Article
Acoustics
Jialu Li, Mark Hasegawa-Johnson, Nancy L. McElwain
Summary: This study focused on classifying infant and parent vocalizations to understand how infants learn to regulate emotions in social interactions. The results showed that neural networks outperformed linear discriminant analysis in terms of classification accuracy, with the convolutional neural network slightly outperforming the fully-connected network.
SPEECH COMMUNICATION
(2021)
Article
Computer Science, Information Systems
Xin Cai, Hongjuan Zhang
Summary: The paper discusses a new method to improve the accuracy of music genre classification, combining auditory image features, traditional acoustic features, and spectral features. Experimental results demonstrate that the proposed method outperforms many state-of-the-art classification methods in terms of classification accuracy and stability.
MULTIMEDIA SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Sadegh Salesi, Georgina Cosma
Summary: Evolutionary Computation (EC) algorithms are powerful techniques for feature selection, but they often suffer from the stability issue of reaching different solutions in each run. This paper introduces a novel algorithm called Generalisation Power Analysis (GPA) to evaluate feature subsets based on their generalisation power over multiple classifiers, outperforming alternative methods in achieving high generalisation power. Despite requiring more computation time, using GPA during feature selection results in a robust prediction model developed with features not biased towards a specific classifier.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Multidisciplinary Sciences
Jumpei Matsumoto, Kouta Kanno, Masahiro Kato, Hiroshi Nishimaru, Tsuyoshi Setogawa, Choijiljav Chinzorig, Tomohiro Shibata, Hisao Nishijo
Summary: To study the biological mechanisms underlying social behaviors in mice, a new acoustic camera system, USVCAM, has been developed which allows for simpler and faster localization and assignment of ultrasonic vocalizations. This system has been used to analyze vocal interactions between mice in a home cage and has revealed novel vocal interactions.
Article
Agriculture, Multidisciplinary
Weizheng Shen, Nan Ji, Yanling Yin, Baisheng Dai, Ding Tu, Baihui Sun, Handan Hou, Shengli Kou, Yize Zhao
Summary: This paper proposes a feature fusion method combining acoustic and deep features for pig cough recognition. The combination of acoustic and visual features is used to identify pig cough sounds, achieving an accuracy of 97.35%.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Computer Science, Theory & Methods
Shailesh Mohine, Pooja Gupta, Babankumar S. Bansod, Rakesh Bhalla, Anshul Basra
Summary: In this article, the authors studied various robust features for acoustic modality based moving vehicle identification system. The proposed features were extracted from the experimentally generated dataset of moving vehicles. The study showed that FFT based features had better performance in vehicle identification, with the SVM classifier achieving an identification accuracy of over 90%.
MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Automation & Control Systems
Nageshwar Nath Pandey, Naresh Babu Muppalaneni
Summary: Road accidents have become a significant problem due to driver's drowsy behavior. To tackle this issue, a reliable system is necessary. In this study, a large drowsiness video dataset from the University of Texas was analyzed. Two models, Model-A for temporal features and Model-B for spatiotemporal characteristics, were created. Despite having lower accuracy, Model-A showed superiority in terms of training period compared to Model-B.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Mathematics
Xuefei Huang, Ka-Hou Chan, Wei Ke, Hao Sheng
Summary: This work proposes a parallel-based dense video captioning method that can address the mutual constraint between event proposals and captions. It introduces a deformable Transformer framework to reduce or eliminate manual threshold of hyperparameters. Experimental results show that the proposed method outperforms other methods in this area, providing competitive results on the ActivityNet Caption dataset.
Article
Multidisciplinary Sciences
Moises Rivera, Jacob A. A. Edwards, Mark E. E. Hauber, Sarah M. N. Woolley
Summary: Birdsong has been widely used to study evolution and biodiversity. In this study, high quality song recordings from seven species in the family Estrildidae were analyzed. Acoustic features of syllables were measured, and machine learning classifiers were used to accurately assign syllables to species. Frequency features were found to be more influenced by genetics and therefore have a higher species identification power, while power distribution and spectrotemporal features were more influenced by learning processes and individual recognition.
SCIENTIFIC REPORTS
(2023)
Article
Clinical Neurology
Yanmei Jiang, Jianxin Peng, Lijuan Song
Summary: The study aimed to identify OSAHS patients by analyzing acoustic features derived from overnight snoring sounds. Top-6 features selected from 10 acoustic features showed the best performance in combination with logistic regression model, successfully distinguishing OSAHS patients from simple snorers, providing higher accuracy for evaluating OSAHS with lower computational complexity and great potential for developing a portable sleep snore monitoring device.
Article
Computer Science, Information Systems
Kaveh Kadkhoda Mohammadmosaferi, Hassan Naderi
Summary: The study introduces the AFIF method, which efficiently extracts structural features from social networks and predicts future changes in community evolution.
