Abstract

The sudden shift to online education due to the pandemic has led to widespread learning gaps in the student population, increasing the need for individualistic attention to student learning as we transition back to physical classrooms. One can take advantage of the advancements in technology to help in this process by developing tools that can assist teachers decrease the amount of administrative workload and improve their ability to track the learning and understanding of every student in the classroom. The current work proposes a framework for accurate, low-cost, and scalable computer visionbased attendance and attention tracking in physical classroom environment to tackle this problem

Abstract

Deployment of Accident Relief Medical Vans (ARMV) used for accident relief and rescue operations is generally done heuristically. ARMV is an ambulance-train equipped with various tools like jacks, heavy cutting tools, generators, operation theatre, artificial breathing equipment etc. to ease the rescue process. Taking North Eastern Railway (NER) as a case study, Location Set Covering Problem (LSCP) model will be used to find the minimum number of ARMVs required for the given network and their locations so that all demand points can be ‘covered’ within a maximum of one hour @ 100 kmph for each of the nearest facility. This paper proposes a new mathematical model based on the Cluster Coverage Model (CCM) to provide a better coverage of ARMV’s demands. We have used Girvan-Newman (GN) algorithm, a weight-based graph for clustering of NER network where nodes are taken as depots with ARMV parking facilities & crew availability and distance between these nodes is taken as edge weight of the graph. Finally, we present a comparison of results between the proposed cluster coverage models with LSCP and suggest relocations of the existing ARMVs

Abstract

In this study, we show that DNA methylation markers can be used for the early detection of breast cancer subtypes based on the status of Estrogen, Progesterone and HER2 receptors. A machine learning approach is used to predict breast cancer patients’ receptor status. DNA methylation datasets created using Illumina Hypermethylation 450K platform from four different studies from NCBI GEO and TCGA-BRCA are collated to create a dataset of 1514 samples. Of these, 1260 samples passed quality control and had receptor status information available, and these 1260 samples were used for the training and testing of the SVM model. We analysed the prognostic value of DNA methylation-based receptor status prediction by comparing the survival outcomes with the traditional methods. We observe that patients whose classification status does not match with those of traditional methods exhibit lower survival probability. This could possibly be due to incorrect classification and treatment plans by the traditional IHC method. This suggests that

Abstract

Customer support is an essential part of any company to ensure customer satisfaction and business growth. The responsibility and scale get even higher for enterprise companies like Freshworks that build customer support platforms for its enterprise customers from multiple and previously unseen domains. A ticket may carry issues never seen before, therefore static, and predefined problem labels will not always work. These predefined problem labels are often created manually by admins. For a large customer account, roughly 10-35% of the problem labels could get discovered by this manual process and only 5-9% of the available open tickets could get linked to a problem label. So, there is a need for a system for a new incoming ticket. The system should either automatically detect an existing problem topic with its possible suggestions or systematically generate new problem topic(s) for its assignment. Our system is based on an incremental approach to mine ticket data streams and assigns them to hierarchical soft clusters with auto-generated problem/issue topics. Our system achieves an improvement in ticket assignments up to 97%. To compare with recent clustering advancements, we’ve also evaluated our approach on a public dataset [9] and achieved comparable results. Source code and results of the evaluation are available in detail at: https://github.com/vinidixit/hierarchical-labelled-clustering-evaluation.

Abstract

We derive a formula for p(n) (the number of partitions of n) in terms of the partial Bell polynomials using Faà di Bruno’s formula and Euler’s pentagonal number theorem.

Abstract

Few animals can hide their signatures into their surroundings to hunt or avoid being hunted, termed as natural camouflage. Natural camouflage inspires researchers to design various algorithms to artificially create camouflage images and widely apply them in the military field. It is also essential to evaluate the effectiveness of artificially created camouflage images. Several algorithms have been developed in the literature to evaluate camouflage design techniques. Camouflage breaking systems extract the object from its surroundings. Due to the complexity of the problem, it is challenging to design an algorithm for breaking camouflage.

