Telerobotics: Methodology for the Development of a Through-the-Internet Robotic Teleoperated System

This work presents a methodology for the development of Teleoperated Robotic Systems through the Internet. Initially, it is presented a bibliographical review of the Telerobotic systems that uses Internet as way of control. The methodology is implemented and tested through the development of two systems. The first is a manipulator with two degrees of freedom commanded remotely through the Internet denominated RobWebCam (http://www.graco.unb.br/robwebcam). The second is a system which teleoperates an ABB (Asea Brown Boveri) Industrial Robot of six degrees of freedom denominated RobWebLink (http://webrobot.graco.unb.br). RobWebCam is composed of a manipulator with two degrees of freedom, a video camera, Internet, computers and communication driver between the manipulator and the Unix system; and RobWebLink composed of the same components plus the Industrial Robot. With the use of this technology, it is possible to move far distant positioning objects minimizing transport costs, materials and people; acting in real time in the process that is wanted to be controller. This work demonstrates that the teleoperating via Internet of robotic systems and other equipments is viable, in spite of using rate transmission data with low bandwidth. Possible applications include remote surveillance, control and remote diagnosis and maintenance of machines and equipments.

Reframing the relationship between service design and operations: a service engineering approach

The significance of services as business and human activities has increased dramatically throughout the world in the last three decades. Becoming a more and more competitive and efficient service provider while still being able to provide unique value opportunities for customers requires new knowledge and ideas. Part of this knowledge is created and utilized in daily activities in every service organization, but not all of it, and therefore an emerging phenomenon in the service context is information awareness. Terms like big data and Internet of things are not only modern buzz-words but they are also describing urgent requirements for a new type of competences and solutions. When the amount of information increases and the systems processing information become more efficient and intelligent, it is the human understanding and objectives that may get separated from the automated processes and technological innovations. This is an important challenge and the core driver for this dissertation: What kind of information is created, possessed and utilized in the service context, and even more importantly, what information exists but is not acknowledged or used? In this dissertation the focus is on the relationship between service design and service operations. Reframing this relationship refers to viewing the service system from the architectural perspective. The selected perspective allows analysing the relationship between design activities and operational activities as an information system while maintaining the tight connection to existing service research contributions and approaches. This type of an innovative approach is supported by research methodology that relies on design science theory. The methodological process supports the construction of a new design artifact based on existing theoretical knowledge, creation of new innovations and testing the design artifact components in real service contexts. The relationship between design and operations is analysed in the health care and social care service systems. The existing contributions in service research tend to abstract services and service systems as value creation, working or interactive systems. This dissertation adds an important information processing system perspective to the research. The main contribution focuses on the following argument: Only part of the service information system is automated and computerized, whereas a significant part of information processing is embedded in human activities, communication and ad-hoc reactions. The results indicate that the relationship between service design and service operations is more complex and dynamic than the existing scientific and managerial models tend to view it. Both activities create, utilize, mix and share information, making service information management a necessary but relatively unknown managerial task. On the architectural level, service system -specific elements seem to disappear, but access to more general information elements and processes can be found. While this dissertation focuses on conceptual-level design artifact construction, the results provide also very practical implications for service providers. Personal, visual and hidden activities of service, and more importantly all changes that take place in any service system have also an information dimension. Making this information dimension visual and prioritizing the processed information based on service dimensions is likely to provide new opportunities to increase activities and provide a new type of service potential for customers.

