Window Analysis Research Articles

Changes in coral reef community structure along a sediment gradient in Fouha Bay, Guam

High sedimentation rates have well-documented, deleterious impacts on coral reefs. However, few previous studies have attempted to quantitatively describe a coral reef community across a large continuous sediment gradient. In this study distinct benthic assemblages in Fouha Bay, Guam, were identified using a Moving Window Analysis conducted along a two-order of magnitude sediment gradient, with transition boundaries that were generally consistent with sediment thresholds identified in the literature. Coral richness dropped exponentially with increasing sedimentation rate. Richness was nearly three times greater in assemblages with sedimentation rates <10 mg cm−2 d−1 compared to assemblages experiencing rates between 10 and 50 mg cm−2 d−1, and nearly 30 times greater than assemblages experiencing rates between 50 and 100 mg cm−2 d−1. No corals were found in assemblages with sedimentation rates >110 mg cm−2 d−1. Reducing sedimentation in this area could result in a shift of more diverse and abundant coral assemblages toward the head of the bay.

Dynamic Patterns of Symptoms and Functioning in Predicting Deliberate Self-harm in Patients with First-Episode Schizophrenia-Spectrum Disorders Over 3 Years.

Patients with schizophrenia have a significant risk of self-harm. We aimed to explore the dynamic relationship between symptomatology, functioning and deliberate self-harm (DSH) and evaluate the feasibility of developing a self-harm risk prediction tool for patients with first-episode schizophrenia (FES). Patients with FES (n = 1234) were followed up for 36 months. Symptomatology, functioning, treatment adherence and self-harm information were obtained monthly over the follow-up period. A time-varying vector autoregressive (VAR) model was used to study the contribution of clinical variables to self-harm over the 36th month. Random forest models for self-harm were established to classify the individuals with self-harm and predict future self-harm events. Over a 36-month period, 187 patients with FES had one or more self-harm events. The depressive symptoms contributed the most to self-harm prediction during the first year, while the importance of positive psychotic symptoms increased from the second year onwards. The random forest model with all static information and symptom instability achieved a good area under the receiver operating characteristic curve (AUROC = 0.77 ± 0.023) for identifying patients with DSH. With a sliding window analysis, the averaged AUROC of predicting a self-event was 0.65 ± 0.102 (ranging from 0.54 to 0.78) with the best model being 6-month predicted future 6-month self-harm for month 11-23 (AUROC = 0.7). Results highlight the importance of the dynamic relationship of depressive and positive psychotic symptoms with self-harm and the possibility of self-harm prediction in FES with longitudinal clinical data.

Adverse Pregnancy Outcome in Polycystic Ovarian Syndrome: A Comparative Study.

IntroductionA paucity of data exists regarding pregnancy outcome data in women with polycystic ovarian syndrome (PCOS). Therefore, we conducted this study to compare the pregnancy outcomes of women with and without in Indian population.Materials and methodsA total of 102 antenatal pregnant women aged between 18 and 45 years were included in this study conducted at the Department of Obstetrics and Gynecology, Pradyumna Bal Memorial Hospital, Kalinga Institute of Medical Sciences, Bhubaneswar, India. Fifty-one women had PCOS, and 51 women served as controls. We recorded patient demographic, clinical, menstrual, and pregnancy data for each group. All participants were monitored until delivery, and we recorded maternal outcomes, including spontaneous abortion, preterm birth, gestational diabetes mellitus (GDM), and pregnancy-induced hypertension (PIH). We used IBM SPSS Statistics version 20.0 for Windows (Armonk, NY: IBM Corp.) for statistical analysis and the chi-square test to analyze relationships in categorical variables.ResultsMost participants were aged between 20 and 30 years (64.7%). A high body mass index (BMI) was twice as common in women with PCOS than the control group. Most women with PCOS with pregnancy complications were overweight (62.7%) with a BMI of 25 to 29.9 kg/m2. A majority of women in the PCOS group (86.3%) required reproductive technology assistance, while none in the control group needed the same type of assistance. In the PCOS group, spontaneous abortions (SAB) occurred in 5.9%, GDM occurred in 17.6%, PIH in 21.6%, and preterm births in 33.3%. By contrast, the control group saw SAB occur in only 3.9%, GDM occurred in 9.8%, PIH was identical in 21.6%, and preterm births occurred in 17.6% of women without PCOS. Cesarian delivery occurred in 64.7% of women with PCOS, while only 39.2% of women without PCOS had cesarian delivery was statistically not significant.ConclusionWe conducted this study to assess the impact of PCOS on pregnancy against pregnant women without PCOS. Pregnant women with PCOS were more likely to experience complications such as SAB, GDM, and preterm birth than pregnant women without PCOS. Therefore, pregnancies in women with PCOS are high-risk pregnancies that require frequent and timely antenatal care.

