In ethology research, there have been growing interests in using machine learning method to detect animals and analyze their behaviors, especially from video data. However, behavior analysis is still challenging in th...
详细信息
ISBN:
(纸本)9783031477232;9783031477249
In ethology research, there have been growing interests in using machine learning method to detect animals and analyze their behaviors, especially from video data. However, behavior analysis is still challenging in the outdoor environment because of the dynamic background and sudden illumination changes. Instead of the previous laboratory setting, we aimed to perform animal behavior analysis outdoors. Specifically, our target of detection and behavior analysis is a polar bear captured by a security camera in a zoo. We focus on analyzing stereotypical behavior, which is critical for understanding the psychological stress of animals. For detection and analysis, we proposed a method that includes background extraction, object detection, and repeating pattern detection for stereotypical behavior detection based on the compression ratio of the detected bear's location sequences under serialization. Our experimental result shows our method could provide accurate detection (98.3%AP50) and behavior recognition (Accuracy 90.6%) while maintaining high robustness to various noises.
This paper proposes a human-motion guided frame selection approach for violent video classification. The human-motion features are computed by determining the frame difference within the detected human regions. Additi...
详细信息
ISBN:
(数字)9783031585616
ISBN:
(纸本)9783031585609;9783031585616
This paper proposes a human-motion guided frame selection approach for violent video classification. The human-motion features are computed by determining the frame difference within the detected human regions. Additionally, adaptive gamma correction is introduced in the motion signal to mitigate abrupt motion. The experiment is evaluated on RWF-2000 dataset by using I3D network as a classification model. The empirical results demonstrate that the proposed method outperforms the state-of-the-art methods in violent classification. Selecting more informative frames can improve the classification performance compared to traditional frame selection methods that use uniform sampling. Therefore, the proposed method enables the extraction of more informative frames.
Diabetes is a prevalent global ailment that results in dysfunction in multiple organs throughout the body. Dysfunction in the autonomous nervous system (ANS) and cardiac health due to elevated glucose levels are studi...
详细信息
ISBN:
(数字)9789819713202
ISBN:
(纸本)9789819713196;9789819713202
Diabetes is a prevalent global ailment that results in dysfunction in multiple organs throughout the body. Dysfunction in the autonomous nervous system (ANS) and cardiac health due to elevated glucose levels are studied from one time heart rate variability (HRV) analysis. Regular analysis is essential to monitor the rate of degradation caused by diabetes. This study introduces a three-stage HRV analysis to investigate the cardiac health decline resulting from diabetes. Diabetes data, collected during 15-minute recording sessions in both supine and sitting positions, undergoes analysis in three distinct phases. The time gap between the two ECG readings is six months. Patients with diabetes may or may not be taking medication. The outcomes of a three-point investigation will aid in evaluating changes, either deteriorative or ameliorative, in the cardiac health of these patients. The findings indicate that the orthostatic stress index (OSI) and the LF/HF ratio prove to be highly responsive and efficient indicators for assessing the decline in cardiac health. These parameter values can guide medical practitioners in prescribing appropriate medications.
Designing an algorithm capable of extrapolating a periodic signal with Poisson noise turns out to be a difficult problem. In this work, we focused on the extrapolation of this kind of a signal using a convolutional ne...
详细信息
ISBN:
(纸本)9783031705946;9783031705953
Designing an algorithm capable of extrapolating a periodic signal with Poisson noise turns out to be a difficult problem. In this work, we focused on the extrapolation of this kind of a signal using a convolutional neural network and recurrent neural network. It appears that simulations with real noise level is problematic. For extrapolation to be correct, we need an algorithm that can either predict the signal with real Poisson noise or the pure signal without the noise (Poisson noise can be subsequently added). This means that it must find the character of the signal (period, amplitude, phase, and modulation of the signal). It turns out that convolutional and recurrent neural networks are capable of just such an extrapolation. Next, we focused on the methods of data preprocessing (standardization and normalization) and found out how they affect the results. Although preprocessing is used to make machine learning algorithms work faster and more accurately, it turns out that it is not always the case.
Modern metal fabrication would not be possible without highly efficient welding processes. One of them is Gas Metal Arc Welding (GMAW), which has several variants, including pulsed. Pulsing significantly reduces spatt...
详细信息
ISBN:
(纸本)9783031662676;9783031662683
Modern metal fabrication would not be possible without highly efficient welding processes. One of them is Gas Metal Arc Welding (GMAW), which has several variants, including pulsed. Pulsing significantly reduces spatter and is widely used in fully mechanized and robotic welding systems. On the other side, large-scale welding needs adequate and efficient heat input and seam geometry control. This paper presents models describing heat input as the function of required weld geometry. Research has been made using low-alloyed structural steels with two thicknesses, 4 mm and 8 mm, using pulsed GMAW in horizontal position, while models have been developed using statistical tools. This paper elaborates advantages and disadvantages of such approach, as well as comparison with similar concepts available in literature.
