Search

Code-mixing is a well-studied linguistic phenomenon when two or more languages are mixed in text or speech. Several works have been conducted on building datasets and performing downstream NLP tasks on code-mixed data. Although it is not uncommon to observe code-mixing of three or more languages, most available datasets in this domain contain code-mixed data from only two languages. In this paper, we introduce OffMix-3L, a novel offensive language identification dataset containing code-mixed data from three different languages. We experiment with several models on this dataset and observe that BanglishBERT outperforms other transformer-based models and GPT-3.5., Comment: arXiv admin note: substantial text overlap with arXiv:2310.18023

Code-mixing is a well-studied linguistic phenomenon when two or more languages are mixed in text or speech. Several datasets have been build with the goal of training computational models for code-mixing. Although it is very common to observe code-mixing with multiple languages, most datasets available contain code-mixed between only two languages. In this paper, we introduce SentMix-3L, a novel dataset for sentiment analysis containing code-mixed data between three languages Bangla, English, and Hindi. We carry out a comprehensive evaluation using SentMix-3L. We show that zero-shot prompting with GPT-3.5 outperforms all transformer-based models on SentMix-3L.

Brain tumors pose a significant global health challenge due to their high prevalence and mortality rates across all age groups. Detecting brain tumors at an early stage is crucial for effective treatment and patient outcomes. This study presents a comprehensive investigation into the use of Convolutional Neural Networks (CNNs) for brain tumor detection using Magnetic Resonance Imaging (MRI) images. The dataset, consisting of MRI scans from both healthy individuals and patients with brain tumors, was processed and fed into the CNN architecture. The SoftMax Fully Connected layer was employed to classify the images, achieving an accuracy of 98%. To evaluate the CNN's performance, two other classifiers, Radial Basis Function (RBF) and Decision Tree (DT), were utilized, yielding accuracy rates of 98.24% and 95.64%, respectively. The study also introduced a clustering method for feature extraction, improving CNN's accuracy. Sensitivity, Specificity, and Precision were employed alongside accuracy to comprehensively evaluate the network's performance. Notably, the SoftMax classifier demonstrated the highest accuracy among the categorizers, achieving 99.52% accuracy on test data. The presented research contributes to the growing field of deep learning in medical image analysis. The combination of CNNs and MRI data offers a promising tool for accurately detecting brain tumors, with potential implications for early diagnosis and improved patient care.

Sharing cooking recipes is a great way to exchange culinary ideas and provide instructions for food preparation. However, categorizing raw recipes found online into appropriate food genres can be challenging due to a lack of adequate labeled data. In this study, we present a dataset named the ``Assorted, Archetypal, and Annotated Two Million Extended (3A2M+) Cooking Recipe Dataset" that contains two million culinary recipes labeled in respective categories with extended named entities extracted from recipe descriptions. This collection of data includes various features such as title, NER, directions, and extended NER, as well as nine different labels representing genres including bakery, drinks, non-veg, vegetables, fast food, cereals, meals, sides, and fusions. The proposed pipeline named 3A2M+ extends the size of the Named Entity Recognition (NER) list to address missing named entities like heat, time or process from the recipe directions using two NER extraction tools. 3A2M+ dataset provides a comprehensive solution to the various challenging recipe-related tasks, including classification, named entity recognition, and recipe generation. Furthermore, we have demonstrated traditional machine learning, deep learning and pre-trained language models to classify the recipes into their corresponding genre and achieved an overall accuracy of 98.6\%. Our investigation indicates that the title feature played a more significant role in classifying the genre.

The generative adversarial network (GAN) is an important model developed for high-dimensional distribution learning in recent years. However, there is a pressing need for a comprehensive method to understand its error convergence rate. In this research, we focus on studying the error convergence rate of the GAN model that is based on a class of functions encompassing the discriminator and generator neural networks. These functions are VC type with bounded envelope function under our assumptions, enabling the application of the Talagrand inequality. By employing the Talagrand inequality and Borel-Cantelli lemma, we establish a tight convergence rate for the error of GAN. This method can also be applied on existing error estimations of GAN and yields improved convergence rates. In particular, the error defined with the neural network distance is a special case error in our definition., Comment: 16 pages

