There has been latelly a significant progress in automating tasks for the agricultural sector. One of the advances is the development of robots, based on computer vision, applied to care and management of soy crops. In this task, digital image processing plays an important role, but must solve some important problems, like the ones associated to the variations in lighting conditions during image acquisition. Such variations influence directly on the brightness level of the images to be processed. In this paper we propose an algorithm to segment and measure automatically the leaf area of soy plants. This information is used by the specialists to evaluate and compare the growth of different soy genotypes. This algorithm, based on color filtering using the HSI model, detects green objects from the image background. The segmentation of leaves (foliage) was made applying Mathematical Morphology. The foliage area was calculated counting the pixels that belong to the segmented leaves. From several experiments, consisting in applying the algorithm to measure the foliage of about fifty plants of various genotypes of soy, at different growth stages, we obtained successful results, despite the high brightness variations and shadows in the processed images.

Gesture recognition has multiple applications in medical and engineering fields. The problem of hand gesture recognition consists of identifying, at any moment, a given gesture performed by the hand. In this work, we propose a new model for hand gesture recognition in real time. The input of this model is the surface electromyography measured by the commercial sensor the Myo armband placed on the forearm. The output is the label of the gesture executed by the user at any time. The proposed model is based on the k-nearest neighbor and dynamic time warping algorithms. This model can learn to recognize any gesture of the hand. To evaluate the performance of our model, we measured and compared its accuracy at recognizing 5 classes of gestures to the accuracy of the proprietary system of the Myo armband. As a result of this evaluation, we determined that our model performs better (86% accurate) than the Myo system (83%).

Classical clustering algorithms typically either lack an underlying probability framework to make them predictive or focus on parameter estimation rather than defining and minimizing a notion of error. Recent work addresses these issues by developing a probabilistic framework based on the theory of random labeled point processes and characterizing a Bayes clusterer that minimizes the number of misclustered points. The Bayes clusterer is analogous to the Bayes classifier. Whereas determining a Bayes classifier requires full knowledge of the feature-label distribution, deriving a Bayes clusterer requires full knowledge of the point process. When uncertain of the point process, one would like to find a robust clusterer that is optimal over the uncertainty, just as one may find optimal robust classifiers with uncertain feature-label distributions. Herein, we derive an optimal robust clusterer by first finding an effective random point process that incorporates all randomness within its ...

In the field of information security, there are several areas of study that are under development. Social engineering is one of them that addresses the multidisciplinary challenges of cyber security. Nowadays, the attacks associated with social engineering are diverse, including the so-called Advanced Persistent Threats (APTs). These have been the subject of numerous investigations; however, cybernetic attacks of similar nature as grooming have been excluded from these studies. In the last decade, various efforts have been made to understand the structure and approach of grooming from the field of computer science with the use of computational learning algorithms. Nevertheless, these studies are not aligned with information security. In this work, the study of grooming is formalized as a social engineering attack, contrasting its stages or phases with life cycles associated with APTs. To achieve this goal, we use a database of real cyber-pedophile chats; this information was refined and the Latent Dirichlet Allocation (LDA) topic modeling was applied to determine the stages of the attack. Once the number of stages was determined, we proceed to give them a linguistic context, and with the use of machine learning, a linear model was trained to obtain 97.6% of training accuracy. With these results, it was determined that the study of grooming could support research associated with social engineering and contribute to new fields of information security.

Today, daily life is composed of many computing systems, therefore interacting with them in a natural way makes the communication process more comfortable. Human–Computer Interaction (HCI) has been developed to overcome the communication barriers between humans and computers. One form of HCI is Hand Gesture Recognition (HGR), which predicts the class and the instant of execution of a given movement of the hand. One possible input for these models is surface electromyography (EMG), which records the electrical activity of skeletal muscles. EMG signals contain information about the intention of movement generated by the human brain. This systematic literature review analyses the state-of-the-art of real-time hand gesture recognition models using EMG data and machine learning. We selected and assessed 65 primary studies following the Kitchenham methodology. Based on a common structure of machine learning-based systems, we analyzed the structure of the proposed models and standardized c...