Kaasupoljinohjeen toteuttaminen hybridilinja-auton säätöjärjestelmälle

Sähkö- ja hybridiajoneuvot yleistyvät tiukentuvien päästömääräysten seurauksena, koska sähkömoottoritekniikan avulla ajoneuvon kokonaishyötysuhdetta on mahdollista parantaa merkittävästi. Akkujen kapasiteettiin, kokoon, painoon ja latausaikoihin liittyvien ongelmien vuoksi sekä nestemäistä polttoainetta että sähköä hyödyntävä hybriditekniikka on toistaiseksi pelkkään sähkökäyttöön verrattuna usein toimivampi toteutus. Vanhojen hyötyajoneuvojen hybridikonversiot saattavatkin yleistyä, jos voidaan osoittaa, että konversio on toteutettavissa järkevin resurssein ja voidaan laatia konversion teknisiä haasteita helpottavia ohjeita. Syksyllä 2012 käynnistyi Lappeenrannan Teknillisen Yliopiston vetämä CAMBUS-projekti, jossa on tarkoitus kehittää kaupallisesti tarjolla olevia järjestelmiä pätevämpi hybriditekniikka linja-autokäyttöön. Tämä kandidaatintyö pyrkii kirjallisuuskatsauksen keinoin selvittämään, minkälainen kaasupolkimen toteutus olisi tätä hybridikonversiota ajatellen paras kuljettajan kontrolloiman säätöohjeen käytännön toteutukseen. Lähdemateriaalina on käytetty mm. Boschin ja Automobiltechnische Zeitschriftin ajoneuvoalan käsikirjoja ja oppikirjoja, Volkswagenin koulutuskäsikirjoja ja täydentävästi tieteellisiä artikkeleita ja patentteja. Niiden pohjalta on koottu yleisimmät tämänhetkiset tekniset toteutustavat, pohdittu tiedonsiirron ja sähkömagneettisen yhteensopivuuden haasteita, sekä kokonaissäätöjärjestelmän näkökulmasta säätöohjeen suuretta. Selvityksen perusteella polkimen asentotunnistuksen kannalta oleellista on turvallisuus, eli lähinnä mekaaninen kestävyys ja riittävä häiriösuojaus. Ajoneuvossa ilmeneviä voimakkaita magneettikenttiä hyvin sietävä digitaalinen väyläjärjestelmä voi hyvin toteutettuna myös yksinkertaistaa ajoneuvon sähköjärjestelmän muuta toteutusta. Aineistojen perusteella vääntömomentti on luonnollisin valinta ohjaussuureeksi. Vääntömomenttiohjeen avulla voidaan helposti luoda selkeä ja johdonmukainen tuntuma kuljettajalle voimanlähteiden turvalliseen hallintaan ja se helpottaa myös kommunikointia pidonhallintajärjestelmän ja muiden ajoneuvon hallintaan liittyvien järjestelmien kanssa.

Flexible multibody dynamics and intelligent control of a hydraulically driven hybrid redundant robot machine