Complete chloroplast genome of Lilium ledebourii (Baker) Boiss and its comparative analysis: lights into selective pressure and adaptive evolution

Lilium ledebourii (Baker) Boiss is a rare species, which exhibits valuable traits. However, before its genetic diversity and evolutionary were uncovered, its wild resources were jeopardized. Moreover, some ambiguities in phylogenetic relationships of this genus remain unresolved. Therefore, obtaining the whole chloroplast sequences of L. ledebourii and its comparative analysis along with other Lilium species is crucial and pivotal to understanding the evolution of this genus as well as the genetic populations. A multi-scale genome-level analysis, especially selection pressure, was conducted. Detailed third‑generation sequencing and analysis revealed a whole chloroplast genome of 151,884 bp, with an ordinary quadripartite and protected structure comprising 37.0% GC. Overall, 113 different genes were recognized in the chloroplast genome, consisting of 30 distinct tRNA genes, four distinct ribosomal RNAs genes, and 79 unique protein-encoding genes. Here, 3234 SSRs and 2053 complex repeats were identified, and a comprehensive analysis was performed for IR expansion and contraction, and codon usage bias. Moreover, genome-wide sliding window analysis revealed the variability of rpl32-trnL-ccsA, petD-rpoA, ycf1, psbI-trnS-trnG, rps15-ycf1, trnR, trnT-trnL, and trnP-psaJ-rpl33 were higher among the 48 Lilium cp genomes, displaying higher variability of nucleotide in SC regions. Following 1128 pairwise comparisons, ndhB, psbJ, psbZ, and ycf2 exhibit zero synonymous substitution, revealing divergence or genetic restriction. Furthermore, out of 78 protein-coding genes, we found that accD and rpl36 under positive selection: however, at the entire-chloroplast protein scale, the Lilium species have gone through a purifying selection. Also, a new phylogenetic tree for Lilium was rebuilt, and we believe that the Lilium classification is clearer than before. The genetic resources provided here will aid future studies in species identification, population genetics, and Lilium conservation.

Vibrational dynamics of ethosuximide polymorphs. Infrared absorption and inelastic neutron scattering spectroscopy and model calculations

Commercially available and administered to the patients ethosuximide is a racemic mixture of two enantiomers, each of them exist in different conformations. The presence of the species mentioned are proven by the title experimental methods aided by DFT model calculations. Results of the latter are matched against spectroscopic data by the clustering window analysis. One type of hydrogen bonds exist in the solid forms of ethosuximide NH⋯O, leading to the polymorphic variety of the substance studied.

Estimating sustainable transport efficiency and socioeconomic factors: application of non-parametric approach

ABSTRACT Sustainable transport has received substantial attention globally. Evidently, transportation is a major contributor to global carbon emission, which causes the degradation of environmental quality and safety. Economic-oriented activities are performed in terms of inclination aspect. Thus, this paper aims to analyze whether and how environmental pollution and fatality, economic-oriented transport, and socioeconomic factors affect transport efficiency. For this purpose, panel data from 2000 to 2020 for 35 OECD countries are used. First, data envelopment analysis slack-based measure and windows analysis are employed to measure transport efficiency by using fourteen inputs/output variables. Second, econometric analysis demonstrates the relationship between socioeconomic factors and sustainable transport efficiency. Outcomes suggest that 30.2% increase in sustainable transport efficiency is due to a 1% increase in transport–household expenditures. OECD countries significantly performed with high economic efficiency scores for the examined period. Econometric analysis indicates that socioeconomic factors have a remarkable impact on sustainable transport efficiency.

Spatial-temporalcharacteristics and regional differences of the freight transport industry's carbon emission efficiency in China.

