Research opportunities arising from control and optimization of smart buildings
|
|
- Eleanor Newman
- 5 years ago
- Views:
Transcription
1 ISA Workshop on Frontiers in Systems and Control Research opportunities arising from control and optimization of smart buildings Qianchuan Zhao CFINS, Dept. Automation and TNList, Tsinghua University
2 CFINS Yu-Chi Ho chair professor group and Center for Intelligent and Networked Systems (CFINS) were established in October 2001 to provide a physical and intellectual environment for the intelligent analysis, design, and operation of complex and networked systems such as computer and communication networks, buildings, power systems, and supply chains by making innovative use of analytical methods and information technology. 2
3 What we mean by smart for buildings? 3
4 Potential of ICT technology MOORE s Law AI 4
5 What we mean by smart for buildings? Utilize information relevant to the whole building system thanks to IoT as a result of the fast drop in the cost of hardware for computing, storage and communication; Care about individual occupant thanks to the rapid development of machine learning techniques. 5
6 Energy consumption Type Building faction 40% (68%Electr. ) Transportation 40% Others 20% Energy saving for buildings has been omitted for long, it has great potential! 6
7 Energy consumption in buildings Office Building Elevator 3% Office Equipments 22% Other 10% Lights 28% HVAC 37% Hotel Elevator 9% Office Equipments 4% 18% Other Lights 25% HVAC 44% It was estimated that 20% ~ 30% energy saving can be achieved by optimizing the operation and control of buildings. 7
8 System Architecture Integrated building control for energy saving Data driven modeling + prediction Information fusion 8
9 Control and optimization of building energy system Energy supply in building Controllable devices Distribution Battery Elect. Lighting HVAC Solar Fuel cell Heat Wind CHP E-car Shading Window Micro-grid Minimization of energy cost Comfort: Temp. Humid. Illum. 9 CO2 Occupant demand
10 List of possible challenges Integrated control under full information may suffer the curse of dimensionality problem and time consuming evaluation of performance or constraints. Mache learning in general is a hard problem: design of a good ML algorithm also include many decision variables (model structure, parameters, implementation, input data ) 10
11 Ways to address the challenges According to NFLT, problem specific knowledge is needed to develop efficient solutions. Soft optimization for integrated control: OO, OCBA, COO, NP, ADP, EBO, IPA, Apply problem specific knowledge to reduce the search space for a good ML algorithm. 11
12 Illustration of COO G S N 12
13 Below we will use individual thermal comfort model as an example of ML in smart building applications. 13
14 S et point (oc ) E nergy consum ption (kw ) HVAC system Motivations First invented to serve the machine, manufacturing process, etc. --Set point oriented control When HVAC serves people. Set point oriented control like what they did on the machine S et point E nergy consum ption Set point Day 1 Day 2 Day 3 Day 4 Day /1/ /1/ /1/ /2/3 2008/2/8 2008/2/ /2/ /2/ /2/ /3/4 2008/3/9 2008/3/ /3/ /3/ /3/ /4/3 17 Tokyo Univ survey data FIT, Tsinghua Univ survey data 14
15 Motivations(cont d) Intelligent thermostat? (Perry D. et al, 2011) Task 1: Set to Heat Time (s) Completed Tasks Incomplete Tasks (minutes) WEB TCH SMT BTN HYB User-oriented control system User only inputs sensations Personalized and self-learning Thermostats Human perception Control Perceive Indoor environment 15
16 Existing models The chamber study model Predicted Mean Vote-Predicted Percent Dissatisfied (PMV-PPD) model quantifies the thermal comfort concept as a mapping from the environmental factors and personal factors to a 7-level comfort value scale based on an average over a large data set. Environmental factors Personal factors air temperature radiant temperature relative humidity air velocity clothing level metabolic rate activity level PMV-PPD Model Thermal sensation A 7-level thermal sensation scale cold cool slightly cool neutral slightly warm warm PMV value hot 16
17 Existing models The models based on the human body physiology The two-node (core and skin) model The multi-segment mathematical model of human body The sensation and comfort model for human segments and the wholebody Field study comfort model The original models were presented by Humphreys and Nicol which described a strong relationship of the comfortable temperatures inside a building, to the mean temperatures prevailing inside the building Classified by de Dear and Brager as physiological, behavioral and psychological The ASHRAE adaptive model: ASHRAE standard SCATS: European adaptive comfort standard, EN
18 The main challenges Challenges All these works focus on average thermal comfort models instead of personalized comfort models. There exist less related literature and research on personalized comfort models. The cases for the group are more complicated and challenging. 18
19 Terminal Control Strategies for Energy and Comfort Controller Lights Blind Window AC Sensors Occupants Adaptive HMI metered 70.0 simulated Energy metering Room load W/m2 0.0 Energy Temp... Hot Cold Dry Humid Noisy Temp. Humidity Air speed CO 2 Acoustic level Illuminance Interpreter Dynamic Comfort Region CO 2 RH e 1 R H e o CO 2 Optimization Estimated comfort zone T T Human factors Psychology Engineering industrial design Building manager energy requirement Tsinghua-UTC Building Energy Energy, Safety and Control System Research Center. (CFINS, DBS, IE, CPSR) 19
20 Sensation votes based model Voting software Sensors Setup: 1. Every one hour, the software will pop up to let the user vote. 2. The sensor box will record the environment measurements, store them in local computer through COM and further upload to the server database. 20
21 PDTC -- PMV framework Heat balance equation of human Mapping from the environment to the human thermal vote Cold Cool Neural Warm Hot Heat balance of human body M W C R E S 0 21
22 PDTC -- the proposed model Personalized Dynamic Thermal Comfort(PDTC) Perception thermal vote PTV m ( ) 0 m1 P m2t m3 R C a PDTC( k) m ( k) m ( k) P m ( k) t m ( k)( R C) 0 1 a 2 a 3 Considering the dynamics of human thermal perception a 22
23 Parameter estimation Parameter estimation Least squares N N k 1 2 { mˆ 0, mˆ 1, mˆ 2, mˆ 3} arg min ( k) ( PDTCk ( m0, m1, m2, m3) real vote) m0, m1, m2, m3 k 1 Recursive least squares estimation with forgetting factors Time-variant forgetting factors N N k 1 arg min ( k) ( k) m0, m1, m2, m3 k 1 ( k) [1, P, t, ( R C)] a PDTC( k) ( k) X ( k) a ( k) PDTC( k) truevote( k) 1, if the k and k-1 are in the same day ( k), otherwise 23
