Human identification driven by deep CNN and transfer learning based on multiview feature representations of ECG
Human identification driven by deep CNN and transfer learning based on multiview feature representations of ECG-2021
Increasingly smart techniques for counterfeiting face and fingerprint traits have increased the potential threats to information security systems, creating a substantial demand for improved security and better privacy and identity protection. The internet of Things (IoT)-driven fingertip electrocardiogram (ECG) acquisition provides broad application prospects for ECG-based identity systems. This study focused on three major impediments to fingertip ECG: the impact of variations in acquisition status, the high computational complexity of traditional convolutional neural network (CNN) models and the feasibility of model migration, and a lack of sufficient fingertip samples. Our main contribution is a novel fingertip ECG identification system that integrates transfer learning and a deep CNN. The proposed system does not require manual feature extraction or suffer from complex model calculations, which improves its speed, and it is effective even when only a small set of training data exists. Using 1200 ECG recordings from 600 individuals, we consider 5 simulated yet potentially practical scenarios. When analyzing the overall training accuracy of the model, its mean accuracy for the 540 chest- collected ECG from PhysioNet exceeded 97.60 %, and for 60 subjects from the CYBHi fingertip-collected ECG, its mean accuracy reached 98.77 %. When simulating a real-world human recognition system on 5 public datasets, the validation accuracy of the proposed model can nearly reach 100 % recognition, outperforming the original GoogLeNet network by a maximum of 3.33 %. To some degree, the developed architecture provides a reference for practical applications of fingertip-collected ECG-based biometric systems and for information network security.
Keywords: Off-the-person | Fingertip ECG biometric | Human identification | Convolutional neural network (CNN) | Transfer learning
Person-identification using familiar-name auditory evoked potentials from frontal EEG electrodes
شناسایی فرد با استفاده از پتانسیل نام-آشنا شنوایی الکترودهای EEG جلو برانگیخته-2021
Electroencephalograph (EEG) based biometric identification has recently gained increased attention of re- searchers. However, state-of-the-art EEG-based biometric identification techniques use large number of EEG electrodes, which poses user inconvenience and consumes longer preparation time for practical applications. This work proposes a novel EEG-based biometric identification technique using auditory evoked potentials (AEPs) acquired from two EEG electrodes. The proposed method employs single-trial familiar-name AEPs extracted from the frontal electrodes Fp1 and F7, which facilitates faster and user-convenient data acquisition. The EEG signals recorded from twenty healthy individuals during four experiment trials are used in this study. Different com- binations of well-known neural network architectures are used for feature extraction and classification. The cascaded combinations of 1D-convolutional neural networks (1D-CNN) with long short-term memory (LSTM) and with gated recurrent unit (GRU) networks gave the person identification accuracies above 99 %. 1D-convolutional, LSTM network achieves the highest person identification accuracy of 99.53 % and a half total error rate (HTER) of 0.24 % using AEP signals from the two frontal electrodes. With the AEP signals from the single electrode Fp1, the same network achieves a person identification accuracy of 96.93 %. The use of familiar-name AEPs from frontal EEG electrodes that facilitates user convenient data acquisition with shorter preparation time is the novelty of this work.
Keywords: Auditory evoked potential | Biometrics | Deep learning | Electroencephalogram | Familiar-name | Person identification
A novel multi-lead ECG personal recognition based on signals functional and structural dependencies using time-frequency representation and evolutionary morphological CNN
تشخیص شخصی نوار قلب ECG مبتنی بر وابستگی های عملکردی و ساختاری سیگنالها با استفاده از نمایش فرکانس زمان و CNN مورفولوژیکی تکاملی-2021
Biometric recognition systems have been employed in many aspects of life such as security technologies, data protection, and remote access. Physiological signals, e.g. electrocardiogram (ECG), can potentially be used in biometric recognition. From a medical standpoint, ECG leads have structural and functional dependencies. In fact, precordial ECG leads view the heart from different axial angles, whereas limb leads view it from various coronal angles. This study aimed to design a personal biometric recognition system based on ECG signals by estimating these latent medical variables. To estimate functional dependencies, within-correlation and cross- correlation in time-frequency domain between ECG leads were calculated and represented in the form of extended adjacency matrices. CNN trees were then introduced through genetic programming for the automated estimation of structural dependencies in extended adjacency matrices. CNN trees perform the deep feature learning process by using structural morphology operators. The proposed system was designed for both closed-set identification and verification. It was then tested on two datasets, i.e. PTB and CYBHi, for performance evaluation. Compared with the state-of-the-art methods, the proposed method outperformed all of them.
