A platform architecture for occupancy detection using stream processing and machine learning approaches

Abstract

SummaryContext‐awareness in energy‐efficient buildings has been considered as a crucial fact for developing context‐driven control approaches in which sensing and actuation tasks are performed according to the contextual changes. This could be done by including the presence of occupants, number, actions, and behaviors in up‐to‐date context, taking into account the complex interlinked elements, situations, processes, and their dynamics. However, many studies have shown that occupancy information is a major leading source of uncertainty when developing control approaches. Comprehensive and real‐time fine‐grained occupancy information has to be, therefore, integrated in order to improve the performance of occupancy‐driven control approaches. The work presented in this paper is toward the development of a holistic platform that combines recent IoT and Big Data technologies for real‐time occupancy detection in smart building. The purpose of this work focuses mainly on the presence of occupants by comparing both static and dynamic machine learning techniques. An open‐access occupancy detection dataset was first used to assess the usefulness of the platform and the effectiveness of static machine learning strategies for data processing. This dataset is used for applications that follow the strategy aiming at storing data first and processing it later. However, many smart buildings' applications, such as HVAC and ventilation control, require online data streams processing. Therefore, a distributed real‐time machine learning framework was integrated into the platform and tested to show its effectiveness for this kind of applications. Experiments have been conducted for ventilation systems in energy‐efficient building laboratory (EEBLab) and preliminary results show the effectiveness of this platform in detecting on‐the‐fly presence of occupants, which is required to either make ON or OFF the system and then activate the corresponding embedded control technique (eg, ON/OFF, PID, state‐feedback).

Measuring Indoor Occupancy through Environmental Sensors: A Systematic Review on Sensor Deployment

“…There are particular places that were considered in at least one study (1.07%), such as hospital rooms [ 57 ], a bus [ 58 ], an elderly caring institution [ 59 ], and a university gym [ 12 ]. Furthermore, in six studies (6.45%), specially designed places were used to carry out experiments [ 24 , 55 , 60 , 61 , 62 , 63 ].…”

“…People NO YES 1 min GcForest Accuracy 86% [ 11 ] 4 D Detection, Levels NO YES 5 min FNN Accuracy 83.6–94.3% [ 65 ] 10 D Detection, Num. People YES NO 30 min BN Accuracy 82–91% [ 91 ] 15 D Num.People NO YES 1 min RF, ELM RMSE of RF 2.75–10.44 Accuracy of ELM 67.92–69.17% [ 63 ] 1 D Detection NO YES Dynamic ML [ 68 ] 12 D Num. People NO YES 5 min ANN, MLR 96.5–97.5% …”

Systematic Review Analysis on Smart Building: Challenges and Opportunities

“…The second category [45][46][47][48] uses temperature, humidity, and an infrared camera. The third category uses temperature, humidity and a carbon dioxide sensor data [32,[49][50][51][52][53][54][55][56][57][58]. It is observed that over the years, smart HVAC systems' performance has gradually improved through advanced control strategies whereby ambient conditions and occupants' energy profiles become an integral part of the system.…”

Using Stream Data Processing for Real-Time Occupancy Detection in Smart Buildings

“…The development of many data processing and IoT technologies has created a new development opportunity for data fusion. Furthermore, several problems related to energy management can be solved using data fusion methods, such as occupancy prediction, load forecast, predictive control, and occupants’ comfort scenarios [ 16 , 17 , 18 ]. In fact, most machine learning algorithms that have recently emerged for data fusion and prediction intend improve the performance of different services, such as healthcare, urban road planning, and energy management systems [ 19 , 20 , 21 ].…”