The task of Visual Question Generation (VQG) is to generate human-like questions relevant to the given image. As VQG is an emerging research field, existing works tend to focus only on resource-rich language such as English due to the availability of datasets. In this paper, we propose the first Bengali Visual Question Generation task and develop a novel transformer-based encoder-decoder architecture that generates questions in Bengali when given an image. We propose multiple variants of models - (i) image-only: baseline model of generating questions from images without additional information, (ii) image-category and image-answer-category: guided VQG where we condition the model to generate questions based on the answer and the category of expected question. These models are trained and evaluated on the translated VQAv2.0 dataset. Our quantitative and qualitative results establish the first state of the art models for VQG task in Bengali and demonstrate that our models are capable of generating grammatically correct and relevant questions. Our quantitative results show that our image-cat model achieves a BLUE-1 score of 33.12 and BLEU-3 score of 7.56 which is the highest of the other two variants. We also perform a human evaluation to assess the quality of the generation tasks. Human evaluation suggests that image-cat model is capable of generating goal-driven and attribute-specific questions and also stays relevant to the corresponding image., Comment: 19 pages including references, 4 figures and 3 tables. Accepted in the Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023)

One of the most important tasks related to managing bug reports is localizing the fault so that a fix can be applied. As such, prior work has aimed to automate this task of bug localization by formulating it as an information retrieval problem, where potentially buggy files are retrieved and ranked according to their textual similarity with a given bug report. However, there is often a notable semantic gap between the information contained in bug reports and identifiers or natural language contained within source code files. For user-facing software, there is currently a key source of information that could aid in bug localization, but has not been thoroughly investigated - information from the GUI. We investigate the hypothesis that, for end user-facing applications, connecting information in a bug report with information from the GUI, and using this to aid in retrieving potentially buggy files, can improve upon existing techniques for bug localization. To examine this phenomenon, we conduct a comprehensive empirical study that augments four baseline techniques for bug localization with GUI interaction information from a reproduction scenario to (i) filter out potentially irrelevant files, (ii) boost potentially relevant files, and (iii) reformulate text-retrieval queries. To carry out our study, we source the current largest dataset of fully-localized and reproducible real bugs for Android apps, with corresponding bug reports, consisting of 80 bug reports from 39 popular open-source apps. Our results illustrate that augmenting traditional techniques with GUI information leads to a marked increase in effectiveness across multiple metrics, including a relative increase in Hits@10 of 13-18%. Additionally, through further analysis, we find that our studied augmentations largely complement existing techniques., Comment: 13 pages, to appear in the Proceedings of the 46th International Conference on Software Engineering (ICSE'24)

The collaboration between quantum computing and classical machine learning offers potential advantages in natural language processing, particularly in the sentiment analysis of human emotions and opinions expressed in large-scale datasets. In this work, we propose a methodology for sentiment analysis using hybrid quantum-classical machine learning algorithms. We investigate quantum kernel approaches and variational quantum circuit-based classifiers and integrate them with classical dimension reduction techniques such as PCA and Haar wavelet transform. The proposed methodology is evaluated using two distinct datasets, based on English and Bengali languages. Experimental results show that after dimensionality reduction of the data, performance of the quantum-based hybrid algorithms were consistent and better than classical methods., Comment: 6 pages, 3 figures, To Appear at IEEE ICMLA 2023, FL, USA

Parallelizing sequentially written programs is a challenging task. Even experienced developers need to spend considerable time finding parallelism opportunities and then actually writing parallel versions of sequentially written programs. To address this issue, we present AUTOPARLLM, a framework for automatically discovering parallelism and generating the parallel version of the sequentially written program. Our framework consists of two major components: i) a heterogeneous Graph Neural Network (GNN) based parallelism discovery and parallel pattern detection module, and ii) an LLM-based code generator to generate the parallel counterpart of the sequential programs. We use the GNN to learn the flow-aware characteristics of the programs to identify parallel regions in sequential programs and then construct an enhanced prompt using the GNN's results for the LLM-based generator to finally produce the parallel counterparts of the sequential programs. We evaluate AUTOPARLLM on 11 applications of 2 well-known benchmark suites: NAS Parallel Benchmark and Rodinia Benchmark. Our results show that AUTOPARLLM is indeed effective in improving the state-of-the-art LLM-based models for the task of parallel code generation in terms of multiple code generation metrics. AUTOPARLLM also improves the average runtime of the parallel code generated by the state-of-the-art LLMs by as high as 3.4% and 2.9% for the NAS Parallel Benchmark and Rodinia Benchmark respectively. Additionally, to overcome the issue that well-known metrics for translation evaluation have not been optimized to evaluate the quality of the generated parallel code, we propose OMPScore for evaluating the quality of the generated code. We show that OMPScore exhibits a better correlation with human judgment than existing metrics, measured by up to 75% improvement of Spearman correlation., Comment: 10 pages

