Deep Learning for 3D Reconstruction, Augmentation, and Registration: A Review Paper.

The research groups in computer vision, graphics, and machine learning have dedicated a substantial amount of attention to the areas of 3D object reconstruction, augmentation, and registration. Deep learning is the predominant method used in artificial intelligence for addressing computer vision challenges. However, deep learning on three-dimensional data presents distinct obstacles and is now in its nascent phase. There have been significant advancements in deep learning specifically for three-dimensional data, offering a range of ways to address these issues. This study offers a comprehensive examination of the latest advancements in deep learning methodologies. We examine many benchmark models for the tasks of 3D object registration, augmentation, and reconstruction. We thoroughly analyse their architectures, advantages, and constraints. In summary, this report provides a comprehensive overview of recent advancements in three-dimensional deep learning and highlights unresolved research areas that will need to be addressed in the future.

Processing emotions from faces and words measured by event-related brain potentials.

Affective aspects of a stimulus can be processed rapidly and before cognitive attribution, acting much earlier for verbal stimuli than previously considered. Aimed for specific mechanisms, event-related brain potentials (ERPs), expressed in facial expressions or word meaning and evoked by six basic emotions - anger, disgust, fear, happy, sad, and surprise - relative to emotionally neutral stimuli were analysed in a sample of 116 participants. Brain responses in the occipital and left temporal regions elicited by the sadness in facial expressions or words were indistinguishable from responses evoked by neutral faces or words. Confirming previous findings, facial fear elicited an early and strong posterior negativity. Instead of expected parietal positivity, both the happy faces and words produced significantly more negative responses compared to neutral. Surprise in facial expressions and words elicited a strong early response in the left temporal cortex, which could be a signature of appraisal. The results of this study are consistent with the view that both types of affective stimuli, facial emotions and word meaning, set off rapid processing and responses occur very early in the processing stage.

Towards Context-Aware Facial Emotion Reaction Database for Dyadic Interaction Settings.

Emotion recognition is a significant issue in many sectors that use human emotion reactions as communication for marketing, technological equipment, or human-robot interaction. The realistic facial behavior of social robots and artificial agents is still a challenge, limiting their emotional credibility in dyadic face-to-face situations with humans. One obstacle is the lack of appropriate training data on how humans typically interact in such settings. This article focused on collecting the facial behavior of 60 participants to create a new type of dyadic emotion reaction database. For this purpose, we propose a methodology that automatically captures the facial expressions of participants via webcam while they are engaged with other people (facial videos) in emotionally primed contexts. The data were then analyzed using three different Facial Expression Analysis (FEA) tools: iMotions, the Mini-Xception model, and the Py-Feat FEA toolkit. Although the emotion reactions were reported as genuine, the comparative analysis between the aforementioned models could not agree with a single emotion reaction prediction. Based on this result, a more-robust and -effective model for emotion reaction prediction is needed. The relevance of this work for human-computer interaction studies lies in its novel approach to developing adaptive behaviors for synthetic human-like beings (virtual or robotic), allowing them to simulate human facial interaction behavior in contextually varying dyadic situations with humans. This article should be useful for researchers using human emotion analysis while deciding on a suitable methodology to collect facial expression reactions in a dyadic setting.

A Survey on Deep Learning Based Segmentation, Detection and Classification for 3D Point Clouds.

The computer vision, graphics, and machine learning research groups have given a significant amount of focus to 3D object recognition (segmentation, detection, and classification). Deep learning approaches have lately emerged as the preferred method for 3D segmentation problems as a result of their outstanding performance in 2D computer vision. As a result, many innovative approaches have been proposed and validated on multiple benchmark datasets. This study offers an in-depth assessment of the latest developments in deep learning-based 3D object recognition. We discuss the most well-known 3D object recognition models, along with evaluations of their distinctive qualities.

Ensemble Approach for Detection of Depression Using EEG Features.

