scholarly journals An Indoor Room Classification System for Social Robots via Integration of CNN and ECOC

2019 ◽  
Vol 9 (3) ◽  
pp. 470 ◽  
Author(s):  
Kamal Othman ◽  
Ahmad Rad
Keyword(s):  
Real Time ◽  
Social Robots ◽  
Alternative Form ◽  
Living Room ◽  
Simulation Studies ◽  
Combination Model ◽  
Output Code ◽  
Disparate Data ◽  
Binary Classifiers ◽  
Dining Room

The ability to classify rooms in a home is one of many attributes that are desired for social robots. In this paper, we address the problem of indoor room classification via several convolutional neural network (CNN) architectures, i.e., VGG16, VGG19, & Inception V3. The main objective is to recognize five indoor classes (bathroom, bedroom, dining room, kitchen, and living room) from a Places dataset. We considered 11600 images per class and subsequently fine-tuned the networks. The simulation studies suggest that cleaning the disparate data produced much better results in all the examined CNN architectures. We report that VGG16 & VGG19 fine-tuned models with training on all layers produced the best validation accuracy, with 93.29% and 93.61% on clean data, respectively. We also propose and examine a combination model of CNN and a multi-binary classifier referred to as error correcting output code (ECOC) with the clean data. The highest validation accuracy of 15 binary classifiers reached up to 98.5%, where the average of all classifiers was 95.37%. CNN and CNN-ECOC, and an alternative form called CNN-ECOC Regression, were evaluated in real-time implementation on a NAO humanoid robot. The results show the superiority of the combination model of CNN and ECOC over the conventional CNN. The implications and the challenges of real-time experiments are also discussed in the paper.

Sky Segmentation for Enhanced Depth Reconstruction and Bokeh Rendering with Efficient Architectures

2020 ◽  
Vol 2020 (14) ◽  
pp. 378-1-378-7
Author(s):  
Tyler Nuanes ◽  
Matt Elsey ◽  
Radek Grzeszczuk ◽  
John Paul Shen
Keyword(s):  
Real Time ◽  
Mobile Device ◽  
Computational Cost ◽  
False Positives ◽  
Compact Model ◽  
High Quality ◽  
False Negatives ◽  
Trade Off ◽  
Depth Reconstruction ◽  
Binary Classifiers

We present a high-quality sky segmentation model for depth refinement and investigate residual architecture performance to inform optimally shrinking the network. We describe a model that runs in near real-time on mobile device, present a new, highquality dataset, and detail a unique weighing to trade off false positives and false negatives in binary classifiers. We show how the optimizations improve bokeh rendering by correcting stereo depth misprediction in sky regions. We detail techniques used to preserve edges, reject false positives, and ensure generalization to the diversity of sky scenes. Finally, we present a compact model and compare performance of four popular residual architectures (ShuffleNet, MobileNetV2, Resnet-101, and Resnet-34-like) at constant computational cost.

scholarly journals Hand Detection Using Cascade of Softmax Classifiers

2018 ◽  
Vol 2018 ◽  
pp. 1-11
Author(s):  
Yan-Guo Zhao ◽  
Feng Zheng ◽  
Zhan Song
Keyword(s):  
Logistic Regression ◽  
Real Time ◽  
Sliding Window ◽  
Detection Accuracy ◽  
Hand Posture ◽  
Hand Detection ◽  
Cascade Structure ◽  
Real Time Applications ◽  
Binary Classifiers ◽  
Background Pattern

Sliding-window based multiclass hand posture detections are often performed by detecting postures of each predefined category using an independent detector, which makes it lack efficiency and results in high postures confusion rates in real-time applications. To tackle such problems, in this work, an efficient cascade detector that integrates multiple softmax-based binary (SftB) models and a softmax-based multiclass (SftM) model is investigated to perform multiclass posture detection in parallel. The SftB models are used to distinguish the predefined postures from the background regions, and the SftM model is applied to discriminate among all the predefined hand posture categories. Another usage of the cascade structure is that it could effectively decompose the complexity of background pattern space and therefore improve the detection accuracy. In addition, to balance the detection accuracy and efficiency, the HOG features of increasing resolutions will be adopted by classifiers of increasing stage-levels in the cascade structure. The experiments are implemented under various scenarios with complicated background and challenging lightings. Results show the superiority of the proposed SftB classifiers over the traditional binary classifiers such as logistic regression, as well as the accuracy and efficiency improvements brought by the softmax-based cascade architecture compared with the noncascade multiclass softmax detectors.

