In the rapidly evolving landscape of education, the integration of Big Data and AI presents significant opportunities for improving educational outcomes, especially in the context of Predicting Students Performance (PSP) applications in higher education. Today, Educational Data Mining (EDM) strategies have been implemented to overcome educational challenges in advanced nations. Nonetheless, the issues confronting developing countries, like the unavailability of educational datasets, and challenges with selecting Machine Learning (ML) algorithms that are effective in terms of accuracy, bias, and over-fitting, have never been investigated. Therefore, a novel dataset, UOBEDM, collected from the University of Baluchistan (UoB) in the developing region of Balochistan, Pakistan, comprises 49,835 student records, providing valuable insights into various demographic and academic aspects. Through meticulous data collection and cleaning processes, including feature selection techniques, the dataset was refined to 23,492 instances. Various ML algorithms were fine-tuned on the UOBEDM dataset, with the top five algorithms—Trees, K-Nearest Neighbors (KNN), Naive Bayes (NB), Random Forest (RF), and Support Vector Machines (SVM)—yielding accuracy scores of 0.95, 0.94, 0.92, 0.96, and 0.50, respectively. A novel approach called the Cross-Classification Matrix (CCM) was introduced to assess algorithm performance and select the best model. Trees emerged as the optimal predicting algorithm, simplifying decision-making processes for academics through the development of a graphical tree-based Early Intervention Model (EIM). The significance of the dataset extends beyond classification algorithms, paving the way for research in EDM and addressing educational inequalities. This study underscores the potential of data-driven approaches to enhance educational outcomes and foster innovation in education. The findings contribute to the understanding of predictive modeling in education and provide valuable insights for educators, policymakers, and researchers.

Wrist pathologies, particularly fractures common among children and adolescents, present a critical diagnostic challenge. While X-ray imaging remains a prevalent diagnostic tool, the increasing misinterpretation rates highlight the need for more accurate analysis, especially considering the lack of specialized training among many surgeons and physicians. Recent advancements in deep convolutional neural networks offer promise in automating pathology detection in trauma X-rays. However, distinguishing subtle variations between pediatric wrist pathologies in X-rays remains challenging. Traditional manual annotation, though effective, is laborious, costly, and requires specialized expertise. In this paper, we address the challenge of pediatric wrist pathology recognition with a fine-grained approach, aimed at automatically identifying discriminative regions in X-rays without manual intervention. We refine our fine-grained architecture through ablation analysis and the integration of LION. Leveraging Grad-CAM, an explainable AI technique, we highlight these regions. Despite using limited data, reflective of real-world medical study constraints, our method consistently outperforms state-of-the-art image recognition models on both augmented and original (challenging) test sets. Our proposed refined architecture achieves an increase in accuracy of 1.06% and 1.25% compared to the baseline method, resulting in accuracies of 86% and 84%, respectively. Moreover, our approach demonstrates the highest fracture sensitivity of 97%, highlighting its potential to enhance wrist pathology recognition.

The optical character recognition for the right to left and cursive languages such as Arabic is challenging and received little attention from researchers in the past compared to the other Latin languages. Moreover, the absence of a standard publicly available dataset for several low-resource lan-guages, including the Pashto language remained a hurdle in the advancement of language processing. Realizing that, a clean dataset is the fundamental and core requirement of character recognition, this research begins with dataset generation and aims at a system capable of complete language understanding. Keeping in view the complete and full autonomous recognition of the cursive Pashto script. The first achievement of this research is a clean and standard dataset for the isolated characters of the Pashto script. In this paper, a database of isolated Pashto characters for forty four alphabets using various font styles has been introduced. In order to overcome the font style shortage, the graphical software Inkscape has been used to generate sufficient image data samples for each character. The dataset has been pre-processed and reduced in dimensions to 32 x 32 pixels, and further converted into the binary format with a black background and white text so that it resembles the Modified National Institute of Standards and Technology (MNIST) database. The benchmark database is publicly available for further research on the standard GitHub and Kaggle database servers both in pixel and Comma Separated Values (CSV) formats.

