Wildfire risk has globally increased during the past few years due to several factors. An efficient and fast response to wildfires is extremely important to reduce the damaging effect on humans and wildlife. This work introduces a methodology for designing an efficient machine learning system to detect wildfires using satellite imagery. A convolutional neural network (CNN) model is optimized to reduce the required computational resources. Due to the limitations of images containing fire and seasonal variations, an image augmentation process is used to develop adequate training samples for the change in the forest’s visual features and the seasonal wind direction at the study area during the fire season. The selected CNN model (MobileNet) was trained to identify key features of various satellite images that contained fire or without fire. Then, the trained system is used to classify new satellite imagery and sort them into fire or no fire classes. A cloud-based development studio from Edge Impulse Inc. is used to create a NN model based on the transferred learning algorithm. The effects of four hyperparameters are assessed: input image resolution, depth multiplier, number of neurons in the dense layer, and dropout rate. The computational cost is evaluated based on the simulation of deploying the neural network model on an Arduino Nano 33 BLE device, including Flash usage, peak random access memory (RAM) usage, and network inference time. Results supported that the dropout rate only affects network prediction performance; however, the number of neurons in the dense layer had limited effects on performance and computational cost. Additionally, hyperparameters such as image size and network depth significantly impact the network model performance and the computational cost. According to the developed benchmark network analysis, the network model MobileNetV2, with 160 × 160 pixels image size and 50% depth reduction, shows a good classification accuracy and is about 70% computationally lighter than a full-depth network. Therefore, the proposed methodology can effectively design an ML application that instantly and efficiently analyses imagery from a spacecraft/weather balloon for the detection of wildfires without the need of an earth control centre.

Outlier measurements often presence when locating an object from a number of sensors, which could decrease the positioning performance considerably. This paper addresses the problem of outlier detection in locating an object using TOA measurements. The detection is based on the construction of a spectral graph through pairwise intersection between the lines of position from a measurement pair. Crucial to this technique is the determination for intersection, and we have derived such conditions for 2-D and 3-D positionings. The detected outliers are removed and the remaining measurements are used for the Maximum Likelihood estimator to obtain the object position. Simulation shows that the proposed outlier detection method is very effective with the probability of detection and the probability of false alarms examined. The positioning accuracy is able to reach the CRLB performance after removing the detected outliers.

The presence of measurement outliers can significantly reduce the performance of a localization algorithm. Detection and removal of the outliers are crucial to improve the positioning accuracy. This paper proposes new features together with an Artificial Neural Network (ANN) for outlier detection, where the outlier statistics and the number of outliers are not known a priori. The features reflect the quality of a location estimate using a subset of the measurements and are effective for use with an ANN of two hidden layers for outlier detection. Simulations demonstrate the ability of the proposed method in handling various number of outliers and providing the Cramèr-Rao lower bound (CRLB) localization accuracy under Gaussian noise, and show that it maintains 100% correct detection of outliers while keeping the false detection at a minimum level. The proposed method can work with elliptic and hyperbolic positioning in 2-D and 3-D.

Remote surveying of unknown bound geometries, such as the mapping of underground water supplies and tunnels, remains a challenging task. The obstacles and absorption in media make the long-distance telecommunication and localization process inefficient due to mobile sensors’ power limitations. This work develops a new short-range sequential localization approach to reduce the required amount of signal transmission power. The developed algorithm is based on a sequential localization process that can utilize a multitude of randomly distributed wireless sensors while only employing several anchors in the process. Time delay elliptic and frequency range techniques are employed in developing the proposed algebraic closed-form solution. The proposed method is highly effective as it reaches the Cramer–Rao Lower Bound performance level. The estimated positions can act as initializations for the iterative Maximum Likelihood Estimator (MLE) via the Taylor series linearization to acquire even higher positioning accuracy as needed. By reducing the need for high power at the transmit modules in the sensors, the developed localization approach can be used to design a compact sensor with low power consumption and greater longevity that can be utilized to explore unknown bounded geometries for life-long efficient observation mapping.

This paper proposes a neuro-fuzzy system to model $\beta$-glucosidase activity based on the reaction’s pH level and temperature. The developed fuzzy inference system includes two input variables (pH level and temperature) and one output (enzyme activity). The multi-input fuzzy inference system was developed in two stages: first, developing a single input-single output fuzzy inference system for each input variable (pH, temperature) separately, using the robust adaptive network-based fuzzy inference system (ANFIS) approach. The neural network learning techniques were used to tune the membership functions based on previously published experimental data for $\beta$-glucosidase. Second, each input’s optimized membership functions from the ANFIS technique were embedded in a new fuzzy inference system to simultaneously encompass the impact of temperature and pH level on the activity of $\beta$-glucosidase. The required base rules for the developed fuzzy inference system were created to describe the antecedent (pH and temperature) implication to the consequent (enzyme activity), using the singleton Sugeno fuzzy inference technique. The simulation results from the developed models achieved high accuracy. The neuro-fuzzy approach performed very well in predicting $\beta$-glucosidase activity through comparative analysis. The proposed approach may be used to predict enzyme kinetics for several nonlinear biosynthetic processes.