Abstract

In this paper, we propose a feature set by con-catenating Mel-Frequency Cepstral Coefficients (MFCC) andSpectral Centroid Magnitude Coefficients (SCMC) features forAcoustic Scene Classification (ASC) using Deep Neural Networks(DNN). MFCC features are used to hold the acoustic characteris-tics such as spectral envelope of an acoustic scene in each frame.It also carries the sub-band average energy as a single dimension.SCMC features are used to hold the distribution of energy in asub-band effectively. A test is carried out on Tampere Universityof Technology (TUT) Acoustic Scenes 2017 Dataset. The DNNarchitecture for utterance level classification has been used. Theproposed system’s performance on a 4-fold cross-validation setupis 80.2% and it gives 5.4% relative improvement in performancewhen compared to the baseline system that uses log-Mel bandenergies with Multi-Layer Perceptron model.

Abstract

Herein, we propose an Acoustic Scene Classification(ASC) based on Deep Neural Networks (DNN). The design of Mel-filer bank helps in capturing the acoustic scene characteristicsin the low-frequency regions during MFCC extraction. In thispaper, inverse MFCC are used as interdependent to structureof Mel filter bank. We can effectively capture the acousticinformation in the total audio frequency range using MFCCand IMFCC features. An experiment is carried on TampereUniversity of Technology (TUT) Acoustic Scenes 2017 Dataset.DNN architecture at utterance level classification with supervisedlearning is adopted. Scores from the DNN models correspondingto MFCC and IMFCC features are combined for testing themodel. The relative improvement of 5.22% wih respect to baselinesystem is achieved by the proposed system on setup of 4-foldcross-validation. We participated in the DCASE 2017 challengefor ASC task, also got 45.9% accuracy on given evaluationdataset. This approach got 76thrank out of 97 submissions.

Abstract

Intensity and duration are both pertinent aspects of an emotional experience, yet how they are related is unclear. Though stronger emotions usually last longer, sometimes they abate faster than the weaker ones. We present a quantitative model of affective adaptation, the process by which emotional responses to unchanging affective stimuli weaken with time, that addresses this intensity-duration problem. The model, described by three simple linear algebraic equations, assumes that the relationship between an affective stimulus and its experiencer can be broken down into three parameters. Self-relevance and explanation level combine multiplicatively to determine emotion intensity whereas the interaction of these with explanatory ease determines its duration. The model makes predictions, consistent with available empirical data, about emotion intensity, its duration, and adaptation speed for different scenarios. It predicts when the intensity-duration correlation is positive, negative or even absent, thus offering a solution to the intensity-duration problem. The model also addresses the shortcomings of past models of affective adaptation with its enhanced predictive power and by offering a more complete explanation to empirical observations that earlier models explain inadequately or fail to explain altogether. The model has potential applications in areas such as virtual reality training, games, human-computer interactions, and robotics.

Abstract

Automated shading and integrated lighting control systems are being used in buildings for electrical energy savings and improve occupant’s comfort. These systems facilitate efective utilization of useful daylight in interior spaces that beneft an occupant’s health, well-being, and productivity by preventing glare and overheating while maintaining the adequate illuminance levels. The pragmatic procedure to implement open loop shading and integrated lighting control comprises three parts: (i) a reliable estimation of sky conditions on realtime basis, (ii) determining indoor daylight metrics using outdoor conditions, and (iii) incorporating the metrics in the blind and integrated lighting control techniques. This paper presents a review of experimental studies done on openloop window shade and integrated lighting control strategies. The aim of this paper is to analyse the performance and feasibility of various daylight prediction methods and their application in controlling blinds and integrated lighting system. The review mainly focuses on simulation assisted open loop control techniques that employ real-time daylight estimation methods. The review identifes the current challenges, recommends areas for improvement, and provides signifcant scope for future research. The paper concludes that modifed and improved open loop system are more competent as an alternative compared to the conventional methods for automated blind and lighting control systems. Advanced open-loop control systems along with calibrated simulations have the capability to reduce post commissioning errors, allow easy monitoring of the system and predict daylight more extensively.

Abstract

A building is a boundary between an outdoor climate and indoor conditions. The building energy consumption, notably the energy used for air-conditioning is closely related to outdoor climate. The Solar Radiation, Drybulb Temperature and Relative Humidity are the important climatic parameters which affect building’s thermal and visual conditions. The energy codes development analyses and evaluation of new technologies with respect to energy savings and financial viability have been carried out for selected cities that are supposed to represent any particular climate zone. There is a significant change in thermal loads in different cities of a climate zone. Selection of a representative city for a climatic zone is important because it needs to reflect average climatic conditions for a particular climate zone accurately. This study presents a new method that has been developed for the selection of a representative city in any climate zone, using the principle of Euclidean distance approach having a dry-bulb temperature, wet bulb temperature and solar radiation as three axes. The city having minimum Euclidean distance with respect to remaining cities of the same climatic zone is proposed to be taken as a representative city. The proposed method has been applied on each of the five existing climatic zones of India according to National Building Code (NBC) of India and eight climate zones according to ASHRAE Standard 169-2013.