The freight transport industry is an important field in which to achieve the goal of carbon emission reduction within the transportation industry. Analyzing the spatial–temporal characteristics and regional differences in the freight transport industry’s carbon emissions efficiency (CEE) is an essential prerequisite for developing a reasonable regional carbon abatement policy. However, few studies have conducted an in-depth analysis of the freight transport industry’s CEE from the perspective of geographic space. This study combines the super-efficiency slack-based measure (SBM) model and the window analysis model to measure the freight transport industry’s CEE in 31 Chinese provinces from 2008 to 2019. We then introduced a spatial autocorrelation analysis and the Theil index to analyze the spatial–temporal evolution characteristics and regional differences in the freight transport industry’s CEE in China. The results show that (1) the overall level of the freight transport industry’s CEE is low, with an average of 0.534, which showed a weak downward trend during the study period. This indicates that the freight industry’s CEE has not improved, and there is a massive requirement for energy conservation and emission reduction. (2) From 2008 to 2019, CEE gradually shows a spatial distribution pattern of being “low in the west and high in the east,” with a significant, positive spatial correlation (all passed the significance level test at P < 0.01). This indicates that the spatial diffusion and inhibition of the freight transport industry’s CEE in adjacent areas cannot be ignored. (3) The overall differences in the freight transport industry’s CEE show a fluctuating upward trend from 2008 to 2019. The inter-regional differences of the three regions (east, central, and west) are the main contributors of the total differences. Therefore, narrowing inter-regional gaps in CEE is one of the main ways to improve the freight transport industry’s CEE.

Successful mechanical earth model construction and wellbore stability analysis using elastic and plasticity solutions, a case study

Geomechanics issues and stability of wells are essential parts of the drilling operation. If wellbore stability is not analyzed comprehensively, instability problems or failures can occur in the wellbore leading to many drilling difficulties. Many parameters such as mud weight, well trajectory, in-situ stresses, etc., could affect the wellbore instability. Wellbore stability analysis can be implemented using an elastic or a plastic solution. This paper uses both solutions to analyze wellbore stability for a well called Well-A in an Iranian southwest oil field. First, a mechanical earth model (MEM) was established and calibrated through the required information. Afterward, regarding the linear elastic solution, four rock failure criteria, including Mohr–Coulomb, Mogi–Coulomb, Hoek–Brown, and Modified Lade, were employed to predict the safe mud weight windows. In the section on plasticity, the stability analysis was executed analytically using an elastic/ideally plastic model. Then the numerical solutions using a finite difference code were applied to determine the optimum mud weight and evaluate the results of analytical computations. From the obtained results, it was found that the Mogi–Coulomb criterion provides the most reliable safe mud weight window for an elastic analysis. Numerical solution results sufficiently confirmed the authenticity of analytic elastic and elastic/perfectly plastic solutions. In addition, the numerical method was capable of determining the proper optimum mud weight using Mohr–Coulomb combined with plasticity. According to the depths of Well-A experiencing wellbore instabilities and associated geomechanical problems, the results of both numerical and linear elastic solutions demonstrated an advantageous agreement with the actual observations. Consequently, the study elucidates that in order to achieve superior drilling operations, the approaches used to analyze wellbore stability could be competently employed to determine the possibility of wellbore instabilities and design an appropriate mud weight concerning Well-A or subsequent similar wells located in the present oil field.

DYNAMIC MODEL OF PERFORMANCE MEASUREMENT OF MIDDLE EAST AIRLINES

Over the past decades, the rapid development of the airline industry has occurred in the Middle East and particularly in the United Arab Emirates. The need for the development of the aviation sector has emerged due to the strategically important position that Middle East occupies as the central point between the eastern and western hemispheres. Its major airlines, so called Middle East Big Three (MEB3) - Emirates, Etihad and Qatar Airways, have become dominant in the region, as well as across the globe, primarily thanks to the high quality of their services and globally recognized brand. The focus of the assessment are the airlines’ non-financial performance indicators, such as: the number of carried passengers and cargo, number of employees, serving destinations, fleet size, etc. The analysis covered a period of twelve years, starting from 2005 until 2016, which was characterized by the expansion of these airlines. For each observed company, the efficiency was first separately measured using the Data Envelopment Analysis (DEA) method, followed by the dynamic analysis and measurement of their efficiencies using the DEA Window analysis. In both cases, Emirates Airlines had the best performance.

