The COVID-19 outbreak began in December 2019 and has dreadfully affected our lives since then. More than three million lives have been engulfed by this newest member of the corona virus family. With the emergence of continuously mutating variants of this virus, it is still indispensable to successfully diagnose the virus at early stages. Although the primary technique for the diagnosis is the PCR test, the non-contact methods utilizing the chest radiographs and CT scans are always preferred. Artificial intelligence, in this regard, plays an essential role in the early and accurate detection of COVID-19 using pulmonary images. In this research, a transfer learning technique with fine tuning was utilized for the detection and classification of COVID-19. Four pre-trained models i.e., VGG16, DenseNet-121, ResNet-50, and MobileNet were used. The aforementioned deep neural networks were trained using the dataset (available on Kaggle) of 7232 (COVID-19 and normal) chest X-ray images. An indigenous dataset of 450 chest X-ray images of Pakistani patients was collected and used for testing and prediction purposes. Various important parameters, e.g., recall, specificity, F1-score, precision, loss graphs, and confusion matrices were calculated to validate the accuracy of the models. The achieved accuracies of VGG16, ResNet-50, DenseNet-121, and MobileNet are 83.27%, 92.48%, 96.49%, and 96.48%, respectively. In order to display feature maps that depict the decomposition process of an input image into various filters, a visualization of the intermediate activations is performed. Finally, the Grad-CAM technique was applied to create class-specific heatmap images in order to highlight the features extracted in the X-ray images. Various optimizers were used for error minimization purposes. DenseNet-121 outperformed the other three models in terms of both accuracy and prediction.

As the world is going through an existential global health crisis, i.e., the outbreak of novel coronavirus-caused respiratory disease , the healthcare systems of all the countries require readily available, low cost and highly precise equipment for the rapid diagnostics, monitoring, and treatment of the disease. The performance and precision of this equipment are solely dependent on the sensors being used. The advancement in research and development of micro-electro-mechanical systems (MEMS) based sensors during recent years, has resulted in the improvement of the conventional equipment being used in biomedical and health care applications. Microfluidics (Lab-on-a-chip) and MEMS sensors are now being used extensively for quick and accurate detection, progression monitoring, and treatment of various diseases including Covid-19. The ongoing miniaturization and design improvements have resulted in more precise sensors and actuators for healthcare applications, even for micro and nanoscale measurements in drug delivery and other invasive applications. This article aims at reviewing the MEMS sensors being used or which can be used in the important equipment for the detection and treatment of Covid-19 or other pandemics. An insight into various designs and working principles of the research-based and commercially available MEMS sensors is presented. The study highlights the role and importance of MEMS sensors in the improvement of equipment with conventional sensors. MEMS sensors outperform the conventional sensors due to their small size (1µm-1mm), negligible weight, prompt response, precise measurements, portability, and ease of integration with electronic circuitry.

Breast cancer is one of the leading causes of increasing deaths in women worldwide. The complex nature (microcalcification and masses) of breast cancer cells makes it quite difficult for radiologists to diagnose it properly. Subsequently, various computer-aided diagnosis (CAD) systems have previously been developed and are being used to aid radiologists in the diagnosis of cancer cells. However, due to intrinsic risks associated with the delayed and/or incorrect diagnosis, it is indispensable to improve the developed diagnostic systems. In this regard, machine learning has recently been playing a potential role in the early and precise detection of breast cancer. This paper presents a new machine learning-based framework that utilizes the Random Forest, Gradient Boosting, Support Vector Machine, Artificial Neural Network, and Multilayer Perception approaches to efficiently predict breast cancer from the patient data. For this purpose, the Wisconsin Diagnostic Breast Cancer (WDBC) dataset has been utilized and classified using a hybrid Multilayer Perceptron Model (MLP) and 5-fold cross-validation framework as a working prototype. For the improved classification, a connection-based feature selection technique has been used that also eliminates the recursive features. The proposed framework has been validated on two separate datasets, i.e., the Wisconsin Prognostic dataset (WPBC) and Wisconsin Original Breast Cancer (WOBC) datasets. The results demonstrate improved accuracy of 99.12% due to efficient data preprocessing and feature selection applied to the input data.

This study aims to determine the stock selection ability and market timing ability of mutual fund managers, focusing on conventional funds and Islamic funds in Pakistan.  Although there has been significant growth in the number and assets of mutual funds in recent years, few studies measure the performance of mutual funds managers. The scarcity of existing literature motivates this study. In this study, two models are used to measure the stock selection and market timing on a sample of conventional mutual funds and Islamic mutual funds over 2010 and 2019 using annual returns. Overall, the results indicate that the performance study of conventional mutual funds and Islamic mutual funds indicates that manager performance is not superior in all three portfolios, i.e., conventional funds, Islamic funds, and overall funds in over sample period. This also indicates that both Conventional and Islamic fund managers do not outperform the market (KSE 100 index). Thus, there is a lack of market timing ability. Using Tranoy and mazuy and Jansen models found a lack of stock selection and market timing ability of mutual fund managers in Pakistani mutual funds. In this study, I have applied only two models to examine both the timing and selection ability of conventional and Islamic Pakistani equity funds. For future possibilities, the study suggests adopting several methods and approaches like the TMFF3 model and HM-FF3 model, making the study more comprehensive and accurate than this research.

