多通道神经元锋电位检测和分类的新方法

大脑神经元胞外单细胞动作电位(即锋电位)的检测和分类是提取神经元脉冲序列、研究神经系统信息处理机制的关键．为了提高锋电位的检出率和分类的正确性,设计了一种处理多通道锋电位记录信号的算法,用于分析微电极阵列记录的大鼠海马神经元锋电位信号,电极阵列上的测量点排列紧密,4个通道可以同时记录到来自相同神经元的信号．该算法首先利用一种多通道阈值检测法检出四通道记录信号中的锋电位,然后利用一种基于复合锋电位的主成分特征参数分类法将锋电位分类．仿真数据和实验记录信号的检验结果表明：与相应的单通道算法相比,该算法的锋电位检出率和分类的正确性显著提高,并且可以增加单次实验测得的神经元数目．因此,该算法为实现神经元锋电位的自动检测提供了一种简单有效的新 方法．     

Automatic recognition of bird individuals on an open set using as-is recordings

The most common method used to determine the identity of an individual bird is the capture-mark-recapture technique. The method has several major disadvantages, e.g. some species are difficult to capture/recapture and the capturing process itself may cause significant stress in animals leading even to injuries of more vulnerable species. Some studies introduce systems based on methods used for human identification. An automatic system for recognition of bird individuals (ASRBI) described in this article is based on a Gaussian mixture model (GMM) and a universal background model (GMM-UBM) method extended by an advanced voice activity detection (VAD) algorithm. It is focused on recognizing the bird individuals on an open set, i.e. any number of unknown birds may appear anytime during the identification process as is common in nature. The introduced ASRBI processes the recordings just as if they were recorded by an ornithologist: with durations from seconds to minutes, containing noise and unwanted sounds, as well as masking of the singer, etc. Thanks to the VAD algorithm, the proposed system is fully automatic, no manual pre-processing of recordings is needed, neither by cutting off the songs nor syllables. The overall achieved identification accuracy is 78.5%, the lowest 60.3% and the highest 95.7%. In total, 90% of all experiments reach at least 70% accuracy. The result suggests the application of the GMM-UBM with VAD is feasible for individual identification on the open set processing real-life recordings. The described method is capable of reducing both the time consumption and human intervention in animal monitoring projects.     

Identification of Behaviour in Freely Moving Dogs (Canis familiaris) Using Inertial Sensors

Monitoring and describing the physical movements and body postures of animals is one of the most fundamental tasks of ethology. The more precise the observations are the more sophisticated the interpretations can be about the biology of a certain individual or species. Animal-borne data loggers have recently contributed much to the collection of motion-data from individuals, however, the problem of translating these measurements to distinct behavioural categories to create an ethogram is not overcome yet. The objective of the present study was to develop a “behaviour tracker”: a system composed of a multiple sensor data-logger device (with a tri-axial accelerometer and a tri-axial gyroscope) and a supervised learning algorithm as means of automated identification of the behaviour of freely moving dogs. We collected parallel sensor measurements and video recordings of each of our subjects (Belgian Malinois, N=12; Labrador Retrievers, N=12) that were guided through a predetermined series of standard activities. Seven behavioural categories (lay, sit, stand, walk, trot, gallop, canter) were pre-defined and each video recording was tagged accordingly. Evaluation of the measurements was performed by support vector machine (SVM) classification. During the analysis we used different combinations of independent measurements for training and validation (belonging to the same or different individuals or using different training data size) to determine the robustness of the application. We reached an overall accuracy of above 90% perfect identification of all the defined seven categories of behaviour when both training and validation data belonged to the same individual, and over 80% perfect recognition rate using a generalized training data set of multiple subjects. Our results indicate that the present method provides a good model for an easily applicable, fast, automatic behaviour classification system that can be trained with arbitrary motion patterns and potentially be applied to a wide range of species and situations.     