Keywords: Biometrics | Electrocardiogram | Functional dependencies | Structural dependencies | Genetic programming | Convolutional neural networks
ECB2: A novel encryption scheme using face biometrics for signing blockchain transactions
ECB2: یک طرح رمزگذاری جدید با استفاده از بیومتریک چهره برای امضای تراکنش های بلاک چین-2021
Blockchain is the technology on the basis of the recent smart and digital contracts. It ensures at this system the required characteristics to be effectively applied. In this work, we propose a novel encryption scheme specifically built to authorize and sign transactions in digital or smart contracts. The face is used as a biometric key, encoded through the Convolutional Neural Network (CNN), FaceNet. Then, this encoding is fused with an RSA key by using the Hybrid Information Fusion algorithm (BNIF). The results show a combined key that ensures the identity of the user that is executing the transaction by preserving privacy. Experiments reveal that, even in strong heterogeneous acquisition conditions for the biometric trait, the identity of the user is ensured and the contract is properly signed in less than 1.86 s. The proposed ECB2 encryption scheme is also very fast in the user template creation (0.05s) and requires at most four attempts to recognize the user with an accuracy of 94%.
یک رویکرد فیلترینگ درون حلقه ای پیشرونده شبکههای عصبی پیچشی یا همگشتی (CNN) برای کدگذاری بین فریم (Frame inter)
سال انتشار: 2021 - تعداد صفحات فایل pdf انگلیسی: 11 - تعداد صفحات فایل doc فارسی: 34
ساختارهای شبکههای عصبی پیچشی (CNN) برای فیلترینگ درون حلقهای طراحی شدهاند تا عملکرد کدگذاری ویدئو را بهبود بخشند. این مدلهای CNN معمولا از طریق یادگیری همبستگی بین فریمهای بازسازی شده و اصلی آموزش داده میشوند، که سپس برای هر فریم بازسازی شده اعمال میشوند تا کیفیت کلی ویدئو بهبود یابد. این استراتژی توسعه و آموزش مستقیم مدل برای درون کد گذاری موثر است زیرا یک مدل بهینه محلی کافی است. با این حال، هنگامی که برای رمزگذاری داخلی اعمال میشود، باعث فیلترینگ بیش از حد میشود، زیرا وابستگیهای مرجع درهمتنیده در میان فریمها در نظر گرفته نمیشوند. برای پرداختن به این موضوع، روشهای موجود معمولا به بهینهسازی نرخ تحریف یا اعواج (RDO) متوسل میشوند تا به صورت دلخواه از مدل CNN استفاده کنند، اما در رفع محدودیت استفاده از مدل CNN محلی موفق نیستند. در این مقاله، ما یک روش پیشرفته برای آموزش و ترکیب فیلترهای داخلی مبتنی بر CNN برای کار یکپارچه با کدکنندههای ویدئویی ارائه میکنیم. ابتدا، ما یک روش آموزش پیشرفته را برای به دست آوردن مدل داخلی توسعه میدهیم. با استفاده از یادگیری انتقالی، فریم های بازسازی شده با استفاده از مدل CNN به تدریج وارد آموزش خود مدل CNN میشوند تا وابستگیهای مرجع در کدگذاری داخلی را شبیهسازی کنند. سپس، یک استراتژی انتخاب مدل سطح چارچوب برای کدگذاری نرخ بیت بالا طراحی میکنیم که در آن اثر فیلترینگ بیش از حد رقیق میشود. نتایج تجربی نشان میدهند که روش پیشنهادی از روش RDO که تنها از مدل محلی استفاده میکند، بهتر عمل میکند. رویکرد پیشنهادی همچنین به عملکرد رمزگذاری قابل مقایسه دست مییابد اما پیچیدگی محاسباتی کمتری هنگام یکپارچه سازی مدل مترقی ما در طرح RDO دارد.
