In the modern era consumer awareness on quality aspects has been a growing concern for the fresh produce market due to the fact that consumer perspective defines the bottom line of all agricultural businesses. External damage to produce does not only render fruit less attractive but damaged locations serve as entry points for pathogens resulting is food safety issues. Because tomatoes have a limited shelf life, it is vital to control the factors that lead to earlier deterioration of the quality of the product. Shipping, handling and distribution can cause numerous forms of cuts and bruises on harvested tomatoes which compromise their quality and appearance. Furthermore the economic value to the retailer and grower is reduced (Chonhenchob et al., 2009). Post-harvest science focus mainly on the quality of fresh produce. One of the areas of interest is the shipment of tomatoes using road transport. Trucks are one of the best methods for transporting perishable products because of shorter transport times and the ability to reach more inland destinations than any other mode of transport (Jarimopas et al., 2005; Chonhenchob et al., 2009). Although the flexibility of road transport is an advantage, previous studies have indicated that fruit and vegetables suffer mechanical damage due to in-transit vibrations which is caused by the road condition (Jarimopas et al., 2005). The condition of roads in South Africa is dependent on the management plan execution by the managing agent. The National Road Network, maintained by SANRAL is predominantly in a good condition (Ittmann, 2013). In contrast, condition assessment data for provincial roads indicate that roads are deteriorating at an alarming pace, not to mention that the majority of road networks under municipal authorities have no data at all (SAICE, 2011). To date there is no model that relates tomato damage and loss in shelf life to the road condition, fruit maturity and position in the container. For this experiment the in-transit conditions were monitored on trucks travelling from three farms in Limpopo, owned by the ZZ2 group, to the fresh produce market in Pietermaritzburg. These trucks drive on a variety of roads including gravel or rural roads where higher roughness values are probable along with more produce damage. The experimental setup consisted of two phases. The first phase was the in-transit monitoring of the conditions to which tomatoes are exposed when shipped from grower to the farmers market. The second phase was the laboratory simulation of in-transit conditions to create a model for the prediction of shelf-life under controlled conditions. Equipment for the field experiment included a profilometer to determine road conditions, accelerometers to determine in-transit vibrations, pressure sensors to determine in-transit pressures. Equipment for the laboratory experiment included a vibration table to simulate different road conditions, pressure sensors to measure pressures that can be related to in-transit pressures and a colour meter to measure colour changes in damaged and control tomatoes. From the in-transit pressure analysis it was concluded that the amount of pressure cycles that a tomato experience increase as the roughness of the road increase and the force distribution that is applied to the tomatoes becomes wider to include forces larger in magnitude. Good correlations existed between in-transit and laboratory pressures. Colour measurements had no strong trends that could be related to damage and an experimental model based on consumer perspective was developed. The experimental model was designed based on a marketability matrix that models the decision of the consumer on whether to purchase a tomato or not. Ultimately it is a subjective matter and each consumer would react differently towards the colour and firmness of the tomato in question. The model indicated that for roads with high roughness values (International Roughness Index (IRI) > 8 m/km), which mostly consist of farm roads that are poorly maintained, all tomatoes in the first and second layers would acquire significant damage irrespective of the maturity of the fruit. On well-maintained roads with roughness values less than 3.5 m/km red tomatoes in the top layers tend to damage more with an increase in time as compared to tomatoes in the lower layers. Green and pink tomatoes are more resistant to damage in the top layers than the red tomatoes. From the damage models it is apparent that as the roughness of the road increases the damage to tomatoes increase as well. Tomato maturity and the position of the tomatoes in a container also influence the amount of damage to the fruit. With this information in hand, logistic planners can make informed decisions during route planning in weighing transportation costs to the cost of losses to produce during transportation. Similar models can be developed to include other fruits and vegetables. / Dissertation (MEng)--University of Pretoria, 2017. / Tamatie Produsente Organisasie (TPO) / ZZ2 / Post-Harvest Innovation Program (PHI) / Civil Engineering / MEng / Unrestricted

Road conditions are a critical issue for road users as, if not given sufficient attention, they may threaten users’ lives. The environmental parameters, such as snowy, icy, dry and wet, are important in relation to the condition of roads. This is particularly true in relation to the northern regions and greatest concern should be in relation to snowy and icy situations. In this thesis, a system based on an InGaAs area scan sensor utilizes NIR technology to detect water or ice on the road so as to enable drivers to avoid slippery road conditions. The conditions caused by freezing water on road surface are particularly dangerous and are not easy to observe and it is hope that this project will boost traffic safety. The system is able to assist road maintenance personnel in forecasting and detecting slippery road conditions during winter road maintenance (WRM). The system, which is based on FPGA, has functionalities that display the captured images on an HDMI monitor and send the images to the software on a host PC via the UART protocol. An interface board, which carries the sensor and which connects to the FPGA board, is developed for NIR sensor. VHDL implementation and PC software design are the works included in the project. Besides, this device is exploited utilizing InGaAs image sensor. According to its features, it can be applied in other applications which will also be discussed. Finally, experiments are conducted in order to investigate the system’s operation with the variation of temperature.