24 Results and validations Subject A Recursive Results Parameter Values Subject B Recursive Results m 0 m 1 m 2 m 3 Office layout Time: From Nov, 2009 Jan, Month and Date 24
25 Results and validations Model validation accuracy Subject PDTC R-MSE PDTC R-Bias PDTC P-MSE PDTC P-Bias PMV P-MSE PMV P-Bias A B C D E F G H I R i R i Subject A Subject C R i R i Time offset Subject B Subject D , 1, 2, 3, 4 Bias and MSE Correlation coefficient of residuals and inputs 25
26 A study case of applications 6m Heat transfer of the interior walls Q iw Appliances heat emission Q eqp Lamps heat emission Q lt 6m Human body heat emission Min a, k a, k } Q occ { t, h all 0 1 ak, 2 ak, 3 Sensible and latent heating load for warming and humidifying outside air Q External Wall fa, S fa, L Q, Q East Outside ow, Q ow Heat transfer of the external wall and window s. t. m ( k) m ( k) P m ( k) t m ( k) ( R C) threshod Q h ( h, h ), t ( t a down up a down, t up ) k Personalized energy saving potentials Sensitivity: relative heating load decrease (%) A B C D E F G H I Higher energy cost, higher sentivity in comfor and energy saving tradeoff PMV sensitivity Increase of heating load relative to PMV based results (%) R Q t h Q t h Q t h * * * ( PDTC ( a, a) PMV ( a, a)) / PMV ( a, a) 100% S Q Q Q * * *, PDTC, threshold PDTC, threshold / PDTC PDTC, threshol d 100% 26
27 Limitations of the previous work in real application? Require the user to vote every one hour. Nonlinear comfort constraint when online implemented Can we be more user-friendly? 27
28 Complaint driven : more user-friendly Settings Users only complain whenever they felt necessary. Advantages Less demanding for users No interruption for users Close-loop control Human Machine Interface* *Y.Jiang, et al, A Human Machine Interface for Building Indoor Environment Control, Chinese Patent, ZL
29 Complaint driven : more user-friendly Challenges No intensity information in complaints : binary variables No comfort samples No-complaint periods have many possible explanations Few information of inner complaint region Environmental parameters are set around the comfort region boundary.(closedloop test-bed effects) 29
30 Problem formulation Problem formulation Only given the samples of target class*, i.e. a set of samples of a type of complaint χ = x 1, x 2,, x n,x i R 2, i.e. in the temperature and relative humidity plane, how to obtain a boundary description of the complaint region f(w, x) only based on the complaint samples χ. * Target class, the cold or hot complaints, which are from single subject. 30
31 Important properties Properties of the complaint region The complaint region in the environment parameter space (in normal environment parameter range) for a given complaint is connected. Additionally, some of the parameters are unidirectional 1. Existing researches conclude both the human comfort zone and discomfort zone are connected areas. 2. Unidirectional parameter in human perception generally exists. Some of the parameters are not clear. e.g. temperature in hot and cold complaints is unidirectional, relative humidity is not clear. 31
32 Multi-linear one-class classifier model Pareto-frontier set of the complaint samples A sample x i R 2 is in the pareto-frontier set with respect to the generalized inequality S iff there is no sample x j, j i such that x j S x i. where S is a proper cone* and x j S x i means x j x i S. Complaint samples Relative humidity The cone (direction) of 2 2 S { x R x(1 0 x ), (2) 0} Pareto frontier set in the 2 direction S No samples in this region Temperature * Stephen Boyd, Lieven Vandenberghe, Convex Optimization, Cambridge University Press,
33 Multi-linear one-class classifier model Multi-linear one-class classifier learning Least square linear estimation is performed for each of the pareto-frontier set V k and obtain a set of linear equations (classifiers). T 2 w k x c k ck 1 x V min ( ), 1,2 w k Pareto-frontier set plays the role of support vector in support vector description method Multi-linear approximation of the nonlinear boundary The complain region can be described by j T T 0, if wk xi ck 0, xi Vk fk ( x) w k x ck, k 1,2 0 k,otherwise 33
34 Multi-linear one-class classifier model Performance metrics False Negative Rate (Missing detection rate): the rate of complaints that were missed. False Positive Rate (False detection rate): the rate of complaints that were mistaken as comfort. Empirical Rule If the subject has not complained for 20 minutes and he/she will not complain for next 20minutes, the current environment conditions are regarded as comfort samples. FPR 1 comfort C { yi C } Ncomfo rt i 1 N I 1. The empirical rule is based on the results of transient thermal comfort research. 2. The higher FPR, the more conservative of the classifier is. 34
35 Experiment test-bed* Experiment settings Touch screen Human Machine Interface Dedicated HVAC and other terminals Integrated sensors and computers Closed-loop operation mode in test-bed. Human Machine Interface Sensors Radiant ceiling *Zhuo Mao, Fulin Wang, Teng Gao, Yunchuang Dai, Qianchuan Zhao, Yin Zhao, Biao Sun, Jing Guo, and Fan Zhang, Research of the room occupant complaining behavior pattern for the indoor environmental control, Advanced Materials Research Vols (2012) pp
36 Relative humidity % Relative humidity % Relative humidity % Relative humidity % Results of the experiment data 60 Subject A FPR = Subject B FPR = Temperature 0 C Temperature 0 C Subject C 65 FPR =0.77 FPR = Subject D Temperature 0 C Temperature 0 C Green polygon presents the parameter region of the experiment FPR is estimated as FPR C 36
37 Relative humidity % Relative humidity % Results of the experiment data 65 Subject B 65 Subject D FPR =0.24 FPR = Temperature 0 C Temperature 0 C 1. Cold complaints usually occur in the lower temperature part and while hot complaints in the higher part. 2. Data are collected in 3-4 continuous days during their experiments. 3. Ambiguous region, which both hot and cold complaint had occurred exists. 37
38 Results of the experiment data Comparison with the PMV model Hot Complaints 75 Relative humidity (%) Cold Complaint Region 3. Unexplored Region 2. Possible Uncomfortable region 1. Possible Comfort Region Cold Complaints Hot Complaint Region Relative humidity % Temperature ( o C) Temperature 0 C PMV numerical results in temperature and relative humidity plane. The clothing index was chosen as 0.6 and air velocity was 0, which is accordance with our experiment conditions 1. Complaint-based comfort model may have a larger complaint area than the PMV model, which indicates that indoor environment control based on PMV may cause complaints. 2. Different regions in the learning results represent different perceptions. 38
