Delay Prediction Research Articles

Machine learning based models for predicting presentation delay risk among gastric cancer patients

ObjectivePresentation delay of cancer patients prevents the patient from timely diagnosis and treatment leading to poor prognosis. Predicting the risk of presentation delay is crucial to improve the treatment outcomes. This study aimed to develop and validate prediction models of presentation delay risk in gastric cancer patients by using various machine learning models.Methods875 cases of gastric cancer patients admitted to a tertiary oncology hospital from July 2023 to June 2024 were used as derivation cohort, 200 cases of gastric cancer patients admitted to other 4 tertiary hospital were used as external validation cohort. After collecting the data, statistical analysis was performed to identify discriminative variables for the prediction of presentation delay and 13 statistically significant variables are selected to develop machine learning models. The derivation cohort was randomly assigned to the training and internal validation set by the ratio of 7:3. Prediction models were developed based on six machine learning algorithms, which are logistic regression (LR), support vector machine (SVM), random forest (RF), gradient boosted trees (GBDT), extremely gradient boosting (XGBoost) and muti-layer perceptron (MLP). The discrimination and calibration of each model were assessed based on various metrics including accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1-Score and area under curve (AUC), calibration curves and Brier scores. The best model was selected based on comparing of various metrics. Based on the selected best model, the impact of features to the prediction result was analyzed with the permutation feature importance method.ResultsThe incidence of presentation delay for gastric cancer patients was 39.3%. The developed models achieved performance metrics as AUC (0.893-0.925), accuracy (0.817-0.847), sensitivity (0.857-0.905), specificity (0.783-0.854), PPV (0.728-0.798), NPV (0.897-0.927), F1 score (0.791-0.826) and Brier score (0.107-0.138) in internal validation set, which indicated good discrimination and calibration for the prediction of presentation delay in gastric cancer patients. Among all models, RF based model was selected as the best one as it achieved good discrimination and calibration performance on both of internal and external validation set. Feature ranking results indicated that both of subjective and objective factors have significant impact on the occurrence of presentation delay in gastric cancer patients.ConclusionThis study demonstrated that the RF based model has favorable performance for the prediction of presentation delay in gastric cancer patients. It can help medical staffs to screen out high-risk gastric cancer patients for presentation delay, and to take appropriate and specific interventions to reduce the risk of presentation delay.

Prediction of cerebral palsy and cognitive delay among high-risk children in a developing nation: A successful early detection programme.

Prediction of cerebral palsy and cognitive delay among high-risk children in a developing nation: A successful early detection programme.

A Comparative Analysis of Train Delay Prediction Models for Markov Chains

A Comparative Analysis of Train Delay Prediction Models for Markov Chains

Prediction of cerebral palsy and cognitive delay among high-risk children in a developing nation: A successful early detection programme.

To determine the feasibility of combining the Hammersmith Infant Neurological Examination (HINE) and General Movements Assessment (GMA) within a standard follow-up schedule to predict developmental outcomes in infants at risk in low- and middle-income countries (LMICs). A total of 201 Sri Lankan infants (128 male, 73 female) were prospectively assessed with the GMA before 44 weeks (writhing movements) and at 3 to 4 months (fidgeting movements), followed by the HINE at 5 to 6 months. Developmental outcomes were assessed using the Bayley Scales of Infant and Toddler Development, Fourth Edition and clinical assessment after 24 months. The sensitivity of predicting cerebral palsy (CP) was lower with a single GMA assessment (writhing 89.5%, fidgeting 94.7%) or HINE (89.5%) compared to all three assessments combined (sensitivity 100%, 95% confidence interval [CI] = 82.4-100.0). The GMA and HINE were less predictive of non-CP-related developmental delays, particularly when single assessments were used (< 65% for all domains) compared to all three assessments combined (motor sensitivity > 86.9%, 95% CI = 66.4-97.2; cognitive sensitivity > 86.7%, 95% CI = 69.3-96.2; social-emotional sensitivity > 83.3%, 95% CI = 65.3-94.4). Specificity was lower for the prediction of CP-related (40.1%) and non-CP-related developmental delays (< 46.0% for all). In an LMIC such as Sri Lanka, with limited access to specialist care and neuroimaging, combining two GMA measures and the HINE identified most infants with CP-related and non-CP-related developmental delay, thereby allowing targeted early intervention therapies.

