Fig 3 - uploaded by Martin Sagayam
Content may be subject to copyright.
Cambridge hand dataset: five different classes of hand gesture data (a) Flat to left (b) Flat to right (c) Flat to contract (d) V-shape to left (e) V-shape to right
Source publication
The authors develop an advanced hand motion recognition system for virtual reality applications using a well defined stochastic mathematical approach. Hand gesture is a natural way of interaction with a computer by interpreting the primitive characteristics of gesture movement to the system. This concerns three basic issues: (1) there is no physica...
Contexts in source publication
Context 1
... five different hand gestures in the database: flat to left, flat to right, flat to contract, V-shape left, and V-shape right, which are taken from the Cambridge hand dataset from Imperial college, London [36,37]. Each class has 60 frames per second, dimensions of 320 × 240, and total 300 hand gestures, which are stored in the database shown in Fig. 3. Consider the case of a hand moving from flat to left position which takes the sample data of the 0th, 15th, 30th, 45th, and 60th frame from the total frames per second as shown in Fig. 4. An input hand gesture pattern shows as a shadow on the screen, which leads to the wrong decision while cropping the edge of the hand data. There are ...
Context 2
... this work, five different classes of Cambridge hand gesture data consists of 60 frames with dimensions of 320 × 240, so in total 300 images are stored in the database. These gestures are labeled as flat-to-left, flat-to-right, flat-to-contract, V-shape left, and V-shape right, which are shown in Fig. 3. These data are pre- processed by using an edge detection technique. This is used to crop the hand contour region from the image without cropping the shadow and other content in the image dataset. In edge detection techniques, there are four different operators: Sobel, Prewitt, Canny, and Robert. Among these four, the Sobel operator ...
Similar publications
This article proposes a comparative analysis between Artificial Bee Colony and Genetic Algorithm metaheuristics with Random Search, applied to load balancing problems in electrical energy distribution networks. The objective is to determine the best way to connect different classes of consumers to the system buses, where is desired the combination...
Citations
... In ref. [26], the authors used a well-defined stochastic mathematical technique to build a sophisticated hand motion detection system for use in VR applications. First, the user and system do not make physical contact; second, geometric factors may dictate the hand gesture's rotation; and third, to increase measurement performance, the model parameter must be adjusted. ...
In recent years, Sign Language Recognition (SLR) has become an additional topic of discussion in the human–computer interface (HCI) field. The most significant difficulty confronting SLR recognition is finding algorithms that will scale effectively with a growing vocabulary size and a limited supply of training data for signer-independent applications. Due to its sensitivity to shape information, automated SLR based on hidden Markov models (HMMs) cannot characterize the confusing distributions of the observations in gesture features with sufficiently precise parameters. In order to simulate uncertainty in hypothesis spaces, many scholars provide an extension of the HMMs, utilizing higher-order fuzzy sets to generate interval-type-2 fuzzy HMMs. This expansion is helpful because it brings the uncertainty and fuzziness of conventional HMM mapping under control. The neutrosophic sets are used in this work to deal with indeterminacy in a practical SLR setting. Existing interval-type-2 fuzzy HMMs cannot consider uncertain information that includes indeterminacy. However, the neutrosophic hidden Markov model successfully identifies the best route between states when there is vagueness. This expansion is helpful because it brings the uncertainty and fuzziness of conventional HMM mapping under control. The neutrosophic three membership functions (truth, indeterminate, and falsity grades) provide more layers of autonomy for assessing HMM’s uncertainty. This approach could be helpful for an extensive vocabulary and hence seeks to solve the scalability issue. In addition, it may function independently of the signer, without needing data gloves or any other input devices. The experimental results demonstrate that the neutrosophic HMM is nearly as computationally difficult as the fuzzy HMM but has a similar performance and is more robust to gesture variations.
... Sathish et al also used a radiated source neural network with exponential CSA for the instinctive cataloging in MRI images [39]. Cuckoo search algorithm (CSA) has been also used along with other NIOAs known as the Hybrid Cuckoo search algorithm [37]. Recently in 2016, Agrawal et al proposed a novel idea of developing a Hybrid CS-BFO algorithm for getting the optimized multilevel image threshold value for edge magnitude information [2]. ...