39 Performance analysis Comparison with other models False Negative Rate Comparison Subjects Fisher Linear discriminant model SVM model Proposed model Hot Cold Hot Cold Hot Cold A B C D E F Leave-one-out methods were utilized to evaluate the FNR for each methods. 2. Comfort samples were extracted from the experiment record according to the empirical rule in previous slide. 3. SVM model using the linear kernel function.* The proposed model has low false negative rate. *Richard O.Duda, Peter E.Hart and David G.Stork, Pattern Classification,2nd edition, John Wiley & Sons, Inc,
40 Experimental validation 40
41 Experimental valuation * * 41
42 Group thermal comfort model The group comfort zone model We introduce here is a quite natural one: take the convex hull of the individual comfort zones of the group. Defining group comfort region as the intersection of all group member s individual comfort regions or the intersection of those of the majority when there are conflicts. 42
43 Experiment results The comparison with PMV Large group in Lanzhou Testbed It is obvious that the individual differences in thermal preference often incur dissatisfactions in the group. This indicates that the average model, such as PMV, may have bias in predicting the thermal comfort for large group. Pareto frontier set(cold) Pareto frontier set (hot) 43
44 Challenges Summary Accurate occupant counting or localization problem See: T. Labeodan, W. Zeiler, G. Boxem, et al. Occupancy measurement in commercial office buildings for demand-driven control applications: A survey and detection system evaluation. Energy and Buildings, 2015, 93: Data Mining for integrated building control and optimization See: F. Xiao, C. Fan. Data mining in building automation systems for improving building operational performance. Energy and Buildings, 2014, 75: F. Cheng, X. Fu, C. Yan. A framework for knowledge discovery in massive building automation data and its application in building diagnostics. Automation in Construction, 2015, 50:
45 Links IEEE RAS TC on Smart Buildings Q. Jia, Q. Zhao, H. Darabi, et al. Smart building technology. IEEE Robotics & Automation Magazine, 2014, 21(2): IFAC TC on Smart Cities: Q. Zhao, Research opportunities arising from control and optimization of smart buildings, Control Theory and Technology, Vol. 15, No. 1, pp , February
46 References Jiang Y, Wang FL, Jiang ZY, Hou Y, Zhao QC, Liu Y, Zhang F, Jiang Y, Human- Computer Interface of Two-Way Interactive Architectural Environment Control System, International Patent, WO/2012/019328, Application No. PCT/CN2010/ Zhao QC, Zhao Y, Wang FL, Wang JL, Jiang Y, Zhang F, A data-driven method to describe the personalized dynamic thermal comfort in ordinary office environment: from model to application, Building and Environment, 72( ), 2014 Zhao QC, Zhao Y, Wang FL, Jiang Y, Jiang Y, Zhang F, Preliminary study of learning individual thermal complaint behavior using one-class classifier for indoor environment control, Building and Environment, 72( ), 2014 Zhao QC, Chen ZJ, Wang FL, Jiang Y, Ding JL, Experimental study of group thermal comfort model, 2014 IEEE International Conference on Automation Science and Engineering (CASE), pp: Z. Cheng, Q. Zhao, F. Wang, Y. Jiang, L. Xia, and J. Ding, Satisfaction based Q- learning for integrated lighting and blind control, Energy and Buildings, vol. 127, pp , F. Wang, Z. Chen, Q. Feng, Q. Zhao, Z. Cheng, Z. Guo, Z. Zhong, Experimental comparison between set-point based and satisfaction based indoor thermal environment control, Energy and Buildings, vol. 128, pp ,
47 Thanks Prof. Ho for your inspiring guidance over the years 47
48 Multi-linear one-class classifier model Determine pareto-frontier sets* of samples m A sample x is in the pareto-frontier set with respect to generalized i R inequality iff there does not exist any other sample, x S j, i jsuch that x x. where S is a proper cone in R m j S i Generalized inequality x j S x i means x j x i S Example: 2 2 S x R x(1) x(2) 0, 0 By incorporating the prior knowledge, the pareto-frontier set of a certain class of samples represent boundary profiles in specified direction which we interested most. * Stephen Boyd, Lieven Vandenberghe, Convex Optimization, Cambridge University Press, /43
49 Unbiased theoretically? Expression noise when survey or vote Percentage of Rankings Received by Any Term Across Subjects WW Ranks IMPOSSIBLE IMPROBABLE UNLIKELY POSSIBLE LIKELY PROBABLE CERTAIN 100 WN Ranks IMPOSSIBLE % IMPROBABLE % UNLIKELY % POSSIBLE % PROBABLE LIKELY % % % CERTAIN Jaffe-katz and Budescu, /43
50 An intuitive illustration Cold Cool Neural Warm Hot True vote Noise distribution Noise distribution 50/43
51 Problems in the identification framework Output-dependent observation noise Inputs u Unknown Systems y Observation Noise ŷ Identification ˆ Observation noise is dependent on the system output 51/43
52 Problem in the identification framework Unbiased estimation of the system parameters? Inconsistency of the noise at different outputs Output-dependent mean value (cannot remove the noise by average) Inputs u Unknown Systems y Observation Noise ŷ Identification ˆ E ˆ 52/43
53 Proposed identification methods Key ideas: First identify the noiseless output y(u i ) using the noise model. Decouple the relationship between the parameters and the noise. Then identify the system parameters θ. Return to the normal system identification. Inputs u Unknown Systems y Observation Noise ŷ y(u i ): estimation of y u i. θ: estimation of θ. Identification ˆ E ˆ ( ) yu i Estimate the noiseless output 53/43
54 Noise probability densitity Noise disribution densitity Noise model Output-dependent bounded noise model The noise is bounded and its bound is related to the noiseless output. The probability density function has peak value at 0. Truncated distributions -- examples for different outputs in a bounded range 0.7 Truncated Normal Distribution (TN) Truncated Double Exponential Distribution (TDE) TN(a=-3,b=3, = 1, y = -2.5) TN(a=-3,b=3, = 1, y = -1.5) TN(a=-3,b=3, = 1, y = 0) With noise parameter: σ TDE(a=-3,b=3, = 1,y = -2.5) TDE(a=-3,b=3, = 1,y = -1.5) TDE(a=-3,b=3, = 1,y = 0) With noise parameter: λ w w 54/43
55 Proposed identification methods When the noise parameter (δ) is known Choose the input as uk* I i, i 1,2,..., I d, k 0,1,2,..., K u u... u u 0* I i 1* I i k* I i i Construct the following identification equation K 1 y( u ) E( w( y( u ), )) yˆ ( u ), i 1,2,..., I i i k* I i K 1 k 0 This is the function of y( u ) when the noise parameter is known. i An explicit for of the equation, for example, TN model, is a y( ui) b y( ui) ( ) ( ) K 1 y( u ) ˆ i y( uk* I i ), i 1,..., I b y( ui) a y( ui) 1 k 0 ( ) ( ) K Where φ, Φ are the p.d.f. and c.d.f. of standard normal distribution 55/43
