Nawar Al Hemeary

Conventional classifiers are generally unable to identify samples from classes absent during the model’s training. However, such samples frequently emerge in real-world scenarios, necessitating the extension of classifier capabilities. Open-Set Recognition (OSR) models are designed to address this challenge. Previously, we developed a robust OSR method that employs generated—“fake”—features to model the space of unknown classes encountered during deployment. Like most OSR models, this method was initially designed for image datasets. However, it is essential to extend OSR techniques to other data types, given their widespread use in practice. In this work, we adapt our model to time-series data while preserving its core efficiency advantage. Thanks to the model’s modular design, only the feature extraction component required modification. We implemented three approaches: a one-dimensional convolutional network for accurate representation, a lightweight method based on predefined statistical features, and a frequency-domain neural network. Further, we evaluated combinations of these methods. Experiments on a biometric time-series dataset, used here as a case study, demonstrate that our model achieves excellent open-set detection and closed-set accuracy. Combining feature extraction strategies yields the best performance, while individual methods offer flexibility: CNNs deliver high accuracy, whereas handcrafted features enable resource-efficient deployment. This adaptability makes the proposed framework suitable for scenarios with varying computational constraints.

Open-set recognition models, in addition to generalizing to unseen instances of known categories, have to identify samples of unknown classes during the training phase. The main reason the latter is much more complicated is that there is very little or no information about the properties of these unknown classes. There are methodologies available to handle the unknowns. One possible method is to construct models for them by using generated inputs labeled as unknown. Generative adversarial networks are frequently deployed to generate synthetic samples representing unknown classes to create better models for known classes. In this paper, we introduce a novel approach to improve the accuracy of recognition methods while reducing the time complexity. Instead of generating synthetic input data to train neural networks, feature vectors are generated using the output of a hidden layer. This approach results in a less complex structure for the neural network representation of the classes. A distance-based classifier implemented by a convolutional neural network is used in our implementation. Our solution’s open-set detection performance reaches an AUC value of 0.839 on the CIFAR-10 dataset, while the closed-set accuracy is 91.4%, the highest among the open-set recognition methods. The generator and discriminator networks are much smaller when generating synthetic inner features. There is no need to run these samples through the first part of the classifier with the convolutional layers. Hence, this solution not only gives better performance than generating samples in the input space but also makes it less expensive in terms of computational complexity.

The INS system’s update rate is faster than that of the GNSS receiver. Additionally, GNSS receiver data may suffer from blocking for a few seconds for different reasons, affecting architecture integrations between GNSS and INS. This paper proposes a novel GNSS data prediction method using the k nearest neighbor (KNN) predictor algorithm to treat data synchronization between the INS sensors and GNSS receiver and overcome those GNSS receiver’s blocking, which may occur for a few seconds. The experimental work was conducted on a flying drone over a minor Hungarian (Mátyásföld, 47.4992 N, 19.1977 E) model airfield. The GNSS data are predicted by four different scenarios: the first is no blocking of data, and the other three have blocking periods of 1, 4, and 8 s, respectively. Ultra-tight architecture integration is used to perform the GNSS/INS integration to deal with the INS sensors’ inaccuracy and their divergence throughout the operation. The results show that using the GNSS/INS integration system yields better positioning data (in three axes (X, Y, and Z)) than using a stand-alone INS system or GNSS without a predictor.

Thermal model development for a CubeSat