The assembly and maintenance of the International Thermonuclear Experimental Reactor (ITER) vacuum vessel (VV) is highly challenging since the tasks performed by the robot involve welding, material handling, and machine cutting from inside the VV. The VV is made of stainless steel, which has poor machinability and tends to work harden very rapidly, and all the machining operations need to be carried out from inside of the ITER VV. A general industrial robot cannot be used due to its poor stiffness in the heavy duty machining process, and this will cause many problems, such as poor surface quality, tool damage, low accuracy. Therefore, one of the most suitable options should be a light weight mobile robot which is able to move around inside of the VV and perform different machining tasks by replacing different cutting tools. Reducing the mass of the robot manipulators offers many advantages: reduced material costs, reduced power consumption, the possibility of using smaller actuators, and a higher payload-to-robot weight ratio. Offsetting these advantages, the lighter weight robot is more flexible, which makes it more difficult to control. To achieve good machining surface quality, the tracking of the end effector must be accurate, and an accurate model for a more flexible robot must be constructed. This thesis studies the dynamics and control of a 10 degree-of-freedom (DOF) redundant hybrid robot (4-DOF serial mechanism and 6-DOF 6-UPS hexapod parallel mechanisms) hydraulically driven with flexible rods under the influence of machining forces. Firstly, the flexibility of the bodies is described using the floating frame of reference method (FFRF). A finite element model (FEM) provided the Craig-Bampton (CB) modes needed for the FFRF. A dynamic model of the system of six closed loop mechanisms was assembled using the constrained Lagrange equations and the Lagrange multiplier method. Subsequently, the reaction forces between the parallel and serial parts were used to study the dynamics of the serial robot. A PID control based on position predictions was implemented independently to control the hydraulic cylinders of the robot. Secondly, in machining, to achieve greater end effector trajectory tracking accuracy for surface quality, a robust control of the actuators for the flexible link has to be deduced. This thesis investigates the intelligent control of a hydraulically driven parallel robot part based on the dynamic model and two schemes of intelligent control for a hydraulically driven parallel mechanism based on the dynamic model: (1) a fuzzy-PID self-tuning controller composed of the conventional PID control and with fuzzy logic, and (2) adaptive neuro-fuzzy inference system-PID (ANFIS-PID) self-tuning of the gains of the PID controller, which are implemented independently to control each hydraulic cylinder of the parallel mechanism based on rod length predictions. The serial component of the hybrid robot can be analyzed using the equilibrium of reaction forces at the universal joint connections of the hexa-element. To achieve precise positional control of the end effector for maximum precision machining, the hydraulic cylinder should be controlled to hold the hexa-element. Thirdly, a finite element approach of multibody systems using the Special Euclidean group SE(3) framework is presented for a parallel mechanism with flexible piston rods under the influence of machining forces. The flexibility of the bodies is described using the nonlinear interpolation method with an exponential map. The equations of motion take the form of a differential algebraic equation on a Lie group, which is solved using a Lie group time integration scheme. The method relies on the local description of motions, so that it provides a singularity-free formulation, and no parameterization of the nodal variables needs to be introduced. The flexible slider constraint is formulated using a Lie group and used for modeling a flexible rod sliding inside a cylinder. The dynamic model of the system of six closed loop mechanisms was assembled using Hamilton’s principle and the Lagrange multiplier method. A linearized hydraulic control system based on rod length predictions was implemented independently to control the hydraulic cylinders. Consequently, the results of the simulations demonstrating the behavior of the robot machine are presented for each case study. In conclusion, this thesis studies the dynamic analysis of a special hybrid (serialparallel) robot for the above-mentioned special task involving the ITER and investigates different control algorithms that can significantly improve machining performance. These analyses and results provide valuable insight into the design and control of the parallel robot with flexible rods.

Nurses’ Acceptance of an Internet-Based Support System in The Care of Adolescents with Depression

The overall goal of the study was to describe nurses’ acceptance of an Internet-based support system in the care of adolescents with depression. The data were collected in four phases during the period 2006 – 2010 from nurses working in adolescent psychiatric outpatient clinics and from professionals working with adolescents in basic public services. In the first phase, the nurses’ anticipated perceptions of the usefulness of the Internet-based support system before its implementation was explored. In the second phase, the nurses’ perceived ease of computer and Internet use and attitudes toward it were explored. In the third phase, the features of the support system and its implementation process were described. In the fourth phase, the nurses’ experiences of behavioural intention and actual system use of the Internet-based support were described in psychiatric out-patient care after one year use. The Technology Acceptance Model (TAM) was used to structure the various research phases. Several benefits were identified from the nurses’ perspective in using the Internet-based support system in the care of adolescents with depression. The nurses’ technology skills were good and their attitudes towards computer use were positive. The support system was developed in various phases to meet the adolescents’ needs. Before the implementation of the information technology (IT)-based support system, it is important to pay attention to the nurses’ IT-training, technology support, resources, and safety as well as ethical issues related to the support system. After one year of using the system, the nurses perceived the Internet-based support system to be useful in the care of adolescents with depression. The adolescents’ independent work with the support system at home and the program’s systematic character were experienced as conducive from the point of view of the treatment. However, the Internet-based support system was integrated only partly into the nurseadolescent interaction even though the nurses’ perceptions of it were positive. The use of the IT-based system as part of the adolescents’ depression care was seen positively and its benefits were recognized. This serves as a good basis for future IT-based techniques. Successful implementations of IT-based support systems need a systematic implementation plan and commitment from the part of the organization and its managers. Supporting and evaluating the implementation of an IT-based system should pay attention to changing the nurses’ work styles. Health care organizations should be offered more flexible opportunities to utilize IT-based systems in direct patient care in the future.

