Motivated by the geometric advantages of quaternions in representing rotations and postures, we propose a quaternion-valued supervised learning Hopfield-structured neural network (QSHNN) with a fully connected structure inspired by the classic Hopfield neural network (HNN). Starting from a continuous-time dynamical model of HNNs, we extend the formulation to the quaternionic domain and establish the existence and uniqueness of fixed points with asymptotic stability. For the learning rules, we introduce a periodic projection strategy that modifies standard gradient descent by periodically projecting each $4\times 4$ block of the weight matrix onto the closest quaternionic structure in the least-squares sense. This approach preserves both convergence and quaternionic consistency throughout training. Benefiting from this rigorous mathematical foundation, the experimental model implementation achieves high accuracy, fast convergence, and strong reliability across randomly generated target sets. Moreover, the evolution trajectories of the QSHNN exhibit well-bounded curvature, i.e., sufficient smoothness, which is crucial for applications such as control systems or path planning modules in robotic arms, where joint postures are parameterized by quaternion neurons. Beyond these application scenarios, the proposed model offers a practical implementation framework and a general mathematical methodology for designing neural networks under hypercomplex or non-commutative algebraic structures.

Abstract This paper introduces a novel approach for training generative adversarial networks using federated machine learning. Generative adversarial networks have gained plenty of attention in the research community especially with their abilities to produce high quality synthetic data for a variety of use-cases. Yet, when combined with federated learning, those models suffer from degradation in both training time and quality of results. To address this challenge, this paper introduces a novel approach that uses hierarchical learning techniques to enable the efficient training of federated GAN models. The proposed approach introduces an innovative mechanism that dynamically clusters participant clients to edge servers as well as a novel multi-generator GAN architecture that utilizes non-identical model aggregation stages. The proposed approach has been evaluated on a number of benchmark datasets to measure its performance on higher numbers of participating clients. The results show that HFL-GAN outperforms other comparative state-of-the-art approaches in the training of GAN models in complex non-IID federated learning settings.

Mild cognitive impairment (MCI) has been described as the intermediary stage before Alzheimer's Disease - many people however remain stable or even demonstrate improvement in cognition. Early detection of progressive MCI (pMCI) therefore can be utilised in identifying at-risk individuals and directing additional medical treatment in order to revert conversion to AD as well as provide psychosocial support for the person and their family. This paper presents a novel solution in the early detection of pMCI people and classification of AD risk within MCI people. We proposed a model, MudNet, to utilise deep learning in the simultaneous prediction of progressive/stable MCI classes and time-to-AD conversion where high-risk pMCI people see conversion to AD within 24 months and low-risk people greater than 24 months. MudNet is trained and validated using baseline clinical and volumetric MRI data (n = 559 scans) from participants of the Alzheimer's Disease Neuroimaging Initiative (ADNI). The model utilises T1-weighted structural MRIs alongside clinical data which also contains neuropsychological (RAVLT, ADAS-11, ADAS-13, ADASQ4, MMSE) tests as inputs. The averaged results of our model indicate a binary accuracy of 69.8% for conversion predictions and a categorical accuracy of 66.9% for risk classifications.

Using remote sensing to monitoring grassland for urban area is one of the major environmental applications today. Experts urge that there should be more nature grassland than artificial grassland in urban area, because the former is much important than the latter. It is difficult to identify them using normal methods such as pixel-based classification because both grasslands have similar spectral information. Going far beyond the methodical limits of pixel-based and manual interpretation approaches; object-oriented image analysis approaches are used for extracting information. This paper presents a snapshot of work to detect different grassland information in Daqing city using this patented technique. The result of grassland information extraction is promising and the precision of classification is higher than other conventional processes. It is obvious that this new image analysis approach offers a satisfying solution to extract information quickly and efficiently.

In the present study an attempt has been made to evaluate the value of vegetations' air purification supported by Geographic Information System. Based on the theory and model about valuation of vegetations' air purification services, the material quantities and value of vegetations' air purification in Xi'an city were achieved. The results showed as the follows. Vegetations' air purification services included CO/sub 2/ fixation, O/sub 2/ release, pollutants absorption (SO/sub 2/, HF, NO/sub X/), dust retention, and sterilization. The total value of vegetations' air purification was 3426.35 million Yuan per year, which was six percent of Xian's GDP in 1999. Its value of CO/sub 2/ fixation and O/sub 2/ release was 2718.31 million Yuan per year, and that of absorbing the three pollutants, SO/sub 2/, HF, NO/sub X/, was 182.9031 million Yuan. Their dust retention and sterilization value were 182.51 and 342.64 million Yuan respectively. Using GIS's capabilities for inputting, storage, mapping, analysis and display of spatial data, we obtained spatial map of vegetations' air purification value in Xi'an and discussed the discrepancies of different vegetation types' air purification services.

Three Gorges Project is a great water resource project. After the project is completed, it will partially change Yangtze's water regime and affect ecology and environment of region along Yangtze River, from reservoir region, middle reaches, lower reaches to estuary. As a result, it is of great significance to monitor Yangtze's ecology and environment element, which take place since 1996 with 19 themes over the whole river. This paper introduces the ecology and environment information system for Three Gorges Project. The architecture and working principles of the system is introduced firstly. Then, system functions and key implementation technology are stated. The system is unique and complicate mainly because its monitoring contents are wide, which cover water pollution, agricultural ecology, terraneous ecology, hydrophytic ecology, local climate, social environment and so on. The application of the system will provide decision support for sustainable development of Yangtze's drainage area.