from 0.509 to 0.619. We also assessed the interpretability by performing an adjacency matrix importance analysis, which revealed that our model uses clinically meaningful and appropriate features for prediction. This critical aspect can help clinicians gain insights into the underlying mechanisms of interventions, allowing them to make more informed and precise clinical decisions. Overall, our study represents a significant step forward in the development of decision support systems for ICU patient care, providing a powerful tool for improving clinical outcomes and enhancing patient safety.

Representing Multiview Time-Series Graph Structures for Multivariate Long-Term Time-Series Forecasting

Representing Multiview Time-Series Graph Structures for Multivariate Long-Term Time-Series Forecasting

Application to Quantify Ulcer Areas and Track Their Progress.

Chronic ulcer treatments, such as those for diabetic foot ulcers and pressure sores, require prolonged treatment periods. Availability of effective objective indicators to determine treatment method efficacy is limited. Ulcer area is the agreed-upon indicator for ulcer healing because it contracts and/or undergoes epithelialization as healing occurs. Ulcer surface properties such as healthy or infected granulation and slough or necrotic tissue are also used. This study aimed to develop a user-friendly application automating the ulcer area measurement process and included a graphical time-series display of ulcer components manually classified by users. Images of ulcers photographed with adjacent circular 1.5-cm diameter stickers were prepared. In the application, users manually categorized and color-coded each image into five component types based on different ulcer characteristics. The application calculated the area of each component in pixels and then estimated the actual area using the sticker area as a reference. It also collated color-coded images and presented graphical illustrations of changes in area over time. The results indicated the application successfully automated area measurements of each ulcer component and graphical displays of changes in ulcer component areas over time. It enabled users to visually track quality changes and the chronic ulcer healing process. Historically, ulcer assessments are subjectively conducted via visual examination by physicians, creating less reproducible, objective data. Although ulcer properties still required manual entry by users, our application streamlined ulcer area measurement and time-course visualization and sets the groundwork for a fully automated artificial-intelligence-driven ulcer diagnosis system.

Analysis of Rainwater Availability and Water Requirements in the Amarasi District Area Kupang Regency

The hydrological conditions of the Amarasi District, Kupang Regency have 3-4 wet months and 8-9 dry months according to Oldeman’s classification. Annual rainfall in the last ten years shows the lowest rainfall was 1,461mm and the highest was 2,688mm, the average annual rainfall was 1,859mm. The Amarasi region is included in zones D and E of the Oldeman climate classification. The practice of utilizing limited water resources by planting fodder crops in the form of legumes and grasses as well as food crops in integrated dry land agriculture has been carried out by the Amarasi community. This research examines the availability and demand for domestic, agricultural and livestock water and will produce an availability index as the carrying capacity of regional water availability. The method used to calculate the availability of water originating from rain is runoff analysis based on weighted coefficients for each land use, then analyzed in a monthly series and compared with the level of water demand for each use. Domestic water needs, livestock drinking and irrigation follow SNI 19-6728.1.2002. Then the analysis results are interpreted with tables and time series graphs. The research results show the following time series of water availability: January: 44,626,635.13m3; February: 31,210,646.01m3; March : 20,050,098.53m3; April: 11,726,074.47m3; May : 3,023,180.66m3; June: 1,747,689.52m3; July : 973,284.18m3; August : 168,880.36m3; September: 1,026,614.82m3. October 2,846,522.91m3; November 10,713,903.37m3; and December: 26,871,976.23m3. The amount of water demand in the time series is as follows: January: 1,929,491.70m3; February: 1,391,817.98m3; March: 1,697,543.42m3; April: 781,567.95m3; May : 883,736.22m3; June: 755,911.95m3; July : 284,777.42m3; August : 384,569.42m3; September: 387,871.95m3. October 355,448.02m3; November 3,242,283.15m3; and December: 2,631,159.26m3. Water availability index: January: 4.32 (good), February: 4.46 (good), March: 8.47 (good), April: 6.67 (good), May: 29.23 (slight critical), June: 43.25 (mild critical), July: 29.26 (mild critical), August: 227.27 (bad/severe critical), September: 37.78 (mild critical), October 12.49 (good), November: 30.26 (mild critical) and December 9.79 (good).

