Search

Greenhouse cultivation plays a pivotal role in modern agriculture by providing a controlled environment for plant growth. The significance of greenhouse insulation lies in its ability to create optimal conditions for plant development, ensuring increased crop productivity and quality. This paper emphasizes the criticality of greenhouse insulation and the necessity for effective predictive models to anticipate plant growth and yield accurately. This research proposes the utilization of Machine Learning (ML)and Deep Learning (DL) techniques to forecast plant growth and yield within controlled greenhouse settings. To achieve this, a novel deep recurrent neural network (RNN) architecture employing the Long Short-Term Memory (LSTM) neuron model is deployed in the prediction process.The study offers a comparative analysis involving various ML methodologies such as support vector regression and random forest regression. The performance evaluation of these diverse methods is conducted using the mean square error criterion to assess their effectivenessin predicting plant growth and yield. The model's sophisticated architecture enables it to produce accurate and timely predictions regarding specific growth parameters by leveraging an advanced neural network. This holistic approach introduces a novel perspective in greenhouse tomato cultivation, providing growers with valuable insights to facilitate informed decision-making, streamline resource distribution, and promote heightened agricultural sustainability.

Skin cancer is the most lethal because skin cells develop abnormally. Finding skin cancer early is very important and may help stop some kinds of skin cancer, like melanoma and focal cell carcinoma. Early detection and classification of skin cancer are difficult and costly. Recurrent networks and ConvNets can automatically extract complex data. This paper proposes to use a handmade features-based multi-layer perceptron and a cascaded ensembled network to upgrade ConvNet models. This convolutional neural network model detects non-handmade picture qualities and generates features like color moments and material properties. With ensembled DL, accuracy increased from 85.3% with convolutional neural networks to 98.3%.

Efficient traffic flow prediction is paramount in modern urban transportation management, contributing significantly to energy efficiency and overall sustainability. Traditional traffic prediction models often struggle in complex urban traffic networks, especially at multi-intersection junctions. In response to this challenge, this research paper presents a pioneering approach that not only enhances traffic flow prediction accuracy but also indirectly supports energy efficiency. This study leverages deep learning techniques, specifically the Gated Recurrent Unit (GRU), to analyze traffic patterns simultaneously at multiple intersections within a city. By treating the entire traffic network as a distributed system, the model provides real-time predictions, allowing for better traffic management and reduced fuel consumption. Moreover, the incorporation of data fusion techniques, which integrate data from various sources, including traffic sensors and historical traffic information, bolsters the accuracy and robustness of predictions. By predicting traffic flows with precision, this research aids in optimizing traffic signal timing, reducing congestion, and ultimately promoting more efficient transportation systems, which, in turn, reduces fuel wastage and emissions. This study, therefore, advances intelligent transportation systems and offers a promising pathway toward improved energy efficiency in urban mobility.

The utilization of neural model techniques for predicting learner performance has exhibited success across various technical domains, including natural language processing. In recent times, researchers have progressively directed their attention towards employing these methods to contribute to socioeconomic sustainability, particularly in the context of forecasting student academic performance. Additionally, educational data frequently encompass numerous categorical variables, and the efficacy of prediction models becomes intricately tied to sustainable encoding techniques applied to manage and interpret this data. This approach aligns with the broader goal of fostering sustainable development in education, emphasizing responsible and equitable practices in leveraging advanced technologies for enhanced learning outcomes. Building on this insight, this paper presents a literature review that delves into the use of machine learning techniques for predicting learner outcomes in online training courses. The objective is to offer a summary of the most recent models designed for forecasting student performance, categorical coding methodologies, and the datasets employed. The research conducts experiments to assess the suggested models both against each other and in comparison to certain prediction techniques utilizing alternative machine learning algorithms concurrently. The findings suggest that employing the encoding technique for transforming categorical data enhances the effectiveness of deep learning architectures. Notably, when integrated with long short-term memory networks, this strategy yields exceptional results for the examined issue.