The Relationship between Representational Conflicts, Generalization, and Encoding Requirements in an Instance Memory Network

This paper aims to provide an interpretation of artificial neural networks (ANNs) and explore some of its implications. The interpretation views ANNs as a memory which encodes instances of experience. An experiment explores the behavior of encoding and retrieval of instances from memory. A localised representation ANN is created that allows control over encoding and retrieved memory sample size and is experimented with using the MNIST digits dataset. The relationship between input familiarity, conflict within retrieved samples, and error rates is described and demonstrated to be an effective driver for memory encoding. Results indicate that selective encoding and retrieval samples that allow detection of memory conflicts produce optimal performance, and that error rates are normally distributed with input familiarity and conflict. By using input familiarity and sample consistency to guide memory encoding, the number of encoding trials on the dataset were reduced to 18.33% of the training data while maintaining good recognition performance on the test data.

Face Recognition Using Principal Component Analysis, K-Means Clustering, and Convolutional Neural Network

Face recognition is the problem of identifying or recognizing individuals in an image. This paper investigates a possible method to bring a solution to this problem. The method proposes an amalgamation of Principal Component Analysis (PCA), K-Means clustering, and Convolutional Neural Network (CNN) for a face recognition system. It is trained and evaluated using the ORL dataset. This dataset consists of 400 different faces with 40 classes of 10 face images per class. Firstly, PCA enabled the usage of a smaller network. This reduces the training time of the CNN. Thus, we get rid of the redundancy and preserve the variance with a smaller number of coefficients. Secondly, the K-Means clustering model is trained using the compressed PCA obtained data which select the K-Means clustering centers with better characteristics. Lastly, the K-Means characteristics or features are an initial value of the CNN and act as input data. The accuracy and the performance of the proposed method were tested in comparison to other Face Recognition (FR) techniques namely PCA, Support Vector Machine (SVM), as well as K-Nearest Neighbour (kNN). During experimentation, the accuracy and the performance of our suggested method after 90 epochs achieved the highest performance: 99% accuracy F1-Score, 99% precision, and 99% recall in 463.934 seconds. It outperformed the PCA that obtained 97% and KNN with 84% during the conducted experiments. Therefore, this method proved to be efficient in identifying faces in the images.

Voice Features as the Diagnostic Marker of Autism

The aim of the study is to determine the acoustic features of voice and speech of children with autism spectrum disorders (ASD) as a possible additional diagnostic criterion. The participants in the study were 95 children with ASD aged 5-16 years, 150 typically development (TD) children, and 103 adults – listening to children’s speech samples. Three types of experimental methods for speech analysis were performed: spectrographic, perceptual by listeners, and automatic recognition. In the speech of children with ASD, the pitch values, pitch range, values of frequency and intensity of the third formant (emotional) leading to the “atypical” spectrogram of vowels are higher than corresponding parameters in the speech of TD children. High values of vowel articulation index (VAI) are specific for ASD children’s speech signals. These acoustic features can be considered as diagnostic marker of autism. The ability of humans and automatic recognition of the psychoneurological state of children via their speech is determined.

Vocational Skills, Recognition of Prior Learning and Technology: The Future of Higher Education

