Papers by Md. Saif Hassan Onim

Unleashing the power of generative adversarial networks: A novel machine learning approach for vehicle detection and localisation in the dark
Cognitive Computation and Systems
Machine vision in low‐light conditions is a critical requirement for object detection in road tra... more Machine vision in low‐light conditions is a critical requirement for object detection in road transportation, particularly for assisted and autonomous driving scenarios. Existing vision‐based techniques are limited to daylight traffic scenarios due to their reliance on adequate lighting and high frame rates. This paper presents a novel approach to tackle this problem by investigating Vehicle Detection and Localisation (VDL) in extremely low‐light conditions by using a new machine learning model. Specifically, the proposed model employs two customised generative adversarial networks, based on Pix2PixGAN and CycleGAN, to enhance dark images for input into a YOLOv4‐based VDL algorithm. The model's performance is thoroughly analysed and compared against the prominent models. Our findings validate that the proposed model detects and localises vehicles accurately in extremely dark images, with an additional run‐time of approximately 11 ms and an accuracy improvement of 10%–50% compare...

Proceedings of the Great Lakes Symposium on VLSI 2023
Stress can aggravate age-related diseases that can lead to significant clinical impairment and de... more Stress can aggravate age-related diseases that can lead to significant clinical impairment and decrease the quality of life in older adults. To mitigate the harmful effects of stress and aging, it is important to monitor and manage stress. In this paper, we have developed context-aware stress detection for older adults with machine learning and cortisol biomarker. The Trier Social Stress Test (TSST), a well-known experimental protocol that consistently inflicts stress on people in a social context, was used as the stress protocol for this study. We have used salivary cortisol as a stress biomarker for ground truth estimation. The proposed machine learning model classifies stress into three different levels (no-stress, low-stress, and high-stress) based on data collected from Electro-Dermal Activity (EDA), Blood Volume Pressure (BVP), and Inter Beat Interval (IBI) sensors. To develop a context-aware machine learning model, we have used context features captured from the TSST protocol. Using sensor fusion, our proposed context-aware machine learning model achieved a macro-average F1-score of 0.937 and an accuracy of 92.48% in distinguishing among the three stress levels. We have also illustrated that using context improves the macro-average F1score by 0.20 and accuracy by over 20% compared to the machine learning model without context. CCS CONCEPTS • Computing methodologies → Machine learning approaches.

arXiv (Cornell University), May 9, 2023
The advancement of Image Processing has led to the widespread use of Object Recognition (OR) mode... more The advancement of Image Processing has led to the widespread use of Object Recognition (OR) models in various applications, such as airport security and mail sorting. These models have become essential in signifying the capabilities of AI and supporting vital services like national postal operations. However, the performance of OR models can be impeded by real-life scenarios, such as traffic sign alteration. Therefore, this research investigates the effects of altered traffic signs on the accuracy and performance of object recognition models. To this end, a publicly available dataset was used to create different types of traffic sign alterations, including changes to size, shape, color, visibility, and angles. The impact of these alterations on the YOLOv7 (You Only Look Once) model's detection and classification abilities were analyzed. It reveals that the accuracy of object detection models decreases significantly when exposed to modified traffic signs under unlikely conditions. This study highlights the significance of enhancing the robustness of object detection models in real-life scenarios and the need for further investigation in this area to improve their accuracy and reliability.
DCENSnet: A new deep convolutional ensemble network for skin cancer classification
Biomedical Signal Processing and Control
A Review of Context-Aware Machine Learning for Stress Detection
IEEE Consumer Electronics Magazine
TV broadcasters are increasingly adopting social TV strategies to affect the viewers’ online beha... more TV broadcasters are increasingly adopting social TV strategies to affect the viewers’ online behavior. The research done so far suggests that different drivers play different roles and their effects are different according to the specific type of online behavior. In order to extend this research, through hierarchical linear regression models, we compare the effects of the different drivers on the online behavior of “influencers”, i.e., users having a large number of followers, and “ordinary” users. Despite some limitations, we show relevant differences between the online behaviors of these two kinds of users, particularly the social TV strategies do not affect the online behavior of the “influencers”, while some of them affect the online behavior of “ordinary” users. Keywords-social TV; engagement; online behavior;
In this paper, we introduce Dual-CNN, a semantically-enhanced deep learning model to target the p... more In this paper, we introduce Dual-CNN, a semantically-enhanced deep learning model to target the problem of event detection in crisis situations from social media data. A layer of semantics is added to a traditional Convolutional Neural Network (CNN) model to capture the contextual information that is generally scarce in short, ill-formed social media messages. Our results show that our methods are able to successfully identify the existence of events, and event types (hurricane, floods, etc.) accurately (> 79% F-measure), but the performance of the model significantly drops (61% F-measure) when identifying fine-grained event-related information (affected individuals, damaged infrastructures, etc.). These results are competitive with more traditional Machine Learning models, such as SVM.

