Search results for: scheduler

Authors: Asma Rebaya, Imen Amari, Kaouther Gasmi, Salem Hasnaoui

Abstract:

Over these last years, the number of cores witnessed a spectacular increase in digital signal and general use processors. Concurrently, significant researches are done to get benefit from the high degree of parallelism. Indeed, these researches are focused to provide an efficient scheduling from hardware/software systems to multicores architecture. The scheduling process consists on statically choose one core to execute one task and to specify an execution order for the application tasks. In this paper, we describe an efficient scheduler that calculates the optimal number of cores required to schedule an application, gives a heuristic scheduling solution and evaluates its cost. Our proposal results are evaluated and compared with Preesm scheduler results and we prove that ours allows better scheduling in terms of latency, computation time and number of cores.

Keywords: computation time, hardware/software system, latency, optimization, multi-cores platform, scheduling

Procedia PDF Downloads 245

Authors: Heng Chia Ying, Charmaine Tan Chai Nie, Burra Venkata Durga Kumar

Abstract:

Process scheduling is the method of process management that determines which process the CPU will proceed with for the next task and how long it takes. Some issues were found in process management, particularly for Priority Scheduling (PS) and Round Robin Scheduling (RR). The proposed recommendations made for IPRRS are to combine the strengths of both into a combining algorithm while they draw on others to compensate for each weakness. A significant improvement on the combining technique of scheduler, Incorporating Priority Round-Robin Scheduler (IPRRS) address an algorithm for both high and low priority task to sustain the indefinite blocking issue faced in the priority scheduling algorithm and minimize the average turnaround time (ATT) and average waiting time (AWT) in RR scheduling algorithm. This paper will delve into the simple rules introduced by IPRRS and enhancements that both PS and RR bring to the execution of processes in the operating system. Furthermore, it incorporates the best aspects of each algorithm to build the optimum algorithm for a certain case in terms of prioritized processes, ATT, and AWT.

Keywords: round Robin scheduling, priority scheduling, indefinite blocking, process management, sustain, turnaround time

Procedia PDF Downloads 93

Authors: Desislav Andreev, Veselin Stanev

Abstract:

Linux operating system continues to gain popularity with every passed year. This is due to its open-source license and a great number of distributions, covering users’ needs. At first glance it seems that Linux can be integrated in every type of systems – it is already present in personal computers, smartphones and even in some embedded systems like Raspberry Pi. However, Linux still does not meet the performance and security requirements to run effectively on a real-time system. Real-time systems are very time-restricted – their processes have to execute and finish at strict time intervals. The Completely Fair Scheduler present in Linux does not have such scheduling capabilities and it is not able to ensure that critical-time processes will execute on time. One of the ways to solve this problem is implementing an Adaptive Partition Scheduler solution similar to that present in QNX Neutrino operating system. This type of scheduling divides the CPU in multiple adaptive partitions where each partition holds a percentage of CPU usage called budget, which allows optimal usage of the CPU resources and also provides protection against cyber attacks such as Denial of Service. This approach will also benefit systems, where functional safety is highly demanded, such as the instrumental clusters in the Automotive industry. The purpose of this paper is to present a concept of Adaptive Partition Scheduler designed for Linux-based operating systems.

Keywords: adaptive partitions, Linux kernel modules, real-time systems, scheduling

Procedia PDF Downloads 67

Authors: Md Habibur Rahman, Jaeho Kim

Abstract:

Efficient process scheduling is a crucial factor in ensuring optimal system performance and resource utilization in computer systems. While various algorithms have been proposed over the years, there are still limitations to their effectiveness. This paper introduces a new Wait-Optimized Scheduler (WOS) algorithm that aims to minimize process waiting time by dividing them into two layers and considering both process time and waiting time. The WOS algorithm is non-preemptive and prioritizes processes with the shortest WOS. In the first layer, each process runs for a predetermined duration, and any unfinished process is subsequently moved to the second layer, resulting in a decrease in response time. Whenever the first layer is free or the number of processes in the second layer is twice that of the first layer, the algorithm sorts all the processes in the second layer based on their remaining time minus waiting time and sends one process to the first layer to run. This ensures that all processes eventually run, optimizing waiting time. To evaluate the performance of the WOS algorithm, we conducted experiments comparing its performance with traditional scheduling algorithms such as First-Come-First-Serve (FCFS) and Shortest-Job-First (SJF). The results showed that the WOS algorithm outperformed the traditional algorithms in reducing the waiting time of processes, particularly in scenarios with a large number of short tasks with long wait times. Our study highlights the effectiveness of the WOS algorithm in improving process scheduling efficiency in computer systems. By reducing process waiting time, the WOS algorithm can improve system performance and resource utilization. The findings of this study provide valuable insights for researchers and practitioners in developing and implementing efficient process scheduling algorithms.

Keywords: process scheduling, wait-optimized scheduler, response time, non-preemptive, waiting time, traditional scheduling algorithms, first-come-first-serve, shortest-job-first, system performance, resource utilization

Procedia PDF Downloads 57

Authors: Ionel Zagan, Vasile Gheorghita Gaitan

Abstract:

The development of CPUs and of real-time systems based on them made it possible to use time at increasingly low resolutions. Together with the scheduling methods and algorithms, time organizing has been improved so as to respond positively to the need for optimization and to the way in which the CPU is used. This presentation contains both a detailed theoretical description and the results obtained from research on improving the performances of the nMPRA (Multi Pipeline Register Architecture) processor by implementing specific functions in hardware. The proposed CPU architecture has been developed, simulated and validated by using the FPGA Virtex-7 circuit, via a SoC project. Although the nMPRA processor hardware structure with five pipeline stages is very complex, the present paper presents and analyzes the tests dedicated to the implementation of the CPU and of the memory on-chip for instructions and data. In order to practically implement and test the entire SoC project, various tests have been performed. These tests have been performed in order to verify the drivers for peripherals and the boot module named Bootloader.

Keywords: hardware scheduler, nMPRA processor, real-time systems, scheduling methods

Procedia PDF Downloads 237

Authors: Ionel Zagan, Vasile Gheorghita Gaitan

Abstract:

Minimizing the response time to asynchronous events in a real-time system is an important factor in increasing the speed of response and an interesting concept in designing equipment fast enough for the most demanding applications. The present article will present the results regarding the validation of the nMPRA (Multi Pipeline Register Architecture) architecture using the FPGA Virtex-7 circuit. The nMPRA concept is a hardware processor with the scheduler implemented at the processor level; this is done without affecting a possible bus communication, as is the case with the other CPU solutions. The implementation of static or dynamic scheduling operations in hardware and the improvement of handling interrupts and events by the real-time executive described in the present article represent a key solution for eliminating the overhead of the operating system functions. The nMPRA processor is capable of executing a preemptive scheduling, using various algorithms without a software scheduler. Therefore, we have also presented various scheduling methods and algorithms used in scheduling the real-time tasks.

Keywords: nMPRA architecture, pipeline processor, preemptive scheduling, real-time system

Procedia PDF Downloads 321

Authors: T. Wanyama, B. Far

Abstract:

Automatic irrigation systems usually conveniently protect landscape investment. While conventional irrigation systems are known to be inefficient, automated ones have the potential to optimize water usage. In fact, there is a new generation of irrigation systems that are smart in the sense that they monitor the weather, soil conditions, evaporation and plant water use, and automatically adjust the irrigation schedule. In this paper, we present an agent based smart irrigation system. The agents are built using a mix of commercial off the shelf software, including MATLAB, Microsoft Excel and KEPServer Ex5 OPC server, and custom written code. The Irrigation Scheduler Agent uses fuzzy logic to integrate the information that affect the irrigation schedule. In addition, the Multi-Agent system uses Open Platform Connectivity (OPC) technology to share data. OPC technology enables the Irrigation Scheduler Agent to communicate over the Internet, making the system scalable to a municipal or regional agent based water monitoring, management, and optimization system. Finally, this paper presents simulation and pilot installation test result that show the operational effectiveness of our system.

