Envelope Features Research Articles

Radar HRRP Target Recognition Model Based on a Stacked CNN–Bi-RNN With Attention Mechanism

The range resolution of high-resolution wideband radar is much smaller than the target size. Its echo signals tend to be diverse and sensitive to small changes of targets. Therefore, it is difficult to capture and distinguish the features in radar signals. In this article, we propose a radar target recognition pipeline based on a deep nested neural network. The framework consists of three parts: The translation sensitivity of the training data is first addressed in the preprocessing section. The second step is to obtain an embedded representation of the radar echo signals by the combination of the adjustment layer, convolutional neural network (CNN), and the squeeze and excitation (SE) block. Finally, the target is recognized through inputting embedded representation as a time sequence into the stacked bidirectional recurrent neural network (bi-RNN) based on an attention mechanism. Compared with the traditional methods, the proposed deep nested neural network extracts and takes advantage of the features of radar echo signals more effectively, including the envelope features and local physical structural features. The experimental results based on the test data indicate that the proposed method has a great advantage over other methods in the case of large data sets as well as small training data sets and is robust to the small translation of test samples and noises, exhibiting high engineering practical value.

Research on Multimodal Music Emotion Recognition Method Based on Image Sequence

The work of music performance system is to control the light change by identifying the emotional elements of music. Therefore, once the identification error occurs, it will not be able to create a good stage effect. Therefore, a multimodal music emotion recognition method based on image sequence is studied. The emotional characteristics of music are analyzed, including acoustic characteristics, melody characteristics, and audio characteristics, and the feature vector is constructed. The recognition and classification model based on neural network is trained, the weight and threshold of each layer are adjusted, and then the feature vector is input into the trained model to realize the intelligent recognition and classification of multimodal music emotion. The threshold of the starting point range of a specific humming note is given by the center clipping method, which is used to eliminate the low amplitude part of the humming note signal, extract the short-time spectral structure features and envelope features of the pitch, and complete the multimodal music emotion recognition. The results show that the calculated kappa coefficient k is greater than 0.75, which shows that the recognition and classification results are in good agreement with the actual results, and the classification and recognition accuracy is high.

Functional mapping of language-related areas from natural, narrative speech during awake craniotomy surgery

Accurate localization of brain regions responsible for language and cognitive functions in epilepsy patients is important. Electrocorticography (ECoG)-based real-time functional mapping (RTFM) has been shown to be a safer alternative to electrical cortical stimulation mapping (ESM), which is currently the clinical/gold standard. Conventional methods for analyzing RTFM data mostly account for the ECoG signal in certain frequency bands, especially high gamma. Compared to ESM, they have limited accuracy when assessing channel responses. In the present study, we developed a novel RTFM method based on tensor component analysis (TCA) to address the limitations of current estimation methods. Our approach analyzes the whole frequency spectrum of the ECoG signal during natural continuous speech. We construct third-order tensors that contain multichannel time-frequency information and use TCA to extract low-dimensional temporal, spectral and spatial modes. Temporal modulation scores (correlation values) are then calculated between the time series of voice envelope features and TCA-estimated temporal courses, and significant temporal modulation determines which components' channel weightings are displayed to the neurosurgeon as a guide for follow-up ESM. In our experiments, data from thirteen patients with refractory epilepsy were recorded during preoperative evaluation for their epileptogenic zones (EZs), which were located adjacent to the eloquent cortex. Our results showed higher detection accuracy of our proposed method in a narrative speech task, suggesting that our method complements ESM and is an improvement over the prior RTFM method. To our knowledge, this is the first TCA-based method to pinpoint language-specific brain regions during continuous speech that uses whole-band ECoG.

Automatic modulation classification of noise‐like radar intrapulse signals using cascade classifier

Automatic modulation classification is essential in radar emitter identification. We propose a cascade classifier by combining a support vector machine (SVM) and convolutional neural network (CNN), considering that noise might be taken as radar signals. First, the SVM distinguishes noise signals by the main ridge slice feature of signals. Second, the complex envelope features of the predicted radar signals are extracted and placed into a designed CNN, where a modulation classification task is performed. Simulation results show that the SVM-CNN can effectively distinguish radar signals from noise. The overall probability of successful recognition (PSR) of modulation is 98.52% at 20 dB and 82.27% at −2 dB with low computation costs. Furthermore, we found that the accuracy of intermediate frequency estimation significantly affects the PSR. This study shows the possibility of training a classifier using complex envelope features. What the proposed CNN has learned can be interpreted as an equivalent matched filter consisting of a series of small filters that can provide different responses determined by envelope features.