Depression is a public health issue that severely affects one's well being and can cause negative social and economic effects to society. To raise awareness of these problems, this research aims at determining whether the long-lasting effects of depression can be determined from electroencephalographic (EEG) signals. The article contains an accuracy comparison for SVM, LDA, NB, kNN, and D3 binary classifiers, which were trained using linear (relative band power, alpha power variability, spectral asymmetry index) and nonlinear (Higuchi fractal dimension, Lempel-Ziv complexity, detrended fluctuation analysis) EEG features. The age- and gender-matched dataset consisted of 10 healthy subjects and 10 subjects diagnosed with depression at some point in their lifetime. Most of the proposed feature selection and classifier combinations achieved accuracy in the range of 80% to 95%, and all the models were evaluated using a 10-fold cross-validation. The results showed that the motioned EEG features used in classifying ongoing depression also work for classifying the long-lasting effects of depression.

A Comparison of Neural Networks and Center of Gravity in Muon Hit Position Estimation.

The performance of cosmic-ray tomography systems is largely determined by their tracking accuracy. With conventional scintillation detector technology, good precision can be achieved with a small pitch between the elements of the detector array. Improving the resolution implies increasing the number of read-out channels, which in turn increases the complexity and cost of the tracking detectors. As an alternative to that, a scintillation plate detector coupled with multiple silicon photomultipliers could be used as a technically simple solution. In this paper, we present a comparison between two deep-learning-based methods and a conventional Center of Gravity (CoG) algorithm, used to calculate cosmic-ray muon hit positions on the plate detector using the signals from the photomultipliers. In this study, we generated a dataset of muon hits on a detector plate using the Monte Carlo simulation toolkit GEANT4. We demonstrate that two deep-learning-based methods outperform the conventional CoG algorithm by a significant margin. Our proposed algorithm, Fully Connected Network, produces a 0.72 mm average error measured in Euclidean distance between the actual and predicted hit coordinates, showing great improvement in comparison with CoG, which yields 1.41 mm on the same dataset. Additionally, we investigated the effects of different sensor configurations on performance.

Comprehensive Empirical Evaluation of Deep Learning Approaches for Session-Based Recommendation in E-Commerce.

Boosting the sales of e-commerce services is guaranteed once users find more items matching their interests in a short amount of time. Consequently, recommendation systems have become a crucial part of any successful e-commerce service. Although various recommendation techniques could be used in e-commerce, a considerable amount of attention has been drawn to session-based recommendation systems in recent years. This growing interest is due to security concerns over collecting personalized user behavior data, especially due to recent general data protection regulations. In this work, we present a comprehensive evaluation of the state-of-the-art deep learning approaches used in the session-based recommendation. In session-based recommendation, a recommendation system counts on the sequence of events made by a user within the same session to predict and endorse other items that are more likely to correlate with their preferences. Our extensive experiments investigate baseline techniques (e.g., nearest neighbors and pattern mining algorithms) and deep learning approaches (e.g., recurrent neural networks, graph neural networks, and attention-based networks). Our evaluations show that advanced neural-based models and session-based nearest neighbor algorithms outperform the baseline techniques in most scenarios. However, we found that these models suffer more in the case of long sessions when there exists drift in user interests, and when there are not enough data to correctly model different items during training. Our study suggests that using the hybrid models of different approaches combined with baseline algorithms could lead to substantial results in session-based recommendations based on dataset characteristics. We also discuss the drawbacks of current session-based recommendation algorithms and further open research directions in this field.

Ungulate Detection and Species Classification from Camera Trap Images Using RetinaNet and Faster R-CNN.

Changes in the ungulate population density in the wild has impacts on both the wildlife and human society. In order to control the ungulate population movement, monitoring systems such as camera trap networks have been implemented in a non-invasive setup. However, such systems produce a large number of images as the output, hence making it very resource consuming to manually detect the animals. In this paper, we present a new dataset of wild ungulates which was collected in Latvia. Moreover, we demonstrate two methods, which use RetinaNet and Faster R-CNN as backbones, respectively, to detect the animals in the images. We discuss the optimization of training and impact of data augmentation on the performance. Finally, we show the result of aforementioned tune networks over the real world data collected in Latvia.