In this work, density functional theory (DFT) is used to find out the ground state structures of A2AuScX6 (A= Cs, Rb; X= Cl, Br, I) double Perovskite (DP) halides for the first time. The DP A2AuScX6 halides were studied for their structural phase stability and optoelectronic properties in order to identify potential materials for energy harvesting systems. The stability criteria were verified by computing the formation energy, binding energy, phonon dispersion curve, stiffness constants, tolerance, and octahedral factors. The electronic band structure, carrier effective mass, density of states (DOS), and charge density distribution were calculated to reveal the nature of electronic conductivity and the chemical bonding nature present within them. For Cs2AuScX6 (Rb2AuScX6) [X = Cl, Br, I], the corresponding values of band gap [using TB-mBJ] are 1.88 (1.93), 1.68 (1.71), and 1.30 (1.32) eV. The optical constants (dielectric function, absorption coefficient, refractive index, energy loss function, photoconductivity, and reflectivity) were also calculated to get more insights into their electronic nature. For Cs2AuScX6 (Rb2AuScX6) [X = Cl, Br, I], the absorption coefficient in the visible range are 3.33 (3.45) 105 cm-1, 2.70 (2.81) 105 cm-1, and 2.13 (2.18) 105 cm-1, respectively. We also investigated the thermoelectric properties to predict promising applications in thermoelectric devices. Our calculations revealed high ZT values of 0.92, 1.07, and 1.06 for Cs2AuScX6 (X = Cl, Br, I) and 0.97, 0.99, and 1.01 for Rb2AuScX6 (X = Cl, Br, I) at 300 K. To further aid in predicting any novel materials, routine research was also done on the thermo-mechanical characteristics. The results suggest the compounds considered as potential candidates for use in solar cells and/or thermoelectric devices., Comment: 38

Information Maximizing Generative Adversarial Network (infoGAN) can be understood as a minimax problem involving two networks: discriminators and generators with mutual information functions. The infoGAN incorporates various components, including latent variables, mutual information, and objective function. This research demonstrates that the two objective functions in infoGAN become equivalent as the discriminator and generator sample size approaches infinity. This equivalence is established by considering the disparity between the empirical and population versions of the objective function. The bound on this difference is determined by the Rademacher complexity of the discriminator and generator function class. Furthermore, the utilization of a two-layer network for both the discriminator and generator, featuring Lipschitz and non-decreasing activation functions, validates this equality

Monitoring the electrical pulse of fetal heart through a non-invasive fetal electrocardiogram (fECG) can easily detect abnormalities in the developing heart to significantly reduce the infant mortality rate and post-natal complications. Due to the overlapping of maternal and fetal R-peaks, the low amplitude of the fECG, systematic and ambient noises, typical signal extraction methods, such as adaptive filters, independent component analysis, empirical mode decomposition, etc., are unable to produce satisfactory fECG. While some techniques can produce accurate QRS waves, they often ignore other important aspects of the ECG. Our approach, which is based on 1D CycleGAN, can reconstruct the fECG signal from the mECG signal while maintaining the morphology due to extensive preprocessing and appropriate framework. The performance of our solution was evaluated by combining two available datasets from Physionet, "Abdominal and Direct Fetal ECG Database" and "Fetal electrocardiograms, direct and abdominal with reference heartbeat annotations", where it achieved an average PCC and Spectral-Correlation score of 88.4% and 89.4%, respectively. It detects the fQRS of the signal with accuracy, precision, recall and F1 score of 92.6%, 97.6%, 94.8% and 96.4%, respectively. It can also accurately produce the estimation of fetal heart rate and R-R interval with an error of 0.25% and 0.27%, respectively. The main contribution of our work is that, unlike similar studies, it can retain the morphology of the ECG signal with high fidelity. The accuracy of our solution for fetal heart rate and R-R interval length is comparable to existing state-of-the-art techniques. This makes it a highly effective tool for early diagnosis of fetal heart diseases and regular health checkups of the fetus., Comment: 24 pages, 11 figures