Poor quality images in Magnetic Resonance Imaging (MRI) may not provide enough information for visual interpretation of the affected areas of the human body. Cuckoo Search Constrained Gamma Masking for MRI Image Contrast Enhancement is a novel adaptive image enhancement technique described in this paper to improve image views and give computational support. Nature-inspired algorithms are widely applied in the arena of image enhancement for various optimization purposes. Cuckoo search is one of the prominent nature-inspired performance algorithms that we employed in this work for the enhancement of magnetic resonance imaging (MRI). We proposed a wavelet-based masking technique employing a cuckoo search algorithm whose masking value is corrected by gamma function for the contrast enhancement of MRI images. The cuckoo search algorithm can inevitably fine-tune the relation of nest building using genetic operatives like adaptive cusp and alteration. The proposed contrast enhancement scheme is examined quantitatively for different types of MRI images. Extensive simulation results compared with quantitative values have revealed that the traditional nest building of cuckoo search optimization is improved by adaptive gamma correction. Comparative analysis with the existing works establishes the usefulness of the proposed methodology over the other standard approaches.
... We studied three common classification methods suitable for the MediaPipe framework [18,23,24]: (1) the BP neural network approach, with the structure of the neural network model shown in Table 2; (2) the LSTM network, with the structure of the LSTM network model shown in Table 3; and (3) by calculating the distance between the sampling sequence and the template sequence. The commonly used method for calculating the time series distance is dynamic time warping (DTW). ...
As in-vehicle information systems (IVIS) grow increasingly complex, the demand for innovative artificial intelligence-based interaction methods that enhance cybersecurity becomes more crucial. In-air gestures offer a promising solution due to their intuitiveness and individual uniqueness, potentially improving security in human–computer interactions. However, the impact of in-air gestures on driver distraction during in-vehicle tasks and the scarcity of skeleton-based in-air gesture recognition methods in IVIS remain largely unexplored. To address these challenges, we developed a skeleton-based framework specifically tailored for IVIS that recognizes in-air gestures, classifying them as static or dynamic. Our gesture model, tested on the large-scale AUTSL dataset, demonstrates accuracy comparable to state-of-the-art methods and increased efficiency on mobile devices. In comparative experiments between in-air gestures and touch interactions within a driving simulation environment, we established an evaluation system to assess the driver’s attention level during driving. Our findings indicate that in-air gestures provide a more efficient and less distracting interaction solution for IVIS in multi-goal driving environments, significantly improving driving performance by 65%. The proposed framework can serve as a valuable tool for designing future in-air gesture-based interfaces for IVIS, contributing to enhanced cybersecurity.
... Furthermore, increasing the training percentage to 50% greatly improves the RR of our system from 81.11% to 92.89%. The achieved RR exceeds the performance of HMM used in [55], yet the methods used in [63] achieved a higher RR of 98.23%. ...
In recent years, researchers have been focusing on developing Human-Computer Interfaces that are fast, intuitive, and allow direct interaction with the computing environment. One of the most natural ways of communication is hand gestures. In this context, many systems were developed to recognize hand gestures using numerous vision-based techniques, these systems are highly affected by acquisition constraints, such as resolution, noise, lighting condition, hand shape, and pose. To enhance the performance under such constraints, we propose a static and dynamic hand gesture recognition system, which utilizes the Dual-Tree Complex Wavelet Transform to produce an approximation image characterized by less noise and redundancy. Subsequently, the Histogram of Oriented Gradients is applied to the resulting image to extract relevant information and produce a compact features vector. For classification, we compare the performance of three Artificial Neural Networks, namely, MLP, PNN, and RBNN. Random Decision Forest and SVM classifiers are also used to ameliorate the efficiency of our system. Experimental evaluation is performed on four datasets composed of alphabet signs and dynamic gestures. The obtained results demonstrate the efficiency of the combined features, for which the achieved recognition rates were comparable to the state-of-the-art.
... Sathish and Elango also used a radiated source neural network with exponential CSA for the instinctive cataloging in MRI images [35]. Cuckoo search algorithm (CSA) has been also used along with other NIOAs known as the Hybrid Cuckoo search algorithm [36]. Recently in 2016, Choubey et al. proposed a novel idea of developing a Hybrid CS-BFO algorithm for getting the optimized multilevel image threshold value for edge magnitude information [37]. ...