Heart sound classification based on sub-band envelope and convolution neural network

Automatic classification of heart sounds plays an important role in the early diagnosis of congenital heart disease. A kind of heart sound classification algorithms based on sub-band envelope feature and convolution neural network was proposed in this paper, which did not need to segment the heart sounds according to cardiac cycle accurately. Firstly, the heart sound signal was divided into some frames. Then, the frame level heart sound signal was filtered with Gammatone filter bank to obtain the sub-band signals. Next, the sub-band envelope was extracted by Hilbert transform. After that, the sub-band envelope was stacked into a feature map. Finally, type Ⅰ and type Ⅱ convolution neural network were selected as classifier. The result shown that the sub-band envelope feature was better in type Ⅰ than type Ⅱ. The algorithm is tested with 1 000 heart sound samples. The test results show that the overall performance of the algorithm proposed in this paper is significantly improved compared with other similar algorithms, which provides a new method for automatic classification of congenital heart disease, and speeds up the process of automatic classification of heart sounds applied to the actual screening.

Temperature-induced response in algal cell surface properties and behaviour: an experimental approach

Microalgae are considered an accurate indicator of ecosystem perturbations induced by global climate change. The present work aims to investigate the alteration of temperature on surface properties and behaviour of three algal species using the complementary surface methods (electrochemical and atomic force microscopy). The results showed that the temperature-induced response of algae is species-specific due to the structural features of the cell envelope. Wall-less algae experience the largest nanomechanical and chemical change, while algae with silicified walls show the pronounced chemical change in the degree of hydrophobicity. Alterations of surface properties suggest a molecular modification of the algal barrier and cytoskeletal rearrangements due to a change in cell size, while algal morphology reveals no change. The physiological activity of cells showed a different organisation of released extracellular substances in the form of fine fibrillar structures, aggregated particles, and dense networks. Both types of algal responses, physiological activity, and molecular modification of the cell barrier determine the cell adhesion and motility. This study highlights the role of surface properties in cell-substrate and cell–cell interactions, which is important for the understanding of algal behaviour at natural interfaces and the mechanism of algal biofilm and aggregate formation in aquatic systems under the stress.Graphical abstract

Diversity-Robust Acoustic Feature Signatures Based on Multiscale Fractal Dimension for Similarity Search of Environmental Sounds

This paper proposes new acoustic feature signatures based on the multiscale fractal dimension (MFD), which are robust against the diversity of environmental sounds, for the content-based similarity search. The diversity of sound sources and acoustic compositions is a typical feature of environmental sounds. Several acoustic features have been proposed for environmental sounds. Among them is the widely-used Mel-Frequency Cepstral Coefficients (MFCCs), which describes frequency-domain features. However, in addition to these features in the frequency domain, environmental sounds have other important features in the time domain with various time scales. In our previous paper, we proposed enhanced multiscale fractal dimension signature (EMFD) for environmental sounds. This paper extends EMFD by using the kernel density estimation method, which results in better performance of the similarity search tasks. Furthermore, it newly proposes another acoustic feature signature based on MFD, namely very-long-range multiscale fractal dimension signature (MFD-VL). The MFD-VL signature describes several features of the time-varying envelope for long periods of time. The MFD-VL signature has stability and robustness against background noise and small fluctuations in the parameters of sound sources, which are produced in field recordings. We discuss the effectiveness of these signatures in the similarity sound search by comparing with acoustic features proposed in the DCASE 2018 challenges. Due to the unique descriptiveness of our proposed signatures, we confirmed the signatures are effective when they are used with other acoustic features.

SpeechCollectR: An R package for web-based speech data collection

To accommodate web-based speech production and perception data collection during the COVID-19 pandemic, we developed the R package, SpeechCollectR (https://github.com/abbey-thomas/speechcollectr), designed for speech scientists familiar with R [R Core Team, R: A Language and Environment for Statistical Computing (R Foundation for Statistical Computing, Vienna, 2021]. SpeechCollectR employs existing R functions for acoustic analysis, allowing researchers to collect, visualize, and analyze speech production and perception data with a single program. SpeechCollectR lets researchers construct interfaces that embed experimental tasks in games to sustain participant attention amid distractions in non-laboratory environments. The application for production experiments saves uncompressed audio data as WAV files, one recording per trial. Amplitude envelope features are used to isolate a speech token in each recording. This token is compared to the remainder of the recording to assess signal-to-noise ratio. Performing this analysis after each trial, we can supply the participant with feedback to improve recording quality. We tested the efficacy of using SpeechCollectR, collecting 1344 recordings of three types of affective prosody from 32 participants. 83% of these recordings were usable for analysis of prosodic variables. We present a bootstrap analysis demonstrating reliability of affective prosodic features despite variations in recording equipment and environment.