Neonatal non-contact respiratory monitoring based on real-time infrared thermography

Background

The duration of bronchoscopy examinations varies considerably depending on the diagnostic and therapeutic procedures used. It can last more than 20 minutes if a complex diagnostic work-up is included. With wide access to videobronchoscopy, the whole procedure can be recorded as a video sequence. Common practice relies on an active attitude of the bronchoscopist who initiates the recording process and usually chooses to archive only selected views and sequences. However, it may be important to record the full bronchoscopy procedure as documentation when liability issues are at stake. Furthermore, an automatic recording of the whole procedure enables the bronchoscopist to focus solely on the performed procedures. Video recordings registered during bronchoscopies include a considerable number of frames of poor quality due to blurry or unfocused images. It seems that such frames are unavoidable due to the relatively tight endobronchial space, rapid movements of the respiratory tract due to breathing or coughing, and secretions which occur commonly in the bronchi, especially in patients suffering from pulmonary disorders.

Methods

The use of recorded bronchoscopy video sequences for diagnostic, reference and educational purposes could be considerably extended with efficient, flexible summarization algorithms. Thus, the authors developed a prototype system to create shortcuts (called summaries or abstracts) of bronchoscopy video recordings. Such a system, based on models described in previously published papers, employs image analysis methods to exclude frames or sequences of limited diagnostic or education value.

Results

The algorithm for the selection or exclusion of specific frames or shots from video sequences recorded during bronchoscopy procedures is based on several criteria, including automatic detection of "non-informative", frames showing the branching of the airways and frames including pathological lesions.

Conclusions

The paper focuses on the challenge of generating summaries of bronchoscopy video recordings.     

Medical Ultrasound Video Coding with H.265/HEVC Based on ROI Extraction

High-efficiency video compression technology is of primary importance to the storage and transmission of digital medical video in modern medical communication systems. To further improve the compression performance of medical ultrasound video, two innovative technologies based on diagnostic region-of-interest (ROI) extraction using the high efficiency video coding (H.265/HEVC) standard are presented in this paper. First, an effective ROI extraction algorithm based on image textural features is proposed to strengthen the applicability of ROI detection results in the H.265/HEVC quad-tree coding structure. Second, a hierarchical coding method based on transform coefficient adjustment and a quantization parameter (QP) selection process is designed to implement the otherness encoding for ROIs and non-ROIs. Experimental results demonstrate that the proposed optimization strategy significantly improves the coding performance by achieving a BD-BR reduction of 13.52% and a BD-PSNR gain of 1.16 dB on average compared to H.265/HEVC (HM15.0). The proposed medical video coding algorithm is expected to satisfy low bit-rate compression requirements for modern medical communication systems.     

Real-time fish detection in complex backgrounds using probabilistic background modelling

Computer vision and image processing approaches for automatic underwater fish detection are gaining attention of marine scientists as quicker and low-cost methods for estimating fish biomass and assemblage in oceans and fresh water bodies. However, the main challenge that is encountered in unconstrained underwater imagery is poor luminosity, turbidity, background confusion and foreground camouflage that make conventional approaches compromise on their performance due to missed detections or high false alarm rates. Gaussian Mixture Modelling is a powerful approach to segment foreground fish from the background objects through learning the background pixel distribution. In this paper, we present an algorithm based on Gaussian Mixture Models together with Pixel-Wise Posteriors for fish detection in complex background scenarios. We report the results of our method on the benchmark Complex Background dataset that is extracted from Fish4Knowledge repository. Our proposed method yields an F-score of 84.3%, which is the highest score reported so far on the aforementioned dataset for detecting fish in an unconstrained environment.     

Neural network based temporal video segmentation

The organization of video information in video databases requires automatic temporal segmentation with minimal user interaction. As neural networks are capable of learning the characteristics of various video segments and clustering them accordingly, in this paper, a neural network based technique is developed to segment the video sequence into shots automatically and with a minimum number of user-defined parameters. We propose to employ growing neural gas (GNG) networks and integrate multiple frame difference features to efficiently detect shot boundaries in the video. Experimental results are presented to illustrate the good performance of the proposed scheme on real video sequences.     