A continuous training approach for risk informed supplier selection and order allocation

ABSTRACT Supplier selection and order allocation, a longstanding challenge in supply chain management, has recently begun incorporating risk minimization alongside cost, reflecting growing interest in supply chain resilience and risk mitigation. In response, hybrid frameworks leveraging artificial intelligence and machine learning have emerged. However, current methods often lack mechanisms to update decisions over time and typically rely solely on demand forecasts. To address these gaps, this study introduces a new hybrid approach that integrates machine learning–based predictions of supplier delivery delays into a linear programming model for multiperiod supplier selection and order allocation. Additionally, the proposed method evaluates a continuous training strategy, wherein predictions and decisions are refreshed as new data become available. Empirical evidence from an automotive case study demonstrates that this approach reduces prediction errors and total costs more effectively than models without continuous training, albeit with increased order allocation instability.

Machine learning-based tropospheric delay prediction for real-time precise point positioning under extreme weather conditions

Satellite signals from the Global Navigation Satellite System (GNSS) are refracted as they pass through the troposphere, owing to the variable density and composition of the atmosphere, causing tropospheric delay. Typically, tropospheric delay is treated as an unknown parameter in GNSS data processing. Given the growing need for real-time GNSS applications, accurate tropospheric delay predictions are crucial to improve Precise Point Positioning (PPP). In this paper, time-series of tomography data are used for wet refractivity prediction employing Machine Learning (ML) techniques in both Poland and California, under extreme weather conditions including sweeping rain bands and storms. The predicted wet refractivity is implemented for tropospheric delay determination through ray-tracing technique. PPP processing is conducted in both static and kinematic modes using different setups. These are: (1) common PPP, called Com-PPP, (2) Ray-PPP, which applies obtained tropospheric delay on GNSS observations and thus eliminates tropospheric parameters from unknowns, and (3) Dif-PPP, which applies the difference of estimated tropospheric delay from ray-tracing and GNSS measurements to compensate for the remaining tropospheric delay in the observations. The results show that Dif-PPP reduces the Mean Absolute Error (MAE) of the Three-Dimensional (3-D) component between 8 and 33% in static mode compared to the Com-PPP method. Additionally, it can improve the convergence time of the up component in the kinematic mode by between 6 and 17%.

Improved adaptive graph local spatial–temporal multi-head self-attention network: a deep learning framework for flight delay prediction

Improved adaptive graph local spatial–temporal multi-head self-attention network: a deep learning framework for flight delay prediction

A Spatio-Temporal Approach With Self-Corrective Causal Inference for Flight Delay Prediction

A Spatio-Temporal Approach With Self-Corrective Causal Inference for Flight Delay Prediction

Developing a jam-absorption strategy for mixed traffic flow at signalized intersections using deep reinforcement learning

ABSTRACT Jam-absorption driving (JAD) can effectively prevent the generation and propagation of traffic oscillation. To alleviate the traffic congestion in the signalized intersection with mixed traffic flow, including human driving vehicles (HDVs) and connected and automated vehicles (CAVs), this study provides a jam-absorption driving strategy based on the traffic delay prediction of the mixed platoon under traffic congestion. An online traffic congestion prediction method with the objective of JAD is proposed and focuses on the leaving state of the trajectory to achieve fast capture of congestion features. Then, with real-time status and prediction information, we develop a Jam-absorption driving strategy based on a deep reinforcement learning (DRL) model to improve adaptability to the mixed traffic environment. The results show that this strategy can suppress more than 70% of traffic oscillations with excellent execution efficiency, improving traffic safety and efficiency.