کلمات کلیدی: شبکههای عصبی پیچشی یا همگشتی (CNN) | فیلترینگ درون حلقهای | آموزش مدل | کدگذاری داخلی
|مقاله ترجمه شده|
A fusing framework of shortcut convolutional neural networks
چارچوبی تلفیقی از شبکه های عصبی پیچشی میانبر-2021
Convolutional neural networks (CNNs) have proven to be very successful in learning task- specific computer vision features. To integrate features from different layers in standard CNNs, we present a fusing framework of shortcut convolutional neural networks (S-CNNs). This framework can fuse arbitrary scale features by adding weighted shortcut connections to the standard CNNs. Besides the framework, we propose a shortcut indicator (SI) of binary string to stand for a specific S-CNN shortcut style. Additionally, we design a learning algorithm for the proposed S-CNNs. Comprehensive experiments are conducted to compare its performances with standard CNNs on multiple benchmark datasets for different visual tasks. Empirical results show that if we choose an appropriate fusing style of shortcut connections with learnable weights, S-CNNs can perform better than standard CNNs regarding accuracy and stability in different activation functions and pooling schemes initializations, and occlusions. Moreover, S-CNNs are competitive with ResNets and can outperform GoogLeNet, DenseNets, Multi-scale CNN, and DeepID.© 2021 Elsevier Inc. All rights reserved.
Keywords: Convolutional neural networks | Computer vision | Shortcut connections
American Society of Biomechanics Early Career Achievement Award 2020: Toward Portable and Modular Biomechanics Labs: How Video and IMU Fusion Will Change Gait Analysis
انجمن آمریکایی بیومکانیک جایزه دستاورد اولیه شغلی 2020: به سوی آزمایشگاههای بیومکانیک قابل حمل و مدولار: چگونه تجزیه ویدئو و IMU تجزیه و تحلیل راه رفتن را تغییر می دهد-2021
The field of biomechanics is at a turning point, with marker-based motion capture set to be replaced by portable and inexpensive hardware, rapidly improving markerless tracking algorithms, and open datasets that will turn these new technologies into field-wide team projects. Despite progress, several challenges inhibit both inertial and vision-based motion tracking from reaching the high accuracies that many biomechanics applications require. Their complementary strengths, however, could be harnessed toward better solutions than those offered by either modality alone. The drift from inertial measurement units (IMUs) could be corrected by video data, while occlusions in videos could be corrected by inertial data. To expedite progress in this direction, we have collected the CMU Panoptic Dataset 2.0, which contains 86 subjects captured with 140 VGA cameras, 31 HD cameras, and 15 IMUs, performing on average 6.5 minutes of activities, including range of motion activities and tasks of daily living. To estimate ground-truth kinematics, we imposed simultaneous consistency with the video and IMU data. Threedimensional joint centers were first computed by geometrically triangulating proposals from a convolutional neural network applied to each video independently. A statistical meshed model parametrized in terms of body shape and pose was then fit through a top-down optimization approach that enforced consistency with both the video-based joint centers and IMU data. This sensor-dense dataset can be used to benchmark new methods that integrate a much sparser set of videos and IMUs to estimate both kinematics and kinetics in a markerless fashion.
Key words: markerless motion tracking | computer vision | inertial measurement units
Computer-vision classification of corn seed varieties using deep convolutional neural network
طبقه بندی بینایی ماشین انواع بذر ذرت با استفاده از شبکه عصبی پیچیده عمیق-2021
Automated classiﬁcation of seed varieties is of paramount importance for seed producers to maintain the purity of a variety and crop yield. Traditional approaches based on computer vision and simple feature extraction could not guarantee high accuracy classiﬁcation. This paper presents a new approach using a deep convolutional neural network (CNN) as a generic feature extractor. The extracted features were classiﬁed with artiﬁcial neural network (ANN), cubic support vector machine (SVM), quadratic SVM, weighted k-nearest-neighbor (kNN), boosted tree, bagged tree, and linear discriminant analysis (LDA). Models trained with CNN-extracted features demonstrated better classiﬁcation accuracy of corn seed varieties than models based on only simple features. The CNN-ANN classiﬁer showed the best performance, classifying 2250 test instances in 26.8 s with classiﬁcation accuracy 98.1%, precision 98.2%, recall 98.1%, and F1-score 98.1%. This study demonstrates that the CNN-ANN classiﬁer is an efﬁcient tool for the intelligent classiﬁcation of different corn seed varieties.© 2021 Elsevier Ltd. All rights reserved.