56 Proposed identification methods When the noise parameter (δ) is known (cont d) If the identification equation has unique solution K 1 y( u ) E( w( y( u ), )) yˆ ( u ), i 1,2,..., I i i k* I i K 1 k 0 yu ( i ) K The identification can be done by solving the following noiseless identification T Where [ ( u ), ( u ),..., ( u )] T and Y [ y( u ), y( u ),..., y( u ) ] T. Y K i 2 I K 1 K 2 K I K Note: 1. The solution of identification is related to the number of repeated input K. 2. The inputs ui, i 1,2,... I should satisfy the Persistent Exciting Condition. 3. We name the identification method as Basic Identification Algorithm (BIA). 56/43
57 Proposed identification methods When the noise parameter (δ) is unknown Underdetermined problem: I identification equations with I + 1 unknown variables y( u ), i 1,2,..., I,. Introduce an additional criterion i Maximum likelihood under the constraint of identification equations s.t. max log L(, D) K 1 y( u ) E( w( y( u, ))) yˆ ( u ), i 1,..., I i i k* I i K 1 k 0 T y( u ) ( u ), i 1,..., I i i Note: 1. When the system is identifiable, then given δ, there is unique θ and y u i. 2. The unknown parameter is usually a scalar and the optimization is converted to the one-dimension search problem, where each search step involves a procedure of identification when the noise parameter is known. 3. We name the algorithm as Joint Identification Algorithm (JIA). 57/43
58 Algorithms Theorem 1 Under the condition that the identification equation has unique solution, then the proposed algorithm can obtain the unbiased estimate of the unknown system parameter when K 58/43
59 Algorithms(cont d) Theorem 2 When the identification equations have unique solution for different, the results of Joint Identification converge to the true system parameter θ and noise parameter δ with in probability when K. 59/43
60 Numerical test and application 60/43
61 Numerical test and application Application in PDTC model Y. Zhao and Q. Zhao, System Identification for Output-dependent Bounded Noises and its Application in Learning Personalized Thermal Comfort Model, To appear in IEEE Proceedings of International Conference on Robotics and Automation, Karlsruhe, Germany, /43
CAE 331/513 Building Science Fall 2017
CAE 331/513 Building Science Fall 2017 September 19, 2017 Human thermal comfort Advancing energy, environmental, and sustainability research within the built environment www.built-envi.com Twitter: @built_envi
More informationThermal behavior and Energetic Dispersals of the Human Body under Various Indoor Air Temperatures at 50% Relative Humidity
Thermal behavior and Energetic Dispersals of the Human Body under Various Indoor Air Temperatures at 50% Relative Humidity Hakan CALISKAN Usak University, Department of Mechanical Engineering, Usak, Turkey
More informationEnvironmental Engineering
Environmental Engineering 1 Indoor Environment and Thermal Comfort Vladimír Zmrhal (room no. 814) Master degree course 1 st semester (winter) Dpt. of Environmental Engineering 1 Environmental Engineering
More informationISO 7730 INTERNATIONAL STANDARD
INTERNATIONAL STANDARD ISO 7730 Third edition 2005-11-15 Ergonomics of the thermal environment Analytical determination and interpretation of thermal comfort using calculation of the PMV and PPD indices
More informationPredicting Individual Thermal Comfort using Machine Learning Algorithms
Predicting Individual Thermal Comfort using Machine Learning Algorithms Asma Ahmad Farhan 1, Krishna Pattipati 2, Bing Wang 1, and Peter Luh 2 Abstract thermal sensation in an environment may be delayed,
More informationBSE Public CPD Lecture Numerical Simulation of Thermal Comfort and Contaminant Transport in Rooms with UFAD system on 26 March 2010
BSE Public CPD Lecture Numerical Simulation of Thermal Comfort and Contaminant Transport in Rooms with UFAD system on 26 March 2010 Organized by the Department of Building Services Engineering, a public
More informationThe Pennsylvania State University. The Graduate School. College of Engineering USING OCCUPANT FEEDBACK IN MODEL PREDICTIVE CONTROL
The Pennsylvania State University The Graduate School College of Engineering USING OCCUPANT FEEDBACK IN MODEL PREDICTIVE CONTROL FOR INDOOR THERMAL COMFORT AND ENERGY OPTIMIZATION A Dissertation in Mechanical
More informationSensor fault detection in building energy management systems
Sensor fault detection in building energy management systems Dionissia Kolokotsa Anastasios Pouliezos and George Stavrakakis Technological Educational Institute of Crete Technical University of Crete 7333
More informationAN OCCUPANT BEHAVIOR MODEL BASED ON ARTIFICIAL INTELLIGENCE FOR ENERGY BUILDING SIMULATION
AN OCCUPANT BEHAVIOR MODEL BASED ON ARTIFICIAL INTELLIGENCE FOR ENERGY BUILDING SIMULATION Mathieu Bonte, Alexandre Perles, Bérangére Lartigue, and Françoise Thellier Université Toulouse III - Paul Sabatier,
More informationTHERMAL COMFORT IN HIGHLY GLAZED BUILDINGS DETERMINED FOR WEATHER YEARS ON ACCOUNT OF SOLAR RADIATION. Dominika Knera 1 and Dariusz Heim 1
THERMAL COMFORT IN HIGHLY GLAZED BUILDINGS DETERMINED FOR WEATHER YEARS ON ACCOUNT OF SOLAR RADIATION Dominika Knera 1 and Dariusz Heim 1 1 Department of Heat and Mass Transfer, Lodz University of Technology
More informationAir Diffusion Designing for Comfort
Air Diffusion Designing for Comfort Occupant Comfort Air Diffusion Selection ADPI Air Diffusion Performance index Ventilation Effectiveness Induction Room Space Induction Design Criteria ISO7730 ASHRAE
More informationPrinciples and Applications of Building Science Dr. E Rajasekar Department of Civil Engineering Indian Institute of Technology, Roorkee
Principles and Applications of Building Science Dr. E Rajasekar Department of Civil Engineering Indian Institute of Technology, Roorkee Lecture - 04 Thermal Comfort in Built Environment 2 In previous module,
More informationMODELLING THERMAL COMFORT FOR TROPICS USING FUZZY LOGIC
Eighth International IBPSA Conference Eindhoven, Netherlands August 11-14, 2003 MODELLING THERMAL COMFORT FOR TROPICS USING FUZZY LOGIC Henry Feriadi, Wong Nyuk Hien Department of Building, School of Design
More informationA Simulation Tool for Radiative Heat Exchangers
Purdue University Purdue e-pubs International Refrigeration and Air Conditioning Conference School of Mechanical Engineering 2012 A Simulation Tool for Radiative Heat Exchangers Yunho Hwang yhhwang@umd.edu
More informationModeling Human Thermoregulation and Comfort. CES Seminar
Modeling Human Thermoregulation and Comfort CES Seminar Contents 1 Introduction... 1 2 Modeling thermal human manikin... 2 2.1 Thermal neutrality... 2 2.2 Human heat balance equation... 2 2.3 Bioheat equation...
