Search

Abstract BackgroundThe rise of wearable sensors marks a significant development in the era of affective computing. Their popularity is continuously increasing, and they have the potential to improve our understanding of human stress. A fundamental aspect within this domain is the ability to recognize perceived stress through these unobtrusive devices. ObjectiveThis study aims to enhance the performance of emotion recognition using multitask learning (MTL), a technique extensively explored across various machine learning tasks, including affective computing. By leveraging the shared information among related tasks, we seek to augment the accuracy of emotion recognition while confronting the privacy threats inherent in the physiological data captured by these sensors. MethodsTo address the privacy concerns associated with the sensitive data collected by wearable sensors, we proposed a novel framework that integrates differential privacy and federated learning approaches with MTL. This framework was designed to efficiently identify mental stress while preserving private identity information. Through this approach, we aimed to enhance the performance of emotion recognition tasks while preserving user privacy. ResultsComprehensive evaluations of our framework were conducted using 2 prominent public datasets. The results demonstrate a significant improvement in emotion recognition accuracy, achieving a rate of 90%. Furthermore, our approach effectively mitigates privacy risks, as evidenced by limiting reidentification accuracies to 47%. ConclusionsThis study presents a promising approach to advancing emotion recognition capabilities while addressing privacy concerns in the context of empathetic sensors. By integrating MTL with differential privacy and federated learning, we have demonstrated the potential to achieve high levels of accuracy in emotion recognition while ensuring the protection of user privacy. This research contributes to the ongoing efforts to use affective computing in a privacy-aware and ethical manner.

Objectives: This study explores the feasibility and effects of low-intensity blood flow restriction exercise on forearm muscle strength and function in individuals with spinal cord injury. Study design: Pilot randomized clinical trial. Patients and methods: Ten male and female adult participants with chronic cervical and thoracic spinal cord injury underwent an 8-week low-intensity blood flow restriction exercise programme that targeted forearm muscles. Each participant’s contralateral forearm served as the control. Grip strength was the primary outcome measure, and participants also provided qualitative feedback on their experiences. Results: The study revealed a significant increase in participants’ forearm muscle strength on the experimental side engaged in low-intensity blood flow restriction training, with an average strength gain of 7.5 ± 0.36 kg after 16 exercise sessions (Cohen’s d = –6.32, 95% CI –8.34, –6.68). In comparison, the control side, following a conventional high- intensity exercise regimen without BFR, showed a more modest strength increase of 4.4 ± 0.67 kg. A mean Patient’s Global Impression of Change score of 2.2 reflected overall improvements in participants’ daily activities and health status. Conclusion: This study highlights the feasibility and effectiveness of low-intensity blood flow restriction exercise as a safe and promising approach to enhancing forearm muscle strength in individuals with spinal cord injury. The observed positive outcomes, coupled with a high level of participant satisfaction, underscore the potential of this innovative method to significantly improve limb muscle strength, thereby contributing to greater functional independence in this population.

Stress, a natural process affecting individuals' wellbeing, has a profound impact on overall quality of life. Researchers from diverse fields employ various technologies and methodologies to investigate it and alleviate the negative effects of this phenomenon. Wearable devices, such as smart bands, capture physiological data, including heart rate variability, motions, and electrodermal activity, enabling stress level monitoring through machine learning models. However, labeling data for model accuracy assessment poses a significant challenge in stress-related research due to incomplete or inaccurate labels provided by individuals in their daily lives. To address this labeling predicament, our study proposes implementing Semi-Supervised Learning (SSL) models. Through comparisons with deep learning-based supervised models and clustering-based unsupervised models, we evaluate the performance of our SSL models. Our experiments show that our SSL models achieve 77% accuracy with a classifier trained on an augmented dataset prepared using the label propagation (LP) algorithm. Additionally, our deep autoencoder network achieves 76% accuracy. These results highlight the superiority of SSL models over unsupervised learning techniques and their comparable performance to supervised learning models, even with limited labeled data. By relieving the burden of labeling in daily life stress recognition, our study advances stress-related research, recognizing stress as a natural process rather than a disease. This facilitates the development of more efficient and accurate stress monitoring methods in the wild.

Gold is one of the most counterfeited precious metals. The color of copper is like gold. For this reason, copper is one of the most used materials for color counterfeiting. When the chemical properties are concerned, wolfram is like gold (density of gold and tungsten are 19.30 g/ml and 19.25 g/ml, respectively), so it can be used as a chemical counterfeit. The purity of gold can be determined by X-ray, but this method is costly. The current low-cost methods of jewelers have been experimented with for counterfeit gold detection in this paper. When a gold matter is hit by a subject, the sound frequency is higher than the frequency of sound when the same experiment is done with copper. Furthermore, counterfeit gold color is brighter than real ones. The color of gold is unique, and it is called "gold yellow". In this research, by employing sound and image processing, counterfeit and original gold are differentiated. For the image processing part, first a Convolutional Neural Network (CNN)-based toolbox for segmenting the gold material is applied. Then, deep CNNs for differentiating the color of the gold and copper materials are employed. Promising results are achieved with both sound and image processing techniques.