There is a great need to develop systems that can continuously provide correct information about road surface status depending on the prevailing weather conditions. This will minimize accidents and optimize transportation. In this thesis different methods for the determination of the road surface status have been studied and analyzed, and suggestions of new technology are proposed. Information about the road surface status is obtained traditionally from various sensors mounted directly in the road surface. This information must then be analyzed to create automated warning systems for road users and road maintenance personnel. The purpose of this thesis is to investigate how existing technologies can be used to obtain a more accurate description of the current road conditions. Another purpose is also to investigate how existing technologies can be used to obtain a more accurate description of the current road conditions. Furthermore, the aim is to develop non-contact technologies able to determine and classify road conditions over a larger area, since there is no system available today that can identify differences in road surface status in the wheel tracks and between the wheel tracks. Literature studies have been carried out to find the latest state of the art research and technology, and the research work is mainly based on empirical studies. A large part of the research has involved planning and setting up laboratory experiments to test and verify hypotheses that have emerged from the literature studies. Initially a few traditional road-mounted sensors were analyzed regarding their ability to determine the road conditions and the impact on their measured values when the sensors were exposed to contamination agents such as glycol and oil. Furthermore, non-contact methods for determining the status of the road surface have been studied. Images from cameras working in the visible range, together data from the Swedish Transportation Administration road weather stations, have been used to develop computerized road status classification models that can distinguish between a dry, wet, icy and snowy surface. Field observations have also been performed to get the ground truth for developing these models. In order to improve the ability to accurately distinguish between different surface statuses, measurement systems involving sensors working in the Near-Infrared (NIR) range have been utilized. In this thesis a new imaging method for determining road conditions with NIR camera technology is developed and described. This method was tested in a field study performed during the winter 2013-2014 with successful results. The results show that some traditional sensors could be used even with future user-friendly de-icing chemicals. The findings from using visual camera systems and meteorological parameters to determine the road status showed that they provide previously unknown information about road conditions. It was discovered that certain road conditions such as black ice is not always detectable using this technology. Therefore, research was performed that utilized the NIR region where it proved to be possible to detect and distinguish different road conditions, such as black ice. NIR camera technology was introduced in the research since the aim of the thesis was to find a method that provides information on the status of the road over a larger area. The results show that if several images taken in different spectral bands are analyzed with the support of advanced computer models, it is possible to distinguish between a dry, wet, icy and snowy surface. This resulted in the development of a NIR camera system that can distinguish between different surface statuses. Finally, two of these prototype systems for road condition classification were evaluated. These systems were installed at E14 on both sides of the border between Sweden and Norway. The results of these field tests show that this new road status classification, based on NIR imaging spectral analysis, provides new information about the status of the road surface, compared to what can be obtained from existing measurement systems, particularly for detecting differences in and between the wheel tracks.