Prediction of sgRNA Off-Target Activity in CRISPR/Cas9 Gene Editing Using Graph Convolution Network.

CRISPR/Cas9 is a powerful genome-editing technology that has been widely applied in targeted gene repair and gene expression regulation. One of the main challenges for the CRISPR/Cas9 system is the occurrence of unexpected cleavage at some sites (off-targets) and predicting them is necessary due to its relevance in gene editing research. Very few deep learning models have been developed so far to predict the off-target propensity of single guide RNA (sgRNA) at specific DNA fragments by using artificial feature extract operations and machine learning techniques; however, this is a convoluted process that is difficult to understand and implement for researchers. In this research work, we introduce a novel graph-based approach to predict off-target efficacy of sgRNA in the CRISPR/Cas9 system that is easy to understand and replicate for researchers. This is achieved by creating a graph with sequences as nodes and by using a link prediction method to predict the presence of links between sgRNA and off-target inducing target DNA sequences. Features for the sequences are extracted from within the sequences. We used HEK293 and K562 t datasets in our experiments. GCN predicted the off-target gene knockouts (using link prediction) by predicting the links between sgRNA and off-target sequences with an auROC value of 0.987.

Statistical Machine Learning for Human Behaviour Analysis.

Human behaviour analysis has introduced several challenges in various fields, such as applied information theory, affective computing, robotics, biometrics and pattern recognition [...].

Emotion Recognition from Skeletal Movements.

Automatic emotion recognition has become an important trend in many artificial intelligence (AI) based applications and has been widely explored in recent years. Most research in the area of automated emotion recognition is based on facial expressions or speech signals. Although the influence of the emotional state on body movements is undeniable, this source of expression is still underestimated in automatic analysis. In this paper, we propose a novel method to recognise seven basic emotional states-namely, happy, sad, surprise, fear, anger, disgust and neutral-utilising body movement. We analyse motion capture data under seven basic emotional states recorded by professional actor/actresses using Microsoft Kinect v2 sensor. We propose a new representation of affective movements, based on sequences of body joints. The proposed algorithm creates a sequential model of affective movement based on low level features inferred from the spacial location and the orientation of joints within the tracked skeleton. In the experimental results, different deep neural networks were employed and compared to recognise the emotional state of the acquired motion sequences. The experimental results conducted in this work show the feasibility of automatic emotion recognition from sequences of body gestures, which can serve as an additional source of information in multimodal emotion recognition.

Action Recognition Using Single-Pixel Time-of-Flight Detection.

Action recognition is a challenging task that plays an important role in many robotic systems, which highly depend on visual input feeds. However, due to privacy concerns, it is important to find a method which can recognise actions without using visual feed. In this paper, we propose a concept for detecting actions while preserving the test subject's privacy. Our proposed method relies only on recording the temporal evolution of light pulses scattered back from the scene. Such data trace to record one action contains a sequence of one-dimensional arrays of voltage values acquired by a single-pixel detector at 1 GHz repetition rate. Information about both the distance to the object and its shape are embedded in the traces. We apply machine learning in the form of recurrent neural networks for data analysis and demonstrate successful action recognition. The experimental results show that our proposed method could achieve on average 96.47 % accuracy on the actions walking forward, walking backwards, sitting down, standing up and waving hand, using recurrent neural network.

Dielectric elastomer stack actuator-based autofocus fluid lens.