Seasonality of Birth Weight in Singleton Full-term Births in Finland

Seasonal birth weight has been identified across different climate zones. Finland has wide seasonal and regional variation in climate within the country. We explore the potential seasonality of birth weight in singleton full-term births in Finland, and its variations across time and within the country. We apply descriptive time-series graphs, linear regression across regions, and linear regression with mother fixed effects using Finnish register data consisting of more than 1,800,000 infants born from 1987 to 2021. The descriptive findings indicate a decline in birth weight from 1987 to 2021. A monthly seasonal trend with peaks in spring and autumn and troughs in summer and winter is observed. The pattern gets less distinct with time and shows within-country variations. The seasonal pattern is also present when applying mother fixed effects. We suggest that the seasonal variation is more related to variations in climate than stable characteristics at the family level.

Generalized Linear Mixed Effects Modeling (GLMM) of Functional Analysis Graphical Construction Elements on Visual Analysis

Multielement designs are the quintessential design tactic to evaluate outcomes of a functional analysis in applied behavior analysis. Protecting the credibility of the data collection, graphing, and visual analysis processes from a functional analysis increases the likelihood that optimal intervention decisions are made for individuals. Time-series graphs and visual analysis are the most prevalent method used to interpret functional analysis data. The current project included two principal aims. First, we tested whether the graphical construction manipulation of the x-to-y axes ratio (i.e., data points per x- axis to y-axis ratio [DPPXYR]) influenced visual analyst’s detection of a function on 32 multielement design graphs displaying functional analyses. Second, we investigated the alignment between board certified behavior analysts (BCBAs; N = 59) visual analysis with the modified visual inspection criteria (Roane et al., Journal of Applied Behavior Analysis, 46, 130-146, 2013). We found that the crossed GLMM that included random slopes, random intercepts, and did not include an interaction effect (AIC = 1406.1, BIC = 1478.2) performed optimally. Second, alignment between BCBAs decisions and the MVI appeared to be low across data sets. We also leveraged current best practices in Open Science for raw data and analysis transparency.

Root cause localization for wind turbines using physics guided multivariate graphical modeling and fault propagation analysis

Under the background of widespread utilization of wind energy, the improvement of power generation efficiency and the reduction of operation and maintenance costs have increased the demand for anomaly detection and localization of wind turbines through fault propagation analysis, while the large-scale data collected by SCADA systems provide sufficient data support and promising assistance for this purpose. It is an effective and cost-saving solution to this demand to construct a high-precision wind turbine digital twin model under normal operating conditions based on multivariate monitoring data, and to realize root cause localization based on prediction deviation and backtracking analysis. This paper proposes a root cause localization framework for wind turbines based on explicit-implicit knowledge fusion and multivariate time-series graph neural networks, fully utilizing the inter-variable dependencies mining capability of graph structure learning and the temporal prediction advantage of time-series graph neural networks. Five types of explicit knowledge based on explicit rules are constructed to describe the explicit relationships between monitoring variables. The fused knowledge (i.e., graph adjacency matrix) is obtained by fusing the explicit knowledge with the implicit knowledge hidden in the data through a quasi-hard-attention mechanism based on the idea of graph structure learning. A high-precision digital twin model for wind turbines based on fused knowledge is constructed using the multivariate time-series graph neural network. The anomaly degree of monitoring variables’ state is defined based on the prediction deviation, with which the propagation of fault's state over time can be accurately described, and the root cause localization through backtracking analysis can be achieved. Case studies are conducted using field fault data from a wind farm, a sugar factory and a thermal power plant. The results show that the proposed framework can provide a solution for studying the fault propagation process and root cause localization, also demonstrating certain robustness and generalizability.