Trafikverket, the agency in charge of state road maintenance in Sweden, have a number of so-called Road Weather Information Systems (RWIS). The main purpose of the stations is to provide winter road maintenance workers with information to decide when roads need to be plowed and/or salted. Each RWIS have a number of sensors which make road weather-related measurements every 30 minutes. One of the sensors is dug into the road which can cause traffic disturbances and be costly for Trafikverket. Other RWIS sensors fail occasionally. This project aims at modelling a set of RWIS sensors using supervised machine learning algorithms. The sensors that are of interest to model are: Optic Eye, Track Ice Road Sensor (TIRS) and DST111. Optic Eye measures precipitation type and precipitation amount. Both TIRS and DST111 measure road surface temperature. The difference between TIRS and DST111 is that the former is dug into the road, and DST111 measures road surface temperature from a distance via infrared laser. Any supervised learning algorithm trained to model a given measurement made by a sensor, may only train on measurements made by the other sensors as input features. Measurements made by TIRS may not be used as input in modelling other sensors, since it is desired to see if TIRS can be removed. The following input features may also be used for training: road friction, road surface condition and timestamp. Scikit-learn was used as machine learning software in this project. An experimental approach was chosen to achieve the project results: A pre-determined set of supervised algorithms were compared using different amount of top relevant input features and different hyperparameter settings. Prior to achieving the results, a data preparation process was conducted. Observations with suspected or definitive errors were removed in this process. During the data preparation process, the timestamp feature was transformed into two new features: month and hour. The results in this project show that precipitation type was best modelled using Classification And Regression Tree (CART) on Scikit-learn default settings, achieving a performance score of Macro-F1test = 0.46 and accuracy = 0.84 using road surface condition, road friction, DST111 road surface temperature, hour and month as input features. Precipitation amount was best modelled using k-Nearest Neighbor (kNN); with k = 64 and road friction used as the only input feature, a performance score of MSEtest = 0.31 was attained. TIRS road surface temperature was best modelled with Multi-Layer Perceptron (MLP) using 64 hidden nodes and DST111 road surface temperature, road surface condition, road friction, month, hour and precipitation type as input features, with which a performance score of MSEtest = 0.88 was achieved. DST111 road surface temperature was best modelled using Random forest on Scikit-learn default settings with road surface condition, road friction, month, precipitation type and hour as input features, achieving a performance score of MSEtest = 10.16.

This thesis introduces a multi-Bayesian framework for detection and classification of features in environments abundant with error-inducing noise. The approach takes advantage of Bayesian correction and classification in three distinct stages. The corrective scheme described here extracts useful but highly stochastic features from a data source, whether vision-based or otherwise, to aid in higher-level classification. Unlike many conventional methods, these features’ uncertainties are characterized so that test data can be correctively cast into the feature space with probability distribution functions that can be integrated over class decision boundaries created by a quadratic Bayesian classifier. The proposed approach is specifically formulated for road crack detection and characterization, which is one of the potential applications. For test images assessed with this technique, ground truth was estimated accurately and consistently with effective Bayesian correction, showing a 33% improvement in recall rate over standard classification. Application to road cracks demonstrated successful detection and classification in a practical domain. The proposed approach is extremely effective in characterizing highly probabilistic features in noisy environments when several correlated observations are available either from multiple sensors or from data sequentially obtained by a single sensor. / Master of Science / Humans have an outstanding ability to understand things about the world around them. We learn from our youngest years how to make sense of things and perceive our environment even when it is not easy. To do this, we inherently think in terms of probabilities, updating our belief as we gain new information. The methods introduced here allow an autonomous system to think similarly, by applying a fairly common probabilistic technique to the task of perception and classification. In particular, road cracks are observed and classified using these methods, in order to develop an autonomous road condition monitoring system. The results of this research are promising; cracks are identified and correctly categorized with 92% accuracy, and the additional “intelligence” of the system leads to a 33% improvement in road crack assessment. These methods could be applied in a variety of contexts as the leading edge of robotics research seeks to develop more robust and human-like ways of perceiving the world.

