arXiv subjects

Kashif Javed

Publications and source records attributed to Kashif Javed.

4 recordsLinked to original sources

arXiv2025

Enhanced Urdu Intent Detection with Large Language Models and Prototype-Informed Predictive Pipelines

Multifarious intent detection predictors are developed for different languages, including English, Chinese and French, however, the field remains underdeveloped for Urdu, the 10th most spoken language. In the realm of well-known languages, intent detection predictors utilize the strategy of few-shot learning and prediction of unseen classes based on the model training on seen classes. However, Urdu language lacks few-shot strategy based intent detection predictors and traditional predictors are focused on prediction of the same classes which models have seen in the train set. To empower Urdu language specific intent detection, this introduces a unique contrastive learning approach that leverages unlabeled Urdu data to re-train pre-trained language models. This re-training empowers LLMs representation learning for the downstream intent detection task. Finally, it reaps the combined potential of pre-trained LLMs and the prototype-informed attention mechanism to create a comprehensive end-to-end LLMPIA intent detection pipeline. Under the paradigm of proposed predictive pipeline, it explores the potential of 6 distinct language models and 13 distinct similarity computation methods. The proposed framework is evaluated on 2 public benchmark datasets, namely ATIS encompassing 5836 samples and Web Queries having 8519 samples. Across ATIS dataset under 4-way 1 shot and 4-way 5 shot experimental settings LLMPIA achieved 83.28% and 98.25% F1-Score and on Web Queries dataset produced 76.23% and 84.42% F1-Score, respectively. In an additional case study on the Web Queries dataset under same classes train and test set settings, LLMPIA outperformed state-of-the-art predictor by 53.55% F1-Score.

cs.CL↗

arXiv2023

Survey: Image Mixing and Deleting for Data Augmentation

Neural networks are prone to overfitting and memorizing data patterns. To avoid over-fitting and enhance their generalization and performance, various methods have been suggested in the literature, including dropout, regularization, label smoothing, etc. One such method is augmentation which introduces different types of corruption in the data to prevent the model from overfitting and to memorize patterns present in the data. A sub-area of data augmentation is image mixing and deleting. This specific type of augmentation either deletes image regions or mixes two images to hide or make particular characteristics of images confusing for the network, forcing it to emphasize the overall structure of the object in an image. Models trained with this approach have proven to perform and generalize well compared to those trained without image mixing or deleting. An added benefit that comes with this method of training is robustness against image corruption. Due to its low computational cost and recent success, researchers have proposed many image mixing and deleting techniques. We furnish an in-depth survey of image mixing and deleting techniques and provide categorization via their most distinguishing features. We initiate our discussion with some fundamental relevant concepts. Next, we present essentials, such as each category's strengths and limitations, describing their working mechanism, basic formulations, and applications. We also discuss the general challenges and recommend possible future research directions for image mixing and deleting data augmentation techniques. Datasets and codes for evaluation are publicly available here.

cs.CV↗

arXiv2021

Sentiment and Emotion Classification of Epidemic Related Bilingual data from Social Media

In recent years, sentiment analysis and emotion classification are two of the most abundantly used techniques in the field of Natural Language Processing (NLP). Although sentiment analysis and emotion classification are used commonly in applications such as analyzing customer reviews, the popularity of candidates contesting in elections, and comments about various sporting events; however, in this study, we have examined their application for epidemic outbreak detection. Early outbreak detection is the key to deal with epidemics effectively, however, the traditional ways of outbreak detection are time-consuming which inhibits prompt response from the respective departments. Social media platforms such as Twitter, Facebook, Instagram, etc. allow the users to express their thoughts related to different aspects of life, and therefore, serve as a substantial source of information in such situations. The proposed study exploits the bilingual (Urdu and English) data from Twitter and NEWS websites related to the dengue epidemic in Pakistan, and sentiment analysis and emotion classification are performed to acquire deep insights from the data set for gaining a fair idea related to an epidemic outbreak. Machine learning and deep learning algorithms have been used to train and implement the models for the execution of both tasks. The comparative performance of each model has been evaluated using accuracy, precision, recall, and f1-measure.

cs.LG↗

arXiv2017

Predicting physiological developments from human gait using smartphone sensor data

Coronary artery disease, heart failure, angina pectoris and diabetes are among the leading causes of morbidity and mortality over the globe. Susceptibility to such disorders is compounded by changing lifestyles, poor dietary routines, aging and obesity. Besides, conventional diagnostics are limited in their capability to detect such pathologies at an early stage. This generates demand for automatic recommender systems that could effectively monitor and predict pathogenic behaviors in the body. To this end, we propose human gait analysis for predicting two important physiological parameters associated with different diseases, body mass index and age. Predicting age and body mass index by actively profiling the gait samples, could be further used for providing suitable healthcare recommendations. Existing strategies for predicting age and body mass index, however, necessitate stringent experimental settings for achieving appropriate performance. For instance, precisely recorded speech signals were recently used for predicting body mass indices of different subjects. Similarly, age groups were predicted by recording gait samples from on-body and wearable sensors. Such specialized methods limit active and convenient profiling of human age and body mass indices. We address these issues, by introducing smartphone sensors as a means for recording gait signals. Using on-board accelerometer and gyroscope helps in developing easy-to-use and accessible systems for predicting body mass index and age. To empirically show the effectiveness of our proposed methodology, we collected gait samples from sixty-three different subjects that were classified in body mass index and age groups using six well-known machine learning classifiers. We evaluated our system using two different windowing operations for feature extraction, namely Gaussian and Square.

eess.SP↗