More informationMining Classification Knowledge
Mining Classification Knowledge Remarks on NonSymbolic Methods JERZY STEFANOWSKI Institute of Computing Sciences, Poznań University of Technology COST Doctoral School, Troina 2008 Outline 1. Bayesian classification
More informationMulti-wind Field Output Power Prediction Method based on Energy Internet and DBPSO-LSSVM
, pp.128-133 http://dx.doi.org/1.14257/astl.16.138.27 Multi-wind Field Output Power Prediction Method based on Energy Internet and DBPSO-LSSVM *Jianlou Lou 1, Hui Cao 1, Bin Song 2, Jizhe Xiao 1 1 School
More informationRELATIONSHIPS BETWEEN OVERALL THERMAL SENSATION, ACCEPTABILITY AND COMFORT
RELATIONSHIPS BETWEEN OVERALL THERMAL SENSATION, ACCEPTABILITY AND COMFORT Yufeng Zhang 1, and Rongyi Zhao 2 1 State Key Laboratory of Subtropical Building Science, South China University of Technology,
More informationINDIAN INSTITUTE OF TECHNOLOGY ROORKEE NPTEL NPTEL ONLINE CERTIFICATION COURSE. Refrigeration and Air-conditioning. Lecture-37 Thermal Comfort
INDIAN INSTITUTE OF TECHNOLOGY ROORKEE NPTEL NPTEL ONLINE CERTIFICATION COURSE Refrigeration and Air-conditioning Lecture-37 Thermal Comfort with Prof. Ravi Kumar Department of Mechanical and Industrial
More informationSubjective Thermal Comfort in the Environment with Spot Cooling System
Subjective Thermal Comfort in the Environment with Spot ing System Hayato Ohashi 1, Hitomi Tsutsumi 1, Shin-ichi Tanabe 1, Ken-ichi Kimura 1, Hideaki Murakami 2, Koji Kiyohara 3 1 Department of Architecture,
More informationAssignability of Thermal Comfort Models to nonstandard
Department of Architecture Institute of Building Climatology Assignability of Thermal Comfort Models to nonstandard Occupants P. Freudenberg Dresden, 12.06.2013 Thermal Comfort Models: Motivation Objectives
More informationNumerical Simulation and Air Conditioning System Improvement for the Experimental Hall at TLS J.C. Chang a, M.T. Ke b, Z.D. Tsai a, and J. R.
Numerical Simulation and Air Conditioning System Improvement for the Experimental Hall at TLS J.C. Chang a, M.T. Ke b, Z.D. Tsai a, and J. R. Chen a a National Synchrotron Radiation Research Center (NSRRC)
More informationInstitut national des sciences appliquées de Strasbourg GENIE CLIMATIQUE ET ENERGETIQUE APPENDICES
Institut national des sciences appliquées de Strasbourg GENIE CLIMATIQUE ET ENERGETIQUE APPENDICES DEVELOPMENT OF A TOOL, BASED ON THE THERMAL DYNAMIC SIMULATION SOFTWARE TRNSYS, WHICH RUNS PARAMETRIC
More informationHuman Thermal Comfort Study Based on Average Skin Temperature
Journal of Artificial Intelligence Practice (6) : 36-44 Clausius Scientific Press, Canada Human Thermal Comfort Study Based on Average Skin Temperature Yalong Yang,,a, Bao Xie,,b, Qiansheng Fang,,c*, Mingyue
More informationHD32.2 WBGT Index HD 32.2 INSTRUMENT FOR THE ANALYSIS OF THE WBGT INDEX
HD32.2 WBGT Index HD32.2 instrument can detect simultaneously the following quantities Globe thermometer temperature Tg. Wet bulb temperature with natural ventilation Tn. Environment temperature T. Starting
More informationBetter Weather Data Equals Better Results: The Proof is in EE and DR!
Better Weather Data Equals Better Results: The Proof is in EE and DR! www.weatherbughome.com Today s Speakers: Amena Ali SVP and General Manager WeatherBug Home Michael Siemann, PhD Senior Research Scientist
More informationIndoor Environment Quality. Study the world Capture the elements Environmental testing made easy. MI 6201 Multinorm. MI 6401 Poly.
Study the world Capture the elements Environmental testing made easy MI 6401 Poly MI 6201 Multinorm MI 6301 FonS Find out more about Indoor Environment Quality parameters testing Indoor Environmental Quality
More informationHD32.2 WBGT Index HD32.3 WBGT-PMV. [ GB ] - WBGT index. - PMV index and PPD
HD32.2 WBGT Index HD32.3 WBGT-PMV [ GB ] - WBGT index. - PMV index and PPD [ GB ] [ GB ] Description HD32.2 WBGT Index is an instrument made by Delta Ohm srl for the analysis of WBGT index (Wet Bulb Glob
More informationONR Mine Warfare Autonomy Virtual Program Review September 7, 2017
ONR Mine Warfare Autonomy Virtual Program Review September 7, 2017 Information-driven Guidance and Control for Adaptive Target Detection and Classification Silvia Ferrari Pingping Zhu and Bo Fu Mechanical
More informationDetermination of the Acceptable Room Temperature Range for Local Cooling
ICEB6, Shenzhen, China Maximize IAQ, Vol. I-1-4 Determination of the Acceptable Room Temperature Range for Local Cooling Yufeng Zhang Rongyi Zhao Assistant Professor Professor South China University of
More informationCombined GIS, CFD and Neural Network Multi-Zone Model for Urban Planning and Building Simulation. Methods
Combined GIS, CFD and Neural Network Multi-Zone Model for Urban Planning and Building Simulation Meng Kong 1, Mingshi Yu 2, Ning Liu 1, Peng Gao 2, Yanzhi Wang 1, Jianshun Zhang 1 1 School of Engineering
More informationAnalysis of Energy Savings and Visual Comfort Produced by the Proper Use of Windows
Analysis of Energy Savings and Visual Comfort Produced by the Proper Use of Windows I. Acosta, M. A. Campano, and J. F. Molina Abstract The aim of this research is to quantify the daylight autonomy and
More informationA Bayesian Approach for Learning and Predicting Personal Thermal Preference
Purdue University Purdue e-pubs International High Performance Buildings Conference School of Mechanical Engineering 2016 A Bayesian Approach for Learning and Predicting Personal Thermal Preference Seungjae
More informationOPERATIVE TEMPERATURE SIMULATION OF ENCLOSED SPACE WITH INFRARED RADIATION SOURCE AS A SECONDARY HEATER
OPERATIVE TEMPERATURE SIMULATION OF ENCLOSED SPACE WITH INFRARED RADIATION SOURCE AS A SECONDARY HEATER L. Hach 1, K. Hemzal 2, Y. Katoh 3 1 Institute of Applied Physics and Mathematics, Faculty of Chemical
More informationSwitching-state Dynamical Modeling of Daily Behavioral Data
Switching-state Dynamical Modeling of Daily Behavioral Data Randy Ardywibowo Shuai Huang Cao Xiao Shupeng Gui Yu Cheng Ji Liu Xiaoning Qian Texas A&M University University of Washington IBM T.J. Watson
More informationMining Classification Knowledge
Mining Classification Knowledge Remarks on NonSymbolic Methods JERZY STEFANOWSKI Institute of Computing Sciences, Poznań University of Technology SE lecture revision 2013 Outline 1. Bayesian classification