This dissertation presents an approach to reconstruct degenerate near-planar road surface in three-dimensional (3D) while automatically detect road defects. Three techniques are developed in this dissertation to establish the proposed approach. The first technique is proposed to reconstruct the degenerate near-planar road surface into 3D from one camera. Unlike the traditional Structure from Motion (SfM) technique which has the degeneracy issue for near-planar object 3D reconstruction, the uniqueness of the proposed technique lies in the use of near-planar characteristics of surfaces in the 3D reconstruction process, which solves the degenerate road surface reconstruction problem using only two images. Following the accuracy-enhanced 3D reconstructed road surface, the second technique automatically detects and estimates road surface defects. As the 3D surface is inversely solved from 2D road images, the detection is achieved by jointly identifying irregularities from the 3D road surfaces and the corresponding image information, while clustering road defects and obstacles using a mean-shift algorithm with flat kernel to estimate the depth, size, and location of the defects. To enhance the physics-driven automatic detection reliability, the third technique proposes and incorporates a self-supervised learning structure with data-driven Convolutional Neural Networks (CNN). Different from supervised learning approaches which need labeled training images, the road anomaly detection network is trained by road surface images that are automatically labeled based on the reconstructed 3D surface information. In order to collect clear road surface images on the public road, a road surface monitoring system is designed and integrated for the road surface image capturing and visualization. The proposed approach is evaluated in both simulated environment and through real-world experiments. The parametric study of the proposed approach shows the small error of the 3D road surface reconstruction influenced by different variables such as the image noise, camera orientation, and the vertical movement of the camera in a controlled simulation environment. The comparison with traditional SfM technique and the numerical results of the proposed reconstruction using real-world road surface images then indicate that the proposed approach effectively reconstructs high quality near-planar road surface while automatically detects road defects with high precision, accuracy, and recall rates without the degenerate issue. / Doctor of Philosophy / Road is one of the key infrastructures for ground transportation. A good road surface condition can benefit mainly on three aspects: 1. Avoiding the potential traffic accident caused by road surface defects, such as potholes. 2. Reducing the damage to the vehicle initiated by the bad road surface condition. 3. Improving the driving and riding comfort on a healthy road surface. With all the benefits mentioned above, it is important to examine and check the road surface quality frequently and efficiently to make sure that the road surface is in a healthy condition. In order to detect any road surface defects on public road in time, this dissertation proposes three techniques to tackle the road surface defects detection problem: First, a near-planar road surface three-dimensional (3D) reconstruction technique is proposed. Unlike traditional 3D reconstruction technique, the proposed technique solves the degenerate issue for road surface 3D reconstruction from two images. The degenerate issue appears when the object reconstructed has near-planar surfaces. Second, after getting the accuracy-enhanced 3D road surface reconstruction, this dissertation proposes an automatic defects detection technique using both the 3D reconstructed road surface and the road surface image information. Although physics-based detection using 3D reconstruction and 2D images are reliable and explainable, it needs more time to process these data. To speed up the road surface defects detection task, the third contribution is a technique that proposes a self-supervised learning structure with data-driven Convolutional Neural Networks (CNN). Different from traditional neural network-based detection techniques, the proposed combines the 3D road information with the CNN output to jointly determine the road surface defects region. All the proposed techniques are evaluated using both the simulation and real-world experiments. Results show the efficacy and efficiency of the proposed techniques in this dissertation.