Voice Pathologies Classification and Detection Using EMD-DWT Analysis Based on Higher Order Statistic Features

BackgroundThe voice is a prominent tool allowing people to communicate and to change information in their daily activities. However, any slight alteration in the voice production system may affect the voice quality. Over the last years, researchers in biomedical engineering field worked to develop a robust automatic system that may help clinicians to perform a preventive diagnosis in order to detect the voice pathologies in an early stage.MethodIn this context, pathological voice detection and classification method based on EMD-DWT analysis and Higher Order Statistics (HOS) features, is proposed. Also DWT coefficients features are extracted and tested. To carry out our experiments a wide subset of voice signal from normal subjects and subjects which suffer from the five most frequent pathologies in the Saarbrücken Voice Database (SVD), is selected. In The first step, we applied the Empirical Mode Decomposition (EMD) to the voice signal. Afterwards, among the obtained candidates of Intrinsic Mode Functions (IMFs), we choose the robust one based on temporal energy criterion. In the second step, the selected IMF was decomposed via the Discrete Wavelet Transform (DWT). As a result, two features vector includes six HOSs parameters, and a features vector includes six DWT features were formed from both approximation and detail coefficients. In order to classify the obtained data a support vector machine (SVM) is employed. After having trained the proposed system using the SVD database, the system was evaluated using voice signals of volunteer's subjects from the Neurological department of RABTA Hospital of Tunis.ResultsThe proposed method gives promising results in pathological voices detection. The accuracies reached 99.26% using HOS features and 93.1% using DWT features for SVD database. In the classification, an accuracy of 100% was reached for “Funktionelle Dysphonia vs. Rekrrensparese” based on HOS features. Nevertheless, using DWT features the accuracy achieved was 90.32% for “Hyperfunktionelle Dysphonia vs. Rekurrensparse”. Furthermore, in the validation the accuracies reached were 94.82%, 91.37% for HOS and DWT features, respectively. In the classification the highest accuracies reached were for classifying “Parkinson versus Paralysis” 94.44% and 88.87% based on HOS and DWT features, respectively.ConclusionHOS features show promising results in the automatic voice pathology detection and classification compared to DWT features. Thus, it can reliably be used as noninvasive tool to assist clinical evaluation for pathological voices identification.     

Fast Fight Detection

Action recognition has become a hot topic within computer vision. However, the action recognition community has focused mainly on relatively simple actions like clapping, walking, jogging, etc. The detection of specific events with direct practical use such as fights or in general aggressive behavior has been comparatively less studied. Such capability may be extremely useful in some video surveillance scenarios like prisons, psychiatric centers or even embedded in camera phones. As a consequence, there is growing interest in developing violence detection algorithms. Recent work considered the well-known Bag-of-Words framework for the specific problem of fight detection. Under this framework, spatio-temporal features are extracted from the video sequences and used for classification. Despite encouraging results in which high accuracy rates were achieved, the computational cost of extracting such features is prohibitive for practical applications. This work proposes a novel method to detect violence sequences. Features extracted from motion blobs are used to discriminate fight and non-fight sequences. Although the method is outperformed in accuracy by state of the art, it has a significantly faster computation time thus making it amenable for real-time applications.     

Non-invasive devices and methods for large animal monitoring using automated video processing

ObjectivesIt is now standard for polysomnographical equipment to include video recording, although this modality is generally underexploited, since there is no automated processing associated with the latter. In the present report, we investigated the set of features that can be automatically extracted from a video recording, in the context of monitoring of freely moving, non-sedated, newborn lambs.Material and methodsOur database contained seven lambs and a total of 11 recordings, using two different cameras allowing a top view and a side view. Using appropriate methodologies, we show that it is possible to estimate the lamb's movements, its posture (standing or lying) as well as its covered trajectory.ResultsResults are discussed as a function of the camera and show that side view recording is well suited for accurate scoring of the lamb's posture, whereas trajectory is best estimated using the top view camera. On the other hand, both cameras provide qualitatively similar results for the estimation of movement of the animals.ConclusionThe data gained from automated video processing, as reported herein, may have multiple applications, especially for animal studies, but may also be extended to human sleep monitoring.     

Play it again: the use of video records in behavioural studies with small cetaceans

Some difficulties arise in studying the behaviour of marine mammals at their natural habitat mainly because they spend most of their time underwater and have complex behaviours. Therefore, many protocols and sample methods are available to better assess the behavioural ecology of this animals. Here, we compared two behavioural recording methods. The first one was the direct visual observation. The second one was recording using a digital video recorder. We hypothesise that the possibility of watching recorded videos repeatedly leads to a higher quantification of behaviours compared with the direct observation method. We found a slight variation in the frequency of behaviours according to the method used. Furthermore, we found that the video recordings should not be used as a replacement for the direct observation method. Finally, we highlighted the strengths and weaknesses of both methods. We recommend that in behavioural research, the use of video recording should be careful; it is preferable that an experienced researcher uses the direct observation method, while it is best for a person with low know–how to the use the video recording method.     