More informationOutdoor Thermal Comfort and Local Climate Change: Exploring Connections
Outdoor Thermal Comfort and Local Climate Change: Exploring Connections ROBERTA COCCI GRIFONI 1, MARIANO PIERANTOZZI 2, SIMONE TASCINI 1 1 School of Architecture and Design E. Vittoria, University of Camerino,
More informationPersonalized Thermal Comfort Forecasting for Smart Buildings via Locally Weighted Regression with Adaptive Bandwidth
Personalized Thermal Comfort Forecasting for Smart Buildings via Locally Weighted Regression with Adaptive Bandwidth Carlo Manna, Nic Wilson and Kenneth N. Brown Cork Constraint Computation Centre(4C),
More informationAPPENDIX A. Guangzhou weather data from 30/08/2011 to 04/09/2011 i) Guangzhou Weather Data: Day 242 (30/08/2011) Diffuse Solar Radiation (W/m2)
APPENDIX A Guangzhou weather data from 30/08/2011 to 04/09/2011 i) Guangzhou Weather Data: Day 242 (30/08/201 Rariation(W/m2) (W/m2) (oc) Relative Humidity (%) (o) 30/08/2011 08:00 166.00 74.00 0.1000
More informationFault prediction of power system distribution equipment based on support vector machine
Fault prediction of power system distribution equipment based on support vector machine Zhenqi Wang a, Hongyi Zhang b School of Control and Computer Engineering, North China Electric Power University,
More informationPredicting the Electricity Demand Response via Data-driven Inverse Optimization
Predicting the Electricity Demand Response via Data-driven Inverse Optimization Workshop on Demand Response and Energy Storage Modeling Zagreb, Croatia Juan M. Morales 1 1 Department of Applied Mathematics,
More informationAMBIENT WELL-BEING PARAMETERS IN THE INDOOR SPACES OF OFFICE BUILDINGS. CASE STUDY
PRESENT ENVIRONMENT AND SUSTAINABLE DEVELOPMENT, VOL. 6, no. 1, 2012 AMBIENT WELL-BEING PARAMETERS IN THE INDOOR SPACES OF OFFICE BUILDINGS. CASE STUDY Nicoleta Ionac 1, Adrian-Cătălin Mihoc 2, Paula Tăbleţ
More informationPROCESS CONTROL FOR THERMAL COMFORT MAINTENANCE USING FUZZY LOGIC
Journal of ELECTRICAL ENGINEERING, VOL. 59, NO. 1, 2008, 34 39 PROCESS CONTROL FOR THERMAL COMFORT MAINTENANCE USING FUZZY LOGIC Zoran L. Baus Srete N. Nikolovski Predrag Ž. Marić This paper presents the
More informationKeywords: Multimode process monitoring, Joint probability, Weighted probabilistic PCA, Coefficient of variation.
2016 International Conference on rtificial Intelligence: Techniques and pplications (IT 2016) ISBN: 978-1-60595-389-2 Joint Probability Density and Weighted Probabilistic PC Based on Coefficient of Variation
More informationA Hybrid Time-delay Prediction Method for Networked Control System
International Journal of Automation and Computing 11(1), February 2014, 19-24 DOI: 10.1007/s11633-014-0761-1 A Hybrid Time-delay Prediction Method for Networked Control System Zhong-Da Tian Xian-Wen Gao
More informationModeling Zero Energy Building with a Three- Level Fuzzy Cognitive Map
Modeling Zero Energy Building with a Three- Level Fuzzy Cognitive Map Eleni S. Vergini 1, Theodora-Eleni Ch. Kostoula 2, P. P. Groumpos 3 Abstract The concept of Zero Energy Buildings (ZEB) is briefly
More informationWater terminal control solutions
Water Terminal Control Solutions Water terminal control solutions Carrier offers a wide range of fan coil units designed to meet the needs of different systems and applications: from cabinet units in the
More informationQuality of life and open spaces: A survey of microclimate and comfort in outdoor urban areas
Quality of life and open spaces: A survey of microclimate and comfort in outdoor urban areas NIOBE CHRISOMALLIDOU, KATERINA TSIKALOUDAKI AND THEODORE THEODOSIOU Laboratory of Building Construction and
More informationCoupled CFD/Building Envelope Model for the Purdue Living Lab
Proceedings of the 2012 High Performance Buildings Conference at Purdue, 2012 (Accepted) 3457, Page, 1 Coupled CFD/Building Envelope Model for the Purdue Living Lab Donghun KIM (kim1077@purdue.edu), James
More informationSTUDY ON THE THERMAL PERFORMANCE AND AIR DISTRIBUTION OF A DISPLACEMENT VENTILATION SYSTEM FOR LARGE SPACE APPLICATION
STUDY ON THE THERMAL PERFORMANCE AND AIR DISTRIBUTION OF A DISPLACEMENT VENTILATION SYSTEM FOR LARGE SPACE APPLICATION K Sakai 1*, E Yamaguchi 2, O Ishihara 3 and M Manabe 1 1 Dept. of Architectural Engineering,
More informationEXPERIMENTAL ANALYSIS OF AIR-CONDITIONING IN HOSPITAL ROOMS BY MEANS OF LIGHT RADIANT CEILINGS
EXPERIMENTAL ANALYSIS OF AIR-CONDITIONING IN HOSPITAL ROOMS BY MEANS OF LIGHT RADIANT CEILINGS Renato M. Lazzarin renato@gest.unipd.it Francesco Castellotti caste@gest.unipd.it Filippo Busato busato@gest.unipd.it
More informationSupport Vector Machines. Introduction to Data Mining, 2 nd Edition by Tan, Steinbach, Karpatne, Kumar
Data Mining Support Vector Machines Introduction to Data Mining, 2 nd Edition by Tan, Steinbach, Karpatne, Kumar 02/03/2018 Introduction to Data Mining 1 Support Vector Machines Find a linear hyperplane
More informationTransient Heat Measurement in a Wall Using Thermoelectric Heat Flux Meter: A Mathematical Model
Transient Heat Measurement in a Wall Using Thermoelectric Heat Flux Meter: A Mathematical Model Mohamad Asmidzam Ahamat 1*, Razali Abidin 2, Eida Nadirah Roslin 1, Norazwani Muhammad Zain 1, Muhammad Khalilul
More informationDetection of comfortable temperature based on thermal events detection indoors
Detection of comfortable temperature based on thermal events detection indoors Andrzej Szczurek 1, Monika Maciejewska 1,*, and Mariusz Uchroński 2 1 Wroclaw University of Science and Technology, Faculty
More informationSupport Vector Machine II
Support Vector Machine II Jia-Bin Huang ECE-5424G / CS-5824 Virginia Tech Spring 2019 Administrative HW 1 due tonight HW 2 released. Online Scalable Learning Adaptive to Unknown Dynamics and Graphs Yanning
More informationML (cont.): SUPPORT VECTOR MACHINES
ML (cont.): SUPPORT VECTOR MACHINES CS540 Bryan R Gibson University of Wisconsin-Madison Slides adapted from those used by Prof. Jerry Zhu, CS540-1 1 / 40 Support Vector Machines (SVMs) The No-Math Version
More informationNUMERICAL ANALYSIS OF THERMAL COMFORT PARAMETERS IN LIVING QUARTERS
acta mechanica et automatica, vol.5 no.4 (2011) NUMERICAL ANALYSIS OF THERMAL COMFORT PARAMETERS IN LIVING QUARTERS Aneta BOHOJŁO * * phd student, Faculty of Mechanical Engineering, Bialystok University
More informationDoes a Neutral Thermal Sensation Determine Thermal Comfort?