Forwarding Collision Assessment with the Localization Information Using the Machine Learning Method

Freeway crashes occupied 30% of total crashes. The advanced driver-assistance system (ADAS) often underestimates or omits the necessary collision warning. To investigate the forward collision in complex traffic conditions, the TTC (time-to-collision) is regarded as a surrogate for collision risk assessment. The study aims to design a forward-collision warning method for ADAS in the urban freeway scenario. The testing vehicle is equipped with sensors and a satellite navigation system. The TTC was collected from the Xi’an Rao Cheng expressway for the car-following scenario for three days. A comprehensive Gaussian model, which consists of three sub-GMM models is applied to describe the TTC distribution. The vehicle trajectories were extracted in the car-following state. To improve the efficiency of the forwarding collision system, four seconds are chosen as an analysis window in the car-following state. Two time-series machine models were used to predict TTC in advance. The TTC prediction models were constructed on the basis of the long short-term memory (LSTM). The prediction result was compared with the deep belief network (DBN) model. The comparison results show that the LSTM model is faster than the DBN model. The number of iterations is 100. The loss function of the LSTM is 0.06. The LSTM outperforms the DBN model and is suitable for car-following warnings.

Anomaly Detection in Log Files Using Selected Natural Language Processing Methods

In this article, we address the problem of detecting anomalies in system log files. Computer systems generate huge numbers of events, which are noted in event log files. While most of them report normal actions, an unusual entry may inform about a failure or malware infection. A human operator may easily miss such an entry; therefore, anomaly detection methods are used for this purpose. In our work, we used an approach known from the natural language processing (NLP) domain, which operates on so-called embeddings, that is vector representations of words or phrases. We describe an improved version of the LogEvent2Vec algorithm, proposed in 2020. In contrast to the original version, we propose a significant shortening of the analysis window, which both increased the accuracy of anomaly detection and made further analysis of suspicious sequences much easier. We experimented with various binary classifiers, such as decision trees or multilayer perceptrons (MLPs), and the Blue Gene/L dataset. We showed that selecting an optimal classifier (in this case, MLP) and a short log sequence gave very good results. The improved version of the algorithm yielded the best F1-score of 0.997, compared to 0.886 in the original version of the algorithm.

Characterisation of the Complete Chloroplast Genomes of Seven Hyacinthus orientalis L. Cultivars: Insights into Cultivar Phylogeny

To improve agricultural performance and obtain potential economic benefits, an understanding of phylogenetic relationships of Hyacinthus cultivars is needed. This study aims to revisit the phylogenetic relationships of Hyacinthus cultivars using complete chloroplast genomes. Nine chloroplast genomes were de novo sequenced, assembled and annotated from seven cultivars of Hyacinthus orientalis and two Scilloideae species including Bellevalia paradoxa and Scilla siberica. The chloroplast genomes of Hyacinthus cultivars ranged from 154,458 bp to 154,641 bp, while those of Bellevalia paradoxa and Scilla siberica were 154,020 bp and 154,943 bp, respectively. Each chloroplast genome was annotated with 133 genes, including 87 protein-coding genes, 38 transfer RNA genes and 8 ribosomal RNA genes. Simple sequence repeats AAGC/CTTG and ACTAT/AGTAT were identified only in ‘Eros’, while AAATC/ATTTG were identified in all cultivars except ‘Eros’. Five haplotypes were identified based on 460 variable sites. Combined with six other previously published chloroplast genomes of Scilloideae, a sliding window analysis and a phylogenetic analysis were performed. Divergence hotspots ndhA and trnG-UGC were identified with a nucleotide diversity threshold at 0.04. The phylogenetic positions of Hyacinthus cultivars were different from the previous study using ISSR. Complete chloroplast genomes serve as new evidence in Hyacinthus cultivar phylogeny, contributing to cultivar identification, preservation and breeding.

Time-Frequency connectedness of policy uncertainty, geopolitical risk and Chinese commodity markets: evidence from rolling window analysis

ABSTRACT This article investigates the time-frequency connectedness of categorical policy uncertainty, geopolitical risk and Chinese commodity markets by applying the vector autoregression method for the period from August 2004 to March 2021. Specifically, our research employs rolling window analysis of wavelet decomposition series to uncover the dynamic properties of connectedness with a time-frequency framework. The results indicate that heterogeneity exists across time scales for policy-specific uncertainty, geopolitical risk and commodities throughout the study period. In particular, the directional connectedness shows that the commodity markets are most closely related to monetary policy uncertainty, followed by exchange rate policy uncertainty, fiscal policy uncertainty and trade policy uncertainty, and finally geopolitical risk. In addition, connectedness exhibits an obvious changing trend during the crisis period, and the spillover effects of policy uncertainty and geopolitical risk increase dramatically. Finally, the long-term connectedness between policy uncertainty, geopolitical risk and commodities are stronger than that in the short-term periods. Overall, our findings provide valuable implications that policymakers and investors should pay attention to dynamic and time-frequency features of connectedness when making decisions.