Auditory evoked potentials for the assessment of depth of anaesthesia: different configurations of artefact detection algorithms.

Monitoring the depth of anaesthesia has become an important research topic in the field of biosignal processing. Auditory evoked potentials (AEPs) have been shown to be a promising tool for this purpose. Signals recorded in the noisy environment of an operating theatre are often contaminated by artefacts. Thus, artefact detection and elimination in the underlying electroencephalogram (EEG) are mandatory before AEP extraction. Determination of a suitable artefact detection configuration based on EEG data from a clinical study is described. Artefact detection algorithms and an AEP extraction procedure encompassing the artefact detection results are presented. Different configurations of artefact detection algorithms are evaluated using an AEP verification procedure and support vector machines to determine a suitable configuration for the assessment of depth of anaesthesia using AEPs.     

The implicit association between odors and illness

Some individuals ascribe health symptoms to odor exposures, even when none would be expected based on toxicological dose-effect relationships. In these situations, symptoms are believed to have been mediated by beliefs regarding the potential health effects from odorants, which implies a controlled type of information processing. From an evolutionary perspective, such a form of processing may hardly be the only route. The aim of the present study was to explore the viability of a fast and implicit route, by investigating automatic odor-related associations in the context of health. An Implicit Association Test assessing association strengths between the concept odor and the concepts healthy and sick was conducted. Three experiments (N=66, N=64, and N=64) showed a significantly stronger association between the concepts odor and sick than between odor and healthy. These results did not match explicit associations and provide evidence for a fast and automatic route of processing that may complement consciously controlled processes. A dual-processing theory of olfactory information is proposed leading to new hypotheses regarding the development and maintenance of odor-induced health symptoms.     

Vertebral pathologies in two early modern period (16th-19th century) populations from Croatia

In order to test to what degree Schmorl's nodes (SN), osteophytosis of the vertebral bodies (VO), and osteoarthritis of the articular facets (OA) are useful indicators of activity-related stress, an analysis of their frequencies and severity of expression was conducted in two early Modern period skeletal samples from Croatia--Koprivno and Sisak. Historic and contemporary ethnographic sources suggest that living conditions were more demanding in Koprivno, and that a sexual division of labor existed in both populations. A total of 2,552 vertebral bodies (990 from Koprivno and 1,562 from Sisak) and 5,186 articular facets (2,135 from Koprivno and 3,051 from Sisak) were analyzed. Koprivno exhibits significantly higher total frequencies of SN, VO, and OA than Sisak, and the total frequencies of SN and OA in both series are significantly higher in males. When, however, the series were analyzed by age and sex categories, the same trend was noted only in SN. The frequencies and severity of VO and OA could not be interpreted in keeping with the historic and contemporary ethnographic sources and were additionally, unlike SN, found to be strongly correlated with increased age. This study, therefore, suggests that while SN are useful indicators of different lifestyles and/or different activity patterns between various archaeological populations, VO and OA are-possibly because of their more varied etiologies-less useful markers of activity-related stress.     

Particle Swarm Optimization Based Feature Enhancement and Feature Selection for Improved Emotion Recognition in Speech and Glottal Signals

In the recent years, many research works have been published using speech related features for speech emotion recognition, however, recent studies show that there is a strong correlation between emotional states and glottal features. In this work, Mel-frequency cepstralcoefficients (MFCCs), linear predictive cepstral coefficients (LPCCs), perceptual linear predictive (PLP) features, gammatone filter outputs, timbral texture features, stationary wavelet transform based timbral texture features and relative wavelet packet energy and entropy features were extracted from the emotional speech (ES) signals and its glottal waveforms(GW). Particle swarm optimization based clustering (PSOC) and wrapper based particle swarm optimization (WPSO) were proposed to enhance the discerning ability of the features and to select the discriminating features respectively. Three different emotional speech databases were utilized to gauge the proposed method. Extreme learning machine (ELM) was employed to classify the different types of emotions. Different experiments were conducted and the results show that the proposed method significantly improves the speech emotion recognition performance compared to previous works published in the literature.     