Automatic traffic sign inventory- and condition analysis

This thesis researches automatic traffic sign inventory and condition analysis using machine vision and pattern recognition methods. Automatic traffic sign inventory and condition analysis can be used to more efficient road maintenance, improving the maintenance processes, and to enable intelligent driving systems. Automatic traffic sign detection and classification has been researched before from the viewpoint of self-driving vehicles, driver assistance systems, and the use of signs in mapping services. Machine vision based inventory of traffic signs consists of detection, classification, localization, and condition analysis of traffic signs. The produced machine vision system performance is estimated with three datasets, from which two of have been been collected for this thesis. Based on the experiments almost all traffic signs can be detected, classified, and located and their condition analysed. In future, the inventory system performance has to be verified in challenging conditions and the system has to be pilot tested.

Intelligent mapping of stresses in a hydraulic crane

Continuous loading and unloading can cause breakdown of cranes. In seeking solution to this problem, the use of an intelligent control system for improving the fatigue life of cranes in the control of mechatronics has been under study since 1994. This research focuses on the use of neural networks as possibilities of developing algorithm to map stresses on a crane. The intelligent algorithm was designed to be a part of the system of a crane, the design process started with solid works, ANSYS and co-simulation using MSc Adams software which was incorporated in MATLAB-Simulink and finally MATLAB neural network (NN) for the optimization process. The flexibility of the boom accounted for the accuracy of the maximum stress results in the ADAMS model. The flexibility created in ANSYS produced more accurate results compared to the flexibility model in ADAMS/View using discrete link. The compatibility between.ADAMS and ANSYS softwares was paramount in the efficiency and the accuracy of the results. Von Mises stresses analysis was more suitable for this thesis work because the hydraulic boom was made from construction steel FE-510 of steel grade S355 with yield strength of 355MPa. Von Mises theory was good for further analysis due to ductility of the material and the repeated tensile and shear loading. Neural network predictions for the maximum stresses were then compared with the co-simulation results for accuracy, and the comparison showed that the results obtained from neural network model were sufficiently accurate in predicting the maximum stresses on the boom than co-simulation.

Cardiorespiratory adaptations induced by aerobic training in middle-aged men: the importance of a decrease in sympathetic stimulation for the contribution of dynamic exercise tachycardia

We investigated the effects of aerobic training on the efferent autonomic control of heart rate (HR) during dynamic exercise in middle-aged men, eight of whom underwent exercise training (T) while the other seven continued their sedentary (S) life style. The training was conducted over 10 months (three 1-h sessions/week on a field track at 70-85% of the peak HR). The contribution of sympathetic and parasympathetic exercise tachycardia was determined in terms of differences in the time constant effects on the HR response obtained using a discontinuous protocol (4-min tests at 25, 50, 100 and 125 watts on a cycle ergometer), and a continuous protocol (25 watts/min until exhaustion) allowed the quantification of the parameters (anaerobic threshold, VO2 AT; peak O2 uptake, VO2 peak; power peak) that reflect oxygen transport. The results obtained for the S and the T groups were: 1) a smaller resting HR in T (66 beats/min) when compared to S (84 beats/min); 2) during exercise, a small increase in the fast tachycardia (D0-10 s) related to vagal withdrawal (P<0.05, only at 25 watts) was observed in T at all powers; at middle and higher powers a significant decrease (P<0.05 at 50, 100 and 125 watts) in the slow tachycardia (D1-4 min) related to a sympathetic-dependent mechanism was observed in T; 3) the VO2 AT (S = 1.06 and T = 1.33 l/min) and VO2 peak (S = 1.97 and T = 2.47 l/min) were higher in T (P<0.05). These results demonstrate that aerobic training can induce significant physiological adaptations in middle-aged men, mainly expressed as a decrease in the sympathetic effects on heart rate associated with an increase in oxygen transport during dynamic exercise.

Effects of exercise training on autonomic and myocardial dysfunction in streptozotocin-diabetic rats

Several investigators have demonstrated that diabetes is associated with autonomic and myocardial dysfunction. Exercise training is an efficient non-pharmacological treatment for cardiac and metabolic diseases. The aim of the present study was to investigate the effects of exercise training on hemodynamic and autonomic diabetic dysfunction. After 1 week of diabetes induction (streptozotocin, 50 mg/kg, iv), male Wistar rats (222 ± 5 g, N = 18) were submitted to exercise training for 10 weeks on a treadmill. Arterial pressure signals were obtained and processed with a data acquisition system. Autonomic function and intrinsic heart rate were studied by injecting methylatropine and propranolol. Left ventricular function was assessed in hearts perfused in vitro by the Langendorff technique. Diabetes (D) bradycardia and hypotension (D: 279 ± 9 bpm and 91 ± 4 mmHg vs 315 ± 11 bpm and 111 ± 4 mmHg in controls, C) were attenuated by training (TD: 305 ± 7 bpm and 100 ± 4 mmHg). Vagal tonus was decreased in the diabetic groups and sympathetic tonus was similar in all animals. Intrinsic heart rate was lower in D (284 ± 11 bpm) compared to C and TD (390 ± 8 and 342 ± 14 bpm, respectively). Peak systolic pressure developed at different pressures was similar for all groups, but +dP/dt max was decreased and -dP/dt max was increased in D. In conclusion, exercise training reversed hypotension and bradycardia and improved myocardial function in diabetic rats. These changes represent an adaptive response to the demands of training, supporting a positive role of physical activity in the management of diabetes.

Effects of aerobic exercise training on heart rate variability during wakefulness and sleep and cardiorespiratory responses of young and middle-aged healthy men

The purpose of the present study was to evaluate the effects of aerobic physical training (APT) on heart rate variability (HRV) and cardiorespiratory responses at peak condition and ventilatory anaerobic threshold. Ten young (Y: median = 21 years) and seven middle-aged (MA = 53 years) healthy sedentary men were studied. Dynamic exercise tests were performed on a cycloergometer using a continuous ramp protocol (12 to 20 W/min) until exhaustion. A dynamic 24-h electrocardiogram was analyzed by time (TD) (standard deviation of mean R-R intervals) and frequency domain (FD) methods. The power spectral components were expressed as absolute (a) and normalized units (nu) at low (LF) and high (HF) frequencies and as the LF/HF ratio. Control (C) condition: HRV in TD (Y: 108, MA: 96 ms; P<0.05) and FD - LFa, HFa - was significantly higher in young (1030; 2589 ms²/Hz) than in middle-aged men (357; 342 ms²/Hz) only during sleep (P<0.05); post-training effects: resting bradycardia (P<0.05) in the awake condition in both groups; VO2 increased for both groups at anaerobic threshold (P<0.05), and at peak condition only in young men; HRV in TD and FD (a and nu) was not significantly changed by training in either groups. The vagal predominance during sleep is reduced with aging. The resting bradycardia induced by short-term APT in both age groups suggests that this adaptation is much more related to intrinsic alterations in sinus node than in efferent vagal-sympathetic modulation. Furthermore, the greater alterations in VO2 than in HRV may be related to short-term APT.

Swimming training increases cardiac vagal activity and induces cardiac hypertrophy in rats

The effect of swimming training (ST) on vagal and sympathetic cardiac effects was investigated in sedentary (S, N = 12) and trained (T, N = 12) male Wistar rats (200-220 g). ST consisted of 60-min swimming sessions 5 days/week for 8 weeks, with a 5% body weight load attached to the tail. The effect of the autonomic nervous system in generating training-induced resting bradycardia (RB) was examined indirectly after cardiac muscarinic and adrenergic receptor blockade. Cardiac hypertrophy was evaluated by cardiac weight and myocyte morphometry. Plasma catecholamine concentrations and citrate synthase activity in soleus muscle were also determined in both groups. Resting heart rate was significantly reduced in T rats (355 ± 16 vs 330 ± 20 bpm). RB was associated with a significantly increased cardiac vagal effect in T rats (103 ± 25 vs 158 ± 40 bpm), since the sympathetic cardiac effect and intrinsic heart rate were similar for the two groups. Likewise, no significant difference was observed for plasma catecholamine concentrations between S and T rats. In T rats, left ventricle weight (13%) and myocyte dimension (21%) were significantly increased, suggesting cardiac hypertrophy. Skeletal muscle citrate synthase activity was significantly increased by 52% in T rats, indicating endurance conditioning. These data suggest that RB induced by ST is mainly mediated parasympathetically and differs from other training modes, like running, that seems to mainly decrease intrinsic heart rate in rats. The increased cardiac vagal activity associated with ST is of clinical relevance, since both are related to increased life expectancy and prevention of cardiac events.

Effects of diet and exercise training on neurovascular control during mental stress in obese women

Since neurovascular control is altered in obese subjects, we hypothesized that weight loss by diet (D) or diet plus exercise training (D + ET) would improve neurovascular control during mental stress in obese women. In a study with a dietary reduction of 600 kcal/day with or without exercise training for 4 months, 53 obese women were subdivided in D (N = 22, 33 ± 1 years, BMI 34 ± 1 kg/m²), D + ET (N = 22, 33 ± 1 years, BMI 33 ± 1 kg/m²), and nonadherent (NA, N = 9, 35 ± 2 years, BMI 33 ± 1 kg/m²) groups. Muscle sympathetic nerve activity (MSNA) was measured by microneurography and forearm blood flow by venous occlusion plethysmography. Mental stress was elicited by a 3-min Stroop color word test. Weight loss was similar between D and D + ET groups (87 ± 2 vs 79 ± 2 and 85 ± 2 vs 76 ± 2 kg, respectively, P < 0.05) with a significant reduction in MSNA during mental stress (58 ± 2 vs 50 ± 2, P = 0.0001, and 59 ± 3 vs 50 ± 2 bursts/100 beats, P = 0.0001, respectively), although the magnitude of the response was unchanged. Forearm vascular conductance during mental stress was significantly increased only in D + ET (2.74 ± 0.22 vs 3.52 ± 0.19 units, P = 0.02). Weight loss reduces MSNA during mental stress in obese women. The increase in forearm vascular conductance after weight loss provides convincing evidence for D + ET interventions as a nonpharmacologic therapy of human obesity.

Eccentric and concentric cardiac hypertrophy induced by exercise training: microRNAs and molecular determinants

Among the molecular, biochemical and cellular processes that orchestrate the development of the different phenotypes of cardiac hypertrophy in response to physiological stimuli or pathological insults, the specific contribution of exercise training has recently become appreciated. Physiological cardiac hypertrophy involves complex cardiac remodeling that occurs as an adaptive response to static or dynamic chronic exercise, but the stimuli and molecular mechanisms underlying transduction of the hemodynamic overload into myocardial growth are poorly understood. This review summarizes the physiological stimuli that induce concentric and eccentric physiological hypertrophy, and discusses the molecular mechanisms, sarcomeric organization, and signaling pathway involved, also showing that the cardiac markers of pathological hypertrophy (atrial natriuretic factor, β-myosin heavy chain and α-skeletal actin) are not increased. There is no fibrosis and no cardiac dysfunction in eccentric or concentric hypertrophy induced by exercise training. Therefore, the renin-angiotensin system has been implicated as one of the regulatory mechanisms for the control of cardiac function and structure. Here, we show that the angiotensin II type 1 (AT1) receptor is locally activated in pathological and physiological cardiac hypertrophy, although with exercise training it can be stimulated independently of the involvement of angiotensin II. Recently, microRNAs (miRs) have been investigated as a possible therapeutic approach since they regulate the translation of the target mRNAs involved in cardiac hypertrophy; however, miRs in relation to physiological hypertrophy have not been extensively investigated. We summarize here profiling studies that have examined miRs in pathological and physiological cardiac hypertrophy. An understanding of physiological cardiac remodeling may provide a strategy to improve ventricular function in cardiac dysfunction.