Increasing cycling as a means of personal travel couldgenerate environmental benefits if associated with acorresponding decrease in car-based transport. In seeking topromote cycling in wintertime, it is desirable to understandhow important the road surface condition is compared to otherfactors in people's decision to cycle or not. In this thesis,the possibility of increasing the number of cyclists byimproving the winter maintenance servicelevel on cycleways isexamined. The attitudes towards cycling during winter ingeneral, and in relation to winter maintenance of cycleways inparticular, is studied through questionnaire surveys. Bicyclemeasurements are related to weather data from Road WeatherInformation System, in order to know the influence on cycleflow during winter from different weather factors. Fieldstudies are performed testing unconventional winter maintenancemethods, in order to see if a higher service level could beachieved on cycleways and if that would lead to an increase inwinter cycling frequency. The field studies are evaluatedthrough road condition observations, measurements of friction,bicycle counts, a questionnaire survey and interviews. A visualmethod to assess winter road conditions on cycleways isdeveloped, in order to compare the service levels achievedusing different winter maintenance methods. There is a clear difference in mode choice between seasons.With improved winter maintenance service level it could bepossible to increase the number of bicycle trips to work duringwinter with, at the most, 18 %, and decrease the number of cartrips with 6 %. However, it could not be concluded with bicyclemeasurements, that an enhanced service level in fact, generateda higher winter cycling frequency. To increase cycling during winter, snow clearance is themost important maintenance measure. Skid control is not assignificant for the choice of mode but is important to attendto for safety reasons. Winter road condition propertiesimportant both with regard to safety and accessibility ofcyclists, are icy tracks formed when wet snow freezes, snowdepths greater than about 3 cm of loose snow or slush,unevenness in a snow covered surface, loose grit on a baresurface. Weather factors with negative influence on winter cyclingfrequency, are temperatures below +5 ° C,precipitationand strong winds. Only the occurrence of precipitation, not theamount of rain or snow, is significant for the cycle flow. Lowtemperatures are more important in reducing the cycle flow thanprecipitation. Temperatures around 0 ° C seem to be extracritical for cyclists, probably due to the larger influence ofprecipitation and slippery road conditions at thesetemperatures. An unconventional method using a power broom for snowclearance and brine or pre-wetted salt for de-icing, provides ahigher service level than winter maintenance methodstraditionally used, but it is about 2 to 3 times moreexpensive. The method has great potential in regions, such assouthern Sweden, with low snow accumulations but with major iceformation problems. To assess the maintenance service level,the visual assessment method developed and tested in thisproject is adequate for the purpose, however, furtherimprovements are desirable. As a complement to the visualassessment, a Portable Friction Tester can be used to measurethe surface friction on cycleways during wintertime. Keywords:Cycleways, winter maintenance, maintenanceservice level, mode choice, winter cycling frequency, wintermaintenance equipment, winter road condition assessment,bicycle measurements, friction measurement.

<p>Increasing cycling as a means of personal travel couldgenerate environmental benefits if associated with acorresponding decrease in car-based transport. In seeking topromote cycling in wintertime, it is desirable to understandhow important the road surface condition is compared to otherfactors in people's decision to cycle or not. In this thesis,the possibility of increasing the number of cyclists byimproving the winter maintenance servicelevel on cycleways isexamined. The attitudes towards cycling during winter ingeneral, and in relation to winter maintenance of cycleways inparticular, is studied through questionnaire surveys. Bicyclemeasurements are related to weather data from Road WeatherInformation System, in order to know the influence on cycleflow during winter from different weather factors. Fieldstudies are performed testing unconventional winter maintenancemethods, in order to see if a higher service level could beachieved on cycleways and if that would lead to an increase inwinter cycling frequency. The field studies are evaluatedthrough road condition observations, measurements of friction,bicycle counts, a questionnaire survey and interviews. A visualmethod to assess winter road conditions on cycleways isdeveloped, in order to compare the service levels achievedusing different winter maintenance methods.