Methods and Evaluation of AI-Based Meteorological Models for Zenith Tropospheric Delay Prediction

Zenith Tropospheric Delay (ZTD) is a significant error source affecting the accuracy of certain space geodetic measurements. This study evaluates the performance of Artificial Intelligence (AI) based meteorological models, such as Fengwu and Pangu, in estimating real-time ZTD. The results from these AI models were compared with those obtained from the Global Navigation Satellite System (GNSS), the fifth-generation European Centre for Medium-Range Weather Forecasts (ECMWF) Atmospheric Reanalysis (ERA5), and the third generation of the Global Pressure–Temperature data model (GPT3) to assess their accuracy across different time intervals, seasons, and geographic locations. The findings reveal that AI-driven models, particularly Fengwu, offer higher long-term forecasting accuracy. An analysis of data from 81 stations throughout 2023 indicates that Fengwu’s 7-day ZTD forecast achieved an RMSE of 2.85 cm when compared to GNSS-derived ZTD. However, in oceanic regions and areas with complex climatic dynamics, the Fengwu model exhibited a larger error compared to in other land regions. Additionally, seasonal variations and station altitude were found to influence the accuracy of ZTD predictions, emphasizing the need for detailed modeling in complex climatic zones.

AI-federated novel delay-aware link-scheduling for Industry 4.0 applications in IoT networks

PurposeWith the advent of AI-federated technologies, it is feasible to perform complex tasks in industrial Internet of Things (IIoT) environment by enhancing throughput of the network and by reducing the latency of transmitted data. The communications in IIoT and Industry 4.0 requires handshaking of multiple technologies for supporting heterogeneous networks and diverse protocols. IIoT applications may gather and analyse sensor data, allowing operators to monitor and manage production systems, resulting in considerable performance gains in automated processes. All IIoT applications are responsible for generating a vast set of data based on diverse characteristics. To obtain an optimum throughput in an IIoT environment requires efficiently processing of IIoT applications over communication channels. Because computing resources in the IIoT are limited, equitable resource allocation with the least amount of delay is the need of the IIoT applications. Although some existing scheduling strategies address delay concerns, faster transmission of data and optimal throughput should also be addressed along with the handling of transmission delay. Hence, this study aims to focus on a fair mechanism to handle throughput, transmission delay and faster transmission of data. The proposed work provides a link-scheduling algorithm termed as delay-aware resource allocation that allocates computing resources to computational-sensitive tasks by reducing overall latency and by increasing the overall throughput of the network. First of all, a multi-hop delay model is developed with multistep delay prediction using AI-federated neural network long–short-term memory (LSTM), which serves as a foundation for future design. Then, link-scheduling algorithm is designed for data routing in an efficient manner. The extensive experimental results reveal that the average end-to-end delay by considering processing, propagation, queueing and transmission delays is minimized with the proposed strategy. Experiments show that advances in machine learning have led to developing a smart, collaborative link scheduling algorithm for fairness-driven resource allocation with minimal delay and optimal throughput. The prediction performance of AI-federated LSTM is compared with the existing approaches and it outperforms over other techniques by achieving 98.2% accuracy.Design/methodology/approachWith an increase of IoT devices, the demand for more IoT gateways has increased, which increases the cost of network infrastructure. As a result, the proposed system uses low-cost intermediate gateways in this study. Each gateway may use a different communication technology for data transmission within an IoT network. As a result, gateways are heterogeneous, with hardware support limited to the technologies associated with the wireless sensor networks. Data communication fairness at each gateway is achieved in an IoT network by considering dynamic IoT traffic and link-scheduling problems to achieve effective resource allocation in an IoT network. The two-phased solution is provided to solve these problems for improved data communication in heterogeneous networks achieving fairness. In the first phase, traffic is predicted using the LSTM network model to predict the dynamic traffic. In the second phase, efficient link selection per technology and link scheduling are achieved based on predicted load, the distance between gateways, link capacity and time required as per different technologies supported such as Bluetooth, Wi-Fi and Zigbee. It enhances data transmission fairness for all gateways, resulting in more data transmission achieving maximum throughput. Our proposed approach outperforms by achieving maximum network throughput, and less packet delay is demonstrated using simulation.FindingsOur proposed approach outperforms by achieving maximum network throughput, and less packet delay is demonstrated using simulation. It also shows that AI- and IoT-federated devices can communicate seamlessly over IoT networks in Industry 4.0.Originality/valueThe concept is a part of the original research work and can be adopted by Industry 4.0 for easy and seamless connectivity of AI and IoT-federated devices.

