Accurate drug-drug interaction (DDI) prediction is essential to prevent adverse effects, especially with the increased use of multiple medications during the COVID-19 pandemic. Traditional machine learning methods often miss the complex relationships necessary for effective DDI prediction. This study introduces a deep learning-based classification framework to assess adverse effects from interactions between Fluvoxamine and Curcumin. Our model integrates a wide range of drug-related data (e.g., molecular structures, targets, side effects) and synthesizes them into high-level features through a specialized deep neural network (DNN). This approach significantly outperforms traditional classifiers in accuracy, precision, recall, and F1-score. Additionally, our framework enables real-time DDI monitoring, which is particularly valuable in COVID-19 patient care. The model’s success in accurately predicting adverse effects demonstrates the potential of deep learning to enhance drug safety and support personalized medicine, paving the way for safer, data-driven treatment strategies.

The purpose of Vehicular Ad Hoc Network (VANET) is to provide users with better information services through effective communication. For this purpose, IEEE 802.11p proposes a protocol standard based on enhanced distributed channel access (EDCA) contention. In this standard, the backoff algorithm randomly adopts a lower bound of the contention window (CW) that is always fixed at zero. The problem that arises is that in severe network congestion, the backoff process will choose a smaller value to start backoff, thereby increasing conflicts and congestion. The objective of this paper is to solve this unbalanced backoff interval problem in saturation vehicles and this paper proposes a method that is a deep neural network Q-learning-based channel access algorithm (DQL-CSCA), which adjusts backoff with a deep neural network Q-learning algorithm according to vehicle density. Network simulation is conducted using NS3, the proposed algorithm is compared with the CSCA algorithm. The find is that DQL-CSCA can better reduce EDCA collisions.

Human settlement patterns in the South are clearly inequitable and dysfunctional, with tenure insecurity remaining a significant issue. Consequently, there has been a dramatic increase in housing demand driven by rising household sizes and accelerated urbanization. Local governments have a clear mandate to ensure socio-economic development and promote democracy, which necessitates ongoing consultations and renegotiations with citizens. This paper critically examines the de-densification of informal settlements as a pivotal strategy to enhance the quality of life for citizens, all while maintaining essential social networks. Governments must take decisive action against pandemics by transforming spaces into liveable settlements that improve livelihoods. A qualitative method was employed, analyzing data drawn from interviews to gain insights into individual views, attitudes, and behaviors regarding the improvement of livelihoods in informal settlements. The study utilized a simple random sampling technique, ensuring that every individual in the population selected had an equal opportunity for inclusion. Semi-structured interviews were conducted with twenty community members in Cornubia, alongside discussions with three officials from eThekwini Municipality and KwaZulu Natal (KZN) Provincial Department of Human Settlements. Data was analyzed using thematic analysis, and the findings hold substantial benefits for the most disadvantaged citizens. Therefore, municipalities have an obligation to transform urban areas by reducing inequality, bolstered by national government policy, to achieve a resilient, safe, and accessible urban future. The evidence presented in this paper underscores that local governments, through municipalities, must prioritize de-densifying informal settlements in response to pandemics or hazards. It is vital to leverage community-driven initiatives and reinforce networks within these communities. The paper calls for the establishment of a socially centered government through the District Development Model (DDM), emphasizing socio-economic transformation as a pathway to enhance community quality of life.

The evolution of the internet has led to the emergence of social media (SM) platforms, offering dynamic environments for user interaction and content creation. Social media, characterized by user-generated content, has become integral to electronic communication, fostering higher engagement and interaction. This study aims to explore the utilization of SM marketing, particularly in Higher Education Institutions (HEIs), focusing on Széchenyi István University’s academic social network sites (SNS) as a case study to enhance student engagement and satisfaction. The primary objective of this study is to review recent academic literature on SM marketing, especially for HEI marketing, and investigate the potential of the University’s SNS platforms as a case study in increasing student engagement. First a systematic literature review was conducted using Scopus and Science Direct databases to analyze recent research in academic SM. Then the article examined the University’s website and SNS platforms using the Facepager program to collect and analyze posts’ content. The findings from the literature review and observation indicate the growing importance of SM in higher education marketing. The university’s use of various SM strategies, such as visual storytelling, multimedia content, blogs, and user-generated content, contributes to increased student engagement of the university’s values.

This research presents a novel approach utilizing a self-enhanced chimp optimization algorithm (COA) for feature selection in crowdfunding success prediction models, which offers significant improvements over existing methods. By focusing on reducing feature redundancy and improving prediction accuracy, this study introduces an innovative technique that enhances the efficiency of machine learning models used in crowdfunding. The results from this study could have a meaningful impact on how crowdfunding campaigns are designed and evaluated, offering new strategies for creators and investors to increase the likelihood of campaign success in a rapidly evolving digital funding landscape.

Among contemporary computational techniques, Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are favoured because of their capacity to tackle non-linear modelling and complex stochastic datasets. Nondeterministic models involve some computational intricacies when deciphering real-life problems but always yield better outcomes. For the first time, this study utilized the ANN and ANFIS models for modelling power generation/electric power output (EPO) from databases generated in a combined cycle power plant (CCPP). The study presents a comparative study between ANNs and ANFIS to estimate the power output generation of a combined cycle power plant in Turkey. The inputs of the ANN and ANFIS models are ambient temperature (AT), ambient pressure (AP), relative humidity (RH), and exhaust vacuum (V), correlated with electric power output. Several models were developed to achieve the best architecture as the number of hidden neurons varied for the ANNs, while the training process was conducted for the ANFIS model. A comparison of the developed hybrid models was completed using statistical criteria such as the coefficient of determination (R²), mean average error (MAE), and average absolute deviation (AAD). The R² of 0.945, MAE of 3.001%, and AAD of 3.722% for the ANN model were compared to those of R² of 0.9499, MAE of 2.843% and AAD of 2.842% for the ANFIS model. Even though both ANN and ANFIS are relevant in estimating and predicting power production, the ANFIS model exhibits higher superiority compared to the ANN model in accurately estimating the EPO of the CCPP located in Turkey and its environment.