</p><p>There is a clear difference in mode choice between seasons.With improved winter maintenance service level it could bepossible to increase the number of bicycle trips to work duringwinter with, at the most, 18 %, and decrease the number of cartrips with 6 %. However, it could not be concluded with bicyclemeasurements, that an enhanced service level in fact, generateda higher winter cycling frequency.</p><p>To increase cycling during winter, snow clearance is themost important maintenance measure. Skid control is not assignificant for the choice of mode but is important to attendto for safety reasons. Winter road condition propertiesimportant both with regard to safety and accessibility ofcyclists, are icy tracks formed when wet snow freezes, snowdepths greater than about 3 cm of loose snow or slush,unevenness in a snow covered surface, loose grit on a baresurface.</p><p>Weather factors with negative influence on winter cyclingfrequency, are temperatures below +5 ° C,precipitationand strong winds. Only the occurrence of precipitation, not theamount of rain or snow, is significant for the cycle flow. Lowtemperatures are more important in reducing the cycle flow thanprecipitation. Temperatures around 0 ° C seem to be extracritical for cyclists, probably due to the larger influence ofprecipitation and slippery road conditions at thesetemperatures.</p><p>An unconventional method using a power broom for snowclearance and brine or pre-wetted salt for de-icing, provides ahigher service level than winter maintenance methodstraditionally used, but it is about 2 to 3 times moreexpensive. The method has great potential in regions, such assouthern Sweden, with low snow accumulations but with major iceformation problems. To assess the maintenance service level,the visual assessment method developed and tested in thisproject is adequate for the purpose, however, furtherimprovements are desirable. As a complement to the visualassessment, a Portable Friction Tester can be used to measurethe surface friction on cycleways during wintertime.</p><p><b>Keywords:</b>Cycleways, winter maintenance, maintenanceservice level, mode choice, winter cycling frequency, wintermaintenance equipment, winter road condition assessment,bicycle measurements, friction measurement.</p>

本研究從「使用與滿足」理論，以警察廣播電臺為探討的對象，研究聽眾願意主動提供路況資訊的使用動機與滿足程度。 警察廣播電臺為公營廣播媒體，節目內容以治安交通等公共服務為主。警廣自1971年設立第一座交通專業電臺臺北臺，以電話接收聽眾提供路況；於1996年率先啟用智慧型電話系統，將全省免付費路況提供專線統一為0800000123，受理來自全省各地聽眾提供即時路況。近年來，路況報導為廣播閱聽眾收聽廣播的重要因素之一，且從幾次重大的意外災害發生後，警廣很快的從聽眾提供的資訊掌握災情，聽眾主動提供的資訊發揮了功能。 本研究以量化研究方式，採用問卷調查法。研究結果發現，聽眾願意主動提供路況的動機，分別為「分享參與」、「資訊守望」、「人際連絡」、「尋求解決困難的方法」以及「個人化需求」等五個構面。並且想知道即時的路況是聽眾收聽警廣最主要的動機。 關鍵詞：使用與滿足、主動的閱聽人、廣播、路況報導 / Radio Listener’s Media Use and Gratification－ Example of the Police Broadcasting Service Abstract This study employs 「uses and gratifications」theory to investigate motivations for actively providing road condition information and resulting gratification among listeners of Police Broadcasting Service. Police Broadcasting Service is a public radio station with program content chiefly comprising public service matters connected with law and order and transportation. Since it established Taiwan's first specialized traffic station—Taipei Station—in 1971, Police Broadcasting Service has received telephone reports of road conditions from listeners. The station launched the 0800000123 smart phone system—Taiwan's first—in 1996, to provide a Taiwan-wide toll-free road condition hotline to accept real-time road condition reports from listeners throughout Taiwan. In recent years, the station's road reports have become one of the most important factors causing the public to listen to the station. Furthermore, after several major accidents that occurred in the past, Police Broadcasting Service quickly gained a picture of the situation from information provided by listeners, showing that the voluntary provision of information by listeners is very effective. This study employed a quantitative research approach and used the questionnaire survey method. The study's findings indicated that listeners' motivations for actively providing road information included the five aspects of 「shared participation」, 「information watchman」, 「interpersonal contact」,「looking for means of solving problems」, and 「individual needs」. Furthermore, wishing to hear real-time road conditions constitutes listeners' chief motivation for listening to Police Broadcasting Service. Keywords: uses and gratifications、active audience、listeners、radio station、road condition report