Numerical investigation of prediction method for propagation delay of low-frequency radio signal based on the Changhe-II and Loran-C navigation system in East Asia

As an important part of low-frequency communication research, the “Changhe-II” and Loran-C navigation systems have been integral to long-distance radio communication since their inception, being widely used for positioning, navigation, and timing. This paper analyzes data from the “Changhe-II” South China Sea chain to Xinxiang and Qingdao, as well as the Loran-C Northwest Pacific chain to Wuchang, Xinxiang, and Qingdao, using the wave-hop theory to study methods for predicting low-frequency sky wave propagation delays. The results demonstrate that the wave-hop theory can provide highly accurate predictions of low-frequency sky wave propagation delays in East Asia, with an average RMSE of less than 2 μs. Furthermore, the predictive performance, evaluated across both temporal and spatial dimensions, is influenced by factors such as propagation links and seasonal variations. The results of this paper are of significant reference value for optimizing the design of low-frequency navigation systems, ultimately supporting more extensive and accurate navigation services.

Truncated predictive control for delayed cyber–physical systems under deception attacks

In this work, the state tracking, input delay prediction, uncertainty and disturbance rejection problems are studied for the delayed cyber–physical systems under uncertainties, nonlinearities and external disturbances in which the addressed model is described by the fuzzy technique. More specifically, such an input-delayed system is linearized through an interval type-2 fuzzy technique accompanied by a parallel distribution compensation method. Further, the presence of constant input delays in the examined system is proficiently compensated with the assistance of a truncated predictor feedback approach. In parallel, the impacts of external disturbances and uncertainties that are occurred in the system are estimated by means of uncertainty and disturbance estimator method in an efficacious way. With the help of this estimated information, an uncertainty and disturbance estimator-based truncated predictive tracking control protocol is formulated to acquire the state tracking results of the underlying system in the presence of external disturbances and uncertainties. Remarkably, in this study, the interval type-2 fuzzy is blended with the designed reference system. Furthermore, the secure tracking control law is designed for the considered system under the random deception attacks. To address the deception attacks, the Bernoulli stochastic distribution is considered in this study. Moreover, the constraints are expressed for computing the truncated predictive feedback control gain matrices. Conclusively, the numerical simulation analysis is carried out to demonstrate the usefulness of the devised approach.

A Genetic Optimized Federated Learning Approach for Joint Consideration of End-to-End Delay and Data Privacy in Vehicular Networks

In 5G vehicular networks, two key challenges have become apparent, including end-to-end delay minimization and data privacy. Learning-based approaches have been used to alleviate these, either by predicting delay or protecting privacy. Traditional approaches train machine learning models on local devices or cloud servers, each with their own trade-offs. While pure-federated learning protects privacy, it sacrifices delay prediction performance. In contrast, centralized training improves delay prediction but violates privacy. Existing studies in the literature overlook the effect of training location on delay prediction and data privacy. To address both issues, we propose a novel genetic algorithm optimized federated learning (GAoFL) approach in which end-to-end delay prediction and data privacy are jointly considered to obtain an optimal solution. For this purpose, we analytically define a novel end-to-end delay formula and data privacy metrics. Accordingly, a novel fitness function is formulated to optimize both the location of training model and data privacy. In conclusion, according to the evaluation results, it can be advocated that the outcomes of the study highlight that training location significantly affects privacy and performance. Moreover, it can be claimed that the proposed GAoFL improves data privacy compared to centralized learning while achieving better delay prediction than other federated methods, offering a valuable solution for 5G vehicular computing.