From its start, the so-called Islamic State of Iraq and the Levant (ISIL/ISIS) has been successfu... more From its start, the so-called Islamic State of Iraq and the Levant (ISIL/ISIS) has been successfully exploiting social media networks, most notoriously Twitter, to promote its propaganda and recruit new members, resulting in thousands of social media users adopting pro ISIS stance every year. Automatic identification of pro-ISIS users on social media has, thus, become the centre of interest for various governmental and research organisations. In this paper we propose a semantic-based approach for radicalisation detection on Twitter. Unlike most previous works, which mainly rely on the lexical and contextual representation of the content published by Twitter users, our approach extracts and makes use of the underlying semantics of words exhibited by these users to identify their pro/anti-ISIS stances. Our results show that classifiers trained from words’ semantics outperform those trained from lexical and network features by 2% on average F1-measure.

Sentiment analysis over Twitter offers organisations and individuals a fast and effective way to ... more Sentiment analysis over Twitter offers organisations and individuals a fast and effective way to monitor the publics' feelings towards them and their competitors. To assess the performance of sentiment analysis methods over Twitter a small set of evaluation datasets have been released in the last few years. In this paper we present an overview of eight publicly available and manually annotated evaluation datasets for Twitter sentiment analysis. Based on this review, we show that a common limitation of most of these datasets, when assessing sentiment analysis at target (entity) level, is the lack of distinctive sentiment annotations among the tweets and the entities contained in them. For example, the tweet "I love iPhone, but I hate iPad" can be annotated with a mixed sentiment label, but the entity iPhone within this tweet should be annotated with a positive sentiment label. Aiming to overcome this limitation, and to complement current evaluation datasets, we present STS-Gold, a new evaluation dataset where tweets and targets (entities) are annotated individually and therefore may present different sentiment labels. This paper also provides a comparative study of the various datasets along several dimensions including: total number of tweets, vocabulary size and sparsity. We also investigate the pair-wise correlation among these dimensions as well as their correlations to the sentiment classification performance on different datasets.
Lecture Notes in Computer Science, 2014
Sentiment lexicons for sentiment analysis offer a simple, yet effective way to obtain the prior s... more Sentiment lexicons for sentiment analysis offer a simple, yet effective way to obtain the prior sentiment information of opinionated words in texts. However, words' sentiment orientations and strengths often change throughout various contexts in which the words appear. In this paper, we propose a lexicon adaptation approach that uses the contextual semantics of words to capture their contexts in tweet messages and update their prior sentiment orientations and/or strengths accordingly. We evaluate our approach on one state-of-the-art sentiment lexicon using three different Twitter datasets. Results show that the sentiment lexicons adapted by our approach outperform the original lexicon in accuracy and F-measure in two datasets, but give similar accuracy and slightly lower F-measure in one dataset.

The Semantic Web – ISWC 2014, 2014
Most existing approaches to Twitter sentiment analysis assume that sentiment is explicitly expres... more Most existing approaches to Twitter sentiment analysis assume that sentiment is explicitly expressed through affective words. Nevertheless, sentiment is often implicitly expressed via latent semantic relations, patterns and dependencies among words in tweets. In this paper, we propose a novel approach that automatically captures patterns of words of similar contextual semantics and sentiment in tweets. Unlike previous work on sentiment pattern extraction, our proposed approach does not rely on external and fixed sets of syntactical templates/patterns, nor requires deep analyses of the syntactic structure of sentences in tweets. We evaluate our approach with tweet-and entity-level sentiment analysis tasks by using the extracted semantic patterns as classification features in both tasks. We use 9 Twitter datasets in our evaluation and compare the performance of our patterns against 6 state-of-the-art baselines. Results show that our patterns consistently outperform all other baselines on all datasets by 2.19% at the tweet-level and 7.5% at the entity-level in average F-measure.

Semantic Web, 2017
Sentiment analysis over social streams offers governments and organisations a fast and effective ... more Sentiment analysis over social streams offers governments and organisations a fast and effective way to monitor the publics' feelings towards policies, brands, business, etc. General purpose sentiment lexicons have been used to compute sentiment from social streams, since they are simple and effective. They calculate the overall sentiment of texts by using a general collection of words, with predetermined sentiment orientation and strength. However, words' sentiment often vary with the contexts in which they appear, and new words might be encountered that are not covered by the lexicon, particularly in social media environments where content emerges and changes rapidly and constantly. In this paper, we propose a lexicon adaptation approach that uses contextual as well as semantic information extracted from DBPedia to update the words' weighted sentiment orientations and to add new words to the lexicon. We evaluate our approach on three different Twitter datasets, and show that enriching the lexicon with contextual and semantic information improves sentiment computation by 3.7% in average accuracy, and by 3% in average F1 measure.
Performance Analysis of Machine Learning Models for Cheating Detection in Online Examinations
2022 25th International Conference on Computer and Information Technology (ICCIT)