Does a Neutral Thermal Sensation Determine Thermal Comfort? Dr Sally Shahzad PhD Department of Mechanical Engineering and the Built Environment, University of Derby sally.shahzad@gmail.com John Brennan
More informationAn Empirical Study of Building Compact Ensembles
An Empirical Study of Building Compact Ensembles Huan Liu, Amit Mandvikar, and Jigar Mody Computer Science & Engineering Arizona State University Tempe, AZ 85281 {huan.liu,amitm,jigar.mody}@asu.edu Abstract.
More informationElectrical Energy Modeling In Y2E2 Building Based On Distributed Sensors Information
Electrical Energy Modeling In Y2E2 Building Based On Distributed Sensors Information Mahmoud Saadat Saman Ghili Introduction Close to 40% of the primary energy consumption in the U.S. comes from commercial
More informationUse of Phase-Change Materials to Enhance the Thermal Performance of Building Insulations
Introduction Use of Phase-Change Materials to Enhance the Thermal Performance of Building Insulations R. J. Alderman, Alderman Research Ltd., Wilmington, DE David W. Yarbrough, R&D Services, Inc., Cookeville,
More informationMultiple Bits Distributed Moving Horizon State Estimation for Wireless Sensor Networks. Ji an Luo
Multiple Bits Distributed Moving Horizon State Estimation for Wireless Sensor Networks Ji an Luo 2008.6.6 Outline Background Problem Statement Main Results Simulation Study Conclusion Background Wireless
More informationInternational Conference on Mechanics, Materials and Structural Engineering (ICMMSE 2016)
International Conference on Mechanics, Materials and Structural Engineering (ICMMSE 2016) hermal Model Parameter Estimation for HVAC Facility using Recursive Least Square Method Dae Ki Kim1, a, Kyu Chul
More informationEnergy flows and modelling approaches
Energy flows and modelling approaches Energy flows in buildings external convection infiltration & ventilation diffuse solar external long-wave radiation to sky and ground local generation fabric heat
More informationNonlinear Adaptive Robust Control. Theory and Applications to the Integrated Design of Intelligent and Precision Mechatronic Systems.
A Short Course on Nonlinear Adaptive Robust Control Theory and Applications to the Integrated Design of Intelligent and Precision Mechatronic Systems Bin Yao Intelligent and Precision Control Laboratory
More informationSTUDY OF A PASSIVE SOLAR WINTER HEATING SYSTEM BASED ON TROMBE WALL
STUDY OF A PASSIVE SOLAR WINTER HEATING SYSTEM BASED ON TROMBE WALL Dr. G.S.V.L.Narasimham Chief Research Scientist, RAC, Dept. of Mechanical Engineering, Indian Institute of Science,Bengaluru- 560012,
More informationNumerical Learning Algorithms
Numerical Learning Algorithms Example SVM for Separable Examples.......................... Example SVM for Nonseparable Examples....................... 4 Example Gaussian Kernel SVM...............................
More informationDynamic Data Modeling of SCR De-NOx System Based on NARX Neural Network Wen-jie ZHAO * and Kai ZHANG
2018 International Conference on Modeling, Simulation and Analysis (ICMSA 2018) ISBN: 978-1-60595-544-5 Dynamic Data Modeling of SCR De-NOx System Based on NARX Neural Network Wen-jie ZHAO * and Kai ZHANG
More informationClustering. Professor Ameet Talwalkar. Professor Ameet Talwalkar CS260 Machine Learning Algorithms March 8, / 26
Clustering Professor Ameet Talwalkar Professor Ameet Talwalkar CS26 Machine Learning Algorithms March 8, 217 1 / 26 Outline 1 Administration 2 Review of last lecture 3 Clustering Professor Ameet Talwalkar
More informationLinear & nonlinear classifiers
Linear & nonlinear classifiers Machine Learning Hamid Beigy Sharif University of Technology Fall 1396 Hamid Beigy (Sharif University of Technology) Linear & nonlinear classifiers Fall 1396 1 / 44 Table
More informationSection 3.5 Thermal Comfort and Heat Stress
Section 3.5 Thermal Comfort and Heat Stress Table 3.6 Metabolic rate as a function of physical activity for a 70 kg adult man (abstracted from ASHRAE, 1997). activity metabolic rate (W) metabolic rate
More informationIntroduction to Convex Optimization
Introduction to Convex Optimization Daniel P. Palomar Hong Kong University of Science and Technology (HKUST) ELEC5470 - Convex Optimization Fall 2018-19, HKUST, Hong Kong Outline of Lecture Optimization
More informationLearning-based Model Predictive Control and User Feedback in Home Automation
3 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) November 3-7, 3. Tokyo, Japan Learning-based Model Predictive Control and User Feedback in Home Automation Christopher C. W.