Keywords: Machine vision | Deep learning | Feature extraction | Non-handcrafted features | Texture descriptors
Automated classification of fauna in seabed photographs: The impact of training and validation dataset size, with considerations for the class imbalance
طبقه بندی خودکار جانوران در عکس های بستر دریا: تأثیر اندازه مجموعه داده های آموزش و اعتبار سنجی ، با ملاحظاتی برای عدم تعادل کلاس-2021
Machine learning is rapidly developing as a tool for gathering data from imagery and may be useful in identifying (classifying) visible specimens in large numbers of seabed photographs. Application of an automated classifi- cation workflow requires manually identified specimens to be supplied for training and validating the model. These training and validation datasets are generally generated by partitioning the available manual identified specimens; typical ratios of training to validation dataset sizes are 75:25 or 80:20. However, this approach does not facilitate the desired scalability, which would require models to successfully classify specimens in hundreds of thousands to millions of images after training on a relatively small subset of manually identified specimens. A second problem is related to the ‘class imbalance’, where natural community structure means that fewer spec- imens of rare morphotypes are available for model training. We investigated the impact of independent variation of the training and validation dataset sizes on the performance of a convolutional neural network classifier on benthic invertebrates visible in a very large set of seabed photographs captured by an autonomous underwater vehicle at the Porcupine Abyssal Plain Sustained Observatory. We tested the impact of increasing training dataset size on specimen classification in a single validation dataset, and then tested the impact of increasing validation set size, evaluating ecological metrics in addition to computer vision metrics. Computer vision metrics (recall, precision, F1-score) indicated that classification improved with increasing training dataset size. In terms of ecological metrics, the number of morphotypes recorded increased, while diversity decreased with increasing training dataset size. Variation and bias in diversity metrics decreased with increasing training dataset size. Multivariate dispersion in apparent community composition was reduced, and bias from expert-derived data declined with increasing training dataset size. In contrast, classification success and resulting ecological metrics did not differ significantly with varying validation dataset sizes. Thus, the selection of an appropriate training dataset size is key to ensuring robust automated classifications of benthic invertebrates in seabed photographs, in terms of ecological results, and validation may be conducted on a comparatively small dataset with confidence that similar results will be obtained in a larger production dataset. In addition, our results suggest that automated classification of less common morphotypes may be feasible, providing that the overall training dataset size is sufficiently large. Thus, tactics for reducing class imbalance in the training dataset may produce improvements in the resulting ecological metrics.
Keywords: Computer vision | Deep learning | Benthic ecology | Image annotation | Marine photography | Artificial intelligence | Convolutional neural networks | Sample size
Vision-assisted recognition of stereotype behaviors for early diagnosis of Autism Spectrum Disorders
تشخیص رفتارهای کلیشه ای برای تشخیص زودهنگام اختلالات طیف اوتیسم با کمک بینایی ماشین-2021
Medical diagnosis supported by computer-assisted technologies is getting more popularity and acceptance among medical society. In this paper, we propose a non-intrusive vision-assisted method based on human action recognition to facilitate the diagnosis of Autism Spectrum Disorder (ASD). We collected a novel and comprehensive video dataset f the most distinctive Stereotype actions of this disorder with the assistance of professional clinicians. Several frameworks as a function of different input modalities were developed and used to produce extensive baseline results. Various local descriptors, which are commonly used within the Bag-of-Visual-Words approach, were tested with Multi-layer Perceptron (MLP), Gaussian Naive Bayes (GNB), and Support Vector Machines (SVM) classifiers for recognizing ASD associated behaviors. Additionally, we developed a framework that first receives articulated pose-based skeleton sequences as input and follows an LSTM network to learn the temporal evolution of the poses. Finally, obtained results were compared with two fine-tuned deep neural networks: ConvLSTM and 3DCNN. The results revealed that the Histogram of Optical Flow (HOF) descriptor achieves the best results when used with MLP classifier. The promising baseline results also confirmed that an action-recognition-based system can be potentially used to assist clinicians to provide a reliable, accurate, and timely diagnosis of ASD disorder.© 2021 Elsevier B.V. All rights reserved.
Keywords: Action recognition | Autism Spectrum Disorder | Patient monitoring | Bag-of-visual-words | Convolutional neural networks