A rapid evaluation method for design strategies of high-rise office buildings achieving nearly zero energy in Guangzhou

The construction of nearly zero energy buildings (NZEB) has achieved dramatical impact on global warming and energy crises. It is still a challenge for designers to derive design strategies on how to achieve NZEB in the early design stage, because a complex modelling process with many input parameters of the current NZEB design and evaluation tool is still unavoidable. This article, therefore, aims to introduce a tool suitable for the rapid and reliable evaluation of NZEB design strategies for high rise office building in the city of Guangzhou in China. Firstly, a high-rise office building with typical geometry features is established by sensitivity analysis and survey, thereby the reference building consumption is obtained. Secondly, comprehensive simulations on cases with various envelope features, air conditioning performances and lighting control methods is carried out. Based on the sensitivity analysis on simulation results, key influencing parameters are selected out, effective strategies which fulfills “Technical standard for nearly zero energy buildings (NZEBTS)” are put forward. Finally, a parametric building energy evaluation model is built by regression analysis on simulation results. Combined with energy efficiency index from “NZEBTS”, an evaluation tool is developed to help designer determine NZEB strategies. The results revealed that the most effective strategies to achieve NZEB in Guangzhou are to apply high performance external windows, improve air conditioning systems and utilize intelligent zone-controlled lighting systems, meanwhile, the utilization ratio of renewable energy (ηs) should be more than 40% of building total annual energy consumption.

Classification of autism spectrum disorders individuals and controls using phase and envelope features from resting-state fMRI data

ABSTRACT This study uses phase and envelope features extracted from fMRI data for discriminating between Autism Spectrum Disorders (ASD) and control subjects. We exploit the transfer function perturbation (TFP) method to estimate the instantaneous phase and envelope of intrinsic resting-state brain network components from fMRI data. Then we calculated power, entropy, and coherency features. We examined three different classifiers and two different feature selection algorithms, in a way that the subsets of features that best predict classes were selected using a sequential forward feature selection (SFFS) algorithm and principal component analysis (PCA). Afterwards, three different categories of calculated features, including phase features, envelope features, and a combination of phase and envelope features, fed into non-linear Support Vector Machine (SVM), K-Nearest Neighbours (K-NN), and Deep Neural Network (DNN). Results illustrate that phase features are significantly discriminative and considerably improve ADSs and control subjects’ classification accuracy and lead to robust prediction. Moreover, 91% of classification accuracy was obtained when the dimension of phase features was reduced by PCA and fed to the non-linear SVM. Eventually, the two-sample t-test and Pearson’s correlation coefficient illustrated that phase features had a significantly lower correlation than envelope features.

Comparative Analyses Based on Simulations to Improve Energy Consumption in Office Buildings in Egypt. (Dept. A)

A growing attention has been paid to building envelope features for achieving lower energy consumption especially in large office buildings and hot climate zones, since these features and their variables are affecting energy consumption widely and with different sensitivity. Therefore, this paper conducts simulation-based comparative analyses between main envelope features with their internal variables; the selected features for this study are building geometry ratios, orientations and common envelope finishing materials (FMs). Two applications have been conducted (comparing cases with either a same or different building volumes), and more than 500 cases/simulations have been conducted and studied in total. Accordingly, sensitive features and variables have been determined to enrich design decisions for different cases, along with best variables' integrations that achieve best energy consumption through the proposed applications and cases. Cubic office buildings in Egypt have been used to demonstrate the study, and energy simulations have been achieved using eQuest (DOE-2). Results show that lower height with wider roof achieves best energy consumption if building volume is fixed via comparisons, and vice versa. Gravel and galvanized steel represent best studied roof and walls' FMs, while roofing shingles is the worst one. If building volume is varied via comparisons, horizontal dimensions are the most sensitive feature that affects energy consumption per m2, while FMs and height represent lowest sensitivity among studied features. Ranking of cases, features, variables along with sensitive features in details have been analyzed and discussed through the paper.