Nature-inspired algorithms are widely applied in the arena of image enhancement for various optimization purposes. To address the optimization complexities in various image enhancement approaches, nature-inspired optimization algorithms play a vital role. Cuckoo search is one of the prominent nature-inspired performance algorithms that we employed in this work for the enhancement of magnetic resonance imaging (MRI). We proposed a wavelet-based masking technique employing a cuckoo search algorithm whose masking value is corrected by gamma function for the contrast enhancement of MRI images. The cuckoo search algorithm can inevitably fine-tune the relation of nest building using genetic operatives like adaptive cusp and alteration. The proposed contrast enhancement scheme is examined quantitatively for different types of MRI images. Extensive simulation results compared with quantitative values have revealed that the traditional nest building of cuckoo search optimization is improved by adaptive gamma correction. Comparative analysis with the existing works establishes the usefulness of the proposed methodology over the other standard approaches.
... There is a situation where the distribution of one class differs from other class (or classes), known as the class imbalance problem [3]. Since the imbalance situation is recurring in many real-world applications, it has been a topic of interest for researchers in recent years [4][5][6][7][8][9][10][11][12][13][14]. ...
In classification, one of the common problems is the class imbalance problem. This phenomenon that is growing significance emerges in most real fields and occurs when data samples are distributed among classes unevenly. This means that most of the data are in the larger class, and there are fewer data in the smaller class. Since standard classifiers do not consider the distribution of imbalanced class, they indicate undesirable behavior in facing them. Many techniques have been proposed to solve the problem of class imbalance. Among these methods, a group called preprocessing techniques tries to create a balance between training sets. These methods balance the classes’ distribution by removing redundant samples from the larger class or creating new samples for the smaller one. The first group is known as under-sampling, and the second one is known as over-sampling techniques. In this paper, we propose a score-based preprocessing technique based on both under-sampling and over-sampling to overcome the weakness of classifiers in class imbalance problems. For this purpose, we apply the sharing strategy in both stages to determine more suitable samples based on their importance in the feature space. In the over-sampling stage, the smaller class’s synthetic samples are generated by interpolating between more sparse samples. After that, in the under-sampling stage, denser samples of the larger class are selected to be removed. We use the binary tournament selection operator in both stages to perform over-sampling and under-sampling based on probabilities. In experiments, the support vector machine (SVM) is employed to train a classification model from the balanced training sets obtained by different preprocessing methods. Besides, F-measure and AUC measures are considered as evaluation tools. At the last step, we compare all methods in terms of the classification model’s complexity. According to the results obtained from 44 standard imbalanced datasets, the proposed method’s superiority and effectiveness compared to other methods have been revealed.
... The difficulty of visual tracking is to ensure the algorithm's accuracy, adaptability, and real-time performance while the target and environment constantly change. Appearance and scale changes caused by object movement or nonrigid deformation, shooting angle and ambient illumination variation, obscured objects or targets beyond the field of view are likely to impact feature extraction, search strategy, and the final tracking performance [54,55,65]. Many classical algorithms have been proposed to solve the above problems, such as distance measurement similarity [1,27,49,52], mean-shift [11][12][13], particle filtering [25,45], and correlation filtering [4,26]. ...
Visual tracking is a challenging task in computer vision, which intends to estimate the motion state of the target of interest in subsequent video frames. In that context, it is well-known that the rapid movement and rotation of the target affects the tracking results. This article proposes a novel single-target tracking algorithm based on the spatially weighted generalized Gaussian mixture model framework. The clustering method for color compression in preprocessing is considered to modify the frames to make them have sharper distributions. Then, the mixture models are built to express the color statistical features of the aimed area and context. The segmentation weights obtained from the responsivity of the pixels in the candidate ellipse to the target and background will guide the update of the target position and size in a heuristic way. The adjustment of models will depend on the aspect ratio change of the bounding ellipse. The performance of the proposed approach is verified on public datasets and compared with other algorithms. The experimental results show that our method achieved more accurate and robust tracking.
