Millions of people throughout the world have been harmed by plastic pollution. There are microscopic pieces of plastic in the food we eat, the water we drink, and even the air we breathe. Every year, the average human consumes 74,000 microplastics, which has a significant impact on their health. This pollution must be addressed before it has a significant negative influence on the population. This research benchmarks six state-of-the-art convolutional neural network models pre-trained on the ImageNet Dataset. The models Resnet-50, ResNeXt, MobileNet_v2, DenseNet, SchuffleNet and AlexNet were tested and evaluated on the WaDaBa plastic dataset, to classify plastic types based on their resin codes by integrating the power of transfer learning. The accuracy and training time for each model has been compared in this research. Due to the imbalance in the data, the under-sampling approach has been used. The ResNeXt model attains the highest accuracy in fourteen minutes.

The next generation of wireless networks, 5G, and beyond will bring more complexities and configuration issues to set the new wireless networks, besides requirements for important and new services. These new generations of wireless networks, to be implemented, are in extreme dependence on the adoption of artificial intelligence techniques. The integration of unmanned aerial vehicles (UAV) in wireless communication networks has opened several possibilities with increased flexibility and performance. Besides, they are considered as one of the most promising technologies to be used in the new wireless networks. Thus, UAVs are expected to be one of the most important applications to provide a new way of connectivity to the 5G network, and it is expected to grow from being a 19.3 billion USD industry in 2019 to 45.8 billion USD by 2025. In this paper, we provide a proposal of handover management on aerial 5G network utilizing the fuzzy system. The simulations performed prove the benefits of our proposal by QoS/QoE (quality of service/quality of experience) metrics.

The extreme nonlinearity of robotic systems renders the control design step harder. The consideration of adaptive control in robotic manipulation started in the 1970s. However, in the presence of bounded disturbances, the limitations of adaptive control rise considerably, which led researchers to exploit some “algorithm modifications”. Unfortunately, these modifications often require a priori knowledge of bounds on the parameters and the perturbations and noise. In the 1990s, the field of Artificial Neural Networks was hugely investigated in general, and for control of dynamical systems in particular. Several types of Neural Networks (NNs) appear to be promising candidates for control system applications. In robotics, it all boils down to making the actuator perform the desired action. While purely control-based robots use the system model to define their input-output relations, Artificial Intelligence (AI)-based robots may or may not use the system model and rather manipulate the robot based on the experience they have with the system while training or possibly enhance it in real-time as well. In this paper, after discussing the drawbacks of adaptive control with bounded disturbances and the proposed modifications to overcome these limitations, we focus on presenting the work that implemented AI in nonlinear dynamical systems and particularly in robotics. We cite some work that targeted the inverted pendulum control problem using NNs. Finally, we emphasize the previous research concerning RL and Deep RL-based control problems and their implementation in robotics manipulation, while highlighting some of their major drawbacks in the field.

Emotion on our face can determine our feelings, mental state and can directly impact our decisions. Humans are subjected to undergo an emotional change in relation to their living environment and or at a present circumstance. These emotions can be anger, disgust, fear, sadness, happiness, surprise or neutral. Due to the intricacy and nuance of facial expressions and their relationship to emotions, accurate facial expression identification remains a difficult undertaking. As a result, we provide an end-to-end system that uses residual blocks to identify emotions and improve accuracy in this research field. After receiving a facial image, the framework returns its emotional state. The accuracy obtained on the test set of FERGIT dataset (an extension of the FER2013 dataset with 49300 images) was 75%. This proves the efficiency of the model in classifying facial emotions as this database poses a bunch of challenges such as imbalanced data, intraclass variance, and occlusion. To ensure the performance of our model, we also tested it on the CK+ database and its output accuracy was 97% on the test set.

Precise control is of importance for robots, whereas, due to the presence of modeling errors and uncertainties under the complex working environment, it is difficult to obtain an accurate dynamic model of the robot, leading to decreased control performances. This work presents an open-closed-loop iterative learning control applied to a four-limb parallel Schönflies-motion robot, aiming to improve the tracking accuracy with high movement, in which the controller can learn from the iterative errors to make the robot end-effector approximate to the expected trajectory. The control algorithm is compared with classical D-ILC, which is illustrated along with an industrial trajectory of pick-and-place operation. External repetitive and non-repetitive disturbances are added to verify the robustness of the proposed approach. To verify the overall performance of the proposed control law, multiple trajectories within the workspace, different working frequencies for a prescribed trajectory, and different design methods are selected, which show the effectiveness and the generalization ability of the designed controller.