The vocational education, enhanced by technology and Recognition of Prior Learning (RPL) is going to be the main ingredient of the future of education. This is coming from the various issues of the current educational system like cost, time, type of course, type of curriculum, unemployment, to name the major reasons. Most millennials like to perform and learn rather than learning how to perform. This is the essence of vocational education be it any field from cooking, painting, plumbing to modern technologies using computers. Even a more theoretical course like entrepreneurship can be taught as to be an entrepreneur and learn about its nuances. The best way to learn accountancy is actually keeping accounts for a small business or grocer and learn the ropes of accountancy and finance. The purpose of this study is to investigate the relationship between vocational skills, RPL and new technologies with future employability. This study implies that individual's knowledge and skills are essential aspects to be emphasized in future education and to give credit for prior experience for future employability. Virtual reality can be used to stimulate workplace situations for vocational learning for fields like hospitality, medical emergencies, healthcare, draughtsman ship, building inspection, quantity surveying, estimation, to name a few. All disruptions in future education, especially vocational education, are going to be technology driven with the advent of AI, ML, IoT, VR, VI etc. Vocational education not only helps institutes cut costs drastically, but allows all students to have hands-on experiences, rather than to be observers. The earlier experiential learning theory and the recent theory of knowledge and skills-based learning modified and applied to the vocational education and development of skills is the proposed contribution of this paper. Apart from secondary research study on major scholarly articles, books, primary research using interviews, questionnaire surveys have been used to validate and test the reliability of the suggested model using Partial Least Square- Structural Equation Method (PLS-SEM), the factors being assimilated using an existing literature review. Major findings have been that there exists high relationship between the vocational skills, RPL, new technology to the future employability through mediation of future employability skills.

Domestic Violence against Children and Trafficking in Human Beings: Two Worrying Phenomena in Kosovo

Domestic violence, trafficking with human beings especially violence against children, is a worldwide problem. Hence, it remains one of the most widespread forms of violence in Kosovo and which often continues to be described as a "closed door issue". Recognition, acceptance and prioritization of cases of domestic violence definitely require a much greater awareness of individuals in institutions for the risks, consequences and costs that the lack of such a well-coordinated response brings to the country. Considering that children are the future and the wealth of the country, violence and neglect against them should be treated as carefully as possible. The purpose of this paper is to identify steps towards prevention of the domestic violence and trafficking with human beings, so that the reflection of the consequences and the psychological flow do not reflect to a large extent in society. In this study is described: How is the phenomenon of domestic violence related to trafficking in human beings? The methods used are: historical, comparative, qualitative. Data derived from the relevant institutions were presented, i.e., by the actors who are the first reactors as well as the policy makers. Although these phenomena are present in all countries of the world, Kosovo is no exception and therefore comparisons of the development of child abuse have been made with other countries in the region as well. Since Kosovo is a country in transition, a country with a relatively high level of education, low economic development, high unemployment, political instability, dysfunctional legal infrastructure, it can be concluded that the potential for the development of negative phenomena is present and inevitable. Thus, during the research, the stages of development of these phenomena are analyzed, determining the causes and consequences which come from abuse, neglect of children and the impact on trafficking in human beings. The Kosovar family (parental responsibility), culture and religion, social services, the dignity of the abused child, etc. were analyzed. The review was also done on the legislation, educational institutions (curricula), governmental and non-governmental institutions their responsibilities and cooperation towards combating child abuse and trafficking. It is worth noting that during the work on paper, recommendations and conclusions have been drawn where it is concluded that we need an environment with educational reforms, stability in the political environment, economic development, a review of social policies, greater awareness of society, more adequate information through media, so that information and awareness could penetrate even in the most remote places of Kosovo society.

Applying Biosensors’ Electromyography Signals through an Artificial Neural Network to Control a Small Unmanned Aerial Vehicle

This work describes a system that uses electromyography (EMG) signals obtained from muscle sensors and an Artificial Neural Network (ANN) for signal classification and pattern recognition that is used to control a small unmanned aerial vehicle using specific arm movements. The main objective of this endeavor is the development of an intelligent interface that allows the user to control the flight of a drone beyond direct manual control. The sensor used were the MyoWare Muscle sensor which contains two EMG electrodes used to collect signals from the posterior (extensor) and anterior (flexor) forearm, and the bicep. The collection of the raw signals from each sensor was performed using an Arduino Uno. Data processing algorithms were developed with the purpose of classifying the signals generated by the arm’s muscles when performing specific movements, namely: flexing, resting, and motion of the arm. With these arm motions roll control of the drone was achieved. MATLAB software was utilized to condition the signals and prepare them for the classification. To generate the input vector for the ANN and perform the classification, the root mean square and the standard deviation were processed for the signals from each electrode. The neuromuscular information was trained using an ANN with a single 10 neurons hidden layer to categorize the four targets. The result of the classification shows that an accuracy of 97.5% was obtained. Afterwards, classification results are used to generate the appropriate control signals from the computer to the drone through a Wi-Fi network connection. These procedures were successfully tested, where the drone responded successfully in real time to the commanded inputs.

