Results 21 to 30 of about 79,420 (168)

Research on deep learning-based network intrusion detection methods for smart ships

Brodogradnja
As the development of intelligent ships rapidly progresses, the importance of maritime network security escalates. Intrusion Detection Systems (IDS) serve as a pivotal defense mechanism against cyberattacks targeting these vessels.
Ziming Lu, Hong Zeng, Zhilong Zheng, Caowei Li, Xiao Dong   +4 more
doaj   +1 more source

In vitro and in vivo functions of T cells produced in complemented thymi of chimeric mice generated by blastocyst complementation

Scientific Reports, 2022
Blastocyst complementation is an intriguing way of generating humanized animals for organ preparation in regenerative medicine and establishing novel models for drug development.
Kazuto Yamazaki, Kenji Kubara, Satoko Ishii, Peng Li, Ryo Dairiki, Taro Hihara, Yuta Ishizuka, Yukina Izumi, Minoru Kumai, Tsutomu Kamisako, Hiroyoshi Ishizaki, Hideyuki Sato, Hideki Masaki, Naoaki Mizuno, Kaoru Mitsuhashi, Masashi Ito, Sanae Hamanaka, Tomoyuki Yamaguchi, Motoo Watanabe, Fumihiro Sugiyama, Hiromitsu Nakauchi   +20 more
doaj   +1 more source

Characterization method of material constitutive relationship at high strain rates based on GNN/KAN

Baozha yu Chongji
To accurately characterize the stress-strain constitutive relationship of metal materials under high strain-rate conditions, a novel, high-precision constitutive-relationship-prediction model based on Graph Neural Networks (GNNs) and Kolmogorov-Arnold ...
Jichen YUAN, Xiaxu HUANG, Guoliang XIE
doaj   +1 more source

An Interpretable Machine Learning Model for Predicting 5‐Year Survival in Breast Cancer Based on Integration of Proteomics and Clinical Data

iMetaMed, Volume 1, Issue 2, December 2025.
This study first introduced Kolmogorov–Arnold Network (KAN) into the deep learning model for the integration of clinical and proteomics data in predicting 5‐year survival in breast cancer. The optimal predictive model with 13 key predictors demonstrated excellent predictive performance with strong accuracy, precision, and F1.
Zhixuan Wu, Shengnan Yao, Lingli Jin, Xue Wu, Rongrong Zhang, Ouchen Wang, Erjie Xia   +6 more
wiley   +1 more source

Cellular automata and Kan extensions

Natural Computing, 2023
In this paper, we formalize precisely the sense in which the application of cellular automaton to partial configuration is a natural extension of its local transition function through the categorical notion of Kan extension. In fact, the two possible ways to do such an extension and the ingredients involved in their definition are related through Kan ...
Fernandez, Alexandre, Maignan, Luidnel, Spicher, Antoine   +2 more
openaire   +6 more sources

Distribution of ABO and Rh blood group systems in Cukurova region

Çukurova Üniversitesi Tıp Fakültesi Dergisi, 2016
Purpose: It is well established that distribution of ABO and Rhesus (Rh) blood groups systems show differences between regions and lands even in etnic groups.
sule Menziletoglu Yildiz
doaj   +1 more source

KAN See in the Dark

IEEE Signal Processing Letters
Existing low-light image enhancement methods are difficult to fit the complex nonlinear relationship between normal and low-light images due to uneven illumination and noise effects. The recently proposed Kolmogorov-Arnold networks (KANs) feature spline-based convolutional layers and learnable activation functions, which can effectively capture ...
Aoxiang Ning, Minglong Xue, Jinhong He, Chengyun Song   +3 more
openaire   +2 more sources

Genetic resistance in barley against Japanese soil-borne wheat mosaic virus functions in the roots

Frontiers in Plant Science, 2023
Infection by the Japanese soil-borne wheat mosaic virus (JSBWMV) can lead to substantial losses in the grain yield of barley and wheat crops. While genetically based resistance to this virus has been documented, its mechanistic basis remains obscure.
Kaori Okada, Wenjing Xu, Kohei Mishina, Youko Oono, Youko Oono, Tsuneo Kato, Kiyoshi Namai, Takao Komatsuda, Takao Komatsuda, Takao Komatsuda   +9 more
doaj   +1 more source

From KAN to GR-KAN: Advancing Speech Enhancement with KAN-Based Methodology

Interspeech 2025
Deep neural network (DNN)-based speech enhancement (SE) usually uses conventional activation functions, which lack the expressiveness to capture complex multiscale structures needed for high-fidelity SE. Group-Rational KAN (GR-KAN), a variant of Kolmogorov-Arnold Networks (KAN), retains KAN's expressiveness while improving scalability on complex tasks.
Li H., Hu Y., Chen C., Siniscalchi S. M., Liu S., Chng E. S.   +5 more
openaire   +2 more sources

Türk Kızılay’ı Bölge Kan Merkezlerinde Kan Ürünleri İmha Oranı ve Nedenleri Üzerine Tanımlayıcı Retrospektif Bir Çalışma

Ankara Sağlık Bilimleri Dergisi
Amaç: Kan, insan hayatı için vazgeçilmez ve değerli sıvılardan biridir. Bu çalışmanın amacı Türk Kızılay’ı Kan Hizmetleri Genel Müdürlüğüne bağlı 18 bölge kan merkezinde üretilen ve imha edilen kan ürünlerinin miktarını ve imha nedenlerini ortaya ...
Yasemin Aslan, Beyza Yilmaz
doaj   +1 more source