Muhammad Imran

Mental illness prediction through text involves employing natural language processing (NLP) techniques and deep learning algorithms to analyze textual data for the identification of mental disorders. Therefore, machine learning and deep learning algorithms have been utilized in the existing literature for the detection of mental illness. However, current systems exhibit suboptimal performance primarily due to their reliance on traditional embedding techniques and generic language models to generate text embeddings. To address this limitation, there is a requirement for domain-specific pretrained language models that comprehensively understand the context found in posts of mentally ill patients. Posts from individuals with mental illness often contain metaphorical expressions, posing a challenge for existing models in understanding such figurative language. In this study, we propose a hybrid transformer architecture, comprising MentalBERT and MelBERT pretrained language models, cascaded with CNN models to generate and concatenate deep features. MentalBERT is pretrained on an extensive corpus of text data specifically related to the mental health domain, while MelBERT is trained on a large corpus of metaphorical data for improved understanding of metaphorical expressions. The results reveal outstanding performance of the proposed architecture with an overall accuracy of 92% and an F1-score of 92%, surpassing state-of-the-art models in comparison. This study underscores the necessity for further research in this field and illustrates the potential of advanced technologies to address mental health issues in contemporary society.

Most companies nowadays are using digital platforms for the recruitment of new employees to make the hiring process easier. The rapid increase in the use of online platforms for job posting has resulted in fraudulent advertising. The scammers are making money through fraudulent job postings. Online recruitment fraud has emerged as an important issue in cybercrime. Therefore, it is necessary to detect fake job postings to get rid of online job scams. In recent studies, traditional machine learning and deep learning algorithms have been implemented to detect fake job postings; this research aims to use two transformer-based deep learning models, i.e., Bidirectional Encoder Representations from Transformers (BERT) and Robustly Optimized BERT-Pretraining Approach (RoBERTa) to detect fake job postings precisely. In this research, a novel dataset of fake job postings is proposed, formed by the combination of job postings from three different sources. Existing benchmark datasets are outdated and limited due to knowledge of specific job postings, which limits the existing models’ capability in detecting fraudulent jobs. Hence, we extend it with the latest job postings. Exploratory Data Analysis (EDA) highlights the class imbalance problem in detecting fake jobs, which tends the model to act aggressively toward the minority class. Responding to overcome this problem, the work at hand implements ten top-performing Synthetic Minority Oversampling Technique (SMOTE) variants. The models’ performances balanced by each SMOTE variant are analyzed and compared. All implemented approaches are performed competitively. However, BERT+SMOBD SMOTE achieved the highest balanced accuracy and recall of about 90%.

The convergence of smart technologies and predictive modelling in prisons presents an exciting opportunity to revolutionize the monitoring of inmate behaviour, allowing for the early detection of signs of distress and the effective mitigation of suicide risks. While machine learning algorithms have been extensively employed in predicting suicidal behaviour, a critical aspect that has often been overlooked is the interoperability of these models. Most of the work done on model interpretations for suicide predictions often limits itself to feature reduction and highlighting important contributing features only. To address this research gap, we used Anchor explanations for creating human-readable statements based on simple rules, which, to our knowledge, have never been used before for suicide prediction models. We also overcome the limitation of anchor explanations, which create weak rules on high-dimensionality datasets, by first reducing data features with the help of SHapley Additive exPlanations (SHAP). We further reduce data features through anchor interpretations for the final ensemble model of XGBoost and random forest. Our results indicate significant improvement when compared with state-of-the-art models, having an accuracy and precision of 98.6% and 98.9%, respectively. The F1-score for the best suicide ideation model appeared to be 96.7%.

One of the challenges in image processing involves single-image deraining (SID). Existing methods do not exploit images at multi-scales and often overlook spatial and channel information. These methods fail to account for different rain conditions, leading to challenges in effectively removing a wide range of rain streak patterns, such as diverse directional or dense streaks. Moreover, they often result in the loss of fine texture details or a blurred background in the process of eliminating rain streaks from images captured in heavy rain. Mostly state-of-the-art (SOTA) deraining models achieve higher performance in removing rain from rainy images but at the expense of a high number of parameters, which results in computational complexity and memory requirements. Furthermore, they also do not consider high-level visioned evaluation metrics to perform deep evaluations of the proposed models. In this paper, a simple lightweight network with few parameters and relatively shallow depth is proposed by fusing the traditional Gaussian-Laplacian pyramid technique with the attention module. We propose a novel attention-based lightweight pyramid network for image deraining and detection (LPN-IDD) to achieve better deraining performance. The proposed model includes a dual attention module integrated with the Gaussian-Laplacian pyramids network. In LPN-IDD, different levels of laplacian pyramids can extract multi-scale features to adapt to different shapes and types of rain streaks. Residual and recursive blocks are used in each subnetwork along with dual attention blocks to resist the occlusion or texture feature while suppressing unnecessary features. Extensive experimentation performed on the SID synthetic and real-world datasets demonstrate the effectiveness of the proposed model in image deraining tasks. For deep evaluation of the proposed methodology, object detection models including faster-RCNN, YOLO-V3, YOLO-V7 are used along with full reference evaluation metrics.