Hand gesture recognition systems have several applications including medicine and engineering. A gesture recognition system should identify the class, time, and duration of a gesture executed by a user. Gesture recognition systems based on electromyographies (EMGs) produce good results when the EMG sensor is placed on the same orientation for training and testing. However, when the orientation of the sensor changes between training and testing, which is very common in practice, the classification and recognition accuracies degrade significantly. In this work, we propose a system for recognizing, in real time, five gestures of the right hand. These gestures are the same ones recognized by the proprietary system of the Myo armband. The proposed system is based on the use of a shallow artificial feed-forward neural network. This network takes as input the covariances between the channels of an EMG and the result of a bag of five functions applied to each channel of an EMG. To correct t...

We propose a sign language recognition system based on wearable electronics and two different classification algorithms. The wearable electronics were made of a sensory glove and inertial measurement units to gather fingers, wrist, and arm/forearm movements. The classifiers were k-Nearest Neighbors with Dynamic Time Warping (that is a non-parametric method) and Convolutional Neural Networks (that is a parametric method). Ten sign-words were considered from the Italian Sign Language: cose, grazie, maestra, together with words with international meaning such as google, internet, jogging, pizza, television, twitter, and ciao. The signs were repeated one-hundred times each by seven people, five male and two females, aged 29–54 y ± 10.34 (SD). The adopted classifiers performed with an accuracy of 96.6% ± 3.4 (SD) for the k-Nearest Neighbors plus the Dynamic Time Warping and of 98.0% ± 2.0 (SD) for the Convolutional Neural Networks. Our system was made of wearable electronics among the mo...

In this paper, we propose a real-time hand gesture recognition model. This model is based on both a shallow feedforward neural network with 3 layers and an electromyography (EMG) of the forearm. The structure of the proposed model is composed of 5 modules: data acquisition using the commercial device Myo armband and a sliding window approach, preprocessing, automatic feature extraction, classification, and postprocessing. The proposed model has an accuracy of 90.1% at recognizing 5 categories of gestures (fist, wave-in, wave-out, open, and pinch), and an average time response of 11 ms in a personal computer. The main contributions of this work include (1) a hand gesture recognition model that responds quickly and with relative good accuracy, (2) an automatic method for feature extraction from time series of varying length, and (3) the code and the dataset used for this work, which are made publicly available.

Hand gesture recognition (HGR) systems using electromyography (EMG) bracelet-type sensors are currently largely used over other HGR technologies. However, bracelets are susceptible to electrode rotation, causing a decrease in HGR performance. In this work, HGR systems with an algorithm for orientation correction are proposed. The proposed orientation correction method is based on the computation of the maximum energy channel using a synchronization gesture. Then, the channels of the EMG are rearranged in a new sequence which starts with the maximum energy channel. This new sequence of channels is used for both training and testing. After the EMG channels are rearranged, this signal passes through the following stages: pre-processing, feature extraction, classification, and post-processing. We implemented user-specific and user-general HGR models based on a common architecture which is robust to rotations of the EMG bracelet. Four experiments were performed, taking into account two d...

Classical clustering algorithms typically either lack an underlying probability framework to make them predictive or focus on parameter estimation rather than defining and minimizing a notion of error. Recent work addresses these issues by developing a probabilistic framework based on the theory of random labeled point processes and characterizing a Bayes clusterer that minimizes the number of misclustered points. The Bayes clusterer is analogous to the Bayes classifier. Whereas determining a Bayes classifier requires full knowledge of the featurelabel distribution, deriving a Bayes clusterer requires full knowledge of the point process. When uncertain of the point process, one would like to find a robust clusterer that is optimal over the uncertainty, just as one may find optimal robust classifiers with uncertain feature-label distributions. Herein, we derive an optimal robust clusterer by first finding an effective random point process that incorporates all randomness within its o...

Aperture filters are image operators which combine mathematical morphology and pattern recognition theory to design windowed classifiers. Previous works propose designing and representing such operators using large decision tables and classic linear pattern classifiers. These approaches demand an enormous computational cost in order to solve real image problems. The current work presents a new method to automatically design Aperture filters for color and grayscale image processing. This approach consists of designing a family of Aperture filters using artificial feed-forward neural networks. The resulting Aperture filters are combined into a single one using an ensemble method. The performance of the proposed approach was evaluated by segmenting blood vessels in ocular images of the DRIVE database. The results show the suitability of this approach: It outperforms window operators designed using neural networks and logistic regression as well as Aperture filters designed using logist...

