Decentralized tasks use machine learning models with certain assumptions. The first is the sharing of weights and feature extractors. The second is maintaining the privacy of the data. The idea of learning using multiple models can also be applied in parallel training, where a given model is trained on a different thread. This has applications in creating models based on federated learning, the Internet of Things and Digital Twins. This paper proposes a new neural network model that uses the atrous technique and attention modules. In addition, we propose a hierarchical-based training strategy, where the best model shares weights and is omitted during further training. This reduces the number of training epochs and increases the model's adaptability to a given set. The tests conducted on a publicly available medical database indicate high learning potential for both the proposed model and the hierarchical learning strategy.

Agricultural health monitoring is a critical task in ensuring the stability of modern agriculture. Many plant diseases share visual similarities, making manual inspection both time consuming and error prone, which is why robust and adaptable disease detection frameworks are not only desirable but essential to maintaining a resilient agricultural ecosystem. In this paper, we propose a hybrid federated learning (FL) framework that integrates a globally shared feature extractor with a client-specific self-attentive branch and classifier. The proposed framework uses a global model with both globally shared and client-tailored branches to achieve better performance for specialized tasks in decentralized training scenarios. The experiments were carried out on a Plant Village data set in a scenario, where each client represented a different crop type and faced a different leaf disease classification problem. The proposed solution revolved around the clients sharing the global weights, thus simultaneously contributing towards better feature extraction of the common leaf features, while the specialized segment of the model focused on proper interpretation of the extracted features (via cross-attention mechanism) and direct classification. The results obtained demonstrate the effectiveness of the proposed approach over standard local training, as training with the proposed hybrid FL framework resulted in a perfect classification of the precision 100% of apple leaf disease.

3D point clouds (LiDAR) are an integral application in robotics, creating 2D or 3D maps that help autonomous vehicles navigate or avoid and recognize obstacles as they drive. In this work, we propose Graph Convolutional Network with Multi-Scale Pooling to classify three-dimensional objects. Previous research very rarely undertakes the transformation of point clouds into graphs and the use of increasingly popular graph networks. Researchers focus on transforming 3D points into voxels and using classical CNN or 3D CNN convolutional networks or methods that directly use the entire cloud, as is evident in the PointNet model. Therefore, we focused on transforming our data into irregular structures (graphs) and classifying them. Our proposed method increases the possibilities for point cloud interpretation by taking into account the relationships between points in space. In order to achieve even better accuracy results, we use the integration of two pooling techniques in the final stage of the model. Our GCN with Multi-Scale Pooling architecture has been trained and tested on the ModeiNetl0 dataset, achieving high-quality metrics: Accuracy, Precision, Recall, and F1-Score compared to other classical SOTA models in the classification domain. Additionally, we carried out experiments based on ShapeNet Core dataset, for which our network achieved almost 100% accuracy. In addition, we showed that our proposed model is built from a much smaller number of parameters compared to other modern methods.

Autonomous vehicles are a key element of the automotive industry, where the impact of the human factor on the condition of the vehicle and driving is minimized. An important element is the analysis of vehicular condition, which allows maintainence of its value and correct operation. We propose a system based on the analysis of the image of vehicles, which determines whether there is any damage. For this purpose, we propose a new model of a Convolutional Neural Network (CNN) that has 0. 395M trained values. The architecture of the network is adapted to the analysis of spatial features that allow networks to be adapted to analyze primarily vehicular shape and orientation in relation to other objects. The model also implements spatial dropout and regularization techniques for preventing overtraining and maintaining model generalization. The modeled architecture contributes to obtaining high classification accuracy at 94.78% using a public database and exceeding metrics of known transfer learning models.

The recent development of Autonomous Guided Vehicles (AGV) use in industry has resulted in the need to model new solutions based on the latest technological achievements. One of the areas worth attention and development is Quality of Service (QoS) in relation to communication between vehicles. QoS makes it possible to divide the bandwidth in such a way that tasks performed by devices are completed with a certain priority. However, in order to manage these resources effectively, it is necessary to anticipate available network throughput. Therefore, this paper presents a neural-based model to ensure throughput prediction for AGV. The proposed solution assumes the use of information on both historical throughput values and data obtained from other sensors that AGV are equipped with. Therefore, the idea is to integrate two neural networks with another network, which is supposed to predict the result based on these two previously obtained predictions. Ultimately, prediction results with a Root Mean Squared Error (RMSE) of 0.1 for the downlink and 1.6 for the uplink were obtained.

Automated guided vehicles (AGV) allow for the automation of operations in warehouse environments. From an application point of view, vehicles can use sensors to move and perform a variety of tasks, including moving objects. In this paper, we focus on the analysis of the environment and the preparation of data for vehicle navigation. The proposed solution is based on two paths of action. In the first, the image of the room is processed by heuristics to locate the robot’s target - the palette. The found pattern allows one to locate the destination as well as create a mask. The mask can be used to train the U-Net network. When a network is trained, the use of heuristics for pallet location can be omitted. Locating the target allows the image to be processed to obtain an AGV navigation map. The proposed solution based on heuristics and U-Net networks has been described and tested in simulations to indicate the potential of the proposed approach.