arXiv subjects

Atiq Ur Rehman

Publications and source records attributed to Atiq Ur Rehman.

4 recordsLinked to original sources

arXiv2026

When Less Is More: A Controlled Benchmark of Lightweight CNNs for Satellite Land-Cover Segmentation on DeepGlobe

High-resolution satellite imagery is the backbone of good land-cover classification, and without that, environmental monitoring, urban planning, and sustainable resource management all fall short. Deep learning architectures perform well in semantic segmentation, but the efficiency-accuracy trade-off across classical convolutional encoders is not well quantified under controlled, reproducible conditions. This study compares five architectures VGG16, MobileNetV2, InceptionV3, AlexNet, and CNN on the DeepGlobe Land Cover Classification dataset using three progressively optimized iterations to isolate regularisation, transfer learning, and architectural depth. To ensure performance differentials reflect architectural properties, all experiments used identical preprocessing, hyperparameter, and training protocols without data augmentation or class-imbalance correction. At 24.98 MB, MobileNetV2_v1 had the highest overall accuracy (0.7906) and mean Intersection over Union (0.4625), outperforming deeper alternatives like InceptionV3_v2 (125.17 MB, accuracy 0.7610) and VGG16_v2 (71.13 MB, accuracy 0.7653). Class-wise analysis showed strength in urban, agricultural, and water categories, but rangeland-barren confusion showed that architectural optimization alone cannot optimize spectrally similar minority classes. Strong spatial generalization and crisp boundary delineation were confirmed on held-out test imagery, validating operational applicability. These results show that lightweight, transfer-learned models can match or outperform deeper models in resource-constrained remote-sensing environments, enabling scalable land-cover mapping.

cs.CV↗

arXiv2026

Unveiling Public Opinion: A Study of Sentiment Analysis Using LSTM and Traditional Models

In this age of social media, sites like Twitter have become meeting places for people to share their views and feelings on a wide range of issues and current events as they unfold in real time. Sentiment analysis, a critical application of NLP, has become indispensable due to the massive influx of user-generated content, enabling the extraction of meaningful insights from the opinions and emotions expressed in textual data. Sentiment analysis on Twitter employs sophisticated computational techniques to categorize tweets into positive, negative, or neutral sentiments. This method not only examines individual expressions but also analyzes vast databases related to specific subjects or events. By spotting these emotions, machine learning models help improve public opinion interpretation and trend forecasting. This paper examines the effectiveness of various machine learning and deep learning approaches. Designed for this use, the system evaluates logistic regression, random forest, naïve bayes, gradient boosting, and LSTM networks, among other algorithms applied in sentiment classification. This work identifies the optimal sentiment analysis model using a Kaggle Twitter dataset that has been preprocessed through tokenization, lemmatization, and stopword elimination. Emphasizing the better performance of the LSTM approach, the model attained a training accuracy of 90.98%, a testing accuracy of 80.00%, and a micro-average ROC- AUC score of 0.92. These results show that the model outperforms conventional machine learning techniques in capturing contextual and sequential textual aspects.

cs.CL↗

arXiv2025

High-dimensional covariance matrix regularization using informative targets

The sample covariance matrix becomes non-invertible in high-dimensional settings, making classical multivariate statistical methods inapplicable. Various regularization techniques address this issue by imposing a structured target matrix to improve stability and invertibility. While diagonal matrices are commonly used as targets due to their simplicity, more informative target matrices can enhance performance. This paper explores the use of such targets and estimates the underlying correlation parameter using maximum likelihood. The proposed method is analytically straightforward, computationally efficient, and more accurate than recent regularization techniques when targets are correctly specified. Its effectiveness is demonstrated through extensive simulations and a real-world application.

stat.ME↗

arXiv2020

IoT-Flock: An Open-source Framework for IoT Traffic Generation

Network traffic generation is one of the primary techniques that is used to design and analyze the performance of network security systems. However, due to the diversity of IoT networks in terms of devices, applications and protocols, the traditional network traffic generator tools are unable to generate the IoT specific protocols traffic. Hence, the traditional traffic generator tools cannot be used for designing and testing the performance of IoT-specific security solutions. In order to design an IoT-based traffic generation framework, two main challenges include IoT device modelling and generating the IoT normal and attack traffic simultaneously. Therefore, in this work, we propose an open-source framework for IoT traffic generation which supports the two widely used IoT application layer protocols, i.e., MQTT and CoAP. The proposed framework allows a user to create an IoT use case, add customized IoT devices into it and generate normal and malicious IoT traffic over a real-time network. Furthermore, we set up a real-time IoT smart home use case to manifest the applicability of the proposed framework for developing the security solutions for IoT smart home by emulating the real world IoT devices. The experimental results demonstrate that the proposed framework can be effectively used to develop better security solutions for IoT networks without physically deploying the real-time use case.

cs.NI↗