Social media platforms have recently become a gold mine for organisations to monitor their reputa... more Social media platforms have recently become a gold mine for organisations to monitor their reputation by extracting and analysing the sentiment of the posts generated about them, their markets, and competitors. Among the approaches to analyse sentiment from social media, approaches based on sentiment lexicons (sets of words with associated sentiment scores) have gained popularity since they do not rely on training data, as opposed to Machine Learning approaches. However, sentiment lexicons consider a static sentiment score for each word without taking into consideration the different contexts in which the word is used (e.g, great problem vs. great smile). Additionally, new words constantly emerge from dynamic and rapidly changing social media environments that may not be covered by the lexicons. In this paper we propose a lexicon adaptation approach that makes use of semantic relations extracted from DBpedia to better understand the various contextual scenarios in which words are us...

Microblogs and social media platforms are now considered among the most popular forms of online c... more Microblogs and social media platforms are now considered among the most popular forms of online communication. Through a platform like Twitter, much information reflecting people's opinions and attitudes is published and shared among users on a daily basis. This has recently brought great opportunities to companies interested in tracking and monitoring the reputation of their brands and businesses, and to policy makers and politicians to support their assessment of public opinions about their policies or political issues. A wide range of approaches to sentiment analysis on Twitter, and other similar microblogging platforms, have been recently built. Most of these approaches rely mainly on the presence of affect words or syntactic structures that explicitly and unambiguously reflect sentiment (e.g., "great'', "terrible''). However, these approaches are semantically weak, that is, they do not account for the semantics of words when detecting their sentime...

Energies
Electricity production from photovoltaic (PV) systems has accelerated in the last few decades. Nu... more Electricity production from photovoltaic (PV) systems has accelerated in the last few decades. Numerous environmental factors, particularly the buildup of dust on PV panels have resulted in a significant loss in PV energy output. To detect the dust and thus reduce power loss, several techniques are being researched, including thermal imaging, image processing, sensors, cameras with IoT, machine learning, and deep learning. In this study, a new dataset of images of dusty and clean panels is introduced and applied to the current state-of-the-art (SOTA) classification algorithms. Afterward, a new convolutional neural network (CNN) architecture, SolNet, is proposed that deals specifically with the detection of solar panel dust accumulation. The performance and results of the proposed SolNet and other SOTA algorithms are compared to validate its efficiency and outcomes where SolNet shows a higher accuracy level of 98.2%. Hence, both the dataset and SolNet can be used as benchmarks for fu...

Deep Neural Network (DNN) models with image processing and object localization have the potential... more Deep Neural Network (DNN) models with image processing and object localization have the potential to advance the automatic traffic control and monitoring system. Despite some notable progress in developing robust license plate detection models, research endeavours continue to reduce computational complexities with higher detection accuracy. This paper reports a computationally efficient and reasonably accurate Automatic License Plate Recognition (ALPR) system for Bengali characters with a new DNN model that we call Bengali License Plate Network (BLPnet). Additionally, the cascaded architectures for detecting vehicle regions prior to VLP in the proposed model, would significantly reduce computational cost and false-positives making the system faster and more accurate. Besides, with a new Bengali OCR engine and word-mapping process, the model can readily extract, detect and output the complete license-plate number of a vehicle. The model feeding with17 frames per second (fps) on real-...

Breast cancer is the second most responsible for all cancer types and has been the cause of numer... more Breast cancer is the second most responsible for all cancer types and has been the cause of numerous deaths over the years, especially among women. Any improvisation of the existing diagnosis system for the detection of cancer can contribute to minimizing the death ratio. Moreover, cancer detection at an early stage has recently been a prime research area in the scientific community to enhance the survival rate. Proper choice of machine learning tools can ensure early-stage prognosis with high accuracy. In this paper, we have studied different machine learning algorithms to detect whether a patient is likely to face breast cancer or not. Due to the implicit behavior of early-stage features, we have implemented a multilayer perception model with the integration of PCA and suggested it to be more viable than other detection algorithms. Our 4 layers MLP-PCA network has obtained the best accuracy of 100% with a mean of 90.48% accuracy on the BCCD dataset.
Manual interpretation and classification of ECG signals lack both accuracy and reliability. These... more Manual interpretation and classification of ECG signals lack both accuracy and reliability. These continuous timeseries signals are more effective when represented as an image for CNN-based classification. A continuous Wavelet transform filter is used here to get corresponding images. In achieving the best result generic CNN architectures lack sufficient accuracy and also have a higher run-time. To address this issue, we propose an ensemble method of transfer learning-based models to classify ECG signals. In our work, two modified VGG-16 models and one InceptionResNetV2 model with added feature extracting layers and ImageNet weights are working as the backbone. After ensemble, we report an increase of 6.36% accuracy than previous MLP based algorithms. After 5-fold cross-validation with the Physionet dataset, our model reaches an accuracy of 99.98%.
Uploads
Papers by Md. Saif Hassan Onim