Abnormal growth of cells in the brain and its surrounding tissues is known as a brain tumor. There are two types, one is benign (non-cancerous) and another is malignant (cancerous) which may cause death. The radiologists' ability to diagnose malignancies is greatly aided by magnetic resonance imaging (MRI). Brain cancer diagnosis has been considerably expedited by the field of computer-assisted diagnostics, especially in machine learning and deep learning. In our study, we categorize three different kinds of brain tumors using four transfer learning techniques. Our models were tested on a benchmark dataset of $3064$ MRI pictures representing three different forms of brain cancer. Notably, ResNet-50 outperformed other models with a remarkable accuracy of $99.06\%$. We stress the significance of a balanced dataset for improving accuracy without the use of augmentation methods. Additionally, we experimentally demonstrate our method and compare with other classification algorithms on the CE-MRI dataset using evaluations like F1-score, AUC, precision and recall., Comment: 6 pages, 2 figures, To Appear at IEEE ICMLA 2023, FL, USA

Sleep stage classification from electroencephalogram (EEG) is significant for the rapid evaluation of sleeping patterns and quality. A novel deep learning architecture, ``DenseRTSleep-II'', is proposed for automatic sleep scoring from single-channel EEG signals. The architecture utilizes the advantages of Convolutional Neural Network (CNN), transformer network, and Bidirectional Long Short Term Memory (BiLSTM) for effective sleep scoring. Moreover, with the addition of a weighted multi-loss scheme, this model is trained more implicitly for vigorous decision-making tasks. Thus, the model generates the most efficient result in the SleepEDFx dataset and outperforms different state-of-the-art (IIT-Net, DeepSleepNet) techniques by a large margin in terms of accuracy, precision, and F1-score.

One of the most popular downstream tasks in the field of Natural Language Processing is text classification. Text classification tasks have become more daunting when the texts are code-mixed. Though they are not exposed to such text during pre-training, different BERT models have demonstrated success in tackling Code-Mixed NLP challenges. Again, in order to enhance their performance, Code-Mixed NLP models have depended on combining synthetic data with real-world data. It is crucial to understand how the BERT models' performance is impacted when they are pretrained using corresponding code-mixed languages. In this paper, we introduce Tri-Distil-BERT, a multilingual model pre-trained on Bangla, English, and Hindi, and Mixed-Distil-BERT, a model fine-tuned on code-mixed data. Both models are evaluated across multiple NLP tasks and demonstrate competitive performance against larger models like mBERT and XLM-R. Our two-tiered pre-training approach offers efficient alternatives for multilingual and code-mixed language understanding, contributing to advancements in the field.

We propose a novel approach to enhance the performance of perovskite solar cells (PSCs) by incorporating grated Cadmium Sulfide (CdS) and plasmonic gold nanoparticles (Au NPs) into the absorber layer. The CdS grating acts as the electron transport layer and penetrates into the perovskite absorber layer, increasing the absorption of the active layer and reducing the electron-hole recombination rate. The plasmonic Au NPs enhance the absorption in the infrared region by scattering and trapping the incident light. We perform a coupled optical and electrical study that shows a significant improvement in the short circuit current density (JSC) and power conversion efficiency (PCE) of the PSC after introducing the CdS grating and plasmonic Au NPs. Specifically, we observe a 48% increase in average optical absorption from 800 nm to 1400 nm and a 7.42 mA/cm^2 increase in JSC. We also find that the PCE of the PSC is increased by 7.91% when comparing the planar reference structure (without the CdS grating and the plasmonic Au NP). However, metal nanoparticles introduce ohmic losses and temperature rise in the solar cell. We analyze the non-radiative heat profile, electric field distribution, and temperature distribution across the PSC. We observe a temperature increase of approximately 14 K above the ambient temperature for the grated CdS layer with incorporated Au NPs, which is comparable to the temperature increase observed in the planar reference structure. Our results have the potential to pave the way for the development of highly efficient and stable PSCs in the future., Comment: 15 pages, 14 figures

