Fires in smart cities can have devastating consequences, causing damage to property, and endangering the lives of citizens. Traditional fire detection methods have limitations in terms of accuracy and speed, making it challenging to detect fires in real time. This paper proposes an improved fire detection approach for smart cities based on the YOLOv8 algorithm, called the smart fire detection system (SFDS), which leverages the strengths of deep learning to detect fire-specific features in real time. The SFDS approach has the potential to improve the accuracy of fire detection, reduce false alarms, and be cost-effective compared to traditional fire detection methods. It can also be extended to detect other objects of interest in smart cities, such as gas leaks or flooding. The proposed framework for a smart city consists of four primary layers: (i) Application layer, (ii) Fog layer, (iii) Cloud layer, and (iv) IoT layer. The proposed algorithm utilizes Fog and Cloud computing, along with the IoT layer, to collect and process data in real time, enabling faster response times and reducing the risk of damage to property and human life. The SFDS achieved state-of-the-art performance in terms of both precision and recall, with a high precision rate of 97.1% for all classes. The proposed approach has several potential applications, including fire safety management in public areas, forest fire monitoring, and intelligent security systems.

Water quality is very dominant for humans, animals, plants, industries, and the environment. In the last decades, the quality of water has been impacted by contamination and pollution. In this paper, the challenge is to anticipate Water Quality Index (WQI) and Water Quality Classification (WQC), such that WQI is a vital indicator for water validity. In this study, parameters optimization and tuning are utilized to improve the accuracy of several machine learning models, where the machine learning techniques are utilized for the process of predicting WQI and WQC. Grid search is a vital method used for optimizing and tuning the parameters for four classification models and also, for optimizing and tuning the parameters for four regression models. Random forest (RF) model, Extreme Gradient Boosting (Xgboost) model, Gradient Boosting (GB) model, and Adaptive Boosting (AdaBoost) model are used as classification models for predicting WQC. K-nearest neighbor (KNN) regressor model, decision tree (DT) regressor model, support vector regressor (SVR) model, and multi-layer perceptron (MLP) regressor model are used as regression models for predicting WQI. In addition, preprocessing step including, data imputation (mean imputation) and data normalization were performed to fit the data and make it convenient for any further processing. The dataset used in this study includes 7 features and 1991 instances. To examine the efficacy of the classification approaches, five assessment metrics were computed: accuracy, recall, precision, Matthews's Correlation Coefficient (MCC), and F1 score. To assess the effectiveness of the regression models, four assessment metrics were computed: Mean Absolute Error (MAE), Median Absolute Error (MedAE), Mean Square Error (MSE), and coefficient of determination (R²). In terms of classification, the testing findings showed that the GB model produced the best results, with an accuracy of 99.50% when predicting WQC values. According to the experimental results, the MLP regressor model outperformed other models in regression and achieved an R² value of 99.8% while predicting WQI values.

Diagnosing a brain tumor takes a long time and relies heavily on the radiologist’s abilities and experience. The amount of data that must be handled has increased dramatically as the number of patients has increased, making old procedures both costly and ineffective. Many researchers investigated a variety of algorithms for detecting and classifying brain tumors that were both accurate and fast. Deep Learning (DL) approaches have recently been popular in developing automated systems capable of accurately diagnosing or segmenting brain tumors in less time. DL enables a pre-trained Convolutional Neural Network (CNN) model for medical images, specifically for classifying brain cancers. The proposed Brain Tumor Classification Model based on CNN (BCM-CNN) is a CNN hyperparameters optimization using an adaptive dynamic sine-cosine fitness grey wolf optimizer (ADSCFGWO) algorithm. There is an optimization of hyperparameters followed by a training model built with Inception-ResnetV2. The model employs commonly used pre-trained models (Inception-ResnetV2) to improve brain tumor diagnosis, and its output is a binary 0 or 1 (0: Normal, 1: Tumor). There are primarily two types of hyperparameters: (i) hyperparameters that determine the underlying network structure; (ii) a hyperparameter that is responsible for training the network. The ADSCFGWO algorithm draws from both the sine cosine and grey wolf algorithms in an adaptable framework that uses both algorithms’ strengths. The experimental results show that the BCM-CNN as a classifier achieved the best results due to the enhancement of the CNN’s performance by the CNN optimization’s hyperparameters. The BCM-CNN has achieved 99.98% accuracy with the BRaTS 2021 Task 1 dataset.

Crop Recommendation Systems are invaluable tools for farmers, assisting them in making informed decisions about crop selection to optimize yields. These systems leverage a wealth of data, including soil characteristics, historical crop performance, and prevailing weather patterns, to provide personalized recommendations. In response to the growing demand for transparency and interpretability in agricultural decision-making, this study introduces XAI-CROP an innovative algorithm that harnesses eXplainable artificial intelligence (XAI) principles. The fundamental objective of XAI-CROP is to empower farmers with comprehensible insights into the recommendation process, surpassing the opaque nature of conventional machine learning models. The study rigorously compares XAI-CROP with prominent machine learning models, including Gradient Boosting (GB), Decision Tree (DT), Random Forest (RF), Gaussian Naïve Bayes (GNB), and Multimodal Naïve Bayes (MNB). Performance evaluation employs three essential metrics: Mean Squared Error (MSE), Mean Absolute Error (MAE), and R-squared (R2). The empirical results unequivocally establish the superior performance of XAI-CROP. It achieves an impressively low MSE of 0.9412, indicating highly accurate crop yield predictions. Moreover, with an MAE of 0.9874, XAI-CROP consistently maintains errors below the critical threshold of 1, reinforcing its reliability. The robust R² value of 0.94152 underscores XAI-CROP's ability to explain 94.15% of the data's variability, highlighting its interpretability and explanatory power.

Diagnosis of autism considers a challenging task for medical experts since the medical diagnosis mainly depends on the abnormalities in the brain functions that may not appear in the early stages of early onset of autism disorder. Facial expression can be an alternative and efficient solution for the early diagnosis of Autism. This is due to Autistic children usually having distinctive patterns which facilitate distinguishing them from normal children. Assistive technology has proven to be one of the most important innovations in helping people with autism improve their quality of life. A real-time emotion identification system for autistic youngsters was developed in this study. Face identification, facial feature extraction, and feature categorization are the three stages of emotion recognition. A total of six facial emotions are detected by the propound system: anger, fear, joy, natural, sadness, and surprise. This section proposes an enhanced deep learning (EDL) technique to classify the emotions using convolutional neural network. The proposed emotion detection framework takes the benefit from using fog and IoT to reduce the latency for real-time detection with fast response and to be a location awareness. From the results, EDL outperforms other techniques as it achieved 99.99% accuracy. EDL used GA to select the optimal hyperparameters for the CNN.