Augmented Human Research最新文献

In this paper, we recover an interactive artwork developed by one of the authors to provide possible ways of inserting the playful and artistic perspective into augmented human studies. In this way, a perspective based on play and interactive digital fiction can inspire us to look at other ways of using digital technologies that focus on improving human capabilities. The interactive installation Blind Game brings us a personal, visual, and playful perspective of a person who, at the age of three years, was diagnosed with amblyopia, revealing the subjective world of the character P.. Created in 2001, this installation was an interactive conceptual artwork developed by a young artist who wanted to exorcise the memories of her diagnosis of amblyopia and the tensions caused by the political instability in her home country. Through interaction and playful strategies, the artist sought to abstract herself from the reality around her, reorganizing her subjective relationship with visual impairment and the political tensions of a transition period between a dictatorial government and a democratic one.

This paper presents a brief overview of signature identification and verification systems based on transfer learning. Different databases, namely CEDAR, ICDAR-2011, and BHSig260, are utilized for this study. In the field of biometrics and forensics, automated signature verification plays a crucial role in validating a person’s authenticity. The signature can be offline (handwritten) or online (digital). This study mainly focuses on offline signatures forged by the skilled forgers because offline systems lack dynamic information such as pressure and velocity available in online systems. The offline signatures are analyzed on pretrained models, and their efficiency is analyzed on two critical metrics in the field of biometrics and security systems, namely false acceptance rate (FAR) and false rejection rate (FRR). InceptionV3 model gives highest accuracy of 99.10% and lowest FRR and FAR of 1.03% and 0.74%.

This paper delves into a multidisciplinary workshop, “Speculative [x]culptures: Crafting Future Solutions for Statuary in Public Spaces” conducted at the Department of Digital Arts and Cinema at the National and Kapodistrian University of Athens, Greece. Inspired by the ongoing debate on public statuary initiated by the #BlackLivesMatter movement [1], this workshop engages participants in a creative process integrating speculative design methodology with immersive extended reality (XR) experiences and critical play. It encourages meaningful conversations about historical notions of public statuary in creative ways, based on the socio-political context of an example of Greek national statuary—the Greek revolution statue of Theodoros Kolokotronis in Athens, authored by the sculptor Lazaros Sochos and inaugurated in 1904. Aiming to probe diverse perspectives on public statuary and their significance, thereby contributing to the student’s learning and global skills development in the education 4.0 era, the authors explore the synergies between XR technologies and ludification tools in the rapid critical prototyping of 3D concepts. This innovative pedagogical approach enables participants to explore the relations between statuary and context(s), envisioning and prototyping future solutions that shape public statues’ perception and interpretation. The case study presented sheds light on the practical implications of this interdisciplinary approach, offering insights into the potential of XR and speculative design to foster critical socio-environmental thinking in higher education.

This study evaluates the efficacy of virtual reality (VR)-based cognitive behavioral therapy (CBT) in addressing cognitive distortions among youth, contrasting it with traditional therapeutic methods. A quasi-experimental design was employed, involving 30 cognitively distorted youth who received a psychoeducation session followed by AR-VR-based 3D animated CBT scripts. Assessments were conducted at 6 weeks, 2 months, and 4 months post-intervention. The findings revealed a significant reduction in cognitive distortions post-intervention, which was sustained during follow-ups. The AR-VR-based 3D animated scripts emerged as a promising tool for combating cognitive distortions, potentially supplanting conventional therapies. The innovative use of AR-VR technology not only enhances engagement but also expands treatment options, especially for individuals who are unreceptive to traditional interventions. This research underscores the effectiveness of VR-based CBT in addressing cognitive distortions among youth, contributing to advancements in mental health interventions. The study highlights the potential of augmented reality and virtual reality technologies in cognitive distortion interventions.

Communication with people with hearing or speaking disabilities is always difficult when there is no knowledge of sign language. The presence of sign language is not enough to communicate smoothly, this process requires another easy medium for communication to make it more efficient, that is, via a digital medium. This paper proposes using Feed-Forward Neural Networks on hand landmarks for real-time sign language identification. The hand landmarks identification was carried out using the MediaPipe Hands library. This approach would make the classification problem efficient by making it faster and requiring less memory. Through this, we aim to bridge the gap between the difficulties that arise during communication between people who do and do not know American Sign Language.