This paper summarizes the results of experimenting with Universal Dependencies (UD) adaptation of an Unsupervised, Compositional and Recursive (UCR) rule-based approach for Sentiment Analysis (SA) submitted to the Shared Task at Rest-Mex 2023 (Team Olga/LyS-SALSA) (within the IberLEF 2023 conference). By using basic syntactic rules such as rules of modification and negation applied on words from sentiment dictionaries, our approach exploits some advantages of an unsupervised method for SA: (1) interpretability and explainability of SA, (2) robustness across datasets, languages and domains and (3) usability by non-experts in NLP. We compare our approach with other unsupervised approaches of SA that in contrast to our UCR rule-based approach use simple heuristic rules to deal with negation and modification. Our results show a considerable improvement over these approaches. We discuss future improvements of our results by using modality features as another shifting rule of polarity and word disambiguation techniques to identify the right sentiment words., Comment: Proceedings of IberLEF 2023, Ja\'en, Spain, 2023

Despite significant progress in semi-supervised learning for image object detection, several key issues are yet to be addressed for video object detection: (1) Achieving good performance for supervised video object detection greatly depends on the availability of annotated frames. (2) Despite having large inter-frame correlations in a video, collecting annotations for a large number of frames per video is expensive, time-consuming, and often redundant. (3) Existing semi-supervised techniques on static images can hardly exploit the temporal motion dynamics inherently present in videos. In this paper, we introduce SSVOD, an end-to-end semi-supervised video object detection framework that exploits motion dynamics of videos to utilize large-scale unlabeled frames with sparse annotations. To selectively assemble robust pseudo-labels across groups of frames, we introduce \textit{flow-warped predictions} from nearby frames for temporal-consistency estimation. In particular, we introduce cross-IoU and cross-divergence based selection methods over a set of estimated predictions to include robust pseudo-labels for bounding boxes and class labels, respectively. To strike a balance between confirmation bias and uncertainty noise in pseudo-labels, we propose confidence threshold based combination of hard and soft pseudo-labels. Our method achieves significant performance improvements over existing methods on ImageNet-VID, Epic-KITCHENS, and YouTube-VIS datasets. Code and pre-trained models will be released.

Biomedical Engineering's Internet of Medical Things (IoMT) is helping to improve the accuracy, dependability, and productivity of electronic equipment in the healthcare business. Real-time sensory data from patients may be delivered and subsequently analyzed through rapid development of wearable IoMT devices, such as neuro-stimulation devices with a range of functions. Data from the Internet of Things is gathered, analyzed, and stored in a single location. However, single-point failure, data manipulation, privacy difficulties, and other challenges might arise as a result of centralization. Due to its decentralized nature, blockchain (BC) can alleviate these issues. The viability of establishing a non-invasive remote neurostimulation system employing IoMT-based transcranial Direct Current Stimulation is investigated in this work (tDCS). A hardware-based prototype tDCS device has been developed that can be operated over the internet using an android application. Our suggested framework addresses the problems of IoMTBC-based systems, meets the criteria of real-time remote patient monitoring systems, and incorporates literature best practices in the relevant fields., Comment: 8 Figures and 2 Tables

The struggle of social media platforms to moderate content in a timely manner, encourages users to abuse such platforms to spread vulgar or abusive language, which, when performed repeatedly becomes cyberbullying a social problem taking place in virtual environments, yet with real-world consequences, such as depression, withdrawal, or even suicide attempts of its victims. Systems for the automatic detection and mitigation of cyberbullying have been developed but, unfortunately, the vast majority of them are for the English language, with only a handful available for low-resource languages. To estimate the present state of research and recognize the needs for further development, in this paper we present a comprehensive systematic survey of studies done so far for automatic cyberbullying detection in low-resource languages. We analyzed all studies on this topic that were available. We investigated more than seventy published studies on automatic detection of cyberbullying or related language in low-resource languages and dialects that were published between around 2017 and January 2023. There are 23 low-resource languages and dialects covered by this paper, including Bangla, Hindi, Dravidian languages and others. In the survey, we identify some of the research gaps of previous studies, which include the lack of reliable definitions of cyberbullying and its relevant subcategories, biases in the acquisition, and annotation of data. Based on recognizing those research gaps, we provide some suggestions for improving the general research conduct in cyberbullying detection, with a primary focus on low-resource languages. Based on those proposed suggestions, we collect and release a cyberbullying dataset in the Chittagonian dialect of Bangla and propose a number of initial ML solutions trained on that dataset. In addition, pre-trained transformer-based the BanglaBERT model was also attempted., Comment: 52 Pages