Effects of high-intensity intermittent training on carnitine palmitoyl transferase activity in the gastrocnemius muscle of rats

We examined the capacity of high-intensity intermittent training (HI-IT) to facilitate the delivery of lipids to enzymes responsible for oxidation, a task performed by the carnitine palmitoyl transferase (CPT) system in the rat gastrocnemius muscle. Male adult Wistar rats (160-250 g) were randomly distributed into 3 groups: sedentary (Sed, N = 5), HI-IT (N = 10), and moderate-intensity continuous training (MI-CT, N = 10). The trained groups were exercised for 8 weeks with a 10% (HI-IT) and a 5% (MI-CT) overload. The HI-IT group presented 11.8% decreased weight gain compared to the Sed group. The maximal activities of CPT-I, CPT-II, and citrate synthase were all increased in the HI-IT group compared to the Sed group (P < 0.01), as also was gene expression, measured by RT-PCR, of fatty acid binding protein (FABP; P < 0.01) and lipoprotein lipase (LPL; P < 0.05). Lactate dehydrogenase also presented a higher maximal activity (nmol·min-1·mg protein-1) in HI-IT (around 83%). We suggest that 8 weeks of HI-IT enhance mitochondrial lipid transport capacity thus facilitating the oxidation process in the gastrocnemius muscle. This adaptation may also be associated with the decrease in weight gain observed in the animals and was concomitant to a higher gene expression of both FABP and LPL in HI-IT, suggesting that intermittent exercise is a "time-efficient" strategy inducing metabolic adaptation.

A Bayesian Approach for Forecasting Heat Load in a District Heating System

The growing population in cities increases the energy demand and affects the environment by increasing carbon emissions. Information and communications technology solutions which enable energy optimization are needed to address this growing energy demand in cities and to reduce carbon emissions. District heating systems optimize the energy production by reusing waste energy with combined heat and power plants. Forecasting the heat load demand in residential buildings assists in optimizing energy production and consumption in a district heating system. However, the presence of a large number of factors such as weather forecast, district heating operational parameters and user behavioural parameters, make heat load forecasting a challenging task. This thesis proposes a probabilistic machine learning model using a Naive Bayes classifier, to forecast the hourly heat load demand for three residential buildings in the city of Skellefteå, Sweden over a period of winter and spring seasons. The district heating data collected from the sensors equipped at the residential buildings in Skellefteå, is utilized to build the Bayesian network to forecast the heat load demand for horizons of 1, 2, 3, 6 and 24 hours. The proposed model is validated by using four cases to study the influence of various parameters on the heat load forecast by carrying out trace driven analysis in Weka and GeNIe. Results show that current heat load consumption and outdoor temperature forecast are the two parameters with most influence on the heat load forecast. The proposed model achieves average accuracies of 81.23 % and 76.74 % for a forecast horizon of 1 hour in the three buildings for winter and spring seasons respectively. The model also achieves an average accuracy of 77.97 % for three buildings across both seasons for the forecast horizon of 1 hour by utilizing only 10 % of the training data. The results indicate that even a simple model like Naive Bayes classifier can forecast the heat load demand by utilizing less training data.