COMPUTER COMMUNICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Pierluigi Zama Ramirez, Adriano Cardace, Luca De Luigi, Alessio Tonioni, Samuele Salti, Luigi Di Stefano
Summary: The availability of labelled data is a major obstacle for using deep learning algorithms in computer vision tasks in new domains. However, by learning a mapping between task-specific deep features and implementing it using a neural network, we can share knowledge across tasks and generalize to unseen domains. Additionally, we propose strategies to constrain the learned feature spaces, improving the learning process and the generalization capability of the mapping network.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Hesdras O. Viana, Aluizio F. R. Araujo, Danilo S. Barbosa
Summary: This article introduces an ASR model called Self-Organizing Speech Recognizer (SOSR) which uses acoustic and articulatory features, employs unsupervised and incremental learning, and is suitable for real-time applications. SOSR can learn quickly, handle noisy signals, various speakers, different types of speeches, and assorted lengths of utterances.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Biochemical Research Methods
Weronika Jargielo, Bozena Malysiak-Mrozek, Dariusz Mrozek
Summary: Proteins play a crucial role in living organisms and their atomic interactions are essential for controlling their spatial structures and dynamics. This paper presents the PIF library for Java, which can identify atomic interactions in proteins based on their three-dimensional structures. The library has a universal purpose, supporting drug discovery, protein structure modeling, and AI protein analysis models.
Article
Engineering, Electrical & Electronic
Chen-Chieh Feng, Zhou Guo
Summary: This article proposes a hierarchical approach for point cloud classification, including classification based on segmentation and random forest, extraction of novel 3-D contextual features, and refinement of classification based on primitive and spatial contextual features. The evaluation on two point cloud datasets demonstrates that the proposed method outperforms in classification accuracy.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Behavioral Sciences
Nicolas Giret, Fabien Menardy, Catherine Del Negro
FRONTIERS IN BEHAVIORAL NEUROSCIENCE
(2015)
Article
Neurosciences
Jorge Alliende, Nicolas Giret, Ludivine Pidoux, Catherine del Negro, Arthur Leblois
Review
Behavioral Sciences
Nicolas Giret, Jean-Marc Edeline, Catherine Del Negro
NEUROSCIENCE AND BIOBEHAVIORAL REVIEWS
(2017)
Article
Biodiversity Conservation
Aurelie Albert-Daviaud, Sarah Perillo, Wolfgang Stuppy
Article
Biodiversity Conservation
Aurelie Albert, Kim McConkey, Tommaso Savini, Marie-Claude Huynen
BIOLOGICAL CONSERVATION
(2014)
Article
Neurosciences
F. Menardy, N. Giret, C. Del Negro
EUROPEAN JOURNAL OF NEUROSCIENCE
(2014)
Article
Zoology
Aurelie Albert, Marie-Claude Huynen, Tommaso Savini, Alain Hambuckers
INTERNATIONAL JOURNAL OF PRIMATOLOGY
(2013)
Article
Zoology
Aurelie Albert, Alain Hambuckers, Laurence Culot, Tommaso Savini, Marie-Claude Huynen
INTERNATIONAL JOURNAL OF PRIMATOLOGY
(2013)
Article
Multidisciplinary Sciences
Nicolas Giret, Joergen Kornfeld, Surya Ganguli, Richard H. R. Hahnloser
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2014)
Article
Neurosciences
Aurore Cazala, Nicolas Giret, Jean-Marc Edeline, Catherine Del Negro
JOURNAL OF NEUROSCIENCE
(2019)
Article
Multidisciplinary Sciences
Homare Yamahachi, Anja T. Zai, Ryosuke O. Tachibana, Anna E. Stepien, Diana Rodrigues, Sophie Cave-Lopez, Corinna Lorenz, Ezequiel M. Arneodo, Nicolas Giret, Richard H. R. Hahnloser
Article
Behavioral Sciences
Tereza Roubalova, Nicolas Giret, Dalila Bovet, Richard Policht, Jitka Lindova
Article
Multidisciplinary Sciences
Anja T. Zai, Sophie Cave-Lopez, Manon Rolland, Nicolas Giret, Richard H. R. Hahnloser
NATURE COMMUNICATIONS
(2020)
Article
Multidisciplinary Sciences
Aurore Cazala, Catherine Del Negro, Nicolas Giret
Summary: Neurons in a high-order auditory area in zebra finches are sensitive to natural variations in vocal signals, affecting temporal reliability of responses rather than firing rate. Auditory processing in birds operates on distinct timescales to detect variations and encode the global context.
SCIENTIFIC REPORTS
(2021)
Article
Zoology
Aurelie Albert, Tommaso Savini, Marie-Claude Huynen
RAFFLES BULLETIN OF ZOOLOGY
(2013)