Uninorms in bounded lattices that are outstanding expansions of triangular norms and triangular conorms have drawn much attention from investigators. These operators give permission the identity i to be situated in an...
详细信息
ISBN:
(纸本)9783031671913;9783031671920
Uninorms in bounded lattices that are outstanding expansions of triangular norms and triangular conorms have drawn much attention from investigators. These operators give permission the identity i to be situated in any place of a bounded lattice T that includes the greatest element and smallest element, represented as 1 and 0, respectively. Specifically, a uninorm is transformed into a triangular norm (or triangular conorm) whenever i = 1 (or i = 0). In this article, two procedures are proposed to build innovative forms of uninorms in a bounded lattice T through a uninorm determined in the sublattice [0, k] (or [t, 1]) of T that possesses an identity i is an element of]0, k[ (or i is an element of]t, 1[). Furthermore, some explicatory examples are put forward in order to display that these building procedures for uninorms vary from the present ones in the literature.
In recent years, many of the piping systems used in Japan are more than 50 years old, and the risk of rupture due to aging is increasing. Therefore, many researches related to inspection robots that can navigate insid...
详细信息
ISBN:
(纸本)9783031707216;9783031707223
In recent years, many of the piping systems used in Japan are more than 50 years old, and the risk of rupture due to aging is increasing. Therefore, many researches related to inspection robots that can navigate inside pipes are presented. However, general mobile robots can only be used in large-diameter pipes. In this study, a micro-robot that can be used for small-diameter in-pipe inspection tasks is introduced. The robot is fitted with magnetic wheels that permit locomotion on metal surfaces even in the vertical direction. In addition, a micro ultrasonic motor that can generate high torque is developed for the actuation mechanism. The micromotor generates a torque of about 30 mu Nm at 40 Vp-p. To achieve higher mobility, the micro ultrasonic motor is integrated with the smallest planetary gear system ever built. In the demonstration, the mobility performance of the robot is evaluated through a series of experiments.
Cotton is one of the most widely cultivated crops in the world, with a large proportion grown in developing countries. For better cotton management and yield, deep learning techniques are developed in this work. There...
详细信息
ISBN:
(纸本)9783031477232;9783031477249
Cotton is one of the most widely cultivated crops in the world, with a large proportion grown in developing countries. For better cotton management and yield, deep learning techniques are developed in this work. Therefore, the aim of this paper is twofold: first to create an open-source dataset of healthy and diseased cotton leaves (leaf curl virus-affected). A new custom dataset and the training/validation/testing sets and the raw dataset themselves have been provided in the GitHub repository. Secondly, to develop image classification models based on Convolution Neural networks (CNNs) through an initial baseline model and Vision Transformer ( ViT) of the cotton leaves. It shows how the vanilla model for a vision transformer with the addition of existing algorithms such as shifted patch tokenisation and locality self-attention can be used in this context to give over 80% accuracy on an unseen testing dataset. Facebook Research's ConViT hybrid model with GPSA layers is also evaluated in this context, using the automatic andmanual implementation from code, and has shown the "convit-base" model providing nearly 85% accuracy and better generalisation over the epochs of training than the CNN baselines and the ViT model.
The quantum processors' performance is predicted to surpass the application of variational quantum algorithms in finance has proven to be instrumental in addressing crucial challenges. From enhancing security thro...
详细信息
ISBN:
(纸本)9789819733019;9789819733026
The quantum processors' performance is predicted to surpass the application of variational quantum algorithms in finance has proven to be instrumental in addressing crucial challenges. From enhancing security through anomaly detection and fraud indicator identification to optimizing credit scoring and improving stock price prediction, VQAs demonstrate their versatility and potential to revolutionize the financial industry's analytical capabilities. As quantum computing continues to advance, the integration of VQAs is expected to play an increasingly pivotal role in shaping the future of financial technology. In this paper, we review variational quantum algorithms in anomaly detection and fraud indicator systems, credit scoring, and stock price prediction.
In the article, we evaluate ten precipitation products against rain gauges. The time coverage consists of 25 days in different years, seasons and average daily totals. The metrics used are correlations and RMSE, which...
详细信息
ISBN:
(纸本)9783031702846;9783031702853
In the article, we evaluate ten precipitation products against rain gauges. The time coverage consists of 25 days in different years, seasons and average daily totals. The metrics used are correlations and RMSE, which we categorize by precipitation classes. According to the measured results, the products with the highest average correlations and the lowest average RMSE values are EURAD, Icon and Icon-EU. We have recorded the positive impact of applying different types of pre-processing to precipitation products.
暂无评论