No abstract

With the advancement in technology, digital images can easily be transmitted and stored over the Internet. Encryption is used to avoid illegal interception of digital images. Encrypting large-sized colour images in their original dimension generally results in low encryption/decryption speed along with exerting a burden on the limited bandwidth of the transmission channel. To address the aforementioned issues, a new encryption scheme for colour images employing convolutional autoencoder, DNA and chaos is presented in this paper. The proposed scheme has two main modules, the dimensionality conversion module using the proposed convolutional autoencoder, and the encryption/decryption module using DNA and chaos. The dimension of the input colour image is first reduced from N × M × 3 to P × Q gray-scale image using the encoder. Encryption and decryption are then performed in the reduced dimension space. The decrypted gray-scale image is upsampled to obtain the original colour image having dimension N × M × 3. The training and validation accuracy of the proposed autoencoder is 97% and 95%, respectively. Once the autoencoder is trained, it can be used to reduce and subsequently increase the dimension of any arbitrary input colour image. The efficacy of the designed autoencoder has been demonstrated by the successful reconstruction of the compressed image into the original colour image with negligible perceptual distortion. The second major contribution presented in this paper is an image encryption scheme using DNA along with multiple chaotic sequences and substitution boxes. The security of the proposed image encryption algorithm has been gauged using several evaluation parameters, such as histogram of the cipher image, entropy, NPCR, UACI, key sensitivity, contrast, etc. The experimental results of the proposed scheme demonstrate its effectiveness to perform colour image encryption.

The deployment and efficient use of wireless sensor networks (WSNs) in underwater and underground environments persists to be a difficult task. In addition, the localization of a sensor Rx node in WSNs is an important aspect for the successful communication with the aforementioned environments. To overcome the limitations of electromagnetic, acoustic, and optical communication in underwater and underground wireless sensor networks (UWSNs), magneto-inductive (MI) communication technology emerged as a promising alternative for usage in UWSNs with a wide range of applications. To make the magneto-inductive underwater wireless sensor networks (MI-UWSNs) more efficient, recently, various research studies focused on the optimization of the physical layer, MAC layer, and routing layer, but none of them has taken into account the effect of directionality. Despite the directionality issue posed by the physical nature of a magnetic field, the unique qualities of MI communication open up a gateway for several applications. The directionality issue of MI sensors is a critical challenge that must be taken into account while developing any WSN protocol or localization algorithm. This paper highlights and discusses the severity and impact of the directionality issue in designing a localization algorithm for magneto-inductive wireless sensor networks (MI-WSNs). A received signal strength indicator (RSSI)-based multilateration localization algorithm is presented in this paper, where a minimum of 2 and maximum of 10 anchor Tx nodes are used to estimate the position of the sensor Rx nodes, which are deployed randomly in a 15 m × 15 m simulation environment. This RSSI-based multilateration technique is the most suitable option that can be used to quantify the impact of directionality on the localization of a sensor Rx node.

This study aims to realize Sustainable Development Goals (SDGs), i.e., SDG 9: Industry Innovation and Infrastructure and SDG 14: Life below Water, through the improvement of localization estimation accuracy in magneto-inductive underwater wireless sensor networks (MI-UWSNs). The accurate localization of sensor nodes in MI communication can effectively be utilized for industrial IoT applications, e.g., underwater gas and oil pipeline monitoring, and in other important underwater IoT applications, e.g., smart monitoring of sea animals, etc. The most-feasible technology for medium- and short-range communication in IIoT-based UWSNs is MI communication. To improve underwater communication, this paper presents a machine learning-based prediction of localization estimation accuracy of randomly deployed sensor Rx nodes through anchor Tx nodes in the MI-UWSNs. For the training of ML models, extensive simulations have been performed to create two separate datasets for the two configurations of excitation current provided to the Tri-directional (TD) coils, i.e., configuration1-case1_configuration2-case1 (c1c1_c2c1) and configuration1-case2_configuration2-case2 (c1c2_c2c2). Two ML models have been created for each case. The accuracies of both models lie between 95% and 97%. The prediction results have been validated by both the test dataset and verified simulation results. The other important contribution of this paper is the development of a novel assembling technique of a MI-TD coil to achieve an approximate omnidirectional magnetic flux around the communicating coils, which, in turn, will improve the localization accuracy of the Rx nodes in IIoT-based MI-UWSNs.