The Internet has become one of the significant sources for sharing information and expressing users’ opinions about products and their interests with the associated aspects. It is essential to learn about product reviews; however, to react to such reviews, extracting aspects of the entity to which these reviews belong is equally important. Aspect-based Sentiment Analysis (ABSA) refers to aspects extracted from an opinionated text. The literature proposes different approaches for ABSA; however, most research is focused on supervised approaches, which require labeled datasets with manual sentiment polarity labeling and aspect tagging. This study proposes a semi-supervised approach with minimal human supervision to extract aspect terms by detecting the aspect categories. Hence, the study deals with two main sub-tasks in ABSA, named Aspect Category Detection (ACD) and Aspect Term Extraction (ATE). In the first sub-task, aspects categories are extracted using topic modeling and filtered by an oracle further, and it is fed to zero-shot learning as the prompts and the augmented text. The predicted categories are the input to find similar phrases curated with extracting meaningful phrases (e.g., Nouns, Proper Nouns, NER (Named Entity Recognition) entities) to detect the aspect terms. The study sets a baseline accuracy for two main sub-tasks in ABSA on the Multi-Aspect Multi-Sentiment (MAMS) dataset along with SemEval-2014 Task 4 sub-task 1 to show that the proposed approach helps detect aspect terms via aspect categories.

Artificial intelligence technologies are now advancing swiftly and providing us with a variety of opportunities. The completion of analysis, predicting, and acknowledgment. In recent years, the field of computer vision has become one of highly exciting research. In this paper, we have compared three famous face detectors model, used for face recognition; Dlib, MTCNN, and FaceNet. We have conducted serious of experiments to compare the detection speed and accuracy for above mentioned detectors. FaceNet is the fastest among others without loss in recognition accuracy on commodity hardware.

Vegetation cover classification using mixed or low-resolution scalar images is challenging. Fortunately, recently deep learning object detection methods have emerged as a replacement to the conventional machine learning methods for the detection and classification of land use and land cover. This paper presents a deep learning object detection approach for land use and land cover detection using low/mixed resolution satellite images acquired from Google Earth satellite images. Google Earth images are accessible freely using the Google Earth Pro desktop application. Our dataset consists of two (02) classes (vegetation and non-vegetation) with a total of 450 labeled images captured from different parts of Pakistan. We present a comparison of the recent anchor-free object detection model YOLOX with the anchor-based object detection model YOLOR for solving real-time problems. The end-to-end differentiability, efficient GPU utilization, and absence of hand-crafted parameters make anchor-free models a compelling choice in object detection, and yet not been explored on Land cover classification using satellite images. Our experimental study shows that YOLOX delivers an overall accuracy of 83.50% on Vegetation and 86% on Non-Vegetation classes, which outperformed YOLOR by 30% on Vegetation classes and 34% on non-Vegetation classes for our dataset. We also show how an object detection system can be used for Vegetation and Non-Vegetation classification tasks, which can then be used for change monitoring and assisting in developing geographical maps using low/mixed resolution freely available satellite images.

Infectious disease outbreak has a significant impact on morbidity, mortality and can cause economic instability of many countries. As global trade is growing, goods and individuals are expected to travel across the border, an infected epidemic area carrier can pose a great danger to his hostile. If a disease outbreak is recognized promptly, then commercial products and travelers (traders/visitors) will be effectively vaccinated, and therefore the disease stopped. Early detection of outbreaks plays an important role here, and beware of the rapid implementation of control measures by citizens, public health organizations, and government. Many indicators have valuable information, such as online news sources (RSS) and social media sources (Twitter, Facebook) that can be used, but are unstructured and bulky, to extract information about disease outbreaks. Few early warning outbreak systems exist with some limitation of linguistic (Urdu) and covering areas (Pakistan). In Pakistan, few channels are published the outbreak news in Urdu or English. The aim is to procure information from Pakistan's English and Urdu news channels and then investigate process, integrate, and visualize the disease epidemic. Urdu ontology is not existed before to match extracted diseases, so we also build that ontology of disease.