Keywords: community water usage, fuzzy logic, irrigation, multi-agent system

Procedia PDF Downloads 263

Authors: Bahram Khan, Anderson Rocha Ramos, Rui R. Paulo, Fernando J. Velez

Abstract:

With the growing demand for a new blend of applications, the users dependency on the internet is increasing day by day. Mobile internet users are giving more attention to their own experiences, especially in terms of communication reliability, high data rates and service stability on move. This increase in the demand is causing saturation of existing radio frequency bands. To address these challenges, researchers are investigating the best approaches, Carrier Aggregation (CA) is one of the newest innovations, which seems to fulfill the demands of the future spectrum, also CA is one the most important feature for Long Term Evolution - Advanced (LTE-Advanced). For this purpose to get the upcoming International Mobile Telecommunication Advanced (IMT-Advanced) mobile requirements (1 Gb/s peak data rate), the CA scheme is presented by 3GPP, which would sustain a high data rate using widespread frequency bandwidth up to 100 MHz. Technical issues such as aggregation structure, its implementations, deployment scenarios, control signal techniques, and challenges for CA technique in LTE-Advanced, with consideration of backward compatibility, are highlighted in this paper. Also, performance evaluation in macro-cellular scenarios through a simulation approach is presented, which shows the benefits of applying CA, low-complexity multi-band schedulers in service quality, system capacity enhancement and concluded that enhanced multi-band scheduler is less complex than the general multi-band scheduler, which performs better for a cell radius longer than 1800 m (and a PLR threshold of 2%).

Keywords: component carrier, carrier aggregation, LTE-advanced, scheduling

Procedia PDF Downloads 151

Authors: Nousheen Hashmi, Shoab Ahmad Khan

Abstract:

Active collaboration among the green energy sources and the load demand leads to serious issues related to power quality and stability. The growing number of green energy resources and Distributed-Generators need newer strategies to be incorporated for their operations to keep the power energy stability among green energy resources and micro-grid/Utility Grid. This paper presents a novel technique for energy power management in Grid-Connected Photovoltaic with energy storage system under set of constraints including weather conditions, Load Shedding Hours, Peak pricing Hours by using rule-based fuzzy smart grid controller to schedule power coming from multiple Power sources (photovoltaic, grid, battery) under the above set of constraints. The technique fuzzifies all the inputs and establishes fuzzify rule set from fuzzy outputs before defuzzification. Simulations are run for 24 hours period and rule base power scheduler is developed. The proposed fuzzy controller control strategy is able to sense the continuous fluctuations in Photovoltaic power generation, Load Demands, Grid (load Shedding patterns) and Battery State of Charge in order to make correct and quick decisions.The suggested Fuzzy Rule-based scheduler can operate well with vague inputs thus doesn’t not require any exact numerical model and can handle nonlinearity. This technique provides a framework for the extension to handle multiple special cases for optimized working of the system.

Keywords: photovoltaic, power, fuzzy logic, distributed generators, state of charge, load shedding, membership functions

Procedia PDF Downloads 451

Authors: Asma Rebaya, Kaouther Gasmi, Imen Amari, Salem Hasnaoui

Abstract:

Over these last years, applications such as telecommunications, signal processing, digital communication with advanced features (Multi-antenna, equalization..) witness a rapid evaluation accompanied with an increase of user exigencies in terms of latency, the power of computation… To satisfy these requirements, the use of hardware/software systems is a common solution; where hardware is composed of multi-cores and software is represented by models of computation, synchronous data flow (SDF) graph for instance. Otherwise, the most of the embedded system designers utilize Simulink for modeling. The issue is how to simplify the c code generation, for a multi-cores platform, of an application modeled by Simulink. To overcome this problem, we propose a workflow allowing an automatic transformation from the Simulink model to the SDF graph and providing an efficient schedule permitting to optimize the number of cores and to minimize latency. This workflow goes from a Simulink application and a hardware architecture described by IP.XACT language. Based on the synchronous and hierarchical behavior of both models, the Simulink block diagram is automatically transformed into an SDF graph. Once this process is successfully achieved, the scheduler calculates the optimal cores’ number needful by minimizing the maximum density of the whole application. Then, a core is chosen to execute a specific graph task in a specific order and, subsequently, a compatible C code is generated. In order to perform this proposal, we extend Preesm, a rapid prototyping tool, to take the Simulink model as entry input and to support the optimal schedule. Afterward, we compared our results to this tool results, using a simple illustrative application. The comparison shows that our results strictly dominate the Preesm results in terms of number of cores and latency. In fact, if Preesm needs m processors and latency L, our workflow need processors and latency L'< L.

Keywords: hardware/software system, latency, modeling, multi-cores platform, scheduler, SDF graph, Simulink model, workflow

Procedia PDF Downloads 228

Authors: M. Benbouzid, Q. Bresson, A. Duclos, K. Longo, Q. Morel

Abstract:

Currently, electricity suppliers must predict the consumption of their customers in order to deduce the power they need to produce. It is, then, important in a first step to optimize household consumption to obtain more constant curves by limiting peaks in energy consumption. Here centralized real time scheduling is proposed to manage the equipment's starting in parallel. The aim is not to exceed a certain limit while optimizing the power consumption across a habitat. The Raspberry Pi is used as a box; this scheduler interacts with the various sensors in 6LoWPAN. At the scale of a single dwelling, household consumption decreases, particularly at times corresponding to the peaks. However, it would be wiser to consider the use of a residential complex so that the result would be more significant. So, the ceiling would no longer be fixed. The scheduling would be done on two scales, firstly, per dwelling, and secondly, at the level of a residential complex.

Keywords: smart grid, energy box, scheduling, Gang Model, energy consumption, energy management system, wireless sensor network

Procedia PDF Downloads 271

Authors: Fahad Suleiman

Abstract:

Queuing, in medical system is the process of moving patients in a specific sequence to a specific service according to the patients’ nature of illness. The term scheduling stands for the process of computing a schedule. This may be done by a queuing based scheduler. This paper focuses on the medical consultancy system, the different queuing algorithms that are used in healthcare system to serve the patients, and the average waiting time. The aim of this paper is to build automatic queuing system for organizing the medical queuing system that can analyses the queue status and take decision which patient to serve. The new queuing architecture model can switch between different scheduling algorithms according to the testing results and the factor of the average waiting time. The main innovation of this work concerns the modeling of the average waiting time is taken into processing, in addition with the process of switching to the scheduling algorithm that gives the best average waiting time.

Keywords: queuing systems, queuing system models, scheduling algorithms, patients

Procedia PDF Downloads 320

Authors: Yao Lu, Xiuguo Zhang, Zhiying Cao

Abstract:

In this paper, Load Balancing idea is used in the Web service mobile host. The main idea of Load Balancing is to establish a one-to-many mapping mechanism: An entrance-mapping request to plurality of processing node in order to realize the dividing and assignment processing. Because the mobile host is a resource constrained environment, there are some Web services which cannot be completed on the mobile host. When the mobile host resource is not enough to complete the request, Load Balancing scheduler will divide the request into a plurality of sub-requests and transfer them to different auxiliary mobile hosts. Auxiliary mobile host executes sub-requests, and then, the results will be returned to the mobile host. Service request integrator receives results of sub-requests from the auxiliary mobile host, and integrates the sub-requests. In the end, the complete request is returned to the client. Experimental results show that this technology adopted in this paper can complete requests and have a higher efficiency.

