Monkeypox or Mpox is an infectious virus predominantly found in Africa. It has spread to many countries since its latest outbreak. Symptoms such as headaches, chills, and fever are observed in humans. Lumps and rashes also appear on the skin (similar to smallpox, measles, and chickenpox). Many artificial intelligence (AI) models have been developed for accurate and early diagnosis. In this work, we systematically reviewed recent studies that used AI for mpox-related research. After a literature search, 34 studies fulfilling prespecified criteria were selected with the following subject categories: diagnostic testing of mpox, epidemiological modeling of mpox infection spread, drug and vaccine discovery, and media risk management. In the beginning, mpox detection using AI and various modalities was described. Other applications of ML and DL in mitigating mpox were categorized later. The various machine and deep learning algorithms used in the studies and their performance were discussed. We believe that a state-of-the-art review will be a valuable resource for researchers and data scientists in developing measures to counter the mpox virus and its spread.

Reducing carbon monoxide (CO) emissions is imperative for safeguarding human health and environment. CO adversely affects respiratory health, contributing to respiratory problems and, in severe cases, fatalities. Its reduction aligns with the broader efforts to combat climate change, as CO is often emitted alongside other greenhouse gases. Environmental consequences include air pollution and its detrimental impact on ecosystems. Compliance with emission standards is essential, and reducing Carbon emissions can lead to social and economic benefits, such as increased productivity and reduced healthcare costs. Moreover, the focus on emission reduction drives technological innovation, fostering the development of cleaner and sustainable technologies. In essence, addressing CO emissions is vital for creating a healthier, more sustainable future. However, in most of the cases, there has been no much importance given in scientific management of solid wastes. This has therefore resulted in large magnitude of carbon emission causing serious implications. This paper presents a novel approach to solid waste management, combining carbon emission assessment with advanced object detection technology. We develop an integrated waste management model that employs machine learning techniques for the identification and categorization of metals, non-metals, and plastics within the solid waste stream. To optimize waste sorting and recycling processes, we implement an efficient object detection system that leverages computer vision algorithms. This system enhances the precision of material identification within solid waste, thereby improving sorting accuracy. Additionally, we establish a database to quantify carbon emissions associated with distinct waste management methods, encompassing incineration, composting, recycling, bioremediation, and landfills is used for this work. The novelty of the work lies in the integration of CO2 emissions data and object detection resulting into a decision-making model, providing a holistic evaluation of the environmental impact of varied waste management scenarios. The formulation of recommendations for sustainable waste management practices based on the integrated assessment of carbon footprints and material identification is easy to implement in real world.The technical framework proposed here, aims to inform decision-makers on adopting environmentally conscious strategies for waste management.

The economy of developing nations is heavily reliant on agriculture. For agriculture to remain sustainable and productive, a number of important challenges must be addressed. Plant diseases are among the most alarming issues. To address the challenge of identifying plant diseases from drone-captured images, which often lack sufficient resolution and may lead to mis-classification, we propose Vision-based Image Generation and Analysis Model (VIGAM) framework as a solution. In this study, we introduce the VIGAM framework, a deep learning model-based solution that shows promise as a useful instrument in a variety of plant protection strategy. This comprehensive method using computer vision-based models aids in the interpretation of plant images taken by drones, which are then used to detect plant diseases and offer accurate diagnosis. Large plant picture databases can be analyzed by ML systems to find early indicators of infections or illnesses. Farmers can quickly respond with tailored treatments or the removal of afflicted plants thanks to image recognition models that can identify patterns and symptoms associated with particular plant diseases. Our method is feasible for real-world agricultural applications, and through experiments, we demonstrate that the proposed framework effectively enhances plant identification and disease detection by incorporating high-resolution drone images.