Researchers used visual methods rigorously to improve brain tumor detection in MRI or CT scans, yet there remains a challenge to improve the detection accuracy. Further, the rise of deep learning methods improved tumor detection accuracy up to the mark. But again, many times, we face the challenges of having a bigger dataset and better computing power to achieve an improved and accurate trained model for every object classification problem. In this paper, we propose a deep learning framework single shot multi-box detector (SSD)-based model to detect tumors in the MRI scans. The proposed SSD model is the faster algorithm to detect the tumor even with the ability to detect the smallest spot in the low-resolution MRI scans. We additionally used a lightweight neural network architecture MobileNet v2 with SSD for faster and accurate object classification. The experimental results showed 98% accuracy with the proposed method after training with the smallest dataset of 250 MRI scans. We used the Kaggle database for training and testing the proposed model.

Live video streaming is one of the newly emerged services over the Internet that has attracted immense interest of the service providers. Since Internet was not designed for such services during its inception, such a service poses some serious challenges including cost and scalability. Peer-to-Peer (P2P) Internet Protocol Television (IPTV) is an application-level distributed paradigm to offer live video contents. In terms of ease of deployment, it has emerged as a serious alternative to client server, Content Delivery Network (CDN) and IP multicast solutions. Nevertheless, P2P approach has struggled to provide the desired streaming quality due to a number of issues. Stability of peers in a network is one of the major issues among these. Most of the existing approaches address this issue through older-stable principle. This paper first extensively investigates the older-stable principle to observe its validity in different scenarios. It is observed that the older-stable principle does not hold in several of them. Then, it utilizes machine learning approach to predict the stability of peers. This work evaluates the accuracy of several machine learning algorithms over the prediction of stability, where the Gradient Boosting Regressor (GBR) out-performs other algorithms. Finally, this work presents a proof-of-concept simulation to compare the effectiveness of older-stable rule and machine learning-based predictions for the stabilization of the overlay. The results indicate that machine learning-based stability estimation significantly improves the system.

Unstructured text processing is the first step for several applications such as question answering systems, information retrieval, and recipe classification. In the field of recipe classification, number of frameworks have been proposed. However, it is still very tedious and time consuming to extract the food items from the unstructured text and then process for classification. In this research, an automatic food item detection from unstructured text is proposed based on semantic sense modeling. The candidate nouns are detected which can be food items and then the similarity of those nouns is computed with possible food categories. The candidate noun is treated as food item if the similarity is high. For similarity between possible food item and food category is computed by WordNet ontology. The proposed framework is evaluated on benchmark datasets and competitive performance have been achieved. The F-score on large dataset that contains around 20 K recipes is 0.89 which is improved from 0.56.

Peer-to-peer (P2P) live video streaming is an application-level approach providing ease of deployment with low cost as compared to the IP multicast and client/server (C/S) architecture. These systems solely rely on end-hosts to disseminate the content; therefore, their performance largely banks on end-hosts, called peers. Since peers themselves are controlled by users, users' activities become activities of peers. In such a network, the highly dynamic behavior of users impacts the network performance. Therefore, for performance improvement, a thorough understanding of user behavior is crucial. To explore and understand user behavior, numerous studies have been carried out. However, user behavior is complex, having several elements with dependency relationships, which make it difficult for a single measurement study to represent it comprehensively. Therefore, this work takes a two-step approach. Firstly, it collects existing measurement studies and analyzes, compares, and contrasts them to extract user behavior metrics and their relationships from them. Secondly, in light of the observations gained, this research analyzes traces of user behavior collected from an operational system. Such an outcome is useful, on one hand, for user behavior modelling towards performance improvement in NGWN, and on the other hand, it provides insights for further measurements and analysis.

Sentiment analysis task has widely been studied for various languages such as English and French. However, Roman Urdu sentiment analysis yet requires more attention from peer-researchers due to the lack of Off-the-Shelf Natural Language Processing (NLP) solutions. The primary objective of this study is to investigate the diverse machine learning methods for the sentiment analysis of Roman Urdu data which is very informal in nature and needs to be lexically normalized. To mitigate this challenge, we propose a fine-tuned Support Vector Machine (SVM) powered by Roman Urdu Stemmer. In our proposed scheme, the corpus data is initially cleaned to remove the anomalies from the text. After initial pre-processing, each user review is being stemmed. The input text is transformed into a feature vector using the bag-of-word model. Subsequently, the SVM is used to classify and detect user sentiment. Our proposed scheme is based on a dictionary based Roman Urdu stemmer. The creation of the Roman Urdu stemmer is aimed at standardizing the text so as to minimize the level of complexity. The efficacy of our proposed model is also empirically evaluated with diverse experimental configurations, so as to fine-tune the hyper-parameters and achieve superior performance. Moreover, a series of experiments are conducted on diverse machine learning and deep learning models to compare the performance with our proposed model. We also introduced the largest dataset on Roman Urdu, i.e., Roman Urdu e-commerce dataset (RUECD), which contains 26K+ user reviews annotated by the group of experts. The RUECD is challenging and the largest dataset available of Roman Urdu. The experiments show that the newly generated dataset is quite challenging and requires more attention from the peer researchers for Roman Urdu sentiment analysis.