Random Subspace Neural Classifier for Meteor Recognition in the Night Sky

This article describes the Random Subspace Neural Classifier (RSC) for the recognition of meteors in the night sky. We used images of meteors entering the atmosphere at night between 8:00 p.m.-5: 00 a.m. The objective of this project is to classify meteor and star images (with stars as the image background). The monitoring of the sky and the classification of meteors are made for future applications by scientists. The image database was collected from different websites. We worked with RGB-type images with dimensions of 220x220 pixels stored in the BitMap Protocol (BMP) format. Subsequent window scanning and processing were carried out for each image. The scan window where the characteristics were extracted had the size of 20x20 pixels with a scanning step size of 10 pixels. Brightness, contrast and contour orientation histograms were used as inputs for the RSC. The RSC worked with two classes and classified into: 1) with meteors and 2) without meteors. Different tests were carried out by varying the number of training cycles and the number of images for training and recognition. The percentage error for the neural classifier was calculated. The results show a good RSC classifier response with 89% correct recognition. The results of these experiments are presented and discussed.

Affective Adaptation Design for Better Gaming Experiences

Affective adaptation is a creative way for game designers to add an extra layer of engagement to their productions. When player’s emotions are an explicit factor in mechanics design, endless possibilities for imaginative gameplay emerge. Whilst gaining popularity, existing affective game research mostly runs controlled experiments in restrictive settings and rely on one or more specialist devices for measuring player’s emotional state. These conditions albeit effective, are not necessarily realistic. Moreover, the simplified narrative and intrusive wearables may not be suitable for players. This exploratory study investigates delivering an immersive affective experience in the wild with minimal requirements, in an attempt for the average developer to reach the average player. A puzzle game is created with rich narrative and creative mechanics. It employs both explicit and implicit adaptation and only requires a web camera. Participants played the game on their own machines in various settings. Whilst it was rated feasible, very engaging and enjoyable, it remains questionable whether a fully immersive experience was delivered due to the limited sample size.

Disparities versus Similarities: WHO GPPQCL and ISO/IEC 17025:2017 International Standards for Quality Management Systems in Pharmaceutical Laboratories

Medicines regulatory authorities expect pharmaceutical companies and contract research organizations to seek ways to certify that their laboratory control measurements are reliable. Establishing and maintaining laboratory quality standards are essential in ensuring the accuracy of test results. ‘ISO/IEC 17025:2017’ and ‘WHO Good Practices for Pharmaceutical Quality Control Laboratories (GPPQCL)’ are two quality standards commonly employed in developing laboratory quality systems. A review was conducted on the two standards to elaborate on areas on convergence and divergence. The goal was to understand how differences in each standard's requirements may influence laboratories' choices as to which document is easier to adopt for quality systems. A qualitative review method compared similar items in the two standards while mapping out areas where there were specific differences in the requirements of the two documents. The review also provided a detailed description of the clauses and parts covering management and technical requirements in these laboratory standards. The review showed that both documents share requirements for over ten critical areas covering objectives, infrastructure, management systems, and laboratory processes. There were, however, differences in standard expectations where GPPQCL emphasizes system procedures for planning and future budgets that will ensure continuity. Conversely, ISO 17025 was more focused on the risk management approach to establish laboratory quality systems. Elements in the two documents form common standard requirements to assure the validity of laboratory test results that promote mutual recognition. The ISO standard currently has more global patronage than GPPQCL.