Field Soil Suction Profiles for Expansive Soil

Soil suction–based analyses are paramount to proper design of foundations in expansive soils, yet availability of field soil suction profiles from direct measurement is limited. A method was developed, using directly measured suction profiles obtained from sites across the US, by which routine geotechnical tests can be used to estimate soil suction to expand the database for estimation of field suction profiles. Herein, the expanded database is used to develop best-estimate clay soil suction envelopes for boundary conditions associated with covered or uncovered ground surface subjected to natural climatic surface flux. Where appropriate for site conditions, the proposed soil suction profile envelopes can be used with any suction-based heave/shrinkage analysis. Key features of the field suction envelopes, consistent with current popular approaches, include climate-dependent estimates for equilibrium suction at depth, depth to equilibrium (stable) suction, and variation in soil suction at the ground surface. Comparisons to existing soil suction envelope recommendations are made. Finally, a limited number of cases of developed/irrigated sites are presented for comparison to soil suction profiles obtained for natural climatic surface flux conditions.

Dereverberation of autoregressive envelopes for far-field speech recognition

The task of speech recognition in far-field environments is adversely affected by the reverberant artifacts that elicit as the temporal smearing of the sub-band envelopes. In this paper, we develop a neural model for speech dereverberation using the long-term sub-band envelopes of speech. The sub-band envelopes are derived using frequency domain linear prediction (FDLP) which performs an autoregressive estimation of the Hilbert envelopes. The neural dereverberation model estimates the envelope gain which when applied to reverberant signals suppresses the late reflection components in the far-field signal. The dereverberated envelopes are used for feature extraction in speech recognition. Further, the sequence of steps involved in envelope dereverberation, feature extraction and acoustic modeling for ASR can be implemented as a single neural processing pipeline which allows the joint learning of the dereverberation network and the acoustic model. Several experiments are performed on the REVERB challenge dataset, CHiME-3 dataset and VOiCES dataset. In these experiments, the joint learning of envelope dereverberation and acoustic model yields significant performance improvements over the baseline ASR system based on log-mel spectrogram as well as other past approaches for dereverberation (average relative improvements of 10–24% over the baseline system). A detailed analysis on the choice of hyper-parameters and the cost function involved in envelope dereverberation is also provided.

Analysis of acoustic and voice quality features for the classification of infant and mother vocalizations

Classification of infant and parent vocalizations, particularly emotional vocalizations, is critical to understanding how infants learn to regulate emotions in social dyadic processes. This work is an experimental study of classifiers, features, and data augmentation strategies applied to the task of classifying infant and parent vocalization types. Our data were recorded both in the home and in the laboratory. Infant vocalizations were manually labeled as cry, fus (fuss), lau (laugh), bab (babble) or scr (screech), while parent (mostly mother) vocalizations were labeled as ids (infant-directed speech), ads (adult-directed speech), pla (playful), rhy (rhythmic speech or singing), lau (laugh) or whi (whisper). Linear discriminant analysis (LDA) was selected as a baseline classifier, because it gave the highest accuracy in a previously published study covering part of this corpus. LDA was compared to two neural network architectures: a two-layer fully-connected network (FCN), and a convolutional neural network with self-attention (CNSA). Baseline features extracted using the OpenSMILE toolkit were augmented by extra voice quality, phonetic, and prosodic features, each targeting perceptual features of one or more of the vocalization types. Three web data augmentation and transfer learning methods were tested: pre-training of network weights for a related task (adult emotion classification), augmentation of under-represented classes using data uniformly sampled from other corpora, and augmentation of under-represented classes using data selected by a minimum cross-corpus information difference criterion. Feature selection using Fisher scores and experiments of using weighted and unweighted samplers were also tested. Two datasets were evaluated: a benchmark dataset (CRIED) and our own corpus. In terms of unweighted-average recall of CRIED dataset, the CNSA achieved the best UAR compared with previous studies. In terms of classification accuracy, weighted F1, and macro F1 of our own dataset, the neural networks both significantly outperformed LDA; the FCN slightly (but not significantly) outperformed the CNSA. Cross-examining features selected by different feature selection algorithms permits a type of post-hoc feature analysis, in which the most important acoustic features for each binary type discrimination are listed. Examples of each vocalization type of overlapped features were selected, and their spectrograms are presented, and discussed with respect to the type-discriminative acoustic features selected by various algorithms. MFCC, log Mel Frequency Band Energy, LSP frequency, and F1 are found to be the most important spectral envelope features; F0 is found to be the most important prosodic feature.

