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
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
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
Vision-based hand signal recognition in construction: A feasibility study
تشخیص سیگنال دست مبتنی بر چشم انداز در ساخت و ساز: یک مطالعه امکان سنجی-2021
In construction fields, it is common for workers to rely on hand signals to communicate and express thoughts due to their simple but effective nature. However, the meaning of these hand signals was not always captured precisely. As a result, construction errors and even accidents were produced. This paper presented a feasibility study on investigating whether the hand signals could be captured and interpreted automatically with computer vision technologies. It starts with the literature review of existing hand gesture recognition methods for sign language understanding, human-computer interaction, etc. It is then followed by creating a dataset containing 11 classes of hand signals in construction. The performance of two state-of-the-art 3D convolutional neural networks is measured and compared. The results indicated that a high classification accuracy (93.3%) and a short inference time (0.17 s/gesture) could be achieved, illustrating the feasibility of using computer vision to automate hand signal recognition in construction.
Keywords: Hand signal recognition | Dataset creation | Performance comparison | Feasibility study
Biometric recognition using wearable devices in real-life settings
تشخیص بیومتریک با استفاده از دستگاه های پوشیدنی در تنظیمات واقعی-2021
The popularity of wearable devices, such as smart glasses, chestbands, and wristbands, is nowadays rapidly growing, thanks to the fact that they can be used to track physical activity and monitor users’ health. Recently, researchers have proposed to exploit their capability to collect physiological signals for enabling automatic user recognition. Wearable devices inherently provide the means for detecting their unauthorized usage, or for being used as front-end in biometric recognition systems controlling the access to either physical or virtual locations and services. The present work evaluates the feasibility of performing biometric recognition using signals captured by wearable devices, considering data collected through off-the-shelf commercial wristbands, and comparing recordings taken during two distinct sessions separated by an average time of 7 days. In more detail, recognition is performed leveraging on electrodermal activity (EDA) and blood volume pulse (BVP), considering measurements taken from 17 subjects performing natural activities such as attending or teaching lectures. Several tests have been carried out to determine the most effective representation of the considered EDA and BVP signals, as well as the most suitable classifier. The best recognition performance has been achieved exploiting convolutional neural networks to extract discriminative characteristics from the combined spectrograms of the employed EDA and BVP data, guaranteeing average correct identification rate of 98.58% for test samples lasting 30 seconds.
Keywords: Wearable | Biometrics | Machine learning
Image-based body mass prediction of heifers using deep neural networks
پیش بینی توده بدن مبتنی بر تصویر تلیسه ها با استفاده از شبکه های عصبی عمیق-2021
Manual weighing of heifers is time-consuming, labour-intensive, expensive, and can be dangerous and risky for both humans and animals because it requires the animal to be stationary. To overcome this problem, automated approaches have been developed using computer vision techniques. In this research, the aim was to design a novel mass prediction model using deep learning algorithms for youngstock on dairy farms. The MaskRCNN segmentation algorithm was used to segment the images of heifers and remove the background. A convolutional neural networks (CNN) model was developed on the Keras platform to predict the body mass of heifers. For the case study, a new dataset based on images of 63 heifers was built. Animals were between the age of 0 and 365 days and lived on the same farm in the Netherlands. The range of body mass of the heifers was between 37 kg and 370 kg. The side-view model had a coefficient of determination (R2) of 0.91 and a Root Mean Squared Error (RMSE) of 27 kg, the top-view model had an R2 of 0.96 and an RMSE of 20 kg. The experimental results demonstrated that our proposed mass prediction model using the Mask-RCNN segmentation algorithm, together with a novel CNN-based model, provided remarkable results, and that the top view was more suitable than the side view for predicting the body mass of youngstock in dairy farms.
Keywords: Deep learning | Computer vision | Body weight prediction | Convolutional neural network
Embedded vision device integration via OPC UA: Design and evaluation of a neural network-based monitoring system for Industry 4:0
ادغام دستگاه بینایی توکار از طریق OPC UA: طراحی و ارزیابی یک سیستم مانیتورینگ مبتنی بر شبکه عصبی برای صنعت 4:0-2021
Sensor application is a basis for digitized industrial value creation. However, for existing production and logistics systems, sensor retrofitting is accompanied by challenges, including plant heterogeneity and lack of standards. This work addresses this issue through the design, implementation and evaluation of an embedded vision high-bay shelf monitoring system of an Industry 4.0 demonstrator. Utilizing design science research methodologies, the artifact unites the concepts of computer vision, convolutional neural networks and OPC UA for widely applicable and cost-efficient retrofitting. Design principles derived from the artifact’s design and evaluation cycles can serve as abstracted guidelines for designing retrofit visual sensor systems.© 2021 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0)Peer-review under responsibility of the scientific committee of the 31st CIRP Design Conference 2021.
Keywords: Embedded vision | Retrofitted sensor systems | Neural networks | OPC UA | Industry 4.0
Smart attendance using deep learning and computer vision
حضور هوشمند با استفاده از یادگیری عمیق و بینایی ماشین-2021
Attendance is an essential part of daily classroom evaluation. Traditional classroom follows a manual attendance marking system, i.e., calling a student’s names or by forwarding an attendance sheet. This process is both time-consuming and error-prone, i.e., student proxy, etc. Hence a face recognition based smart classroom attendance management system using computer vision and deep learning implemented on a Raspberry Pi has been proposed. It has been proposed to mount a camera at the top of the blackboard so that the students are visible while they are sitting down. A face detection algorithm followed by face recognition has been used to mark the attendance of the detected student.© 2020 Elsevier Ltd. All rights reserved. Selection and peer-review under responsibility of the scientific committee of the International Conference on Materials, Manufacturing and Mechanical Engineering for Sustainable Developments-2020.
Keywords: Convolutional Neural networks | Deep learning | Facenet | Haar cascades | Raspberry Pi | Smart classroom