Gait Biometric for Person Re-Identification

Biometric identification is to identify unique features in a person like fingerprints, iris, ear, and voice recognition that need the subject's permission and physical contact. Gait biometric is used to identify the unique gait of the person by extracting moving features. The main advantage of gait biometric to identify the gait of a person at a distance, without any physical contact. In this work, the gait biometric is used for person re-identification. The person walking naturally compared with the same person walking with bag, coat and case recorded using long wave infrared, short wave infrared, medium wave infrared and visible cameras. The videos are recorded in rural and in urban environments. The pre-processing technique includes human identified using You Only Look Once, background subtraction, silhouettes extraction and synthesis Gait Entropy Image by averaging the silhouettes. The moving features are extracted from the Gait Entropy Energy Image. The extracted features are dimensionality reduced by the Principal Component Analysis and recognized using different classifiers. The comparative results with the different classifier show that Linear Discriminant Analysis outperform other classifiers with 95.8% for visible in the rural dataset and 94.8% for longwave infrared in the urban dataset.

Smartphone-Based Human Activity Recognition by Machine Learning Methods

As smartphones are continually upgrading, their software and hardware are getting smarter, so the smartphone-based human activity recognition will be described more refined, complex and detailed. In this context, we analyzed a set of experimental data, obtained by observing and measuring 30 volunteers with six activities of daily living (ADL). Due to the large sample size, especially a 561-feature vector with time and frequency domain variables, cleaning these intractable features and training a proper model become extremely challenging. After a series of feature selection and parameters adjustments, a well-performed SVM classifier has been trained. 

Methodology of Personalizing Interior Spaces in Public Libraries

Creating public spaces which are tailored for the specific demands of the individuals is one of the challenges for the contemporary interior designers. Improving the general knowledge as well as providing a forum for all walks of life to exploit is one of the objectives of a public library. In this regard, interior design in consistent with the demands of the individuals is of paramount importance. Seemingly, study spaces, in particular, those in close relation to the personalized sector, have proven to be challenging, according to the literature. To address this challenge, attributes of individuals, namely, perception of people from public spaces and their interactions with the so-called spaces, should be analyzed to provide interior designers with something to work on. This paper follows the analytic-descriptive research methodology by outlining case study libraries which have personalized public libraries with the investigation of the type of personalization as its primary objective and (I) recognition of physical schedule and the know-how of the spatial connection in indoor design of a library and (II) analysis of each personalized space in relation to other spaces of the library as its secondary objectives. The significance of the current research lies in the concept of personalization as one of the most recent methods of attracting people to libraries. Previous research exists in this regard, but the lack of data concerning personalization makes this topic worth investigating. Hence, this study aims to put forward approaches through real-case studies for the designers to deal with this concept.

Cybersecurity for Digital Twins in the Built Environment: Research Landscape, Industry Attitudes and Future Direction

Technological advances in the construction sector are helping to make smart cities a reality by means of Cyber-Physical Systems (CPS). CPS integrate information and the physical world through the use of Information Communication Technologies (ICT). An increasingly common goal in the built environment is to integrate Building Information Models (BIM) with Internet of Things (IoT) and sensor technologies using CPS. Future advances could see the adoption of digital twins, creating new opportunities for CPS using monitoring, simulation and optimisation technologies. However, researchers often fail to fully consider the security implications. To date, it is not widely possible to assimilate BIM data and cybersecurity concepts and, therefore, security has thus far been overlooked. This paper reviews the empirical literature concerning IoT applications in the built environment and discusses real-world applications of the IoT intended to enhance construction practices, people’s lives and bolster cybersecurity. Specifically, this research addresses two research questions: (a) How suitable are the current IoT and CPS security stacks to address the cybersecurity threats facing digital twins in the context of smart buildings and districts? and (b) What are the current obstacles to tackling cybersecurity threats to the built environment CPS? To answer these questions, this paper reviews the current state-of-the-art research concerning digital twins in the built environment, the IoT, BIM, urban cities and cybersecurity. The results of the findings of this study confirmed the importance of using digital twins in both IoT and BIM. Also, eight reference zones across Europe have gained special recognition for their contributions to the advancement of IoT science. Therefore, this paper evaluates the use of digital twins in CPS to arrive at recommendations for expanding BIM specifications to facilitate IoT compliance, bolster cybersecurity and integrate digital twin and city standards in the smart cities of the future.