Sleep apnoea detection from ECG using features extracted from reconstructed phase space and frequency domain

Sleep apnoea is a very common sleep disorder which is able to cause symptoms such as daytime sleepiness, irritability and poor concentration. This paper presents a combinational feature extraction approach based on some nonlinear features extracted from Electro Cardio Graph (ECG) Reconstructed Phase Space (RPS) and usually used frequency domain features for detection of sleep apnoea. Here 6 nonlinear features extracted from ECG RPS are combined with 3 frequency based features to reconstruct final feature set. The nonlinear features consist of Detrended Fluctuation Analysis (DFA), Correlation Dimensions (CD), 3 Large Lyapunov Exponents (LLEs) and Spectral Entropy (SE). The final proposed feature set show about 94.8% accuracy over the Physionet sleep apnoea dataset using a kernel based SVM classifier. This research also proves that using non-linear analysis to detect sleep apnoea can potentially improve the classification accuracy of apnoea detection system.     

Use of cage space by guineapigs

Cage space requirements for laboratory animals have been established by Government Regulation and Recommendations. In order to test the adequacy of these space allocations, the use of cage floor area by breeding groups of guineapigs was studied. A computer-coupled video tracking system capable of imaging in low light intensity as well as total darkness was used to determine the average per cent occupancy by guineapigs in all portions of a cage over 12-h light and dark cycles. Simultaneous time synchronized slow motion video recordings permitted an analysis of activity to be coordinated with cage use data. Results of the study revealed that breeding groups of guineapigs utilize the periphery of the cage almost to the total exclusion of the centre of the cage. Approximately 75-85% of all occupancy in both the day and evening hours occurred in 47% of the cage floor area located along the periphery. Analysis of video recordings revealed that the animals remained active throughout the day and night with no prolonged period of quiescence that could be associated with sleep. Results of this study suggest that while guidelines for housing guineapigs based on area allocation per animal can be formulated and are easy to administer, they cannot be supported by the behavioural characteristics of these animals or careful quantitation of their pattern of cage space utilization.     

Performance evaluation of a machine vision system for insect pests identification of field crops using artificial neural networks

Feature extraction is a crucial part of advanced image recognition systems. In this research, an autonomous detection device was designed and developed for insect pest detection to improve the ability of intelligent systems in order to annihilate harmful insect pests in agricultural crop fields. Device included a dark chamber, a CCD digital camera, a LDR lightening module and a personal computer. The proposed programme for precise insect pest detection was based on an image processing algorithm and artificial neural networks (ANNs). After image acquisition, the insect pests’ images were extracted from original images with Canny filtration. Afterwards, four morphological and three textural features from the obtained images were measured and normalised. Performance of ANN model was tested successfully for Beet armyworm (Spodoptera exigua) recognition in images using back-propagation supervised learning method and inspection data. Results showed that proposed system was able to identify S. exigua in the images from other species. Such this machine vision system can be used in autonomous field robots to achieve a modern farmer’s assistant.     

Classification accuracy of a single tri-axial accelerometer for training background and experience level in runners

Accelerometers are increasingly used tools for gait analysis, but there remains a lack of research on their application to running and their ability to classify running patterns. The purpose of this study was to conduct an exploratory examination into the capability of a tri-axial accelerometer to classify runners of different training backgrounds and experience levels, according to their 3-dimensional (3D) accelerometer data patterns. Training background was examined with 14 competitive soccer players and 12 experienced marathon runners, and experience level was examined with 16 first-time and the same 12 experienced marathon runners. Discrete variables were extracted from 3D accelerations during a short run using root mean square, wavelet transformation, and autocorrelation procedures. A principal component analysis (PCA) was conducted on all variables, including gait speed to account for covariance. Eight PCs were retained, explaining 88% of the variance in the data. A stepwise discriminant analysis of PCs was used to determine the binary classification accuracy for training background and experience level, with and without the PC of Speed. With Speed, the accelerometer correctly classified 96% of runners for both training background and experience level. Without Speed, the accelerometer correctly classified 85% of runners based on training background, but only 68% based on experience level. These findings suggest that the accelerometer is effective in classifying athletes of different training backgrounds, but is less effective for classifying runners of different experience levels where gait speed is the primary discriminator.