The accuracy on MINST dataset for roman numerals is already 99.65%. However, same models showed low accuracy on Sindhi numerals. It is because Sindhi numerals have high correlation between the shapes of the numerals. In this paper, correlation based template matching is used to analyze the shape ambiguity by identifying the dominant false positives (FP) and false negatives (FN) for every numeral. Furthermore, the Gradients Histogram Orientation (GOH) features are used to improve the accuracy of existing classifiers by image-to-image matching. The classical OCR using simple binary features are not sufficient to address the problems of shape ambiguity in Sindhi numerals, i.e., the shape of digits 2, , and 3, , are very similar. The raw pixel values are used as features for the classification in the first stage. In second stage, the input image is matched with the dominant FP and FN of the predicted class, and the final decision is made by the image-to-image matching based on GOH features. Decision based on image to image matching with dominant FP and FN increase the accuracy of the classifier. Support vector machine (SVM), K-nearest neighbor, and template based matching classifiers are used. The proposed extension substantially improves the accuracy of all mentioned classifiers.

IPTV has emerged as one of the popular Internet applications attracting immense interest of academia and industry. Among others, Peer-to-Peer (P2P) approach enables IPTV service with ease of deployment and low cost. P2P systems involve end-hosts, called peers, to share their resources for dissemination of stream. In these systems, user activities, such as join and quit operations, translate as activities of peers. Due to this reason, these systems become highly dynamic as the behavior of users has a significant impact on the stream delivery performance of the whole system. Earlier P2P approaches deal with user behavior indirectly through enabling resilience in the system, which leads to other issues such as increased latency. Latter approaches attempt to address user behavior directly through proposing user behavior models. Such models focus to learn and predict user behavior in order to adapt the overlay network accordingly. Towards this, one important aspect is the classification of users. However, machine-learning classifiers have not been extensively evaluated for their accuracy over the classification problem. In this paper, we extensively evaluate numerous classifiers for their accuracy over different parameters. These results may be used to design intelligent P2P overlays for IPTV services providing better performance in terms of efficient stream delivery to users. Our results show that the Decision tree classifier performs better than other classifiers for this particular problem.

Reported casualties of mine workers is a routine affair, where a huge number of mine workers expire from mining incidents each year in underground coal mines due to harmful gases and suffocation. In this paper, a machine learning-based prediction system is designed to predict the possible hazed behaviour of the sensors to possibly prevent mine explosion or any other accident. An Arduino-based solution is placed in the mines where different sensors are mounted that can perceive the environmental factors, such as temperature and concentration, of different harmful gases. The data acquired from the sensor node is transmitted to the SD card module. The Alarm initiates a caution after sensing gas pressure above the critical state to save mine workers from any hazard. The sensor historical data is reorganized in a sliding window, and machine learning models are used to predict the next readings of each sensor.

In the recent few years, a lot of advancement has been made in Urdu linguistics. There are many portals and news websites that are generating a huge amount of data every day. However, there is still no publicly available dataset nor any framework available for automatic Urdu extractive summary generation. In an automatic extractive summary generation, the sentences with the highest weights are given importance to be included in the summary. The sentence weight is computed by the sum of the weights of the words in the sentence. There are two famous approaches to compute the weight of the words in the English language: local weights (LW) approach and global weights (GW) approach. The sensitivity of the weights depends on the contents of the text, the one word may have different weights in a different article, known as LW based approach. Whereas, in the case of GW, the weights of the words are computed from the independent dataset, which implies the weights of all words remain the same in different articles. In the proposed framework, LW and GW based approaches are modeled for the Urdu language. The sentence weight method and the weighted term-frequency method are LW based approaches that compute the weights of the sentences by the sum of important words and the sum of frequencies of the important words, respectively. Whereas, vector space model (VSM) is GW based approach, that computes the weight of the words from the independent dataset, and then remain the same for all types of the text; GW is widely used in the English language for various applications such as information retrieval and text classification. The extractive summaries are generated by LW and GW based approaches and evaluated with ground-truth summaries that are obtained by the experts. The VSM is used as a baseline framework for sentence weighting. Experiments show that LW based approaches are better for extractive summary generation. The F-score of the sentence weight method and the weighted term-frequency method are 80% and 76%, respectively. The VSM achieved only 62% accuracy on the same dataset. Both, the datasets with ground-truth, and the code are made publicly available for the researchers.