Abstract

This study demonstrates an experimental example of application of time-lapse high dynamic range images for analyzing variations in correlated color temperature (CCT) and circadian lighting in an interior space daylit using a tubular daylight device (TDD). Previous studies have shown that the spectral composition of daylight affects human circadian rhythms, with emphasis on wavelengths towards the blue region of the visible spectrum. Spectrally based metrics such as CCT can therefore aid in evaluating the circadian impact of daylight. TDDs redirect daylight towards interior spaces with changing light levels and color temperatures during the daylight hours. This paper details the color temperature and circadian lighting metrics (circadian luminance and illuminance) in an interior space throughout a period of several days in a mid-latitude, temperate, sunny climate. An automated timelapse HDR photography apparatus was modified to allow for calculation of CCT and circadian lighting metrics using state-of-the art techniques available in the literature. Prior to the measurements in the space with the TDD, this device was calibrated against a spectrophotometer. Results indicate the level of daily variation in CCT and circadian lighting metrics that can be expected in interior spaces daylit by TDDs without any other sources of daylight. Besides showcasing the use of HDR techniques, these results could be used to support design decisions involving daylighting in interior spaces. These techniques can also be used outside the laboratory in the evaluation of the circadian impact of lighting throughout the built environment.

Abstract

Real-time Indoor theft detection from surveillancevideos is not only a challenging problem of object detection and human activity recognition in the field of computer vision, but also an urgent need for preventing theft crimes in real life. The system uses digital cameras to scan the faces of people approaching a security gate i.e. the entry gate, and then matches its faces with the faces in the database, and if found not to be a known one it automatically generates an alert. In this paper, we propose a framework for real-time indoor theft detection based on the combining result of face recognition and pattern matching by analyzing the activities with that of thieves. At last, if detected abnormal it automatically sends a message using Multimedia Message Service with the help of GPRS/GSM modem.

Abstract

Among the extreme events, droughts are the most widespread and slowly developing hydro-meteorological events remain for a long duration affecting natural resources, environment and the people. Few studies included reference evapotranspiration to account for climatic water availability in drought characterization such as Standardized Precipitation–Evapotranspiration Index (SPEI). However, a drought prediction model should consider the actual evapotranspiration to include the physical water availability and land surface changes of a region. The Budyko curve is used to estimate the actual evapotranspiration as a function of the aridity index. The drought index is based on the probability distribution of the difference between precipitation and Actual Evapotranspiration (AET), which represents the measure of the water surplus or deficit for a particular month. The gridded daily precipitation data from India Meteorological Department (IMD) available for the period of 1901 to 2015 at 0.25o X 0.25o resolution and the gridded daily average temperature at a resolution of 1o X 1o resolution was used in the study as temperature observational data sets. The regional drought prediction model developed in the study is applied on Krishna River basin in India. The monthly PET was estimated with the Thornthwaite equation using mean temperatures over the entire Krishna river basin. The AET is estimated at 12 month scale using Budyko equation, which combines the precipitation, AET and PET estimated from Thornthwaite equation. The performance of drought index is evaluated using historical droughts and projected variability under climate change. The results of the study reveal that inclusion of AET in the drought characterization along with PET and precipitation into account can drive the areas into moderate drought that would experience extreme drought under if only PET is considered.

Abstract

In the present study an attempt has been made to study the 1D (One Dimensional), 2D (Two Dimensional) and 3D (Three Dimensional) ground response of pond ash collected from Odisha under different earthquake motions. 1D ground response analysis of pond ash deposit has been carried out by using equivalent linear and nonlinear analysis method using SHAKE2000 and Cyclic1D software respectively. 2D and 3D ground response analysis of pond ash deposit has been carried out by using finite element software Plaxis2D and Plaxis3D respectively. The response analyses of the pond ash deposit have been performed under the excitation of North East India earthquake (Mw-7.5) and Nepal earthquake (Mw-7.8). The results of the response analyses have been presented in terms of acceleration, displacement, excess pore pressure and excess pore pressure ratio. A comparative study between 1D, 2D and 3D ground response analysis has been performed to predict seismic risk of the pond ash site in Odisha.

Abstract

Utilization of fy ash, bottom ash and municipal solid waste in the feld of geotechnical engineering necessitates determination of its physical, chemical, morphological and engineering properties. This paper presents detailed physical, chemical and geotechnical characterization of fy ash, bottom ash and municipal solid waste from Telangana State in India. Fly ash and bottom ash samples were collected from Kakatiya thermal power station in India. Municipal solid waste (MSW) sample was collected from Borabanda municipal dump site in the city of Hyderabad, India. From the experimental results, it is noticed that specifc gravity of fy ash, bottom ash and municipal solid waste were found to be 1.86, 1.77 and 2.2 respectively. Presence of quartz and mullite; quartz, mullite and calcium carbonate; and quartz and corundum are found to be predominant in fy ash, bottom ash and MSW respectively. The peak friction angle of fy ash, bottom ash and municipal solid waste were found to be 37.02°, 33.77° and 35.23° respectively. Permeability characteristics of fy ash, bottom ash and municipal solid waste were observed to be 1.01E−04 cm/s, 2.01E−04 cm/s and 1.16E−04 cm/s respectively. From the observation of experimental results, it can be concluded that fyash, bottom ash and municipal solid waste from Telangana state are efective material to be used as backfll material, flter material and embankment construction