A Metro Passenger Flow Forecasting Model Based On Time-series Evolving Interaction Graph Network

Passenger flow forecasting is an important task in metro operation management. In order to achieve more accurate metro passenger flow forecasting, this paper proposes a metro passenger flow forecasting model based on time-series evolution interaction graph. First, by introducing two kinds of inter-station interaction graphs, namely connectivity graph and temporal correlation graph, to capture the potential interaction relationship among metro passenger flow stations. Then, by using the time-series evolving graph, the weights of the graph convolutional neural network are dynamically evolved in time series. Finally, taking Suzhou Metro as an example, the short-term passenger flow of the metro is forecasted. The experimental results show that the Root Mean Squared Error (RMSE) of this model is 34.17, the Mean Absolute Error (MAE) is 16.35, the R-Squared is 0.94, the Mean Absolute Percent Error (MAPE) is 0.21. All evaluation metrics are better than the baseline models, thus verifying the effectiveness and applicability of the metro passenger flow forecasting model based on the time series evolution interaction graph.

A research on an improved fuzzy approximate entropy algorithm for EMG-based shoulder and neck muscle fatigue detection

A robust muscle fatigue algorithm plays a pivotal role in depicting the degree of muscle fatigue in both time-series EMG signal graphs and spectral graphs, aligning with human perception. While the fuzzy approximate entropy (fApEn) algorithm has been enhanced from the foundation of approximate entropy (ApEn) through the incorporation of fuzzy affiliation, concerns persist regarding the threshold value and the algorithm’s application range. This study extracts EMG signals across varied time durations and head-down angles, employing enhanced signal preprocessing techniques and optimizing the fApEn algorithm. Furthermore, real-time fatigue perceptions of subjects were recorded using the rating of perceived exertion. Experimental outcomes reveal that the EMG signal, post-wavelet analysis preprocessing, demonstrates promising noise reduction capabilities. Notably, the fApEn algorithm exhibits considerable enhancements through the identification of an optimal threshold using the gradient descent algorithm and a machine learning strategy.

Learning-Based Hierarchical Decision-Making Framework for Automatic Driving in Incompletely Connected Traffic Scenarios.

The decision-making algorithm serves as a fundamental component for advancing the level of autonomous driving. The end-to-end decision-making algorithm has a strong ability to process the original data, but it has grave uncertainty. However, other learning-based decision-making algorithms rely heavily on ideal state information and are entirely unsuitable for autonomous driving tasks in real-world scenarios with incomplete global information. Addressing this research gap, this paper proposes a stable hierarchical decision-making framework with images as the input. The first step of the framework is a model-based data encoder that converts the input image data into a fixed universal data format. Next is a state machine based on a time series Graph Convolutional Network (GCN), which is used to classify the current driving state. Finally, according to the state's classification, the corresponding rule-based algorithm is selected for action generation. Through verification, the algorithm demonstrates the ability to perform autonomous driving tasks in different traffic scenarios without relying on global network information. Comparative experiments further confirm the effectiveness of the hierarchical framework, model-based image data encoder, and time series GCN.

HFN: Heterogeneous feature network for multivariate time series anomaly detection

As the key step of anomaly detection for multivariate time-series (MTS) data, learning the relations among different variables has been explored by many approaches. However, most existing approaches overlook the heterogeneity among variables, that is, different types of variables (continuous numerical variables, discrete categorical variables or hybrid variables) may have different edge distributions. In this paper, we propose a novel semi-supervised anomaly detection framework based on a heterogeneous feature network (HFN) for MTS. Specifically, we first combine the embedding similarity subgraph generated by sensor embedding and the feature value similarity subgraph generated by sensor values to construct a time-series heterogeneous graph, which fully utilizes the rich heterogeneous mutual information among variables. Then, a prediction model containing nodes and channel attentions is jointly optimized to obtain better time-series representations. This approach fuses the state-of-the-art technologies of heterogeneous graph structure learning (HGSL) and representation learning. Experimental results on four sensor datasets from real-world applications demonstrate that our approach achieves more accurate anomaly detection compared to baseline methods, laying a foundation for the rapid positioning of anomalies.