Facial paralysis is a debilitating condition that weakens or damages facial muscles resulting in asymmetric or abnormal facial movements. To aid in the diagnosis and rehabilitation of facial paralysis, researchers have developed machine learning and deep learning computer-aided diagnosis systems. However, machine learning models have limitations as they rely on facial landmark techniques and manual face palsy region extraction methods to obtain spatial information. Moreover, deep learning models need large, labelled datasets for training whereas existing available facial paralysis datasets are small and restricted. This presents significant challenges, including difficulties in data acquisition, insufficient patient numbers, and inadequate diversity within the datasets. These limitations can potentially restrict the generalizability of these models and introduce biases in the resulting outcomes. In this study, we propose an approach for the diagnosis and grading of facial paralysis comprised of two datasets, one from MEEI (Massachusetts Eye and Ear Infirmary) videos of patients and the other from the YFP (YouTube Face Palsy) dataset. The model uses a transfer learning approach to fine-tune the VGGFace model, which is pre-trained on facial images, on the prepared datasets for facial paralysis. The resultant model was subsequently renamed FP-VGGFace for the purpose of this research. Additionally, two more pre-trained models on facial images, ResNet50 and VGG16, are also fine-tuned for the facial paralysis task. This was undertaken to conduct a performance comparison of multiple models on the prepared dataset. The findings indicate that the models exhibit high accuracy, benefiting from pre-training on a diverse dataset that enables the capture of spatial information from facial images. The FP-VGGFace model achieves the best accuracy (99.3%) and F1-score (99.3%) surpassing all benchmark models. This study underscores the potential of utilizing pre-trained deep learning models for the diagnosis and rehabilitation of facial paralysis.

This study presents a deep learning model for efficient intracranial hemorrhage (ICH) detection and subtype classification on non-contrast head computed tomography (CT) images. ICH refers to bleeding in the skull, leading to the most critical life-threatening health condition requiring rapid and accurate diagnosis. It is classified as intra-axial hemorrhage (intraventricular, intraparenchymal) and extra-axial hemorrhage (subdural, epidural, subarachnoid) based on the bleeding location inside the skull. Many computer-aided diagnoses (CAD)-based schemes have been proposed for ICH detection and classification at both slice and scan levels. However, these approaches perform only binary classification and suffer from a large number of parameters, which increase storage costs. Further, the accuracy of brain hemorrhage detection in existing models is significantly low for medically critical applications. To overcome these problems, a fast and efficient system for the automatic detection of ICH is needed. We designed a double-branch model based on xception architecture that extracts spatial and instant features, concatenates them, and creates the 3D spatial context (common feature vectors) fed to a decision tree classifier for final predictions. The data employed for the experimentation was gathered during the 2019 Radiologist Society of North America (RSNA) brain hemorrhage detection challenge. Our model outperformed benchmark models and achieved better accuracy in intraventricular (99.49%), subarachnoid (99.49%), intraparenchymal (99.10%), and subdural (98.09%) categories, thereby justifying the performance of the proposed double-branch xception architecture for ICH detection and classification.

As AI advances, new applications and services are being developed to enhance current services. With the emergence of digital twin technology (DT), an exact digital replica of any natural system or physical object/state can be created. DT incorporates several machines and deep learning-based approaches to efficiently analyze and process the collected data in order to understand the system pattern better. Consequently, Health 4.0 applications can get advantages from these cutting-edge technologies. In this article, we focus on Intracranial haemorrhage (ICH) which is a life-threatening emergency that needs immediate diagnosis and treatment. ICH is caused by the bleeding inside the skull or brain. It is classified in five main subtypes; a) subdural hemorrhage (SH), b) epidural haemorrhage (EH), c) intraparenchymal haemorrhage (IH), d) subarachnoid haemorrhage (SAH) and e) intraventricular hemorrhage (IVH). Radiologists typically examine computed tomography (CT) scan of the patients to determine the ICH and its subtype. However, manual assessment of the CT scan is a complex and time-consuming task. Pre-trained convolutional neural networks (CNNs) are state-of-the-art for the ICH classification. But they suffer from the curse of dimensionality and use redundant and noisy features which causes memory and computation overhead. The problem of imbalanced data poses the challenge for achieving model generalization. This paper proposes a hybrid attention-based ResNet architecture for ICH detection and classification. Principal component analysis (PCA) is used for dimensionality reduction and redundant feature removal whereas xtreme gradient boosting (XGBoost) is used for ICH classfication. The class imbalance problem is resolved using deep convolutional generative adversarial network (DCGAN). The proposed system is evaluated using the dataset assembled during Radiologist Society of North America (RSNA) ICH detection challenge 2019. The findings show that our proposed model outperforms existing state-of-the-art models in terms of accuracy and F1-score. ICH classification achieved accuracies of 99.3%, 97.1%, 96.7%, and 96.1%, for detecting EH, IH, IVH, SAH, and SH subtypes respectively, while F1-score is 96.1%, which is also best when compared with the benchmark studies.

In fact, electrochemical method (EC) is a specific and eco-friendly technique with several advantages over common organic synthesis methods. During EC no as such external catalysts are required to initiate the reaction, the current potential in itself acts as a catalyst. Most of the inactive organic compounds can be converted to active species by EC method. This method results in the synthesis of compounds with high yield and purity. This method is also good to be applied for the synthesis of thermally sensitive organic compounds. Such synthesis has significant selectivity and reactivity which enable the synthesis of such compounds that are not feasible while using the conventional methods. This review provides insight into the utilization of EC method in the synthesis of organic compounds and their derivatives. Various prerequisites for such synthesis have been highlighted. The EC method application for preparation of derivatives of benzofuran, and benzoxazole, oxidation of N, N, N’, N’tetramethyl-1,4-phenylenediamine, 5-diethoxy-4-morpholinoaniline, organic compounds containing C=N, benzyl alcohol to benzaldehyde and tetratomic Thioethers have been discussed in detail. In addition, the electrochemical synthesis of biomedical important compounds has been presented. The compounds synthesized through EC methods shows potential antimicrobial activity. Deferent researchers work to study the potential biological application of organic compounds synthesized through EC process. The anti-cancer, anti-bacterial, anti-fungal and other important biological activities has been investigated.