In this paper, we propose an imagined speech-based brain wave pattern recognition using deep learning. Multiple features were extracted concurrently from eight-channel electroencephalography (EEG) signals. To obtain classifiable EEG data with fewer sensors, we placed the EEG sensors on carefully selected spots on the scalp. To decrease the dimensions and complexity of the EEG dataset and to avoid overfitting during the deep learning algorithm, we utilized the wavelet scattering transformation. A low-cost 8-channel EEG headset was used with MATLAB 2023a to acquire the EEG data. The long-short term memory recurrent neural network (LSTM-RNN) was used to decode the identified EEG signals into four audio commands: up, down, left, and right. Wavelet scattering transformation was applied to extract the most stable features by passing the EEG dataset through a series of filtration processes. Filtration was implemented for each individual command in the EEG datasets. The proposed imagined speech-based brain wave pattern recognition approach achieved a 92.50% overall classification accuracy. This accuracy is promising for designing a trustworthy imagined speech-based brain–computer interface (BCI) future real-time systems. For better evaluation of the classification performance, other metrics were considered, and we obtained 92.74%, 92.50%, and 92.62% for precision, recall, and F1-score, respectively.

Autonomous wheelchairs are important tools to enhance the mobility of people with disabilities. Advances in computer and wireless communication technologies have contributed to the provision of smart wheelchairs to suit the needs of the disabled person. This research paper presents the design and implementation of a voice controlled electric wheelchair. This design is based on voice recognition algorithms to classify the required commands to drive the wheelchair. An adaptive neuro-fuzzy controller has been used to generate the required real-time control signals for actuating motors of the wheelchair. This controller depends on real data received from obstacle avoidance sensors and a voice recognition classifier. The wheelchair is considered as a node in a wireless sensor network in order to track the position of the wheelchair and for supervisory control. The simulated and running experiments demonstrate that, by combining the concepts of soft-computing and mechatronics, the implemented wheelchair has become more sophisticated and gives people more mobility.

The object detection technique depends on various methods for duplicating the dataset without adding more images. Data augmentation is a popular method that assists deep neural networks in achieving better generalization performance and can be seen as a type of implicit regularization. This method is recommended in the case where the amount of high-quality data is limited, and gaining new examples is costly and time-consuming. In this paper, we trained YOLOv7 with a dataset that is part of the Open Images dataset that has 8,600 images with four classes (Car, Bus, Motorcycle, and Person). We used five different data augmentations techniques for duplicates and improvement of our dataset. The performance of the object detection algorithm was compared when using the proposed augmented dataset with a combination of two and three types of data augmentation with the result of the original data. The evaluation result for the augmented data gives a promising result for every object, and every kind of data augmentation gives a different improvement. The mAP@.5 of all classes was 76%, and F1-score was 74%. The proposed method increased the mAP@.5 value by +13% and F1-score by +10% for all objects.

Unmanned Aerial Vehicles (UAVs) proliferate quickly and play a significant part in crucial tasks, so it is important to protect the security and integrity of UAV communication channels. Intrusion Detection Systems (IDSs) are required to protect the UAV communication infrastructure from unauthorized access and harmful actions. In this paper, we examine a new approach for enhancing intrusion detection in UAV communication channels by utilizing the Long Short-Term Memory network (LSTM) combined with the Synthetic Minority Oversampling Technique (SMOTE) algorithm, and this integration is the binary classification method (LSTM-SMOTE). We successfully achieved 99.83% detection accuracy by using the proposed approach and the Canadian Institute for Cybersecurity Intrusion Detection Evaluation Dataset 2017 (CICIDS2017) dataset. We demonstrated the efficiency of LSTM-SMOTE in defending UAV communication channels against possible attacks and bolstering the overall security posture through the use of a real-world scenario.

Autonomous agents can explore the environment around them when equipped with advanced hardware and software systems that help intelligent agents minimize collisions. These systems are developed under the term Artificial Intelligence (AI) safety. AI safety is essential to provide reliable service to consumers in various fields such as military, education, healthcare, and automotive. This paper presents the design of an AI safety algorithm for safe autonomous navigation using Reinforcement Learning (RL). Machine Learning Agents Toolkit (ML-Agents) was used to train the agent with a proximal policy optimizer algorithm with an intrinsic curiosity module (PPO + ICM). This training aims to improve AI safety and minimize or prevent any mistakes that can cause dangerous collisions by the intelligent agent. Four experiments have been executed to validate the results of our research. The designed algorithm was tested in a virtual environment with four different models. A comparison was presented in four cases to identify the best-performing model for improving AI safety. The designed algorithm enabled the intelligent agent to perform the required task safely using RL. A goal collision ratio of 64% was achieved, and the collision incidents were minimized from 134 to 52 in the virtual environment within 30 min.

Autonomous wheelchairs are essential for improving the mobility of individuals with disabilities or physical challenges. Advances in computer and wireless communication technologies have paved the way for the design of smart wheelchairs to match the needs of disabled people. This research paper introduces the design and implementation of an electric wheelchair controller using voice recognition. This model is based on a voice recognition algorithm for classifying the essential commands to drive the wheelchair. A pre-designed adaptive neuro-fuzzy controller has been used to generate the required control signals for activating the motors of the wheelchair. This controller alters data gathered from obstacle avoidance sensors and a voice recognition classifier. Deep learning algorithms have made many technological developments and influences modern daily lives. After testing our developed deep learning algorithm, the overall classification accuracy for distinguishing between eight voice commands was 98 %.