The negative effects of online bullying and harassment are increasing with Internet popularity, especially in social media. One solution is using natural language processing (NLP) and machine learning (ML) methods for the automatic detection of harmful remarks, but these methods are limited in low-resource languages like the Chittagonian dialect of Bangla.This study focuses on detecting vulgar remarks in social media using supervised ML and deep learning algorithms.Logistic Regression achieved promising accuracy (0.91) while simple RNN with Word2vec and fastTex had lower accuracy (0.84-0.90), highlighting the issue that NN algorithms require more data., Comment: 5 pages

In this project, we determined the constraints on the modified tidal quality factor, $Q_{pl}'$, of gas-giant planets orbiting close to their host stars. We allowed $Q_{pl}'$ to depend on tidal frequency, accounting for the multiple tidal waves with time-dependent frequencies simultaneously present on the planet. We performed our analysis on 78 single-star and single-planet systems, with giant planets and host stars with radiative cores and convective outer shells. We extracted constraints on the frequency-dependent $Q_{pl}'$ for each system separately and combined them to find general constraints on $Q_{pl}'$ required to explain the observed eccentricity envelope while simultaneously allowing the observed eccentricities of all systems to survive to the present day. Individual systems do not place tight constraints on $Q_{pl}'$. However, since similar planets must have similar tidal dissipation, we require that a consistent, possibly frequency-dependent, model must apply. Under that assumption, we find that the value of $\log_{10}Q_{pl}'$ for HJs is $5.0\pm0.5$ for the range of tidal period from 0.8 to 7 days. We did not see any clear sign of frequency dependence of $Q_{pl}'$., Comment: Accepted for publication in MNRAS 19 pages, 11 figures, 2 tables

This study explores the application and performance of Transformational Machine Learning (TML) in drug discovery. TML, a meta learning algorithm, excels in exploiting common attributes across various domains, thus developing composite models that outperform conventional models. The drug discovery process, which is complex and time-consuming, can benefit greatly from the enhanced prediction accuracy, improved interpretability and greater generalizability provided by TML. We explore the efficacy of different machine learning classifiers, where no individual classifier exhibits distinct superiority, leading to the consideration of ensemble classifiers such as the Random Forest. Our findings show that TML outperforms base Machine Learning (ML) as the number of training datasets increases, due to its capacity to better approximate the correct hypothesis, overcome local optima, and expand the space of representable functions by combining separate classifiers capabilities. However, this superiority is relative to the resampling methods applied, with Near Miss demonstrating poorer performance due to noisy data, overlapping classes, and nonlinear class boundaries. Conversely, Random Over Sampling (ROS) provides a more robust performance given its resistance to noise and outliers, improved class overlap management, and suitability for nonlinear class boundaries.

While software engineers are optimistically adopting crypto-API misuse detectors (or crypto-detectors) in their software development cycles, this momentum must be accompanied by a rigorous understanding of crypto-detectors' effectiveness at finding crypto-API misuses in practice. This demo paper presents the technical details and usage scenarios of our tool, namely Mutation Analysis for evaluating Static Crypto-API misuse detectors (MASC). We developed $12$ generalizable, usage based mutation operators and three mutation scopes, namely Main Scope, Similarity Scope, and Exhaustive Scope, which can be used to expressively instantiate compilable variants of the crypto-API misuse cases. Using MASC, we evaluated nine major crypto-detectors, and discovered $19$ unique, undocumented flaws. We designed MASC to be configurable and user-friendly; a user can configure the parameters to change the nature of generated mutations. Furthermore, MASC comes with both Command Line Interface and Web-based front-end, making it practical for users of different levels of expertise., Comment: To be published in Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering