Filters








889 Hits in 4.5 sec

A wavelet packet image coding algorithm based on quadtree classification and UTCQ

Xingsong Hou, Guizhong Liu
2003 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)  
The image coding results, calculated from actual file sizes and images reconstructed by the decoding algorithm are either comparable to or surpass previous results for texture-rich images.  ...  into two sets: a significant one and an insignificant one, (3) the universal trellis coded quantization, used to code the significant coefficients sets, (4) the entropy coder, used to code the indices  ...  Step 1 wavelet packet transform and best basis selection predefine the classification threshold T. apply the full subband decomposition to the original image. calculate the cost function for each subbands  ... 
doi:10.1109/icme.2003.1221676 dblp:conf/icmcs/HouL03 fatcat:6qumzqytojfcteuyzczaqwahd4

A deep-learning view of chemical space designed to facilitate drug discovery [article]

Paul Maragakis, Hunter Nisonoff, Brian Cole, David E. Shaw
2020 arXiv   pre-print
The use of deep learning technologies could augment the typical practice of using human intuition in the design cycle, and thereby expedite drug discovery projects.  ...  Here we present DESMILES, a deep neural network model that advances the state of the art in machine learning approaches to molecular design.  ...  Acknowledgements The authors thank Michael Eastwood for helpful discussions and Jessica McGillen and Berkman Frank for editorial assistance.  ... 
arXiv:2002.02948v1 fatcat:ha2yyriavrdk5fspwuivk7tia4

Anomaly Detection with Convolutional Autoencoders for Fingerprint Presentation Attack Detection

Jascha Kolberg, Marcel Grimmer, Marta Gomez-Barrero, Christoph Busch
2021 IEEE Transactions on Biometrics Behavior and Identity Science  
Additionally, our best performing AE model is compared to further one-class classifiers (support vector machine, Gaussian mixture model).  ...  In particular, this applies for unsupervised applications, where new attacks unknown to the system operator may occur.  ...  Later, the model can be used to detect unknown PAs by comparing the reconstruction error against a threshold. B.  ... 
doi:10.1109/tbiom.2021.3050036 fatcat:pkokcmdagrgfzghau3xsl2tm3i

Anomaly Detection with Convolutional Autoencoders for Fingerprint Presentation Attack Detection [article]

Jascha Kolberg and Marcel Grimmer and Marta Gomez-Barrero and Christoph Busch
2020 arXiv   pre-print
Additionally, our best performing AE model is compared to further one-class classifiers (support vector machine, Gaussian mixture model).  ...  In recent years, the popularity of fingerprint-based biometric authentication systems significantly increased.  ...  Furthermore, we would like to thank our colleagues from Information Science Institute at University of Southern California for the data collection effort.  ... 
arXiv:2008.07989v2 fatcat:5x5wmd6fvncadbbpuhlo3odgre

Open Set Wireless Transmitter Authorization: Deep Learning Approaches and Dataset Considerations [article]

Samer Hanna, Samurdhi Karunaratne, Danijela Cabric
2020 arXiv   pre-print
The robustness of the RF authorization with respect to temporal changes in fingerprints is also considered in the evaluation.  ...  While deep learning was proposed for transmitter identification, the majority of the work has focused on classification among a closed set of transmitters.  ...  Gaussian Mixture Models [12] , [33] , [34] and statistical hypothesis testing [35] were proposed for transmitter authorization using a set of manually designed features. 2) Deep Learning Based PLA  ... 
arXiv:2005.00954v1 fatcat:runkwug375chlmzp4tp2zjztvi

Speaker diarization of broadcast news in Albayzin 2010 evaluation campaign

Martin Zelenák, Henrik Schulz, Javier Hernando
2012 EURASIP Journal on Audio, Speech, and Music Processing  
In this article, we present the evaluation results for the task of speaker diarization of broadcast news, which was part of the Albayzin 2010 evaluation campaign of language and speech technologies.  ...  The authors would like to thank the organizers of the FALA 2010 workshop for their effort and also the participants for the help with the system descriptions.  ...  Both steps are performed simultaneously in an iterative procedure which uses, for instance, a set of Gaussian mixture models (GMMs) or an ergodic hidden Markov model (HMM).  ... 
doi:10.1186/1687-4722-2012-19 fatcat:wpkbmzqnajbwpnf7poi4d3qx54

PROTEIN IDENTIFICATION USING SEQUENCE DATABASES

Ye Golenko, A Ismailova, Ye Rais
2020 Scientific Journal of Astana IT University  
The identification of peptides from the obtained MS/MS data is most often done using available sequence databases.  ...  We also analyze statistical methods and computational tools for validating peptide compliance with MS/MS data.  ...  The use of databases to identify proteins and peptides makes it possible to decode mass spectra of complex mixtures in a short time.  ... 
doi:10.37943/aitu.2020.91.98.002 fatcat:jzejug2xorb4pi36yyxg4uir4i

Texture to the Rescue: Practical Paper Fingerprinting based on Texture Patterns [article]

Ehsan Toreini, Siamak F. Shahandashti, Feng Hao
2019 arXiv   pre-print
The high amount of DoF for texture-based fingerprints makes our method extremely scalable for recognition among very large databases; it also allows secure usage of the extracted fingerprint in privacy-preserving  ...  Through experiments, we demonstrate that the embedded paper texture provides a more reliable source for fingerprinting than features on the surface.  ...  [31] proposed to embed different material-ultra-violet fibers-into the paper mixture, and use a UV scanner to obtain a unique fingerprint.  ... 
arXiv:1705.02510v3 fatcat:zk4yx6duirhnpjtwxsdp7mcwry

Texture to the Rescue

Ehsan Toreini, Siamak F. Shahandashti, Feng Hao
2017 ACM Transactions on Privacy and Security  
The high amount of DoF for texture-based fingerprints makes our method extremely scalable for recognition among very large databases; it also allows secure usage of the extracted fingerprint in privacy-preserving  ...  Through experiments, we demonstrate that the embedded paper texture provides a more reliable source for fingerprinting than features on the surface.  ...  [31] proposed to embed different material-ultra-violet fibers-into the paper mixture, and use a UV scanner to obtain a unique fingerprint.  ... 
doi:10.1145/3092816 fatcat:fvmshzosfvdcnlfzlm6wvkcgii

A Symmetric Keyring Encryption Scheme for Biometric Cryptosystems [article]

Yen-Lung Lai, Jung-Yeon Hwang, Zhe Jin, Soohyong Kim, Sangrae Cho and Andrew Beng Jin Teoh
2018 arXiv   pre-print
In this paper, we propose a novel biometric cryptosystem for vectorial biometrics named symmetric keyring encryption (SKE) inspired by Rivest's keyring model (2016).  ...  Though SKE can be applied to any vectorial biometrics, we adopt the fingerprint vector as a case of study in this work.  ...  Imposter attempt: For each subject, the first fingerprint vector is used for enrollment, and the second fingerprint vector of other subjects are used to decrypt C for secret retrieval.  ... 
arXiv:1809.11045v1 fatcat:6eg773vv6zeevao3oppjeerzwy

Comparison of ALBAYZIN query-by-example spoken term detection 2012 and 2014 evaluations

Javier Tejedor, Doroteo T. Toledano, Paula Lopez-Otero, Laura Docio-Fernandez, Carmen Garcia-Mateo
2016 EURASIP Journal on Audio, Speech, and Music Processing  
This is the second QbE STD evaluation in Spanish, which allows us to evaluate the progress in this technology for this language.  ...  In 2014, new multi-word and foreign queries were added to the single-word and in-language queries used in 2012.  ...  mixture model (GMM) output densities.  ... 
doi:10.1186/s13636-016-0080-2 fatcat:les5r3cipzcsnhrxrv6lgiuedu

Inkjet-printed unclonable quantum dot fluorescent anti-counterfeiting labels with artificial intelligence authentication

Yang Liu, Fei Han, Fushan Li, Yan Zhao, Maosheng Chen, Zhongwei Xu, Xin Zheng, Hailong Hu, Jianmin Yao, Tailiang Guo, Wanzhen Lin, Yuanhui Zheng (+4 others)
2019 Nature Communications  
, amplifications and the mixture of these parameters.  ...  Here we report a non-destructive, inkjet-printable, artificial intelligence (AI)-decodable and unclonable security label.  ...  Sentinel and concentration, were used to calculate the quantum yields using the expression.  ... 
doi:10.1038/s41467-019-10406-7 pmid:31160579 pmcid:PMC6547729 fatcat:qig2fg7ltzeyjkf7ocae2hnyc4

BinMLM: Binary Authorship Verification with Flow-aware Mixture-of-Shared Language Model [article]

Qige Song, Yongzheng Zhang, Linshu Ouyang, Yige Chen
2022 arXiv   pre-print
We build a mixture-of-shared architecture with multiple shared encoders and author-specific gate layers, which can learn the developers' combination preferences of universal programming patterns and alleviate  ...  BinMLM trains the RNN language model on consecutive opcode traces extracted from the control-flow-graph (CFG) to characterize the candidate developers' programming styles.  ...  ACKNOWLEDGMENT The authors would like to thank the anonymous reviewers for their insightful comments. This work was supported by the National Natural Science Foundation of China under Grant U1736218.  ... 
arXiv:2203.04472v1 fatcat:w46qme7zr5eklkhavu4aszfngi

Securing the Insecure: A First-Line-of-Defense for Nanoscale Communication Systems Operating in THz Band [article]

Waqas Aman, M. Mahboob Ur Rahman, Hassan T. Abbas, Muhammad Arslan Khalid, Muhammad A. Imran, Akram Alomainy, Qammer H. Abbasi
2020 arXiv   pre-print
We used hiddenMarkov Model (HMM) viterbi algorithm to enhance the outputof hypothesis testing.  ...  We also conducted transmitter identificationusing maximum likelihood and Gaussian mixture model (GMM)expectation maximization algorithms.  ...  Waqas Aman would also like to thank Higher Education Commission of Pakistan for providing him IRSIP scholarship to travel to University of Glasgow for his studies.  ... 
arXiv:2007.06818v1 fatcat:7a3knnvcjfhn5h5skk3vjdwqbm

Machine learning on DNA-encoded libraries: A new paradigm for hit-finding [article]

Kevin McCloskey, Eric A. Sigel, Steven Kearnes, Ling Xue, Xia Tian, Dennis Moccia, Diana Gikunju, Sana Bazzaz, Betty Chan, Matthew A. Clark, John W. Cuozzo, Marie-Aude Guié, John P. Guilinger (+5 others)
2020 arXiv   pre-print
The model makes useful predictions even for molecules dissimilar to the original DEL and the compounds identified are diverse, predominantly drug-like, and different from known ligands.  ...  We train models using only DEL selection data and apply automated or automatable filters with chemist review restricted to the removal of molecules with potential for instability or reactivity.  ...  Acknowledgements We acknowledge: AstraZeneca for providing reagents used in screening of both ERα and c-Kit; Zan Armstrong for help with visual design of figures; the X-Chem Library Synthesis and Design  ... 
arXiv:2002.02530v1 fatcat:x2xft34vfbbgxg2lhia243zpli
« Previous Showing results 1 — 15 out of 889 results