Transformer-based ensemble method for multiple predominant instruments recognition in polyphonic music

Multiple predominant instrument recognition in polyphonic music is addressed using decision level fusion of three transformer-based architectures on an ensemble of visual representations. The ensemble consists of Mel-spectrogram, modgdgram, and tempogram. Predominant instrument recognition refers to the problem where the prominent instrument is identified from a mixture of instruments being played together. We experimented with two transformer architectures like Vision transformer (Vi-T) and Shifted window transformer (Swin-T) for the proposed task. The performance of the proposed system is compared with that of the state-of-the-art Han’s model, convolutional neural networks (CNN), and deep neural networks (DNN). Transformer networks learn the distinctive local characteristics from the visual representations and classify the instrument to the group where it belongs. The proposed system is systematically evaluated using the IRMAS dataset with eleven classes. A wave generative adversarial network (WaveGAN) architecture is also employed to generate audio files for data augmentation. We train our networks from fixed-length music excerpts with a single-labeled predominant instrument and estimate an arbitrary number of predominant instruments from the variable-length test audio file without any sliding window analysis and aggregation strategy as in existing algorithms. The ensemble voting scheme using Swin-T reports a micro and macro F1 score of 0.66 and 0.62, respectively. These metrics are 3.12% and 12.72% relatively higher than those obtained by the state-of-the-art Han’s model. The architectural choice of transformers with ensemble voting on Mel-spectro-/modgd-/tempogram has merit in recognizing the predominant instruments in polyphonic music.

Dynamic probability modeling of photovoltaic strings and its application in fault diagnosis

China’s installed photovoltaic (PV) capacity has surged in recent years, and the intelligent operation of PV power generation is of great significance to improve the generating of PV power stations. As the core of the PV power generation system, PV strings are exposed outdoors all the year round, which is easy to bring safety hazards affecting the safe operation of power stations. Affected by weather conditions, the output of PV strings is fluctuating, random and time-varying, which brings great challenges to fault diagnosis. Therefore, taking the uncertainty of the PV power generation system during its operation into consideration, this paper used the nonparametric kernel density estimation method to fit the probability density curve of the output for PV strings, updated the model with the dynamic time window technology, and eventually established a fault diagnosis method based on the dynamic modeling results of PV strings. Different from the typical real-time diagnosis, by setting a dynamic time window for statistical analysis, the PV strings with degraded performance that fail to be detected in real-time monitoring can be identified, which is conducive to fault diagnosis for PV power stations.

HERALDIC MOTIFS IN FAMILY STAINED GLASSES OF THE 16TH CENTURY OF THE VON DIESBACH FAMILY

This article deals with the problem of research and attribution of heraldic stained-glass windows of the Swiss Union in the 16th century, when the art of stained glass was in its heyday. By this time, the formation of a new social class, the burghers, was being completed, whose wealthy families, thanks to the special historical conditions for the development of the Old Confederation, were able to have their own family coat of arms. In order to demonstrate their social status and services to society, coats of arms were placed in stained-glass windows, which were donated to churches. The purpose of the article: using the example of the heraldic stained-glass windows of the von Diesbach family, preserved in the church of the city of Worb, canton of Bern, is to show how the established rules of heraldry were transformed in the heraldic stained-glass windows of the Swiss Union. The study relies on sources in the form of surviving armorials, as well as official documents of the time, which depict the coat of arms of the von Diesbach family, which made it possible to conduct a comparative analysis of coats of arms in manuscripts and stained-glass windows. In the process of research, a technical and technological method was used to identify the possibilities of including heraldic symbols in stained glass compositions. As a result of the analysis of the heraldic stained-glass windows of the von Diesbach family in the church of the city of Worb, canton of Bern, it was concluded that they are a vivid example of the use of stable heraldic symbols, however, in the stained-glass windows of the Old Confederation (Swiss Union). the rules of heraldry were not applied too rigidly and consistently, they were interpreted in stained-glass windows taking into account the social structure of society, the location of stained-glass windows in architecture, as well as the technological possibilities of stained-glass art.

Dynamic Performance Assessment of Hospitals by Applying Credibility-Based Fuzzy Window Data Envelopment Analysis.