Epilepsy seizures are sudden, chaotic neurological functions. The complexity of the brain is revealed via electroencephalography (EEG). Visual examination-based EEG signal analysis is time-consuming, expensive, and difficult. Epilepsy-related mortality is a serious concern. In the diagnostic procedure, computer-assisted diagnosis approaches for precise and automatic detection and classification of epileptic seizures play a crucial role. Due to the classifier's high processing time requirements caused by its mathematical complexity and computational time, we propose a hybrid water cycle algorithm (WCA)–particle swarm optimization (PSO) optimized ensemble extreme learning machine (EELM) classification of seizures to improve the classification performance of the classifier. Firstly, we use feature extraction by utilizing the wavelet transform. The extracted features are aligned as input to the WCA–PSO–EELM for classification. The particle swarm optimization (PSO) algorithm is used to initialize the optimization variables of a WCA algorithm, and the WCA algorithm is used to optimize the input weight of the ELM (i.e., the WCA–PSO–ELM (WPELM)) for classification of seizure and non-seizure EEG signals. University of Bonn database is used for the experiment. The performance measures sensitivity, specificity, and accuracy are considered and achieved 98.78%, 99.23%, and 99.12%, that is, higher than those of other conventional algorithms. To validate the robustness of the WCA–PSO algorithm, three benchmark functions are considered for optimization. The comparison results are presented to visualize the uniqueness of the proposed WCA–PSO–EELM classifier. From the comparison results, it was observed that the proposed WCA–PSO–EELM model outperformed in classifying the seizure and non-seizure EEG signals.

There are a rapid growth of adults with cognitive impairments and an increasing need for cognitive stimulation and rehabilitation to delay cognitive deterioration. COSMA, a cognitive gaming app, was developed to assist cognitive stimulation in people with cognitive decline and dementia. Therefore, the study was conducted to investigate the effectiveness of COSMA in people with mild cognitive impairment (MCI) and early Alzheimer’s disease (AD). The study involved a treatment group who played COSMA at home and during laboratory visits for 28 days and a control group who played only during laboratory visits. Each group was measured on days 1–14–28, where recordings of playing COSMA and Cambridge Neuropsychological Test Automated Battery (CANTAB) tests were taken. The results showed that the MCI treatment group improved sensorimotor skills in 14 days, sustained attention, spatial planning, working and visual memory, and learning in 28 days. The AD treatment group improved in sustained attention in 14 and 28 days and showed a lower cognitive decline in working memory compared to the AD control group in 28 days. Both control groups did not show any level of improvement. Even though the progression of the MCI was faster than that of the early AD, the study showed inspired results of cognitive improvement in both groups. COSMA showed evidence that cognitive stimulation and rehabilitation are possible in MCI and AD and that it is an effective and efficient non-pharmacological therapeutic tool in these groups of patients.

In this article, a highly adaptable method the empirical wavelet transform (EWT) is utilized to compress electrocardiogram (ECG) data. EWT and run-length encoding (RLE)-based technique is used for data compression of ECG rhythms. EWT is chosen because it is highly adaptable and can decompose a non-stationary signal into different frequency modes efficiently. The modified RLE is used to acquire the high reduction performance. The projected method is tested with MIT-BIH arrhythmia database and experiments are carried out in MATLAB R2016b. Performance of the proposed algorithm is evaluated in terms of compression ratio (CR), percent root mean squire difference (PRD), signal-to-noise ratio (SNR), retained energy (RE) and quality score (QS). Result shows a high CR (31%), low PRD (0.0750) and high QS (414). Comparative analysis of the performance of projected technique with several existing techniques is also done, which shows that the proposed technique is superior in terms of PRD and CR. WT is also used to detect the R-peaks (location and amplitude) using amplitude thresholding. The program took 4.452793 s to run.

The quality and quantity of medical data produced by digital devices have improved significantly in recent decades. This has led to cheap and easy data generation. There has therefore been an increased advantage in the areas of Big Data and machine learning. There is a huge application of machine leaning and artificial intelligence in health care sector. The use of machine learning to train the machine to classify the medical cases taking care of the historical data can be a boon in medical studies. In this paper, we have analyzed many machine learning algorithms and classifiers which are used to make prediction on the diabetes based on the chosen features and attributes of the dataset. The implementation of the algorithms and its performance are compared in terms of accuracy; we have also used the soft voting ensemble techniques and applied the standardized PIMA diabetes data for which the highest accuracy is achieved.