Keywords: Dinic, load balancing, mobile host, web service

Procedia PDF Downloads 296

Authors: Sina Saadati

Abstract:

Multiprocessors Systems-On-Chips (MPSOCs) are used widely on modern computers to execute sophisticated software and applications. These systems include different processors for distinct aims. Most of the proposed task schedulers attempt to improve energy consumption. In some schedulers, the processor's temperature is considered to increase the system's reliability and performance. In this research, we have proposed a new method for thermal-aware task scheduling which is based on an artificial neural network (ANN). This method enables us to consider a variety of factors in the scheduling process. Some factors like ambient temperature, season (which is important for some embedded systems), speed of the processor, computing type of tasks and have a complex relationship with the final temperature of the system. This Issue can be solved using a machine learning algorithm. Another point is that our solution makes the system intelligent So that It can be adaptive. We have also shown that the computational complexity of the proposed method is cheap. As a consequence, It is also suitable for battery-powered systems.

Keywords: task scheduling, MOSOC, artificial neural network, machine learning, architecture of computers, artificial intelligence

Procedia PDF Downloads 66

Authors: Paul Han, Jun-Geol Baek

Abstract:

In the flat panel display industry, the scheduler and dispatching system to meet production target quantities and the deadline of production are the major production management system which controls each facility production order and distribution of WIP (Work in Process). In dispatching system, delivery time is a key factor for the time when a lot can be supplied to the facility. In this paper, we use survival analysis methods to identify main factors and a forecasting model of delivery time. Of survival analysis techniques to select important explanatory variables, the cox proportional hazard model is used to. To make a prediction model, the Accelerated Failure Time (AFT) model was used. Performance comparisons were conducted with two other models, which are the technical statistics model based on transfer history and the linear regression model using same explanatory variables with AFT model. As a result, the Mean Square Error (MSE) criteria, the AFT model decreased by 33.8% compared to the existing prediction model, decreased by 5.3% compared to the linear regression model. This survival analysis approach is applicable to implementing a delivery time estimator in display manufacturing. And it can contribute to improve the productivity and reliability of production management system.

Keywords: delivery time, survival analysis, Cox PH model, accelerated failure time model

Procedia PDF Downloads 498

Authors: Patrick May Mukonki

Abstract:

KOV pit (Kamoto Oliveira Virgule) is located 10 km from Kolwezi town, one of the mineral rich town in the Lualaba province of the Democratic Republic of Congo. The KOV pit is currently operating under the Katanga Mining Limited (KML), a Glencore-Gecamines (a State Owned Company) join venture. Recently, the mine optimization process provided a life of mine of approximately 10 years withnice pushbacks using the Datamine NPV Scheduler software. In previous KOV pit studies, we recently outlined the impact of the accuracy of the geological information on a long-term mine plan for a big copper mine such as KOV pit. The approach taken, discussed three main scenarios and outlined some weaknesses on the geological information side, and now, in this paper that we are going to develop here, we are going to highlight, as an overview, those weaknesses, strengths and opportunities, in a global SWOT analysis. The approach we are taking here is essentially descriptive in terms of steps taken to optimize KOV pit and, at every step, we categorized the challenges we faced to have a better tradeoff between what we called strengths and what we called weaknesses. The same logic is applied in terms of the opportunities and threats. The SWOT analysis conducted in this paper demonstrates that, despite a general poor ore body definition, and very rude ground water conditions, there is room for improvement for such high grade ore body.

Keywords: mine planning, mine optimization, mine scheduling, SWOT analysis

Procedia PDF Downloads 190

Authors: Hassen Hamouda, Mohamed Ouwais Kabaou, Med Salim Bouhlel

Abstract:

The growth of wireless technology made opportunistic scheduling a widespread theme in recent research. Providing high system throughput without reducing fairness allocation is becoming a very challenging task. A suitable policy for resource allocation among users is of crucial importance. This study focuses on scheduling multiple streaming flows on the downlink of a WiMAX system based on orthogonal frequency division multiple access (OFDMA). In this paper, we take the first step in formulating and analyzing this problem scrupulously. As a result, we proposed a new scheduling scheme based on Round Robin (RR) Algorithm. Because of its non-opportunistic process, RR does not take in account radio conditions and consequently it affect both system throughput and multi-users diversity. Our contribution called MORRA (Modified Round Robin Opportunistic Algorithm) consists to propose a solution to this issue. MORRA not only exploits the concept of opportunistic scheduler but also takes into account other parameters in the allocation process. The first parameter is called courtesy coefficient (CC) and the second is called Buffer Occupancy (BO). Performance evaluation shows that this well-balanced scheme outperforms both RR and MaxSNR schedulers and demonstrate that choosing between system throughput and fairness is not required.

Keywords: OFDMA, opportunistic scheduling, fairness hierarchy, courtesy coefficient, buffer occupancy

Procedia PDF Downloads 255

Authors: U. Borasi, Amit Kr. Jain, Rakesh, Piyush Jain

Abstract:

Data collection, data preparation, model training, model evaluation, and deployment are all processes in a typical machine learning workflow. Training data needs to be gathered and organised. This often entails collecting a sizable dataset and cleaning it to remove or correct any inaccurate or missing information. Preparing the data for use in the machine learning model requires pre-processing it after it has been acquired. This often entails actions like scaling or normalising the data, handling outliers, selecting appropriate features, reducing dimensionality, etc. This pre-processed data is then used to train a model on some machine learning algorithm. After the model has been trained, it needs to be assessed by determining metrics like accuracy, precision, and recall, utilising a test dataset. Every time a new model is built, both data pre-processing and model training—two crucial processes in the Machine learning (ML) workflow—must be carried out. Thus, there are various Machine Learning algorithms that can be employed for every single approach to data pre-processing, generating a large set of combinations to choose from. Example: for every method to handle missing values (dropping records, replacing with mean, etc.), for every scaling technique, and for every combination of features selected, a different algorithm can be used. As a result, in order to get the optimum outcomes, these tasks are frequently repeated in different combinations. This paper suggests a simple architecture for organizing this largely produced “combination set of pre-processing steps and algorithms” into an automated workflow which simplifies the task of carrying out all possibilities.

Keywords: machine learning, automation, AUTOML, architecture, operator pool, configuration, scheduler

Procedia PDF Downloads 15

Authors: Imen Amari, Kaouther Gasmi, Asma Rebaya, Salem Hasnaoui

Abstract:

The problem of scheduling and mapping data flow applications on multi-core architectures is notoriously difficult. This difficulty is related to the rapid evaluation of Telecommunication and multimedia systems accompanied by a rapid increase of user requirements in terms of latency, execution time, consumption, energy, etc. Having an optimal scheduling on multi-cores DSP (Digital signal Processors) platforms is a challenging task. In this context, we present a novel technic and algorithm in order to find a valid schedule that optimizes the key performance metrics particularly the Latency. Our contribution is based on Satisfiability Modulo Theories (SMT) solving technologies which is strongly driven by the industrial applications and needs. This paper, describe a scheduling module integrated in our proposed Workflow which is advised to be a successful approach for programming the applications based on NoC-DSP platforms. This workflow transform automatically a Simulink model to a synchronous dataflow (SDF) model. The automatic transformation followed by SMT solver scheduling aim to minimize the final latency and other software/hardware metrics in terms of an optimal schedule. Also, finding the optimal numbers of cores to be used. In fact, our proposed workflow taking as entry point a Simulink file (.mdl or .slx) derived from embedded Matlab functions. We use an approach which is based on the synchronous and hierarchical behavior of both Simulink and SDF. Whence, results of running the scheduler which exist in the Workflow mentioned above using our proposed SMT solver algorithm refinements produce the best possible scheduling in terms of latency and numbers of cores.