Object Recognition Pipeline

2018 ◽  
pp. 18-33
Author(s):  
John Alejandro Castro Vargas ◽  
Alberto Garcia Garcia ◽  
Sergiu Oprea ◽  
Sergio Orts Escolano ◽  
Jose Garcia Rodriguez
Keyword(s):  
Object Recognition ◽  
Real Time ◽  
Social Robots ◽  
Social Robot ◽  
Degree Of Disability ◽  
Domestic Environments ◽  
Domestic Assistance

Object grasping in domestic environments using social robots has an enormous potential to help dependent people with a certain degree of disability. In this chapter, the authors make use of the well-known Pepper social robot to carry out such task. They provide an integrated solution using ROS to recognize and grasp simple objects. That system was deployed on an accelerator platform (Jetson TX1) to be able to perform object recognition in real time using RGB-D sensors attached to the robot. By using the system, the authors prove that the Pepper robot shows a great potential for such domestic assistance tasks.

A Calibrated Combination of Probabilistic Precipitation Forecasts to Achieve a Seamless Transition from Nowcasting to Very Short-Range Forecasting

2020 ◽  
Vol 35 (3) ◽  
pp. 773-791
Author(s):  
Peter Schaumann ◽  
Mathieu de Langlard ◽  
Reinhold Hess ◽  
Paul James ◽  
Volker Schmidt
Keyword(s):  
Real Time ◽  
Short Range ◽  
Lead Times ◽  
New Model ◽  
Combination Model ◽  
Logit Transformation ◽  
Interaction Terms ◽  
Probabilistic Forecasts ◽  
Seamless Transition ◽  
The Ideal

Abstract In this paper, a new model for the combination of two or more probabilistic forecasts is presented. The proposed combination model is based on a logit transformation of the underlying initial forecasts involving interaction terms. The combination aims at approximating the ideal calibration of the forecasts, which is shown to be calibrated, and to maximize the sharpness. The proposed combination model is applied to two precipitation forecasts, Ensemble-MOS and RadVOR, which were developed by Deutscher Wetterdienst. The proposed combination model shows significant improvements in various forecast scores for all considered lead times compared to both initial forecasts. In particular, the proposed combination model is calibrated, even if both initial forecasts are not calibrated. It is demonstrated that the method enables a seamless transition between both initial forecasts across several lead times to be created. Moreover, the method has been designed in such a way that it allows for fast updates in nearly real time.

Experimental and simulation studies of a real-time polymerase chain reaction in the presence of a fullerene derivative

2009 ◽  
Vol 20 (41) ◽  
pp. 415101 ◽  
Author(s):  
Junjun Shang ◽  
Tatsiana A Ratnikova ◽  
Sini Anttalainen ◽  
Emppu Salonen ◽  
Pu Chun Ke ◽  
...  
Keyword(s):  
Polymerase Chain Reaction ◽  
Real Time ◽  
Fullerene Derivative ◽  
Simulation Studies ◽  
Chain Reaction ◽  
Polymerase Chain

Time-use in different rooms of selected New Zealand houses and the influence of plan layout

2016 ◽  
Vol 27 (1) ◽  
pp. 19-33 ◽  
Author(s):  
Iman Khajehzadeh ◽  
Brenda Vale ◽  
Nigel Isaacs
Keyword(s):  
New Zealand ◽  
Indoor Air Quality ◽  
Indoor Air ◽  
Time Use ◽  
Living Room ◽  
Indoor Pollutants ◽  
Open Plan ◽  
Dining Room ◽  
The Times ◽  
Potential Level

House interiors are affected by outdoor and indoor pollutants although levels of exposure differ with room type. The times people spend in rooms also differ, and hence their potential level of exposure, which is the focus of this article. Additionally, time spent in a kitchen during cooking, which is the main source of indoor particulates for non-smoking households, could affect indoor air quality in other rooms, especially where the kitchen is part of an open plan arrangement. This study investigated the time people spend in all rooms including kitchens and open plan kitchen/dining/living in New Zealand houses. On average, New Zealanders spend 54% of time at home indoors in usual bedrooms and 29%–36% in a living room, dining room, and kitchen (or combination of these). People in open plan houses spend less time in living areas than those in cellular plan houses, but effectively more time in the ‘kitchen’. Given time spent in a combined living room/dining/kitchen, combined living room/kitchen or combined dining room/kitchen is effectively time spent in a kitchen, people spend respectively 3.23, 1.36 and 0.53 h/day more in the kitchen compared to those having a separate kitchen, which could increase their chance of exposure to kitchen pollutants.

