In this study, the authors generalise Hadamard matrix over and propose a new form of Hadamard matrix, which they call generalised Hadamard (GHadamard) matrix. Then, they focus on generating lightweight (involutory) maximum distance separable (MDS) matrices. They also extend this idea to any matrix form, where k is not necessarily a power of 2. The new matrix form, GHadamard matrix, is used to generate new involutory MDS matrices over and , and involutory/non‐involutory MDS matrices over by considering the minimum exclusive OR (XOR) count, which is a metric defined to estimate the hardware implementation cost. In this context, they improve the best‐known results of XOR counts for involutory/non‐involutory MDS matrices over .

This paper aims to provide a comprehensive survey of the reinforcement learning algorithms given in the literature. Especially model-free reinforcement learning algorithms are given in details and the differences of these algorithms are handled. Finally, some open problems in reinforcement learning are presented for future researches.

Paraphrase generation is a fundamental natural language processing (NLP) task that refers to the process of generating a well‐formed and coherent output sentence that exhibits both syntactic and/or lexical diversity from the input sentence, while simultaneously ensuring that the semantic similarity between the two sentences is preserved. However, the availability of high‐quality paraphrase datasets has been limited, particularly for machine‐generated sentences. In this paper, we present ParaGPT, a new paraphrase dataset of 81,000 machine‐generated sentence pairs, including 27,000 reference sentences (ChatGPT‐generated sentences), and 81,000 paraphrases obtained by using three different large language models (LLMs): ChatGPT, GPT‐3, and T5. We used ChatGPT to generate 27,000 sentences that cover a diverse array of topics and sentence structures, thus providing diverse inputs for the models. In addition, we evaluated the quality of the generated paraphrases using various automatic evaluation metrics. Furthermore, we provide insights into the strengths and drawbacks of each LLM in generating paraphrases by conducting a comparative analysis of the paraphrasing performance of the three LLMs. According to our findings, ChatGPT's performance, as per the evaluation metrics provided, was deemed impressive and commendable, owing to its higher‐than‐average scores for semantic similarity, which implies a higher degree of similarity between the generated paraphrase and the reference sentence, and its relatively lower scores for syntactic diversity, indicating a greater diversity of syntactic structures in the generated paraphrase. ParaGPT is a valuable resource for researchers working on NLP tasks like paraphrasing, text simplification, and text generation. We make the ParaGPT dataset publicly accessible to researchers, and as far as we are aware, this is the first paraphrase dataset produced based on ChatGPT.

In this letter, a fast digital image stabilization method based on local binary pattern (LBP) for real time applications is presented. The LBP approach utilized in this work enables efficient representation of the image frames in 1-bit depth resolution. A simple Boolean exclusive-OR (XOR) based matching criterion is employed to decide global motion vector between consecutive image frames. The constant velocity model based Kalman filtering is executed on the global motion vectors to obtain smoothed frame positions. Experiments show that the proposed approach provides comparable or better performance against the methods at the same category by requiring lower computational complexity.

Background: Despite using a variety of path‐finding algorithms that use tracts, the most significant advancement in this study is considering the values of all brain areas by doing atlas‐based segmentation for a more precise search. Our motivation comes from the literature’s shortcomings in designing and implementing path‐planning methods. Since planning paths with curvatures is a complex problem that requires considering many surgical and physiological constraints, most path‐planning strategies focus on straight paths. There is also a lack of studies that focus on the complete structure of the brain with the tracks, veins, and segmented areas. Instrument dependence is another inadequacy of the methods proposed in the literature.Aims: The aim of this study is to design a new surgical path planning framework that helps to plan the surgical path independently of the instrument, considers the entire structure of the brain, and allows curvilinear surgical paths. Thus, neurosurgeons can generate patient‐specific possible optimal surgical pathways before the neurosurgical procedure.Materials & Methods: The proposed framework includes different path‐finding algorithms (Dijkstra, A*, and their aggressive variants) that find optimal paths by taking the risk scores (surgeons assessed all the segmented regions, considering the extent of damage. In this evaluation, scores ranged from “0 to 10,” with the most critical areas receiving a score of “10,” while the least possible affected areas were assigned a score of "0") for sensitive brain areas into consideration. For the tract image processing the framework includes fractional anisotropy (FA), relative anisotropy (RA), spherical measure (SM), and linear measure (LM) methods.Results: This is the first paper to handle tracts and atlas‐based segmentation of the human brain altogether under a framework for surgical path planning. The framework has a dynamic structure that gives the flexibility to add different path‐finding algorithms and generate different widths of surgical pathways. Moreover, surgeons can update the score table to guarantee minimally invasive surgery. The output file format of all the extracted surgical paths is NRRD, so it can be easily visualised, analysed, or processed over the third part software tools.Discussion: In this study, we generated many possible surgical pathways then these pathways were evaluated by the surgeons the results were impressive because the framework could identify surgical pathways used in real‐world surgery that correspond to the standard pathways such as anterior transsylvian, trans sulcal, transgyral, and sub‐temporal.Conclusion: This study proposes a new surgical path planning framework for neurosurgery. Moreover, in the future by adding/adopting different parameters (such as operation time, and short and long‐term complications after surgery) to the proposed framework, it would be possible to find new surgical pathways for difficult surgical conditions.

To advance the field of brain tumor segmentation, we introduce the Brain Tumor Segmentation Dataset 2024 (BTS-DS 2024), a publicly available dataset comprising 3956 MRI images classified into 14 tumor types. The dataset includes T1-weighted, contrast-enhanced T1 (T1C+), and T2 MRI modalities, providing a comprehensive foundation for segmentation and classification tasks. Using the BTS-DS 2024 dataset, we developed a comprehensive suite of segmentation models, including UNet, ResUNet, Fully Convolutional Networks (FCN), VGG16, and their hybrid variations. In addition, we integrated cutting-edge YOLO architectures—YOLOv8, YOLOv9, and YOLOv11—to assess their effectiveness in brain tumor detection. The experimental results underscore the outstanding performance of YOLOv9e, which achieved the highest $$F_1$$ F 1 score of 92.2538% and an Intersection over Union (IoU) of 85.6214%, demonstrating a strong balance between precision and recall. Moreover, YOLOv11x achieved the highest mean Average Precision (mAP50-95) value of 74.3835%, showcasing superior accuracy across multiple detection thresholds. The originality of this study is exemplified by the introduction of the novel BTS-DS 2024 dataset and the development of models that establish new best-performing scores for $$F_1$$ F 1 , IoU, and mAP50-95 in the literature. These contributions significantly advance the state-of-the-art in brain tumor segmentation, establishing a robust foundation for future research in this domain.