Ali Ghadami

Mohammad Mohammadzadeh, Ali Ghadami, Alireza Taheri et al.

Human activity recognition is a core technology for applications such as rehabilitation, health monitoring, and human-computer interactions. Wearable devices, especially IMU sensors, provide rich features of human movements at a reasonable cost, which can be leveraged in activity recognition. Developing a robust classifier for activity recognition has always been of interest to researchers. One major problem is that there is usually a deficit of training data, which makes developing deep classifiers difficult and sometimes impossible. In this work, a novel GAN network called TheraGAN was developed to generate IMU signals associated with rehabilitation activities. The generated signal comprises data from a 6-channel IMU, i.e., angular velocities and linear accelerations. Also, introducing simple activities simplified the generation process for activities of varying lengths. To evaluate the generated signals, several qualitative and quantitative studies were conducted, including perceptual similarity analysis, comparing manually extracted features to those from real data, visual inspection, and an investigation into how the generated data affects the performance of three deep classifiers trained on the generated and real data. The results showed that the generated signals closely mimicked the real signals, and adding generated data resulted in a significant improvement in the performance of all tested networks. Among the tested networks, the LSTM classifier demonstrated the most significant improvement, achieving a 13.27% boost, effectively addressing the challenge of data scarcity. This shows the validity of the generated data as well as TheraGAN as a tool to build more robust classifiers in case of imbalanced and insufficient data problems.

Ali Ghadami, Alireza Taheri, Ali Meghdari

Sign language is an essential means of communication for millions of people around the world and serves as their primary language. However, most communication tools are developed for spoken and written languages which can cause problems and difficulties for the deaf and hard of hearing community. By developing a sign language recognition system, we can bridge this communication gap and enable people who use sign language as their main form of expression to better communicate with people and their surroundings. This recognition system increases the quality of health services, improves public services, and creates equal opportunities for the deaf community. This research aims to recognize Iranian Sign Language words with the help of the latest deep learning tools such as transformers. The dataset used includes 101 Iranian Sign Language words frequently used in academic environments such as universities. The network used is a combination of early fusion and late fusion transformer encoder-based networks optimized with the help of genetic algorithm. The selected features to train this network include hands and lips key points, and the distance and angle between hands extracted from the sign videos. Also, in addition to the training model for the classes, the embedding vectors of words are used as multi-task learning to have smoother and more efficient training. This model was also tested on sentences generated from our word dataset using a windowing technique for sentence translation. Finally, the sign language training software that provides real-time feedback to users with the help of the developed model, which has 90.2% accuracy on test data, was introduced, and in a survey, the effectiveness and efficiency of this type of sign language learning software and the impact of feedback were investigated.

Ali Ghadami, Mohammadreza Taghimohammadi, Mohammad Mohammadzadeh et al.

Robots' acceptability among humans and their sociability can be significantly enhanced by incorporating human-like reactions. Humans can react to environmental events very quickly and without thinking. An instance where humans show natural reactions is when they encounter a sudden and loud sound that startles or frightens them. During such moments, individuals may instinctively move their hands, turn toward the origin of the sound, and try to determine the event's cause. This inherent behavior motivated us to explore this less-studied part of social robotics. In this work, a multi-modal system composed of an action generator, sound classifier, and YOLO object detector was designed to sense the environment and, in the presence of sudden loud sounds, show natural human fear reactions; and finally, locate the fear-causing sound source in the environment. These valid generated motions and inferences could imitate intrinsic human reactions and enhance the sociability of robots. For motion generation, a model based on LSTM and MDN networks was proposed to synthesize various motions. Also, in the case of sound detection, a transfer learning model was preferred that used the spectrogram of the sound signals as its input. After developing individual models for sound detection, motion generation, and image recognition, they were integrated into a comprehensive "fear" module implemented on the NAO robot. Finally, the fear module was tested in practical application and two groups of experts and non-experts (in the robotics area) filled out a questionnaire to evaluate the performance of the robot. We indicated that the proposed module could convince the participants that the Nao robot acts and reasons like a human when a sudden and loud sound is in the robot's peripheral environment, and additionally showed that non-experts have higher expectations about social robots and their performance.