Muhammad Sajid

This paper presents a supervised machine learning approach using eight popular classifiers for fault classification in power transmission lines. The classification of faults, indicated by behavior of electrical signals associated with them, plays a pivotal role in maintaining the reliability, stability, and security of electrical grids. However, most of the previous studies on fault analysis in power systems relied on proprietary data and lack of standardized benchmarks, hindering the comparison of algorithms and making performance more erratic. Moreover, the non-availability of labeled data for all types of faults is the most problematic. This paper proposes to perform fault classification on a data set created from a real-time Simulink model to standardize performance and advance research in this area. A new strategy for non-intensive feature extraction is applied using relatively simpler techniques, eliminating computationally expensive techniques such as Wavelets. Feature selection through dimensionality reduction techniques is used to improve model performance and more efficient use of computational resources. The performance of the learning algorithms (e.g. Decision Tree, Random Forest etc.) has been analyzed with various preprocessing techniques (e.g. data scaling, transformation, etc.) and tuning of parameters, focusing on the accuracy and computational time ( T_c ), for performance generalization and efficiency. Performing specific operations on data in sequence of steps provided flexibility and adaptability in processing the data, making it easy to train, evaluate and validate the learning algorithms. The results demonstrated that the proposed scheme can be effectively used for fault classification with high accuracy and significant reductions in T_c under various operating conditions. The study also determined the best estimator for each classifier when building and training classifier’s models, offering a variety of options. Logistic Regression, Random Forest and Support Vector Machine were the outperforming classifiers and proved their potential for classifying faults in electric power transmission lines.

Smart Grid is a way of providing bidirectional energy flow with the integration of latest communication technologies and advanced control methods to overcome the issues associated with the current power grid such as unidirectional power flow, resource wastage, reliability, security, enhanced quality, and increasing demand of energy. Integrating Internet of Things (IoTs) makes Smart Grid hyperaware and agile to enhance the efficiency, reliability, and sustainability of electricity distribution. IoT‐enabled Smart Grids use IoT devices and sensors to collect real‐time data, allowing for automated monitoring, predictive maintenance, and better demand management. This study comprehensively reviews various wireless technologies for IoT‐enabled Smart Grids that could be integrated into home area networks (HANs), neighborhood area networks (NANs), and wide‐area networks (WANs). This work provides a comparison of wireless technologies for HANs, NANs, and WANs in terms of data rates, range, adaptability, internet protocol support, and various other parameters. IoT technologies, including ZigBee, Z‐wave, Bluetooth, Wi‐Fi, NFC, 6LoWPAN, wireless HART, and Thread, are suggested for operations in HANs according to the customer requirements with their operating characteristics. Similarly, for NANs and WANs, long‐term evolution (LTE), WiMax, and LPWAN are explored in terms of requirements of utilities. The study further analyzes the applications of IoT‐enabled Smart Grids and elaborates on the associated challenges and issues.

Automated recognition of handwritten characters and digits is a challenging task. Although a significant amount of literature exists for automatic recognition of handwritten characters of English and other major languages in the world, there exists a wide research gap due to lack of research for recognition of Urdu language. The variations in writing style, shape and size of individual characters and similarities with other characters add to the complexity for accurate classification of handwritten characters. Deep neural networks have emerged as a powerful technology for automated classification of character patters and object images. Although deep networks are known to provide remarkable results on large-scale datasets with millions of images, however the use of deep networks for small image datasets is still challenging. The purpose of this research is to present a classification framework for automatic recognition of handwritten Urdu character and digits with higher recognition accuracy by utilizing theory of transfer learning and pre-trained Convolution Neural Networks (CNN). The performance of transfer learning is evaluated in different ways: by using pre-trained AlexNet CNN model with Support Vector Machine (SVM) classifier, and fine-tuned AlexNet for extracting features and classification. We have fine-tuned AlexNet hyper-parameters to achieve higher accuracy and data augmentation is performed to avoid over-fitting. Experimental results and the quantitative comparisons demonstrate the effectiveness of the proposed research for recognition of handwritten characters and digits using fine-tuned AlexNet. The proposed research based on fine-tuned AlexNet outperforms the related state-of-the-art research thereby achieving a classification accuracy of 97.08%, 98.21%, 94.92% for urdu characters, digits and hybrid datasets respectively. The presented methods can be applied for research on Urdu characters and in diverse domains such as handwritten text image retrieval, reading postal addresses, bank’s cheque processing, preserving and digitization of manuscripts from old ages.

Histopathological image analysis is an examination of tissue under a light microscope for cancerous disease diagnosis. Computer-assisted diagnosis (CAD) systems work well by diagnosing cancer from histopathology images. However, stain variability in histopathology images is inevitable due to the use of different staining processes, operator ability, and scanner specifications. These stain variations present in histopathology images affect the accuracy of the CAD systems. Various stain normalization techniques have been developed to cope with inter-variability issues, allowing standardizing the appearance of images. However, in stain normalization, these methods rely on the single reference image rather than incorporate color distributions of the entire dataset. In this paper, we design a novel machine learning-based model that takes advantage of whole dataset distributions as well as color statistics of a single target image instead of relying only on a single target image. The proposed deep model, called stain acclimation generative adversarial network (SA-GAN), consists of one generator and two discriminators. The generator maps the input images from the source domain to the target domain. Among discriminators, the first discriminator forces the generated images to maintain the color patterns as of target domain. While second discriminator forces the generated images to preserve the structure contents as of source domain. The proposed model is trained using a color attribute metric, extracted from a selected template image. Therefore, the designed model not only learns dataset-specific staining properties but also image-specific textural contents. Evaluated results on four different histopathology datasets show the efficacy of SA-GAN to acclimate stain contents and enhance the quality of normalization by obtaining the highest values of performance metrics. Additionally, the proposed method is also evaluated for multiclass cancer type classification task, showing a 6.9% improvement in accuracy on ICIAR 2018 hidden test data.

Electric vehicles’ (EVs) technology is currently emerging as an alternative of traditional Internal Combustion Engine (ICE) vehicles. EVs have been treated as an efficient way for decreasing the production of harmful greenhouse gasses and saving the depleting natural oil reserve. The modern power system tends to be more sustainable with the support of electric vehicles (EVs). However, there have been serious concerns about the network’s safe and reliable operation due to the increasing penetration of EVs into the electric grid. Random or uncoordinated charging activities cause performance degradations and overloading of the network asset. This paper proposes an Optimal Charging Starting Time (OCST)-based coordinated charging algorithm for unplanned EVs’ arrival in a low voltage residential distribution network to minimize the network power losses. A time-of-use (ToU) tariff scheme is used to make the charging course more cost effective. The concept of OCST takes the departure time of EVs into account and schedules the overnight charging event in such a way that minimum network losses are obtained, and EV customers take more advantages of cost-effective tariff zones of ToU scheme. An optimal solution is obtained by employing Binary Evolutionary Programming (BEP). The proposed algorithm is tested on IEEE-31 bus distribution system connected to numerous low voltage residential feeders populated with different EVs’ penetration levels. The results obtained from the coordinated EV charging without OCST are compared with those employing the concept of OCST. The results verify that incorporation of OCST can significantly reduce network power losses, improve system voltage profile and can give more benefits to the EV customers by accommodating them into low-tariff zones.

Doi:10.1093/comjnl/bxaa134 Comp J 2020;00(0): xxxx–xxxx