This paper proposes a new hybrid deep learning model to enhance the accuracy of forecasting very short-term wind power generation. The proposed comprises convolutional layer, long-short-term memory (LSTM) unit, and fully connected neural network. Convolution layer can automatically learn complicated features from raw input, whereas LSTM layers retain useful information through which gradient may flow over extended periods. To obtain best performance model, random search optimization...

<title>Abstract</title> The primary focuses of today’s world are: How to create energy-efficient buildings? design high-performance structures? achieve sustainability in construction? answers lie Building Information Modelling (BIM) and its 6D capabilities for energy efficiency sustainable analysis. This research aims gain a deeper understanding consumption by analyzing the residential building Dhaka, Bangladesh, using BIM tools such as Autodesk Revit 2020, INSIGHT360, Green Studio....

This paper presents 'Expression' - an integrated assistive solution using Google Glass. The key function of the system is to enable user in perceiving social signals during a natural dyadic conversation. design and implementation addressed number technical research cha

The load forecasting plays a pivotal role for buildings' energy management system to schedule and control loads effectively while maintaining the reliability, stability quality of utilized power within buildings. This work proposes new subtractive clustering based adaptive neuro fuzzy inference (ANFIS) residential forecasting. proposed ANFIS prediction considers temperature variable calculated on occupancy week/special days predicting building's consumption. performance has been compared...

Ambient awareness on a sidewalk is critical for safe navigation, especially the people who are blind or visually impaired. An affordable and interactive system necessary this purpose. In paper, we present outcome of experiment off-the-shelf image captioning systems. Design implementation embedded in RPi3 part experiment. The main component include: a. generation meaningful caption from images, b. personalized feedback mechanism efficient communication with minimal cognitive load, c. an user...

Limited access to non-verbal cues hinders the dyadic conversation or social interaction of people who are blind visually impaired. This paper presents Expression --- an integrated assistive solution using Google Glass. The key function system is enable user perceive signals during a natural face-to-face conversation. Empirical evaluation presented with qualitative (Likert score: 4.383/5) and quantitative results (overall F-measure nonverbal expression recognition: 0.768).

The most important feature of load forecasting is enabling the building management system to control and manage its loads with available resources ahead time. electricity usage in residential buildings has increased during COVID-19 period, as compared normal times. Therefore, performance methods impacted, further tuning parameters required cope energy consumption changes due COVID-19. This paper proposes a new adaptive neuro-fuzzy 2 inference (ANFIS2) for both periods. particle swarm...

Load scheduling is an effective way of utilizing loads smart residential buildings according to the preferences inhabitants or grid demands, while reducing cost energy. This work proposes objective functions for load confine energy within consumers’ preference range keeping consumption closer demand as possible, minimize system loss during normal and pandemic condition such COVID-19 periods, fulfilling unique features a net-zero building. The proposed function implemented by considering...

The load forecasting is crucial for energy management to maintain stability, power quality and reliability of the building's system. This work proposes a new two input based fuzzy logic controller method residential forecasting. proposed system considers temperature variable calculated on occupancy week/special days predicting consumption. For comparison purpose, predicted energies by artificial neural network are analyzed against actual consumption data in an apartment building located...

Assistive technology solutions can help people with disability from social isolation, depression, facilitate interaction and enhance the quality of life. Limited access to non-verbal cues hinders who are blind or visually impaired. This paper presents 'Expression' - an integrated assistive solution using Google Glass. The key function system is enable user perceive signals during a natural face-to-face conversation. Subjective evaluation Expression was performed five (5) point Likert Scale...

This work proposes two non-linear and one linear equation-based system for residential load forecasting considering heating degree days, cooling occupancy, day type, which are applicable to any building with small sets of smart meter data. The coefficients the proposed nonlinear equations tuned by particle swarm optimization (PSO) multiple regression method, respectively. For purpose comparison, a subtractive clustering based adaptive neuro fuzzy inference (ANFIS), random forests, gradient...

Segmentation of mouse brain magnetic resonance images (MRI) based on anatomical and/or functional features is an important step towards morphogenetic structure characterization murine models in neurobiological studies. State-of-the-art image segmentation methods register volumes to standard presegmented templates or well-characterized highly detailed atlases. Performance these depends critically the quality skull-stripping, which digital removal tissue signal exterior brain. This is,...

This paper investigates the month-wise impact of COVID-19 conditions on residential load due to people’s presence at home during office hours in Memphis city, Tennessee, USA. The energy consumption patterns four consumers are analyzed based data available from pre-COVID continuing situations. It is observed that consumptions April 2020 June 2021 for all families have increased than months. Therefore, impacts loads distribution transformer terms hottest spot, top-oil temperature, and loss...

This paper proposes a novel hybrid model that combines long short-term memory (LSTM) with light gradient boosting (LightGBM) to achieve precise onshore wind power prediction in Australia. The intermittent nature of renewable energy sources like necessitates accurate forecasting minimize operational costs and enhance system reliability security. showcases promising results 15-minute interval generation data. Performance is evaluated using root mean squared errors (RMSE) means absolute (MAE),...

The demand for sensorless control of surface permanent magnet synchronous motor (SPM) drives has grown tremendously over the past decade in a wide variety industrial applications. Many different methods have been proposed SPM, especially Matsui's current model-based method and extended Kalman filter based gained much attention. However, performance these are severely worsened or may even become unstable under strong disturbances sensing measurement failure conditions. This paper presents...

SafeAccess is an integrated system designed to provide easier and safer access a smart home for people with or without disabilities. The enhance safety promote the independence of disability (i.e., visually impaired). key functionality includes detection identification human generating contextual visual summary from real-time video streams obtained cameras placed in strategic locations around house. In addition, classifies into groups (i.e. friends/families/caregiver versus...

We proposed the full-color three-dimensional (3D) holographic waveguide-type augmented reality (AR) system based on integral imaging using optical element which is mirror array (HMA). Our suggested same as with conventional waveguide. Here, two (HOE) films are located at in-and out-put of holographic-type The main roles HOEs; first HOE in-coupler exist waveguide: HMA film. An has a similar role for image forming properties lens and RGB light beams reflected each reproduce 3D like array-based...

Most of the malarial diagnostic methods either depend on manual counting infected red blood cells or requires complex laboratory facilities. In both cases, is time-consuming, expensive, trained personnel, sometimes produce erroneous results due to intervention, and hinders rapid diagnostics infection. Malaria mostly fatal if not diagnosed treated promptly, therefore, it imperative devise a methodology that provides rapid, cost-effective, accurate diagnosis with proper quantification. Here,...