Winter in Northern Sweden comes with very harsh and unpredictable condition associated with large amounts of snowfall covering roadways thereby affecting transportation by roads. When the road conditions i.e. the snow depth, road unevenness and friction of the road surface are accessed and found to exceed the threshold, a maintenance action must be carried out to retain the road to the required condition for the user. The aim of maintenance, in this case, is to make the road comfortable, safe and economical for the road user. Decision support system, therefore, comes in handy to facilitate on deciding what maintenance action to carry out and when the action should be carried out, where the action should be carried out and how to go about the action based on the various data and resources available. This thesis project concentrates on how to carry out a winter road maintenance after receiving an alert of an action to carry out, when to carry it out and the road network that needs to be maintained. The thesis work focusses only on two of the winter road maintenance actions namely snow ploughing of bus stops in Luleå and application of abrasives commonly referred to as sanding of bus stops. Carrying out winter road maintenance comes at a huge cost from both direct and indirect costs with the Swedish government spending about SEK 1.75 billion every year as indicated by Jana Sochor and Cecilia Yu (Sochor &amp; Yu, 2004). This means that reduction in the maintenance cost of even 5% through optimisation of the maintenance cost would translate into a saving of about 87.5 million SEK per year and in 10 years could amount to close to 1 billion SEK. Optimization also leads to efficiency and effectiveness that could result in improved movement on the road and reduced environmental and social-economic impacts. Maintenance planning thus becomes essential for the effective and efficient execution of work and utilisation of the available scarce resource. This thesis project focusses on the use of Operations research methods to minimise the cost of carrying out a winter road maintenance action by finding the near optimal or if possible optimal solution and still deliver the required service level. The thesis delivers two main things: It first delivers a framework to support winter road maintenance decision making after an alert of an action is received and secondly an algorithm for the route that minimises the cost of maintenance by providing the route that minimises the travel distance of the ploughing/sanding vehicle from its source depot and back to the depot after completing a maintenance action assuming that the vehicle and material (fuel and sand) are in the same depot. The routes with minimum travel distance will, therefore, be that route that will reduce the labour time and in turn the labour cost, reduce the fuel consumption and the maintenance of the equipment due to reduced usage. The project uses a vehicle routing problem which is a generalised travelling Salesman as the optimisation technique to determine the optimal solution for the allocation of resources for carrying out a maintenance action to facilitate efficient utilisation of the available resources. This is with the help of a commercial optimisation software and support tools namely ArcGIS. To come up with the algorithm, the first step was a digital representation of the vehicle road network in Luleå for network analysis after which the bus stops were imported from google earth into the network. A two-stage optimisation was then carried out: first was a model for route optimisation based on the road network in ArcGIS with the objective function to minimise the travel distance and constraints based on the available resources. The results of ii the model were then exported into excel for the second optimisation for the optimal cost of maintenance done through a developed excel algorithm. The total cost of maintenance comprised direct and indirect cost. The direct cost consisted of the cost of fuel, the cost of personnel and the cost of hiring vehicles while the indirect cost results from the penalty fee charged for sanding and ploughing a bus stop after the threshold time given to a maintenance contractor by the municipality. Any bus stop that is ploughed after the threshold attracts a penalty per hour of the exceeded time. Six penalty threshold times were considered i.e. 30, 60, 90, 120, 150 and 180 minutes and a single parameter deterministic sensitivity analysis was carried out for each cost parameters to determine the sensitivity of the total maintenance cost. The more relaxed penalty thresholds were found to be less sensitive to the direct cost and the total maintenance cost compared to the more sensitive ones. When the penalty threshold is relaxed, the optimal maintenance cost reduces, and the required number of vehicles reduces. The cost of vehicle hire was found to be more sensitive than the other costs. The results of this project can help the maintenance contractor in developing a work schedule for the maintenance personnel and improve vehicle fleet management. By modelling the worst scenario, a contractor can plan for the maximum number of vehicles required and consequently the personnel required. With the optimal travel route for each vehicle and the total maintenance cost determined, maintenance contractors can determine the sustainability and profitability of their business and be able to negotiate for a better and more sustainable agreement (Contract) or for the relaxation of the penalty threshold time if it does not affect the service level required i.e. the quality and safety requirements. The approach used in this project can also be used for other winter road maintenance problems.