scholarly journals Effects of Supply Angle on Thermal Environment of Residential Space with Hybrid Desiccant Cooling System for Multi-Room Control

2020 ◽  
Vol 10 (20) ◽  
pp. 7271
Author(s):  
Joon Ahn ◽  
Ho Yup Choi
Keyword(s):  
Thermal Comfort ◽  
Thermal Environment ◽  
Cooling System ◽  
Living Room ◽  
Comfort Zone ◽  
Computational Fluid Dynamics Cfd ◽  
Dining Room ◽  
Typical Summer ◽  
Globe Temperature ◽  
American Society

In this study, local measurement and computational fluid dynamics (CFD) were employed to evaluate the thermal comfort in a residential environment where desiccant cooling is performed in an outdoor air condition, which is the typical summer weather in Korea. The desiccant cooling system in the present study has been developed for multi-room control with a hybrid air distribution, whereby mixing and displacement ventilation occur simultaneously. Due to this distribution of air flow, the thermal comfort was changed, and the thermal comfort indicators conflicted. The evaluation indicators included the ASHRAE (American Society of Heating, Refrigerating and Air-Conditioning Engineers) comfort zone, predicted mean vote (PMV), and effective draft temperature (EDT). The dry-bulb temperature displayed a distribution of 26.2–26.8 °C in the cooling spaces, i.e., living room, kitchen, and dining room. When determined based on the standard ASHRAE comfort zone, the space where desiccant cooling takes place entered the comfort zone for summer. Due to the influence of solar radiation, the globe temperature was more than 2 °C higher than the dry-bulb temperature at the window. A difference of up to 6% in humidity was observed locally in the cooling space. In the dining room located along the outlet of the desiccant cooling device, the PMV entered the comfort zone, but was slightly above 1 in the rest of the space. Conversely, as for the EDT, its value was lower than −1.7 in the dining room, but was included in the comfort zone in the rest of the space. By adjusting the discharge angle upward, the PMV and EDT were expected to be more uniform in the cooling space. In particular, the optimum discharge angle obtained was 40° upward from the discharge surface.

scholarly journals Indoor Thermal Environment Long-Term Data Analytics Using IoT Devices in Korean Apartments: A Case Study

2020 ◽  
Vol 17 (19) ◽  
pp. 7334
Author(s):  
Hyunjun Yun ◽  
Jinho Yang ◽  
Byong Hyoek Lee ◽  
Jongcheol Kim ◽  
Jong-Ryeul Sohn
Keyword(s):  
Real Time ◽  
Thermal Environment ◽  
Temperature Management ◽  
Living Room ◽  
Indoor Thermal Environment ◽  
Long Term Monitoring ◽  
Iot Devices ◽  
Term Monitoring

IoT-based monitoring devices can transmit real-time and long-term thermal environment data, enabling innovative conversion for the evaluation and management of the indoor thermal environment. However, long-term indoor thermal measurements using IoT-based devices to investigate health effects have rarely been conducted. Using apartments in Seoul as a case study, we conducted long-term monitoring of thermal environmental using IoT-based real-time wireless sensors. We measured the temperature, relative humidity (RH), and CO2 in the kitchen, living room, and bedrooms of each household over one year. In addition, in one of the houses, velocity and globe temperatures were measured for multiple summer and autumn seasons. Results of our present study indicated that outdoor temperature is an important influencing factor of indoor thermal environment and indoor RH is a good indicator of residents’ lifestyle. Our findings highlighted the need for temperature management in summer, RH management in winter, and kitchen thermal environment management during summer and tropical nights. This study suggested that IoT devices are a potential approach for evaluating personal exposure to indoor thermal environmental risks. In addition, long-term monitoring and analysis is an efficient approach for analyzing complex indoor thermal environments and is a viable method for application in healthcare.

Sign in / Sign up

Export Citation Format

Share Document