The goal of the current research is to propose the credibility-based fuzzy window data envelopment analysis (CFWDEA) approach as a novel method for the dynamic performance evaluation of hospitals during different periods under data ambiguity and linguistic variables. To reach this goal, a data envelopment analysis (DEA) method, a window analysis technique, a possibilistic programming approach, credibility theory, and chance-constrained programming (CCP) are employed. In addition, the applicability and efficacy of the proposed CFWDEA approach are illustrated utilizing a real data set to evaluate the performance of hospitals in the USA. It should be explained that three inputs including the number of beds, labor-related expenses, patient care supplies, and other expenses as well as three outputs including the number of outpatient department visits, the number of inpatient department admissions, and overall patient satisfaction level, are considered for the dynamic performance appraisal of hospitals. The experimental results show the usefulness of the CFWDEA method for the evaluation and ranking of hospitals in the presence of fuzzy data, linguistic variables, and epistemic uncertainty.

Multiyear temporal variation of b-values at Alaskan volcanoes: The synergetic influence of stress and material heterogeneity

Changes in seismicity parameters is often utilized as a tool for forecasting eruptive activity at volcanoes worldwide. One of these parameters is the slope of the Gutenberg-Richter law, known as the b-value, whose temporal variation is studied here as an indicator of volcanic activity. Four Alaskan volcanoes (Makushin, Martin, Redoubt, Spurr) were selected in order to reconstruct the b-value variation over a multiyear period (≥ 25 years). The magnitude of completeness and the b-value were estimated using a sliding window for each earthquake catalog, while bootstrap uncertainties were estimated for each window. The size of the analysis window was selected by applying the Magnitude Bandwidth Criterion (MBC) that maximizes the number of windows with magnitude bandwidth larger than 2.0 in the complete part of the catalog. All four volcanoes exhibit decreasing b-values before unrest and eruptions, while maximum b-values exceed 1.0 only at Redoubt and Spurr. Previously published laboratory experiments on volcanic rock deformation and failure suggest that the decrease in b-value is a result of increased stress that may stem either from magma intrusions or from exsolution of volatiles. On the other hand, whether the b-value at each volcano will exceed 1.0 or not, is also determined by the degree of material heterogeneity.

Regional Sustainable Performance of Construction Industry in China from the Perspective of Input and Output: Considering Occupational Safety

Improving the poor sustainability of the construction industry requires long-term actions, especially in developing countries such as China. Regional sustainability assessment plays an indispensable role, contributing to a better understanding of the state of development in various regions. However, few studies have focused on the overall sustainability of regional construction industries, and occupational safety is generally ignored. To fill these gaps, an input-output system is established to evaluate regional sustainable performance of the construction industry (SPCI), which is made to include occupational safety by introducing the number of fatalities as an undesirable output. An evaluation model is constructed by combining window analysis with a super-slack-based measure data envelopment analysis (windows-super-SBM DEA). The SPCI in China’s 30 provinces from 2010 to 2017 is dynamically evaluated, and regional differences are further analyzed, with eight regions being defined. The results indicate that (1) the overall SPCI in China has fluctuated smoothly around a slight downward trend. By comparison, the integration of occupational safety refreshes the relative performance of most provinces; (2) dividing China into eight regions presents more detailed information because of those regions’ smaller coverage areas, and more attention should be given to the northeast, northwest, Middle Yellow River region and east coast because of the decrease in the SPCI; and (3) vigorously developing of the construction industry does not necessarily result in a large number of byproducts if the relevant policy is sufficiently strong. The findings of this study are conducive to rationally allocating resources and formulating targeted policies.

Raga Recognition in Indian Carnatic Music Using Convolutional Neural Networks

A vital aspect of Indian Classical music (ICM) is raga, which serves as a melodic framework for compositions and improvisations for both traditions of classical music. In this work, we propose a CNN-based sliding window analysis on mel-spectrogram and modgdgram for raga recognition in Carnatic music. The impor- tant contribution of the work is that the pro- posed method neither requires pitch extraction nor metadata for the estimation of raga. CNN learns the representation of raga from the pat- terns in the melspectrogram/ modgdgram dur- ing training through a sliding-window analysis. We train and test the network on sliced-mel- spectrogram/modgdgram of the original audio while the nal inference is performed on the au- dio as a whole. The performance is evaluated on 15 ragas from the CompMusic dataset. Multi- stream fusion has also been implemented to identify the potential of two feature representations. Multi-stream architecture shows promise in the proposed scheme for raga recognition.