In the field of hand gesture recognition based on electromyography, the selection of features is still a matter of research because the accuracy of feature evaluation techniques depends on the distribution underling a feature space. Currently, there are a lot of kinds of features, so a selection method is required in order to find an optimal feature subset. The selection of features can be done based on either classifier methods or statistical measurement indexes. On one hand, the use of classifier methods takes considerable time, consequently, they are computationally expensive. On the other hand, the use of a statistical index allows to select features based on properties, and they are less expensive in terms of time and computational costs. In this context, this study analyzed different statistical indexes to discover optimal feature subsets and predicts which one may have the best performance in terms of classification and recognition accuracy. For this purpose, four indexes were analyzed: the sum of RES (separation and compactness index), the sum of Fuzzy Entropies, and both of these indexes divided by the mutual information of feature subset. These index values were calculated for 10 different feature subsets obtained from nineteen time-domain features which have been investigated by many researchers for extracting useful information from an electromyography signal. The feature subsets This work has been supported by the

The research consists of hand gesture recognition using a commercial sensor called Leap Motion Controller. For the study, we determined hand tracking carried out for 5 static and 4 dynamic gestures. For this work, the stages of the gesture recognition study were divided into data acquisition, preprocessing, feature extraction, and classification. For the data acquisition stage, we programmed an interface in MATLAB, which generates a structure of output data in images and spatial position forms. The preprocessing consists of taking the data acquired by the leap motion controller and transform them into data readable by MATLAB using the MEX compiler, these data are captured during the execution of the gesture. Besides, the proposed data acquisition interface collect demographic data, hand injuries, and the light intensity of the environment in which the data is taken. These data can be used in hand gesture recognition systems and application fields such as medicine, engineering, and robotics, among others. The development of the acquisition system is parameterized with 30 repetitions at 60 frames per second and the sampling time at 5 s. Finally, the system previews a graph of the gesture recognition test structure in specific activity time.

The mobility restrictions imposed in different countries due to the pandemic of Sars-CoV2 has hugely impacted different areas in the world. In this work, impacts on the social areas of Ecuadorian university students such as education, economy, physical and mental health, and access to telecommunications are analyzed. For this work, in a snapshot between May to September 2020, 1841 students from 6 public and 5 private universities from Ecuador were surveyed through 47 questions, which were grouped into 7 mutually exclusive dimensions. The Partial Least Squares Structural Equation Model (PLS-SEM) was used to analyze the correlations between the responses of the questions and the relations between dimensions. Dimensional relations were used to analyze how students perceive online classes, teachers’ preparation, mood, and the impact on their learning process due to their decreasing family income. Among the most important results, we found that 63.78% of students want to return to on-sit...

Standard video games are applications whose development process often follows a traditional software methodology. Serious Games (SGs) are a tool with an immensely positive impact and great success. SGs enable learning and provide entertainment and self-empowerment, which motivates students. The development of an SG consists of complex processes requiring multi-disciplinary knowledge in multiple domains, including knowing the learning domain and adding the appropriate game mechanics to foster high intrinsic motivation and positive player experience that makes the players feel like they are having fun while learning. Otherwise, the game is viewed as boring and not as a fun and engaging activity. Nevertheless, despite their potential, the application of SGs in education has been limited in terms of pedagogy. Several authors assert that this lack is because SG standards and guidelines have not been developed. There is an imbalance between experts’ contributions to education and game des...

The current research focuses on building a set of games for training and improving people's cognitive abilities with intellectual disabilities. Serious games (SGs) can be an effective training coaching and assistance method for persons with intellectual disabilities because they are effective learning tools that motivate students. The application to stimulate cognitive abilities development consists of 22 mini-games hosted on the LudoMinga platform. For better development in the environment, it is essential that people with intellectual disabilities develop cognitive functions, understood as the mental processes necessary to carry out any task, enabling the reception, selection, transformation, storage, processing, and retrieval of information. For the development of the application, the user-centered design approach of the iPlus methodology is followed. This article illustrates the development of the application using iPlus.

When creating user interfaces, usability considerations are important to ensure the target population an efficient and effective user experience. For this reason, recommendations are proposed for a preliminary prototype of a serious gaming application called HabCog, which consists of a collection of minigames designed for monitoring and evaluating certain cognitive abilities in users. The target population consists of adults with intellectual disabilities who use the services of the FINE Foundation, whose objective is to develop skills and abilities for full inclusion. According to the results, usability recommendations are provided so that the application is better adapted to the target population.