Extremely small cameras and many cell phones simply do not have enough room to allow users to move a rigid lens the distance required for a varying range of focal lengths. An adaptive liquid lens, however, enables small cameras to focus without needing extra room. An autofocus liquid lens provides several advantages over a traditional lens in terms of efficiency, cost, compactness, and flexibility. But one of the main challenges in these lenses is a high driving voltage requirement of around at least 1.8 kV. In this paper, we propose a new design of a liquid lens based on a dielectric elastomer stack actuator (DESA), which significantly overcomes the aforementioned existing problem. The lens consists of a frame (a thin DESA membrane with a hole in the middle), silicon oil, and water. A voltage range is applied on the membrane in order to change the hole dimension. Due to change of hole dimension, a change in meniscus occurs that changes the focal length of the lens. In this research work, various experimental results are achieved by configuring two DESA with different active areas. Depending on the active area of the membrane, the length of the laser beam on the plane varies from 6 to 35 mm, and the driving voltage is in the range of 50-750 V.

Deep convolutional neural networks for detection of abnormalities in chest X-rays trained on the very large dataset.

One of the main challenges in the current pandemic is the detection of coronavirus. Conventional techniques (PT-PCR) have their limitations such as long response time and limited accessibility. On the other hand, X-ray machines are widely available and they are already digitized in the health systems. Thus, their usage is faster and more available. Therefore, in this research, we evaluate how well deep CNNs do when it comes to classifying normal versus pathological chest X-rays. Compared to the previous research, we trained our network on the largest number of images, 103,468 in total, including 5 classes such as COPD signs, COVID, normal, others and Pneumonia. We achieved COVID accuracy of 97% and overall accuracy of 81%. Additionally, we achieved classification accuracy of 84% for categorization into normal (78%) and abnormal (88%).

Enhancing empathy through virtual reality: Developing a universal design training application for students.

The lack of empathy towards disability is a significant societal issue that hampers inclusivity and understanding. Many struggle to comprehend the daily challenges and experiences faced by people with disabilities, leading to ignorance, prejudice, and exclusion. However, empathy plays a pivotal role in addressing this problem and serves as the foundation for developing and creating better products, services, and environments. This article explores the potential of developing virtual reality (VR) applications to enhance students' empathy towards individuals with disabilities. By increasing empathy levels, students are expected to gain significant qualifications in universal design (UD). The full application development process covers the most suitable head-mounted display (HMD) set. The implementation methodology using the Unity programming platform, the approach adopted for conducting classes using the developed VR application, and the deployment stage. Testing was successfully conducted on a student population, receiving positive user feedback. Through the integration of VR technology, the authors thoroughly describe how to address the empathy gap and equip students with essential skills for inclusive and accessible design. The findings presented in this study provide valuable guidance for educators and developers interested in harnessing VR's potential to foster empathy and advance universal design practices. With the presented methodology and proposed application, the authors demonstrate the effectiveness of VR applications in elevating students' empathy levels, consequently enhancing their qualifications in universal design. Med Pr. 2023;74(3):199-210.

Comparative analysis of classification algorithms on the breast cancer recurrence using machine learning.

This paper presents a comparative evaluation of classification algorithms using Waikato Environment for Knowledge Analysis (WEKA) software. The main goal of the paper is to conduct a comprehensive comparison and determine which predictive modelling technique is best for the problem of classifying breast cancer recurrence. The dataset for this study consists of 286 instances (201 instances belong to recurrence class and 85 instances belong to non-recurrence class) and 10 attributes. Comparison analysis is conducted for Naïve Bayes, J48, K*, Random Forest, Multilayer Perceptron (MLP) and Support Vector Machine (SVM) models using different parameters. The performance of the developed models is calculated using the following evaluation metrics: accuracy, precision, sensitivity, specificity, mean absolute error, ROC curves and AUC values. Contribution of the attributes to the classification models is assessed by measuring information gain. Results show that J48 model and the SVM algorithm give the highest accuracy, which is 75.5% and 79.6%, respectively. Implementation of SVM algorithm also shows the highest sensitivity of 99%, while the highest precision is obtained by MLP algorithm which is 79%. In addition, SVM algorithm possesses the lowest mean absolute error. Furthermore, by measuring information gain, it is revealed that a degree of malignant tumour contributes more than other attributes to recurrence of breast cancer.