Biomimetic building facades demonstrate potential to reduce energy consumption for different building typologies in different climate zones.

Greenhouse gas (GHG) emissions leading to anthropogenic global warming continue to be a major issue for societies worldwide. A major opportunity to reduce emissions is to improve building construction, and in particular the effectiveness of building envelope, which leads to a decrease in operational energy consumption. Improving the performance of a building's thermal envelope can substantially reduce energy consumption from heating, ventilation, and air conditioning while maintaining occupant comfort. In previous work, a computational model of a biomimetic building façade design was found to be effective in temperate climates in an office context. Through a case study example based on animal fur and blood perfusion, this paper tests the hypothesis that biomimetic building facades have a broader application in different building typologies across a range of climate zones. Using bioinspiration for innovation opens new ideas and pathways for technological development that traditional engineering design does not provide. This study exemplifies the process in a building façade, integrating a new form of insulation, heating and cooling. Methods of mathematical modelling and digital simulation methods were used to test the energy reduction potential of the biomimetic façade was tested in a set of operational applications (office, school, and aged care) and across different climate zones (tropical, desert, temperate, and cool continental). Results indicated that the biomimetic façade has potential to reduce energy consumption for all building applications, with the greatest benefit shown in residential aged care (67.1% reduction). Similarly, the biomimetic building façade showed potential to reduce operational services energy consumption in all climate zones, with the greatest energy reductions achieved in the tropical (55.4% reduction) and humid continental climates (55.1% reduction). Through these results the hypothesis was confirmed suggesting that facades engineered to mimic biological functions and processes can improve substantially decrease building operational energy consumption and can be applied in different building classifications and different climate zones. These results would significantly decrease operational greenhouse gas emissions over the lifetime of a building and provide substantial savings in energy bills. Such facades can contribute to the further reduction in greenhouse gas emissions in a broad range of contexts in the built environment and other areas of technology and design. The flexibility and adaptability of biomimetic facades exemplify how biological strategies and characteristics can augment and improve performance in different environments, since the organisms that inspire innovation are already well-adapted to the conditions on earth. This study also exemplified a method by which other biomimetic building envelope features may be assessed. Further work is suggested to assess economic viability and constructability of the proposed facades.Graphic abstract

Effects of building layouts and envelope features on wind flow and pollutant exposure in height-asymmetric street canyons

The influences of building layouts on pollutant dispersion within urban street canyons have been widely studied, although they have been rarely considered with envelope features. Different envelope features, such as wing walls, balconies and overhangs, have not yet been quantitatively assessed for their effects on the wind flow patterns around street canyons to a certain degree. Adopting the evaluation indicators of personal intake fraction and daily pollutant exposure, this study aims to investigate the potential influences of building layouts and envelope features that affect pollutant exposure risks for pedestrians and near-road residents via computational fluid dynamics (CFD). The turbulence modelling approach and numerical methods are validated by reported experiments in the literature. Asymmetric street canyons with an aspect ratio of 2 and two typical building layouts, namely, step-up and step-down notch configurations, are further investigated to test their effects. The results indicate that the step-down configuration provides worse situations for wind environments and pollutant dispersion than symmetric and step-up configurations. More specifically, the presence of overhangs has the greatest impact on the personal intake fraction (P_IF) change ratio, followed by balconies. The largest P_IF change ratio occurs on the fifth floor of an upstream building when overhangs are applied to the step-down street canyon. The aforementioned findings are helpful to understand the influences of building layouts together with envelope features on the wind environment as well as pollutant exposure risks experienced by pedestrians and near-road residents.

Limited Evidence for a Relationship between HIV-1 Glycan Shield Features in Early Infection and the Development of Neutralization Breadth.