Scalability and ease of implementation make Peer-to-Peer (P2P) infrastructure an attractive option for live video streaming. Peer end-users or peers in these networks have extremely complex features and exhibit unpredictable behavior, i.e. any peer may join or exit the network without prior notice. Peers' dynamics is considered one of the key problems impacting the Quality of Service (QoS) of the P2P based IPTV services. Since, peer dynamics results in video disruption to consumer peers, for smooth video distribution, stable peer identification and selection is essential. Many research works have been conducted on stable peer identification using classical statistical methods. In this paper, a model based on machine learning is proposed in order to predict the length of a user session on entering the network. This prediction can be utilized in topology management such as offloading the departing peer before its exit. Consequently, this will help peers to select stable provider peers, which are the ones with longer session duration. Furthermore, it will also enable service providers to identify stable peers in a live video streaming network. Results indicate that the SVR based model performance is superior to an existing Bayesian network model.

Polio is one of the most important issues which have caught the global attention. It has been eradicated globally except Pakistan and Afghanistan. Its quiet alarming, where whole world is polio free, still polio cases are emerging from Pakistan. The major motivation behind this research is to study and analyze the past cases (trend analysis) and to predict the number of future cases and obstacles hindering Pakistan to eliminate polio. The areas with peak level of influx could be prioritized for effective tracking, planning and monitoring of vaccination activities and better utilization of human resources for targeted and controlled interventions. It shall provide better management and resource allocation decisions for speedy eradication of this epidemic syndrome. Polio cases are displayed on Google Maps for localization and clustering, and trend analysis is performed for future prediction using linear regression.

Wireless sensor networks (WSN) consist of diverse and minute sensor nodes which are widely employed in different applications, for example, atmosphere monitoring, search and rescue activities, disaster management, untamed life checking and so on. A WSN which is an accumulation of clusters and information exchange occurs with the assistance of cluster head (CH). A lot of sensor nodes' energy is utilized in procedures like detection, information exchange and making clusters using various protocols. In a cluster based WSN, it is profitable to segregate the tasks performed by cluster heads as a fair amount of energy could be conserved. Following this, we propose a solution to include a supplementary node that is named as a 'super node' alongside cluster head in a cluster based WSN in this work. This node is in-charge of all the clusters in a WSN and takes care of the entire cluster's energy information. It manages the cluster heads from their creation to the end. All the clusters in the network send their respective information to this node that eliminates redundant information and forwards the aggregated information towards the sink. This not only saves the CH energy but also conserves individual cluster node's energy by proper monitoring the energy levels. This mechanism enhances the lifetime of the network by minimizing the number of communications between nodes and the sink. In order to evaluate the performance of our proposed mechanism, we use various parameters like packet delay, communication overhead and energy consumption that show the optimality of our approach.

Polio is one of the most important issues which have caught the global attention. It has been eradicated globally except Pakistan and Afghanistan. Its quiet alarming, where whole world is polio free, still polio cases are emerging from Pakistan. The major motivation behind this research is to study and analyze the past cases (trend analysis) and to predict the number of future cases and obstacles hindering Pakistan to eliminate polio. The areas with peak level of influx could be prioritized for effective tracking, planning and monitoring of vaccination activities and better utilization of human resources for targeted and controlled interventions. It shall provide better management and resource allocation decisions for speedy eradication of this epidemic syndrome. Polio cases are displayed on Google Maps for localization and clustering, and trend analysis is performed for future prediction using linear regression.