6D Posture Estimation of Road Vehicles from Color Images

Currently, in the field of object posture estimation, there is research on estimating the position and angle of an object by storing a 3D model of the object to be estimated in advance in a computer and matching it with the model. However, in this research, we have succeeded in creating a module that is much simpler, smaller in scale, and faster in operation. Our 6D pose estimation model consists of two different networks – a classification network and a regression network. From a single RGB image, the trained model estimates the class of the object in the image, the coordinates of the object, and its rotation angle in 3D space. In addition, we compared the estimation accuracy of each camera position, i.e., the angle from which the object was captured. The highest accuracy was recorded when the camera position was 75°, the accuracy of the classification was about 87.3%, and that of regression was about 98.9%.

Adaptive Few-Shot Deep Metric Learning

Currently the most prevalent deep learning methods require a large amount of data for training, whereas few-shot learning tries to learn a model from limited data without extensive retraining. In this paper, we present a loss function based on triplet loss for solving few-shot problem using metric based learning. Instead of setting the margin distance in triplet loss as a constant number empirically, we propose an adaptive margin distance strategy to obtain the appropriate margin distance automatically. We implement the strategy in the deep siamese network for deep metric embedding, by utilizing an optimization approach by penalizing the worst case and rewarding the best. Our experiments on image recognition and co-segmentation model demonstrate that using our proposed triplet loss with adaptive margin distance can significantly improve the performance.

Image Processing Approach for Detection of Three-Dimensional Tree-Rings from X-Ray Computed Tomography

Tree-ring analysis is an important part of the quality assessment and the dating of (archaeological) wood samples. It provides quantitative data about the whole anatomical ring structure, which can be used, for example, to measure the impact of the fluctuating environment on the tree growth, for the dendrochronological analysis of archaeological wooden artefacts and to estimate the wood mechanical properties. Despite advances in computer vision and edge recognition algorithms, detection and counting of annual rings are still limited to 2D datasets and performed in most cases manually, which is a time consuming, tedious task and depends strongly on the operator’s experience. This work presents an image processing approach to detect the whole 3D tree-ring structure directly from X-ray computed tomography imaging data. The approach relies on a modified Canny edge detection algorithm, which captures fully connected tree-ring edges throughout the measured image stack and is validated on X-ray computed tomography data taken from six wood species.

Early Depression Detection for Young Adults with a Psychiatric and AI Interdisciplinary Multimodal Framework

During COVID-19, the depression rate has increased dramatically. Young adults are most vulnerable to the mental health effects of the pandemic. Lower-income families have a higher ratio to be diagnosed with depression than the general population, but less access to clinics. This research aims to achieve early depression detection at low cost, large scale, and high accuracy with an interdisciplinary approach by incorporating clinical practices defined by American Psychiatric Association (APA) as well as multimodal AI framework. The proposed approach detected the nine depression symptoms with Natural Language Processing sentiment analysis and a symptom-based Lexicon uniquely designed for young adults. The experiments were conducted on the multimedia survey results from adolescents and young adults and unbiased Twitter communications. The result was further aggregated with the facial emotional cues analyzed by the Convolutional Neural Network on the multimedia survey videos. Five experiments each conducted on 10k data entries reached consistent results with an average accuracy of 88.31%, higher than the existing natural language analysis models. This approach can reach 300+ million daily active Twitter users and is highly accessible by low-income populations to promote early depression detection to raise awareness in adolescents and young adults and reveal complementary cues to assist clinical depression diagnosis.

Comparative Analysis of Machine Learning Tools: A Review

Machine learning is a new and exciting area of artificial intelligence nowadays. Machine learning is the most valuable, time, supervised, and cost-effective approach. It is not a narrow learning approach; it also includes a wide range of methods and techniques that can be applied to a wide range of complex realworld problems and time domains. Biological image classification, adaptive testing, computer vision, natural language processing, object detection, cancer detection, face recognition, handwriting recognition, speech recognition, and many other applications of machine learning are widely used in research, industry, and government. Every day, more data are generated, and conventional machine learning techniques are becoming obsolete as users move to distributed and real-time operations. By providing fundamental knowledge of machine learning tools and research opportunities in the field, the aim of this article is to serve as both a comprehensive overview and a guide. A diverse set of machine learning resources is demonstrated and contrasted with the key features in this survey.

Generative Adversarial Network Based Fingerprint Anti-Spoofing Limitations

Fingerprint Anti-Spoofing approaches have been actively developed and applied in real-world applications. One of the main problems for Fingerprint Anti-Spoofing is not robust to unseen samples, especially in real-world scenarios. A possible solution will be to generate artificial, but realistic fingerprint samples and use them for training in order to achieve good generalization. This paper contains experimental and comparative results with currently popular GAN based methods and uses realistic synthesis of fingerprints in training in order to increase the performance. Among various GAN models, the most popular StyleGAN is used for the experiments. The CNN models were first trained with the dataset that did not contain generated fake images and the accuracy along with the mean average error rate were recorded. Then, the fake generated images (fake images of live fingerprints and fake images of spoof fingerprints) were each combined with the original images (real images of live fingerprints and real images of spoof fingerprints), and various CNN models were trained. The best performances for each CNN model, trained with the dataset of generated fake images and each time the accuracy and the mean average error rate, were recorded. We observe that current GAN based approaches need significant improvements for the Anti-Spoofing performance, although the overall quality of the synthesized fingerprints seems to be reasonable. We include the analysis of this performance degradation, especially with a small number of samples. In addition, we suggest several approaches towards improved generalization with a small number of samples, by focusing on what GAN based approaches should learn and should not learn.

Loss Function Optimization for CNN-Based Fingerprint Anti-Spoofing

As biometric systems become widely deployed, the security of identification systems can be easily attacked by various spoof materials. This paper contributes to finding a reliable and practical anti-spoofing method using Convolutional Neural Networks (CNNs) based on the types of loss functions and optimizers. The types of CNNs used in this paper include AlexNet, VGGNet, and ResNet. By using various loss functions including Cross-Entropy, Center Loss, Cosine Proximity, and Hinge Loss, and various loss optimizers which include Adam, SGD, RMSProp, Adadelta, Adagrad, and Nadam, we obtained significant performance changes. We realize that choosing the correct loss function for each model is crucial since different loss functions lead to different errors on the same evaluation. By using a subset of the Livdet 2017 database, we validate our approach to compare the generalization power. It is important to note that we use a subset of LiveDet and the database is the same across all training and testing for each model. This way, we can compare the performance, in terms of generalization, for the unseen data across all different models. The best CNN (AlexNet) with the appropriate loss function and optimizers result in more than 3% of performance gain over the other CNN models with the default loss function and optimizer. In addition to the highest generalization performance, this paper also contains the models with high accuracy associated with parameters and mean average error rates to find the model that consumes the least memory and computation time for training and testing. Although AlexNet has less complexity over other CNN models, it is proven to be very efficient. For practical anti-spoofing systems, the deployed version should use a small amount of memory and should run very fast with high anti-spoofing performance. For our deployed version on smartphones, additional processing steps, such as quantization and pruning algorithms, have been applied in our final model.