Data-driven prediction of early language delay at Youth Health Care Services in the Netherlands

Abstract Introduction Language development in early childhood significantly impacts future academic success, social interaction, and emotional well-being. This study aimed to develop and evaluate a prediction model using data on developmental milestones and parents’ socio-economic background known at age 2, and translate the results into an interactive digital dashboard and pilot it with Youth Health Care (YHC) professionals and parents. Methods A mixed-method study on retrospective cohort of children attending YHC at age 2, followed up until age 4. Data on language development, gender, parental education, and home language environment were obtained from YHC digital dossiers and linked to parental socio-economic status characteristics, and perinatal outcomes and healthcare costs using a secure remote access environment of Statistics Netherlands. Random forest and logistic regression models were computed with language development at age 4 as an outcome, initially using all available data at age 2 as predictors and then with a restricted model using variables readily available in YHC settings. Models performance was assessed using sensitivity, specificity, and AUC value. Results were visualized through an interactive dashboard and pilot-tested in simulated consultations. Results Among 9,148 children, 13.2% had language development delay at age 4. The full model had an AUC of 0.78, while the restricted model (gender, parental education, language environment, and language development), achieved an AUC of 0.77. YHC professionals and parents recognized the value of individualized, data-driven risk assessment for potential language delay to stimulate the discussion of preventive interventions. Conclusions A good quality prediction model for language development at age 4 can be derived from just a few background characteristics of the child and parents at age 2. The digital dashboard presents a practical approach of integrating prediction model results into daily YHC practice. Key messages • Language development at age of 4 can be predicted as early as age of 2 using just a few background characteristics of child and parents, which presents a window of opportunity for prevention. • The digital dashboard presents a practical approach of integrating prediction model results into preventive care practice.

Enhancing freight train delay prediction with simulation‐assisted machine learning

AbstractBoosting the rail freight modal share is an ambitious target in Europe and North America. Yards, where freight trains are arranged, can be crucial in realizing this target by reliable dispatching to the network. This paper predicts freight train departures by developing a simulation‐assisted machine learning model with two concepts: general (adding all predictors at once) and step‐wise (adding predictors as they become available in sub‐yard operations) for hump yards with the conventional layout to provide a generalized model for European and North American contexts. The developed model is a decision tree algorithm, validated via 10‐fold cross‐validation. The model's performance on three data sets—a real‐world European yard, a baseline simulation, and an ultimate randomness simulation for a comparable North American yard—shows a respective of 0.90, 0.87, and 0.70. Step‐wise inclusion of the predictors results differently for the real‐world and simulation data. The global feature importance highlights maximum planned length, departure weekday, the number of arriving trains, and minimum arrival deviation as key predictors for the real‐world data. For the simulation data, the most significant predictors are departure yard predictors, the number of arriving trains, and the maximum hump duration. Additionally, utilization rates—except for the receiving yard—enhance the predictions.

Enhanced Infant Movement Analysis Using Transformer-Based Fusion of Diverse Video Features for Neurodevelopmental Monitoring

Neurodevelopment is a highly intricate process, and early detection of abnormalities is critical for optimizing outcomes through timely intervention. Accurate and cost-effective diagnostic methods for neurological disorders, particularly in infants, remain a significant challenge due to the heterogeneity of data and the variability in neurodevelopmental conditions. This study recruited twelve parent–infant pairs, with infants aged 3 to 12 months. Approximately 25 min of 2D video footage was captured, documenting natural play interactions between the infants and toys. We developed a novel, open-source method to classify and analyse infant movement patterns using deep learning techniques, specifically employing a transformer-based fusion model that integrates multiple video features within a unified deep neural network. This approach significantly outperforms traditional methods reliant on individual video features, achieving an accuracy of over 90%. Furthermore, a sensitivity analysis revealed that the pose estimation contributed far less to the model’s output than the pre-trained transformer and convolutional neural network (CNN) components, providing key insights into the relative importance of different feature sets. By providing a more robust, accurate and low-cost analysis of movement patterns, our work aims to enhance the early detection and potential prediction of neurodevelopmental delays, whilst providing insight into the functioning of the transformer-based fusion models of diverse video features.