ABSTRACTIdentifying whether viral features present in acute HIV-1 infection predetermine the development of neutralization breadth is critical to vaccine design. Incorporating such features in vaccine antigens could initiate cross-reactive antibody responses that could sufficiently protect vaccinees from HIV-1 infection despite the uniqueness of each founder virus. To understand the relationship between Env determinants and the development of neutralization breadth, we focused on 197 individuals enrolled in two cohorts in Thailand and East Africa (RV144 and RV217) and followed since their diagnosis in acute or early HIV-1 infection. We analyzed the distribution of variable loop lengths and glycans, as well as the predicted density of the glycan shield, and compared these envelope features to the neutralization breadth data obtained 3 years after infection (n = 121). Our study revealed limited evidence for glycan shield features that associate with the development of neutralization breadth. While the glycan shield tended to be denser in participants who subsequently developed breadth, no significant relationship was found between the size of glycan holes and the development of neutralization breadth. The parallel analysis of 3,000 independent Env sequences showed no evidence of directional evolution of glycan shield features since the beginning of the epidemic. Together, our results highlight that glycan shield features in acute and early HIV-1 infection may not play a role determinant enough to dictate the development of neutralization breadth and instead suggest that the glycan shield’s reactive properties that are associated with immune evasion may have a greater impact.IMPORTANCE A major goal of HIV-1 vaccine research is to design vaccine candidates that elicit potent broadly neutralizing antibodies (bNAbs). Different viral features have been associated with the development of bNAbs, including the glycan shield on the surface of the HIV-1 Envelope (Env). Here, we analyzed data from two cohorts of individuals who were followed from early infection to several years after infection spanning multiple HIV-1 subtypes. We compared Env glycan features in HIV-1 sequences obtained in early infection to the potency and breadth of neutralizing antibodies measured 1 to 3 years after infection. We found limited evidence of glycan shield properties that associate with the development of neutralization breadth in these cohorts. These results may have important implications for antigen design in future vaccine strategies and emphasize that HIV-1 vaccines will need to rely on a complex set of properties to elicit neutralization breadth.

Evolution of the analytical scattering model of live Escherichia coli.

A previously reported multi-scale model for (ultra-)small-angle X-ray (USAXS/SAXS) and (very) small-angle neutron scattering (VSANS/SANS) of live Escherichia coli was revised on the basis of compositional/metabolomic and ultrastructural constraints. The cellular body is modeled, as previously described, by an ellipsoid with multiple shells. However, scattering originating from flagella was replaced by a term accounting for the oligosaccharide cores of the lipopolysaccharide leaflet of the outer membrane including its cross-term with the cellular body. This was mainly motivated by (U)SAXS experiments showing indistinguishable scattering for bacteria in the presence and absence of flagella or fimbrae. The revised model succeeded in fitting USAXS/SAXS and differently contrasted VSANS/SANS data of E. coli ATCC 25922 over four orders of magnitude in length scale. Specifically, this approach provides detailed insight into structural features of the cellular envelope, including the distance of the inner and outer membranes, as well as the scattering length densities of all bacterial compartments. The model was also successfully applied to E. coli K12, used for the authors' original modeling, as well as for two other E. coli strains. Significant differences were detected between the different strains in terms of bacterial size, intermembrane distance and its positional fluctuations. These findings corroborate the general applicability of the approach outlined here to quantitatively study the effect of bactericidal compounds on ultrastructural features of Gram-negative bacteria without the need to resort to any invasive staining or labeling agents.

Online Implementation of a Soft Actor-Critic Agent to Enhance Indoor Temperature Control and Energy Efficiency in Buildings

Recently, a growing interest has been observed in HVAC control systems based on Artificial Intelligence, to improve comfort conditions while avoiding unnecessary energy consumption. In this work, a model-free algorithm belonging to the Deep Reinforcement Learning (DRL) class, Soft Actor-Critic, was implemented to control the supply water temperature to radiant terminal units of a heating system serving an office building. The controller was trained online, and a preliminary sensitivity analysis on hyperparameters was performed to assess their influence on the agent performance. The DRL agent with the best performance was compared to a rule-based controller assumed as a baseline during a three-month heating season. The DRL controller outperformed the baseline after two weeks of deployment, with an overall performance improvement related to control of indoor temperature conditions. Moreover, the adaptability of the DRL agent was tested for various control scenarios, simulating changes of external weather conditions, indoor temperature setpoint, building envelope features and occupancy patterns. The agent dynamically deployed, despite a slight increase in energy consumption, led to an improvement of indoor temperature control, reducing the cumulative sum of temperature violations on average for all scenarios by 75% and 48% compared to the baseline and statically deployed agent respectively.

Envelope Features of Response Amplitude of Hanging Underwater Slender Bodies in Upper End Horizontal Periodical Motion

Envelope Features of Response Amplitude of Hanging Underwater Slender Bodies in Upper End Horizontal Periodical Motion