Abstract

Grain segmentation of sandstone that is partitioning the grain from its surrounding matrix/cement in the thin section is the primary step for computer-aided mineral identification and sandstone classification. The microscopic images of sandstone contain many mineral grains and their surrounding matrix/cement. The distinction between adjacent grains and the matrix is often ambiguous, making grain segmentation difficult. Various solutions exist in literature to handle these problems; however, they are not robust against sandstone petrography's varied pattern. In this paper, we formulate grain segmentation as a pixel-wise two-class (i.e., grain and background) semantic segmentation task. We develop a deep learning-based end-to-end trainable framework named Deep Semantic Grain Segmentation network (DSGSN), a data-driven method, and provide a generic solution. As per the authors' knowledge, this is the first work where the deep neural network is explored to solve the grain segmentation problem. Extensive experiments on microscopic images highlight that our method obtains better segmentation accuracy than various segmentation architectures with more parameters.

Abstract

The goal of this study is to investigate advanced signal processing approaches [single frequency filtering (SFF) and zero-time windowing (ZTW)] with modern deep neural networks (DNNs) [convolution neural networks (CNNs), temporal convolution neural networks (TCN), time-delay neural network (TDNN), and emphasized channel attention, propagation and aggregation in TDNN (ECAPA-TDNN)] for dialect classification of major dialects of English. Previous studies indicated that SFF and ZTW methods provide higher spectro-temporal resolution. To capture the intrinsic variations in articulations among dialects, four feature representations [spectrogram (SPEC), cepstral coefficients, mel filter-bank energies, and mel-frequency cepstral coefficients (MFCCs)] are derived from SFF and ZTW methods. Experiments with and without data augmentation using CNN classifiers revealed that the proposed features performed better than baseline short-time Fourier transform (STFT)-based features on the UT-Podcast database [Hansen, J. H., and Liu, G. (2016). "Unsupervised accent classification for deep data fusion of accent and language information," Speech Commun. 78, 19-33]. Even without data augmentation, all the proposed features showed an approximate improvement of 15%-20% (relative) over best baseline (SPEC-STFT) feature. TCN, TDNN, and ECAPA-TDNN classifiers that capture wider temporal context further improved the performance for many of the proposed and baseline features. Among all the baseline and proposed features, the best performance is achieved with single frequency filtered cepstral coefficients for TCN (81.30%), TDNN (81.53%), and ECAPA-TDNN (85.48%). An investigation of data-driven filters, instead of fixed mel-scale, improved the performance by 2.8% and 1.4% (relatively) for SPEC-STFT and SPEC-SFF, and nearly equal for SPEC-ZTW. To assist related work, we have made the code available ([Kethireddy, R., and Kadiri, S. R. (2022). "Deep neural architectures for dialect classification with single frequency filtering and zero-time windowing feature representations," https://github.com/r39ashmi/e2e_dialect (Last viewed 21 December 2021)].).

Abstract

Measurement error models are studied extensively in the literature. In these models, when the measurement error variance ΣδδΣδδ is known, the estimating techniques require positive definiteness of the matrix Sxx−ΣδδSxx−Σδδ, even when this is positive definite, it might be near singular if the number of observations is small. There are alternative estimators discussed in literature when this matrix is not positive definite. In this paper, estimators when the matrix Sxx−ΣδδSxx−Σδδ is near singular are proposed and it is shown that these estimators are consistent and have the same asymptotic properties as the earlier ones. In addition, we show that our estimators work far better than the earlier estimators in case of small samples and equally good for large samples.

Abstract

This paper proposes a method for displaying the phase information in speech signals through group delay spectrogram, without the need for phase unwrapping. The method involves scaling down the phase values without affecting the shape of the phase or group delay function, thus preserving the information of the phase spectrum. This is accomplished using single-frequency filtering (SFF) of speech signals to obtain the instantaneous complex SFF spectrum. The SFF involves filtering a frequency-shifting signal using a resonator at half the sampling frequency. The SFF spectrum displays characteristics similar to the standard short-time Fourier transform (STFT) spectrum, but without the effects of truncation due to windowing operation. The objective of the present study is to show that features of speech production can also be observed in the phase information, displayed through the group delay spectrogram. The time-frequency resolution in the group delay spectrogram depends on the choice of the bandwidth of the resonator used in the SFF analysis. The speech production features displayed in the group delay spectrogram are examined for different types of speech signals at different time-frequency resolutions.