More informationEAS 535 Laboratory Exercise Weather Station Setup and Verification
EAS 535 Laboratory Exercise Weather Station Setup and Verification Lab Objectives: In this lab exercise, you are going to examine and describe the error characteristics of several instruments, all purportedly
More informationEEL 851: Biometrics. An Overview of Statistical Pattern Recognition EEL 851 1
EEL 851: Biometrics An Overview of Statistical Pattern Recognition EEL 851 1 Outline Introduction Pattern Feature Noise Example Problem Analysis Segmentation Feature Extraction Classification Design Cycle
More informationClassification and Regression Trees
Classification and Regression Trees Ryan P Adams So far, we have primarily examined linear classifiers and regressors, and considered several different ways to train them When we ve found the linearity
More informationGlare and dynamic glare evaluation. Jan Wienold Fraunhofer-Institute for Solar Energy Systems, Freiburg, Germany
Glare and dynamic glare evaluation Jan Wienold Fraunhofer-Institute for Solar Energy Systems, Freiburg, Germany Use of shading devices in non residential buildings Control strategies could be complex Light
More informationReinforcement Learning, Neural Networks and PI Control Applied to a Heating Coil
Reinforcement Learning, Neural Networks and PI Control Applied to a Heating Coil Charles W. Anderson 1, Douglas C. Hittle 2, Alon D. Katz 2, and R. Matt Kretchmar 1 1 Department of Computer Science Colorado
More informationStudy on Thermal Load Calculation for Ceiling Radiant Cooling Panel System
Study on Thermal Load Calculation for Ceiling Radiant Cooling Panel System Sei Ito, Yasunori Akashi, Jongyeon Lim Shimizu Corporation, Tokyo, Japan University of Tokyo, Tokyo, Japan Abstract The ceiling
More informationKernels for Multi task Learning
Kernels for Multi task Learning Charles A Micchelli Department of Mathematics and Statistics State University of New York, The University at Albany 1400 Washington Avenue, Albany, NY, 12222, USA Massimiliano
More informationMEASUREMENT OF THE AIRFLOW AND TEMPERATURE FIELDS AROUND LIVE SUBJECTS AND THE EVALUATION OF HUMAN HEAT LOSS
MEASUREMENT OF THE AIRFLOW AND TEMPERATURE FIELDS AROUND LIVE SUBJECTS AND THE EVALUATION OF HUMAN HEAT LOSS GH Zhou 1, DL Loveday 1, AH Taki 2 and KC Parsons 3 1 Department of Civil and Building Engineering,
More informationTHERMODYNAMIC ASSESSMENT OF HUMAN THERMAL ENVIRONMENT INTERACTION
S. Boregowda et al., Int. Journal of Design & Nature. Vol. 2, No. 4 (2007) 310 318 THERMODYNAMIC ASSESSMENT OF HUMAN THERMAL ENVIRONMENT INTERACTION S. BOREGOWDA, R. HANDY & W. HUTZEL Department of Mechanical
More informationCS4495/6495 Introduction to Computer Vision. 8C-L3 Support Vector Machines
CS4495/6495 Introduction to Computer Vision 8C-L3 Support Vector Machines Discriminative classifiers Discriminative classifiers find a division (surface) in feature space that separates the classes Several
More informationPersonalizing Thermal Comfort in a Prototype Indoor Space
Personalizing Thermal Comfort in a Prototype Indoor Space Sotirios D Kotsopoulos, Federico Casalegno School of Humanities Arts and Social Sciences Massachusetts Institute of Technology Cambridge, Massachusetts,
More informationConnectedness of Random Walk Segmentation
Connectedness of Random Walk Segmentation Ming-Ming Cheng and Guo-Xin Zhang TNList, Tsinghua University, Beijing, China. Abstract Connectedness of random walk segmentation is examined, and novel properties
More informationNeural computing thermal comfort index for HVAC systems
Neural computing thermal comfort index for HVAC systems S. Atthajariyakul, T. Leephakpreeda * School of Manufacturing Systems and Mechanical Engineering, Sirindhorn International Institute of Technology,
More informationCollaborative topic models: motivations cont
Collaborative topic models: motivations cont Two topics: machine learning social network analysis Two people: " boy Two articles: article A! girl article B Preferences: The boy likes A and B --- no problem.
More informationHidden Markov Models. Vibhav Gogate The University of Texas at Dallas
Hidden Markov Models Vibhav Gogate The University of Texas at Dallas Intro to AI (CS 4365) Many slides over the course adapted from either Dan Klein, Luke Zettlemoyer, Stuart Russell or Andrew Moore 1
More informationAvailable online at ScienceDirect. Procedia Engineering 121 (2015 )
Available online at www.sciencedirect.com ScienceDirect Procedia Engineering 121 (2015 ) 2176 2183 9th International Symposium on Heating, Ventilation and Air Conditioning (ISHVAC) and the 3rd International
More informationLightcloud Application
Controlling Your Lightcloud System Lightcloud Application Lightcloud Application Navigating the Application Devices Device Settings Organize Control Energy Scenes Schedules Demand Response Power Up State
More informationPROPOSAL OF SEVEN-DAY DESIGN WEATHER DATA FOR HVAC PEAK LOAD CALCULATION
Ninth International IBPSA Conference Montréal, Canada August 5-8, PROPOSAL OF SEVEN-DAY DESIGN WEATHER DATA FOR HVAC PEAK LOAD CALCULATION Hisaya ISHINO Faculty of Urban Environmental Sciences, Metropolitan
More informationSupport Vector Machines and Kernel Methods
2018 CS420 Machine Learning, Lecture 3 Hangout from Prof. Andrew Ng. http://cs229.stanford.edu/notes/cs229-notes3.pdf Support Vector Machines and Kernel Methods Weinan Zhang Shanghai Jiao Tong University
More informationEVALUATION OF THERMAL ENVIRONMENT AROUND THE BLIND ON NON-UNIFOM RADIANT FIELDS A CFD SIMULATION OF HEAT TRANSFER DISTRIBUTION NEAR THE BLINDS
800 1500 6240 1600 1500 840 Proceedings of BS2015: EVALUATION OF THERMAL ENVIRONMENT AROUND THE BLIND ON NON-UNIFOM RADIANT FIELDS A CFD SIMULATION OF HEAT TRANSFER DISTRIBUTION NEAR THE BLINDS Nozomi
More informationAnalysis of Natural Wind Characteristics and Review of Their Correlations with Human Thermal Sense through Actual Measurements
Analysis of Natural Wind Characteristics and Review of Their Correlations with Human Thermal Sense through Actual Measurements Ki Nam Kang 1,a, Jin Yu 1,b, Doo Sam Song 2,c, Hee Jung Ham 3,d, Kook Jeong
More informationParametric Techniques
Parametric Techniques Jason J. Corso SUNY at Buffalo J. Corso (SUNY at Buffalo) Parametric Techniques 1 / 39 Introduction When covering Bayesian Decision Theory, we assumed the full probabilistic structure
More informationPreviously on TT, Target Tracking: Lecture 2 Single Target Tracking Issues. Lecture-2 Outline. Basic ideas on track life
REGLERTEKNIK Previously on TT, AUTOMATIC CONTROL Target Tracing: Lecture 2 Single Target Tracing Issues Emre Özan emre@isy.liu.se Division of Automatic Control Department of Electrical Engineering Linöping
More informationDEVELOPEMENT OF MODIFIED THERMAL COMFORT EQUATION FOR A ROOM WITH WINDOW OPENINGS AT ADJACENT WALLS
DEVELOPEMENT OF MODIFIED THERMAL COMFORT EQUATION FOR A ROOM WITH WINDOW OPENINGS AT ADJACENT WALLS D.Prakash 1, P.Ravikumar 2 1 Research scholar, Mechanical Engineering department, Anna University, Tamil
More informationEXPERIMENTAL AND SIMULATION TEMPERATURE EVALUATION WHICH DETERMINE THERMAL COMFORT
EXPERIMENTAL AND SIMULATION TEMPERATURE EVALUATION WHICH DETERMINE THERMAL COMFORT ubomír Hargaš, František Drkal, Vladimír Zmrhal Department of Environmental Engineering, Faculty of Mechanical Engineering,
More informationPractice Problems Section Problems
Practice Problems Section 4-4-3 4-4 4-5 4-6 4-7 4-8 4-10 Supplemental Problems 4-1 to 4-9 4-13, 14, 15, 17, 19, 0 4-3, 34, 36, 38 4-47, 49, 5, 54, 55 4-59, 60, 63 4-66, 68, 69, 70, 74 4-79, 81, 84 4-85,
More informationA Hybrid Approach For Air Conditioning Control System With Fuzzy Logic Controller
International Journal of Engineering and Applied Sciences (IJEAS) A Hybrid Approach For Air Conditioning Control System With Fuzzy Logic Controller K.A. Akpado, P. N. Nwankwo, D.A. Onwuzulike, M.N. Orji
More information