Purpose: The purpose of this paper is to investigate the sources of self-efficacy that researchers rely on when using social media for knowledge sharing and to explore how these sources impact their use.Design/methodology/approach: The study employed 30 semi-structured interviews with researchers at a major Scottish university. The authors analysed the interview transcriptions using directed content analysis.Findings: The researchers relied on the four sources of self-efficacy proposed by Bandura (1977) when using social media for knowledge sharing. These sources lead researchers to use social media effectively and frequently for sharing knowledge, although some may discourage its use.Research limitations/implications: It extends the self-efficacy integrative theoretical framework of Bandura (1977) by presenting the relative amount of the influence of these sources for researchers to share their ideas, experiences, questions and research outputs on social media. While the participants included academic staff, postdoctoral researchers, and PhD students, the majority were PhD students.Practical implications: The findings can help universities understand how to promote productive use of social media. For example, academic staff who have high personal mastery experience could mentor those who do not.Originality/value: This is the first known study to investigate the sources of self-efficacy that impact researchers’ use of social media for knowledge sharing.

Purpose: The purpose of this paper is to investigate sources of self-efficacy for researchers and the sources’ impact on the researchers’ use of social media for knowledge sharing. It is a continuation of a larger study (Alshahrani and Rasmussen Pennington, 2018). Design/methodology/approach: The authors distributed an online questionnaire to researchers at the University of Strathclyde (n=144) and analysed the responses using descriptive statistics. Findings: Participants relied on personal mastery experience, vicarious experience, verbal persuasion and emotional arousal for social media use. These elements of self-efficacy mostly led them to use it effectively, with a few exceptions. Research limitations/implications: The convenience sample utilised for this study, which included academic staff, researchers and PhD students at one university, is small and may not be entirely representative of the larger population. Practical implications: This study contributes to the existing literature on social media and knowledge sharing. It can help researchers understand how they can develop their self-efficacy and its sources in order to enhance their online professional presence. Additionally, academic institutions can use these results to inform how they can best encourage and support their researchers in improving their professional social media use. Originality/value: Researchers do rely on their self-efficacy and its sources to use social media for knowledge sharing. These results can help researchers and their institutions eliminate barriers and improve online engagement with colleagues, students, the public and other relevant research stakeholders.

Smart farming helps to increase yield by smartly deciding the steps that should be practised in the season. A few components of precision farming are recommending the crops for cultivation, predicting the weather conditions, examining the soil; determining the pesticides, and fertilizers that have to be used. Smart Farming utilizes advanced technologies namely data mining (DM), machine learning (ML), the Internet of Things (IoT), and data analytics for collecting the data, predicting the outcomes and training the system. One of the most significant parameters is proper soil prediction which decides the proper crop and is manually executed by the agriculturalists. Hence, the farmer’s efficacy can be improved by producing automated tools for soil type classification. This study presents a Chaotic Jaya Optimization Algorithm with Computer Vision based Soil Type Classification (CJOCV-STC) for smart farming. The presented CJOCV-STC technique applies CV with metaheuristic algorithms for the automated soil classification process, which identifies the soil into distinct types. To accomplish this, the presented CJOCV-STC technique uses the SqueezeNet model for producing a set of feature vectors. To improve the performance of the SqueezeNet model, the CJO algorithm is used for the hyperparameter tuning process. Moreover, the Elman neural network (ENN) technique is applied for soil type classification and the parameters related to it can be adjusted by the chicken swarm algorithm (CSA). The soil classification performance of the CJOCV-STC method can be studied on the Kaggle dataset and the outcomes stated the better performance of the CJOCV-STC algorithm over other recent approaches with increased accuracy of 98.47%.

Computed Tomography (CT) is one of the biomedical imaging modalities which are used to confirm COVID-19 cases and/or to identify infected areas in the lung. Therefore, this article aims at assisting this crucial radiological task by proposing squeeze-and-excitation networks (SENets) within the Internet of medical things (IoMT) framework for automated segmentation of COVID-19 infections in lung CT images. The proposed SE block has been directly integrated with deep residual networks to form Seresnets based on U-Net and LinkNet models. Extensive tests were conducted on a public COVID-19 CT dataset including 20 cases and 1800 + annotated slices to evaluate the segmentation results of our proposed method. The proposed Seresnet models showed a good performance with a Dice score of 0.73, structure similarity index of 0.98, enhanced alignment measure of 0.98, and mean absolute error of 0.06. This study demonstrated a new advanced tool for radiologists to achieve automatic segmentation of the COVID-19 infected areas using CT scans. The main prospect of this research work is deploying our proposed IoMT segmentation framework in the medical diagnosis routine of positive COVID-19 patients.

Computational linguistics explores how human language is interpreted automatically and then processed. Research in this area takes the logical and mathematical features of natural language and advances methods and statistical procedures for automated language processing. Slot filling and intent detection are significant modules in task-based dialogue systems. Intent detection is a critical task in any natural language understanding (NLU) system and constitutes the base of a task-based dialogue system. In order to build high-quality, real-time conversational solutions for edge gadgets, there is a demand for deploying intent-detection methods on devices. This mandates an accurate, lightweight, and fast method that effectively operates in a resource-limited environment. Earlier works have explored the usage of several machine-learning (ML) techniques for detecting intent in user queries. In this article, we propose Computational Linguistics with Deep-Learning-Based Intent Detection and Classification (CL-DLBIDC) for natural language understanding. The presented CL-DLBIDC technique receives word embedding as input and learned meaningful features to determine the probable intention of the user query. In addition, the presented CL-DLBIDC technique uses the GloVe approach. In addition, the CL-DLBIDC technique makes use of the deep learning modified neural network (DLMNN) model for intent detection and classification. For the hyperparameter tuning process, the mayfly optimization (MFO) algorithm was used in this study. The experimental analysis of the CL-DLBIDC method took place under a set of simulations, and the results were scrutinized for distinct aspects. The simulation outcomes demonstrate the significant performance of the CL-DLBIDC algorithm over other DL models.

The Federated learning (FL) technique resolves the issue of training machine learning (ML) techniques on distributed networks, including the huge volume of modern smart devices. FL clients frequently use Wi-Fi and have to interact in unstable network surroundings. However, as the present FL aggregation approaches receive and send a large number of weights, accuracy can be decreased considerably in unstable network surroundings. Therefore, this study presents a Quantum with Metaheuristics Algorithm Based Minimization of Communication Costs in Federated Learning (QMAMCC-FL) technique. The presented QMAMCC-FL technique is designed a federated hybrid convolutional neural network with a gated recurrent unit (HCNN-GRU) model with a quantum Aquila optimization (QAO) algorithm. The QMAMCC-FL technique upgrades the global model via weight collection of the learned model, which is commonly used in FL. The proposed model can be employed to increase the performance of network communication and reduce the size of data transmitted from clients to servers such as smartphones and tablets. The experimental analysis of the QMAMCC-FL approach is tested, and the outcomes show better performance over other existing models.