Public Transport Delay Prediction using Deep Learning

A system of trains, buses, subways, ferries, and other vehicles that are accessible to the public is referred to as public transportation, also known as public transit or mass transit. These networks are usually run by private or public organisations are made to efficiently transport large numbers of people in urban and suburban areas. It usually operates on set schedules and routes and has a listed fare for each journey. Long wait periods and lengthy travel times resulting from delays are two problems that frequently plague public transportation services. There are several things that can cause a delay in public transport, such as an excess of passengers, heavy traffic, accidents, and other unforeseen circumstances. The availability of a more accurate delay prediction for public transportation might increase users’ confidence and their willingness to pay more for transit services. Over the past two decades, a number of studies on prediction algorithms for transportation data have been proposed. Most of the work is on machine learning model development, focusing on delay prediction and taking into account several factors such as weather conditions and infrastructure issues. This paper proposes a deep learning model to predict public transportation delays using data from public transportation and the weather. The results obtained from this research work are compared with several other existing works. Our experiment has demonstrated that the deep neural network (DNN) is the best model to predict transit delay compared to several other machine learning and deep learning models.

Collaborative and integrated data-driven delay prediction and supplier selection optimization: A case study in a furniture industry

Optimizing supplier selections is an open ended problem, relevant to the operational performance of both individual companies and entire supply chains. Considering the prediction of future occurrences of delays in the optimization of supplier selections is still an under covered problem. Unlike existing literature, this article suggests a more collaborative and integrated workflow to improve the visibility and involvement of multiple stakeholders in the supplier selection decision-making processes. This is achieved through enhanced collaboration between multiple stakeholders (suppliers, customers, decision-makers from different departments, in addition to data sources from information systems), and better integration between data analysis and decision-making, through data-driven-machine-learning and optimization. The specificities of a French company in the furniture industry are considered. A workflow model is designed to support information sharing and to streamline knowledge and interactions between multiple stakeholders from different expertise domains. A Collaborative Predictive Optimization System (CPOS) is designed to classify expected occurrences of delays, to optimize order allocations, and to enable stakeholder collaboration. Delay prediction involves Decision Trees, Random Forests, and eXtreme Gradient Boosting (XGBoost). Supplier selection is solved using mathematical programming, while considering the classification of expected occurrences of delays. Stakeholder collaboration relies on information systems and uses prediction and optimization to support finding satisfactory agreements. The approach is validated using a real 3.5-year dataset, including 139 suppliers, 7,934 products and 89,080 purchase orders. A detailed experimentation, including sensitivity analysis, best–worst case analysis, and a larger scale analysis on company datasets, shows that the suggested approach enhances collaboration and achieves delay reduction and total procurement cost savings. Valuable managerial insights are collected, including the necessity to adopt digital technologies, to adapt company workflows, and to improve upstream negotiations and supplier commitments to yearly plannings.

AiMap+: Guiding Technology Mapping for ASICs via Learning Delay Prediction

Technology mapping is an essential process in the Electronic Design Automation (EDA) flow which aims to find an optimal implementation of a logic network from a technology library. In application-specific integrated circuit (ASIC) designs, the non-linear delay behaviors of cells in the library essentially guide the search direction of technology mappers. Existing methods for cell delay estimation, however, rely on approximate simplifications that significantly compromise accuracy, thereby limiting the achievement of better Quality-of-Result (QoR). To address this challenge, we propose formulating cell delay estimation as a regression learning task by incorporating multiple perspective features, such as the structure of logic networks and non-linear cell delays, to guide the mapper search. We design a learning model that incorporates a customized attention mechanism to be aware of the pin delay and jointly learns the hierarchy between the logic network and library through a Neural Tensor Network, with the help of proposed parameterizable strategies to generate learning labels. Experimental results show that (i) our proposed method noticeably improves area by 9.3% and delay by 1.5%, and (ii) improves area by 12.0% for delay-oriented mapping, compared with the well-known mapper.