ChaLearn Looking at People: IsoGD and ConGD Large-Scale RGB-D Gesture Recognition.

The ChaLearn large-scale gesture recognition challenge has run twice in two workshops in conjunction with the International Conference on Pattern Recognition (ICPR) 2016 and International Conference on Computer Vision (ICCV) 2017, attracting more than 200 teams around the world. This challenge has two tracks, focusing on isolated and continuous gesture recognition, respectively. It describes the creation of both benchmark datasets and analyzes the advances in large-scale gesture recognition based on these two datasets. In this article, we discuss the challenges of collecting large-scale ground-truth annotations of gesture recognition and provide a detailed analysis of the current methods for large-scale isolated and continuous gesture recognition. In addition to the recognition rate and mean Jaccard index (MJI) as evaluation metrics used in previous challenges, we introduce the corrected segmentation rate (CSR) metric to evaluate the performance of temporal segmentation for continuous gesture recognition. Furthermore, we propose a bidirectional long short-term memory (Bi-LSTM) method, determining video division points based on skeleton points. Experiments show that the proposed Bi-LSTM outperforms state-of-the-art methods with an absolute improvement of 8.1% (from 0.8917 to 0.9639) of CSR.

Antagonist Concepts of Polypyrrole Actuators: Bending Hybrid Actuator and Mirrored Trilayer Linear Actuator.

Following the natural muscle antagonist actuation principle, different adaptations for "artificial muscles" are introduced in this work. Polypyrrole (PPy) films of different polymerization techniques (potentiostatic and galvanostatic) were analyzed and their established responses were combined in several ways, resulting in beneficial actuation modes. A consecutive "one-pot" electrosynthesis of two layers with the different deposition regimes resulted in an all-PPy bending hybrid actuator. While in most cases the mixed-ion activity of conductive polymers has been considered a problem or a drawback, here for the first time, the nearly equal expansions upon oxidation and reduction of carefully selected conditions further allowed to fabricate a "mirrored" trilayer laminate, which behaved as a linear actuator.

The Use of Laminates of Commercially Available Fabrics for Anti-Stab Body-Armor.

Modern personal protective armor has been generally based on the Kevlar fabrics, with the main goal to offer defense against bullets. In addition to the high cost and poor processability, Kevlar has the disadvantage of limited stab-proofing capability. On the other hand, a large number of crimes involving deadly injures represent knife attacks. Our goal in this work was to investigate composites based on traditional commercially available fabrics of linen and silk, using different adhesives-polymers for forming laminates. The silk composites also contained different amounts of in-woven polyester. Three different water-based adhesives of polyurethane, urea formaldehyde and polyvinyl alcohol were considered. It was found, that besides the strength of the fabrics themselves, the adhesives polymers played a crucial role in the obtained performance of the laminates. The laminates were characterized in their mechanical properties, as well as with scanning electron microscopy and FTIR spectroscopy.

A Kirigami Approach of Patterning Membrane Actuators.

Ionic electroactive polymer actuators are typically implemented as bending trilayer laminates. While showing high displacements, such designs are not straightforward to implement for useful applications. To enable practical uses in actuators with ionic electroactive polymers, membrane-type film designs can be considered. The significantly lower displacement of the membrane actuators due to the lack of freedom of motion has been the main limiting factor for their application, resulting in just a few works considering such devices. However, bioinspired patterning designs have been shown to significantly increase the freedom of motion of such membranes. In this work, we apply computer simulations to design cutting patterns for increasing the performance of membrane actuators based on polypyrrole doped with dodecylbenzenesulfonate (PPy/DBS) in trilayer arrangements with a polyvinylidene fluoride membrane as the separator. A dedicated custom-designed device was built to consistently measure the response of the membrane actuators, demonstrating significant and pattern-specific enhancements of the response in terms of displacement, exchanged charge and force.