Keywords: multi-cores DSP, scheduling, SMT solver, workflow

Procedia PDF Downloads 251

Authors: Fahad Y. Al-dawish

Abstract:

The current trend by a large number of organizations and individuals to use cloud computing. Many consider it a significant shift in the field of computing. Cloud computing are distributed and parallel systems consisting of a collection of interconnected physical and virtual machines. With increasing request and profit of cloud computing infrastructure, diverse computing processes can be executed on cloud environment. Many organizations and individuals around the world depend on the cloud computing environments infrastructure to carry their applications, platform, and infrastructure. One of the major and essential issues in this environment related to allocating incoming tasks to suitable virtual machine (cloud task scheduling). Cloud task scheduling is classified as optimization problem, and there are several meta-heuristic algorithms have been anticipated to solve and optimize this problem. Good task scheduler should execute its scheduling technique on altering environment and the types of incoming task set. In this research project a cloud task scheduling methodology based on ant colony optimization ACO algorithm, we call it ACO-TS Ant Colony Optimization for Task Scheduling has been proposed and compared with different scheduling algorithms (Random, First Come First Serve FCFS, and Fastest Processor to the Largest Task First FPLTF). Ant Colony Optimization (ACO) is random optimization search method that will be used for assigning incoming tasks to available virtual machines VMs. The main role of proposed algorithm is to minimizing the makespan of certain tasks set and maximizing resource utilization by balance the load among virtual machines. The proposed scheduling algorithm was evaluated by using Cloudsim toolkit framework. Finally after analyzing and evaluating the performance of experimental results we find that the proposed algorithm ACO-TS perform better than Random, FCFS, and FPLTF algorithms in each of the makespaan and resource utilization.

Keywords: cloud Task scheduling, ant colony optimization (ACO), cloudsim, cloud computing

Procedia PDF Downloads 388

Authors: Haya Salah, Srinivas Sharan

Abstract:

Healthcare facilities use appointment systems to schedule their appointments and to manage access to their medical services. With the growing demand for outpatient care, it is now imperative to manage physician's time effectively. However, high variation in consultation duration affects the clinical scheduler's ability to estimate the appointment duration and allocate provider time appropriately. Underestimating consultation times can lead to physician's burnout, misdiagnosis, and patient dissatisfaction. On the other hand, appointment durations that are longer than required lead to doctor idle time and fewer patient visits. Therefore, a good estimation of consultation duration has the potential to improve timely access to care, resource utilization, quality of care, and patient satisfaction. Although the literature on factors influencing consultation length abound, little work has done to predict it using based data-driven approaches. Therefore, this study aims to predict consultation duration using supervised machine learning algorithms (ML), which predicts an outcome variable (e.g., consultation) based on potential features that influence the outcome. In particular, ML algorithms learn from a historical dataset without explicitly being programmed and uncover the relationship between the features and outcome variable. A subset of the data used in this study has been obtained from the electronic medical records (EMR) of four different outpatient clinics located in central Pennsylvania, USA. Also, publicly available information on doctor's characteristics such as gender and experience has been extracted from online sources. This research develops three popular ML algorithms (deep learning, random forest, gradient boosting machine) to predict the treatment time required for a patient and conducts a comparative analysis of these algorithms with respect to predictive performance. The findings of this study indicate that ML algorithms have the potential to predict the provider service time with superior accuracy. While the current approach of experience-based appointment duration estimation adopted by the clinic resulted in a mean absolute percentage error of 25.8%, the Deep learning algorithm developed in this study yielded the best performance with a MAPE of 12.24%, followed by gradient boosting machine (13.26%) and random forests (14.71%). Besides, this research also identified the critical variables affecting consultation duration to be patient type (new vs. established), doctor's experience, zip code, appointment day, and doctor's specialty. Moreover, several practical insights are obtained based on the comparative analysis of the ML algorithms. The machine learning approach presented in this study can serve as a decision support tool and could be integrated into the appointment system for effectively managing patient scheduling.

Keywords: clinical decision support system, machine learning algorithms, patient scheduling, prediction models, provider service time

Procedia PDF Downloads 83