Reliable forecasting of electricity usage is vital to support economic growth and economic performance. The inherent non-linearity and complex temporal dependencies in energy demand data pose significant challenges for traditional forecasting methods. This report details an extensive investigation into the application of advanced deep learning (DL) architectures for this task. We propose spatial temporal model, namely Spatial-Temporal GRU (ST-GRU), for predicting the electricity consumption. In this work, the term spatial refers to inter-feature relationships within the multivariate input space rather than geographic spatial information. Utilizing a multi-source 15-minute interval dataset, we employ cyclical feature engineering and a sliding window approach to structure the sequential inputs. We conduct a comparative analysis of a diverse suite of sequence models, including baseline GRU and LSTM networks, alongside more sophisticated architectures such as Bidirectional RNNs, Attention-based models, Temporal Convolutional Networks (TCN), Transformers, and Spatial-Temporal models. Our empirical evaluation on a reserved test set reveals that specialized architectures, particularly the Spatial-Temporal Gated Recurrent Unit (ST-GRU), deliver superior predictive accuracy. The proposed ST-GRU reduced RMSE by 6.4% compared to standard GRU and by approximately 25% compared to LSTM on Dataset 1, while maintaining consistent generalization performance across cross-dataset evaluation. The ST-GRU model demonstrates a notable ability to effectively model the inter-feature relationships (spatial dynamics) before capturing their evolution over time (temporal dynamics), resulting in the lowest prediction error. This outcome highlights the substantial potential of architecturally specialized DL frameworks to advance the precision of energy.

Plant diseases are a serious issue that cause food shortages and financial losses. In large-scale farming, traditional disease detection techniques that primarily rely on expert inspection are frequently unfeasible. Deep learning and super-resolution methods for plant disease detection are thoroughly reviewed in this study, with an emphasis on their use in leaf-level imaging and UAV-based monitoring. This thorough review was carried out using the PRISMA framework, looking at peer-reviewed publications from important databases like Google Scholar, ScienceDirect, Web of Science, and Scopus. According to the review, low spatial resolution, environmental variability, occlusion, and domain shift cause convolutional and transformer-based models to perform poorly at canopy and field scales, despite achieving high accuracy on leaf-level datasets. Despite improving the perceptual quality of aerial imagery, super-resolution techniques are still difficult to incorporate into disease detection pipelines because of their high computational overhead, lack of task-aware training, scarcity of annotated UAV datasets, and poor generalization in real-world scenarios. There are few actual architectural implementations of cross-scale integration strategies currently in use; most of them are conceptual. Deep learning for plant disease detection has come a long way, but reliably deploying this technology outside of controlled environments remains challenging due to scale differences and data availability constraints. Coordinated developments in cross-scale learning approaches, data collection, and model design are needed to address these issues. The results also emphasize the significance of multimodal data fusion, super-resolution-assisted domain adaptation, and hierarchical transfer learning as viable approaches to enhancing the scalability and dependability of plant health monitoring systems. This review highlights useful research directions and provides a critical overview of current methods. It encourages the development of AI-powered solutions for better crop management, early disease detection, and sustainable farming methods.

With the revolution of social media, the proper analysis of sentiment expressed through both textual and visual media is one of the most challenging problems. While not all negatively charged memes are harmful, sentiment analysis helps distinguish between general negativity and content that may contribute to online harms, such as cyberbullying, misinformation, or hate speech. Conventional sentiment analysis approaches, which mainly concentrate on text-based content, may miss out on nuanced emotional cues present in images, emojis, or the overall context of a conversation. Subtle negative expressions are often misclassified because models do not effectively learn fine-grained differences between sentiment classes. The existing works having static fusion often lack ability to detect fine-grained or subtle negativity. In this work we propose Gated Contrastive Multimodal Fusion Model that processes the text and image streams in memes, through independent modality-specific neural networks, combined by means of an attention mechanism. The gated fusion block present in our architecture allows the model to pay closer attention to the most sentiment-rich elements. The contrastive block provides an accurate training mechanism to improve the classification of negative memes. Through experiments on benchmark datasets, we show that our methodology provides interpretable insights into the contribution of each modality. Thus, outperform SOTA models and open the door to better identification of online harmful memes.