... Dunleavy et al. designed a quasirandomized parallel controlled study and set up a community, university, and private clinic environments in four locations. 56 CNP participants scored ≥3/10 individuals over 3 months on the Digital Pain Rating Scale (control group n � 17, Pilates n � 20, yoga n � 19) [5]. Intervention exercise participants completed 12 group meetings, which were revised and progressed under the supervision of a physical therapist [6]. ...
Rehabilitation of the pelvic floor after delivery is very important for women. Pelvic floor rehabilitation can speed up the recovery of the postpartum vagina and pelvic floor muscle tension and elasticity and have a good effect on the prevention and treatment of postpartum vaginal prolapse and relaxation, urinary incontinence and other pelvic floor disorders. Thus, this article focuses on yoga exercise to explore its impact on postpartum pelvic floor rehabilitation. This article uses electrical stimulation and the treatment of pelvic floor muscles combined with the posture recognition algorithm, the yoga rehabilitation training program that has the best effect on the parturient is obtained, and the yoga myoelectric stimulation combined method and the traditional myoelectric stimulation method are designed for comparison experiments. The experimental results show that the parturients who have undergone the combined method of yoga myoelectric stimulation, in the resting state, contraction state, and Valsalva state, the position of the bladder meridian, the position of the uterus, and the position of the rectal ampulla of the parturient have a significant recovery compared those who have undergone the traditional electromyography treatment. In addition, the average area of hiatus in the pelvic floor ultrasound examination in the control group 42 days postpartum was 12.2605 cm2, while the average area of the hiatus in the pelvic floor ultrasound examination in the experimental group 42 days postpartum was 10.788 cm2; the average area of hiatus in the pelvic floor ultrasound examination in the control group at 3 months postpartum was 11.4805 cm2, and the average area of hiatus in the pelvic floor ultrasound examination in the experimental group at 3 months postpartum was 8.9475 cm2. To sum up, yoga had a very significant improvement on the physical indicators and mental health of postpartum women.
... Generalized classification of the optimization techniques[1][2][3][4][5][6][7]. ...
Most of the real-world optimization problems involve various complexities, including nonlinearity, nonconvexity, discontinuity, and mixed variable types. In such cases, the classical algorithms are found to be either impractical or ineffective. In response, the search and optimization algorithms developed using heuristics offer a reasonable alternative. They are usually stochastic in nature and mimic the natural, physical, or biological principles. However, the metaheuristic techniques do not claim to achieve the exact global optimal solutions, but they always provide the near-optimal solution in a competitive time. Therefore, their practical appeal and ease of implementation, and the devise of high-speed computational devices made them popular in many application domains. This chapter provides the backgrounds, working principles, flowcharts, and pseudocodes of several popular and widely adopted metaheuristic algorithms. The discussion of the chapter shall assist the readers in understanding the fundamental features and differences of the explored algorithms that eventually guide them to choose the most appropriate algorithms for their problems. Moreover, many of the discussed algorithms are employed in solving several optimization problems throughout this book.
HVAC systems are notorious for their high energy consumption in buildings, particularly in regions with extreme cooling or heating demands. Air filters play a vital role in these systems, affecting both energy efficiency and indoor air quality. However, high-efficiency filters, due to their significant increase in airflow resistance, require excessive energy compared to low-efficiency filters. This poses a challenge in finding the optimal compromise between reducing energy consumption and enhancing indoor air quality. To address this challenge, a meticulous selection process is crucial in achieving a middle ground that satisfies both objectives. Proper sizing and design of air filters are therefore essential for successful HVAC projects. This paper introduces the utilization of optimization techniques as decision-support tools to determine the optimal design parameters of commonly used HVAC air filters under various scenarios. The developed model incorporates multiple objectives and design criteria, including life-cycle cost (LCC), filter size, and efficiency. By leveraging the Differential Evolution (DE) optimization technique, an algorithm is developed to forecast a range of optimal solutions (Pareto front) based on predefined system criteria and boundary conditions. The model is extensively tested and demonstrates exceptional performance in returning optimal solutions, in addition to the capability of narrowing down and converging to a single value. This methodology holds significant potential in assisting investment decisions concerning HVAC air filters, providing valuable insights for optimizing energy efficiency while ensuring satisfactory indoor air quality.