With the increased amount of digitized historical documents, information extraction from them gains pace. Historical maps contain valuable information about historical, geographical and economic aspects of an era. Retrieving information from historical maps is more challenging than processing modern maps due to lower image quality, degradation of documents and the massive amount of non-annotated digital map archives. Convolutional Neural Networks (CNN) solved many image processing challenges with great success, but they require a vast amount of annotated data. For historical maps, this means an unprecedented scale of manual data entry and annotation. In this study, we first manually annotated the Third Military Mapping Survey of Austria-Hungary historical map series conducted between 1884 and 1918 and made them publicly accessible. We recognized different road types and their pixel-wise positions automatically by using a CNN architecture and achieved promising results.

Researchers strive hard to develop effective ways to detect and cope with enduring high-level daily stress as early as possible to prevent serious health consequences. Although research has traditionally been conducted in laboratory settings, a set of new studies have recently begun to be conducted in ecological environments with unobtrusive wearable devices. Since patterns of stress are ideographic, person-independent models have generally lower accuracies. On the contrary, person-specific models have higher accuracies but they require a long-term data collection period. In this study, we developed a hybrid approach of personal level stress clustering by using baseline stress self-reports to increase the success of person-independent models without requiring a substantial amount of personal data. We further added decision level smoothing to our unobtrusive smartwatch based stress level differentiation system to increase the performance by correcting false labels assigned by the machine learning algorithm. In order to test and evaluate our system, we collected physiological data from 32 participants of a summer school with wrist-worn unobtrusive wearable devices. This event is comprised of baseline, lecture, exam and recovery sessions. In the recovery session, a stress management method was applied to alleviate the stress of the participants. The perceived stress in the form of NASA-TLX questionnaires collected from the users as self-reports and physiological stress levels extracted using wearable sensors are examined separately. By using our system, we were able to differentiate the 3-levels of stress successfully. We further substantially increase our performance by personal stress level clustering and by applying high-level accuracy calculation and decision level smoothing methods. We also demonstrated the success of the stress reduction methods by analyzing physiological signals and self-reports.

The use of cloud services that process privacy-sensitive information such as digital banking, pervasive healthcare, smart home applications requires an implicit continuous authentication solution, which will make these systems less vulnerable to the spoofing attacks. Physiological signals can be used for continuous authentication due to their uniqueness. Ubiquitous wrist-worn wearable devices are equipped with photoplethysmogram sensors, which enable us to extract heart rate variability (HRV) features. In this study, we show that these devices can be used for continuous physiological authentication for enhancing the security of the cloud, edge services, and IoT devices. A system that is suitable for the smartband framework comes with new challenges such as relatively low signal quality and artifacts due to placement, which were not encountered in full lead electrocardiogram systems. After the artifact removal, cleaned physiological signals are fed to the machine learning algorithms. In order to train our machine learning models, we collected physiological data using off-the-shelf smartbands and smartwatches in a real-life event. By applying a minimum quality threshold, we achieved a 3.96% Equal Error Rate. Performance evaluation shows that HRV is a strong candidate for continuous unobtrusive implicit physiological authentication.

PURPOSE: The aim of this study was to apply a standardized Quantitative Sensory Testing (QST) approach in patients to investigate whether oral surgery can lead to sensory changes, even if the patients do not report any sensory disturbances. Furthermore, this study determines the degree and duration of possible neuronal hyperexcitability due to local inflammatory trauma after oral surgery. PATIENTS AND METHODS: Orofacial sensory functions were investigated by psychophysical means in 60 patients (30 male, 30 female) in innervation areas of infraorbital nerves, mental nerves and lingual nerves after different interventions in oral surgery. The patients were tested 1 week, 4 weeks, 7 weeks, and 10 weeks postoperatively. As controls for bilateral sensory changes after unilateral surgery, tests were additionally performed in 20 volunteers who did not have any dental restorations. RESULTS: No differences were found between the control group and the control side of the patients. Although not 1 of the patients reported paresthesia or other sensory changes postoperatively, QST detected significant differences between the control and the test side in the mental and lingual regions. Test sides were significantly less sensitive for thermal parameters (cold, warm, and heat). No differences were found in the infraorbital region. Patients showed significantly decreased pain pressure thresholds on the operated side. QST monitored recovery over time in all patients. CONCLUSIONS: The results show that oral surgery can lead to sensory deficits in the mental and lingual region, even if the patients do not notice any sensory disturbances. The applied QST battery is a useful tool to investigate trigeminal nerve function in the early postoperative period. In light of the increasing forensic implication, this tool can serve to objectify clinical findings. [ABSTRACT FROM AUTHOR]

Historical manuscripts and archival documentation are handwritten texts which are the backbone sources for historical inquiry. Recent developments in the digital humanities field and the need for extracting information from the historical documents have fastened the digitization processes. Cutting edge machine learning methods are applied to extract meaning from these documents. Page segmentation (layout analysis), keyword, number and symbol spotting, handwritten text recognition algorithms are tested on historical documents. For most of the languages, these techniques are widely studied and high performance techniques are developed. However, the properties of Arabic scripts (i.e., diacritics, varying script styles, diacritics, and ligatures) create additional problems for these algorithms and, therefore, the number of research is limited. In this research, we first automatically spotted the Arabic numerals from the very first series of population registers of the Ottoman Empire conducted in the mid-nineteenth century and recognized these numbers. They are important because they held information about the number of households, registered individuals and ages of individuals. We applied a red color filter to separate numerals from the document by taking advantage of the structure of the studied registers (numerals are written in red). We first used a CNN-based segmentation method for spotting these numerals. In the second part, we annotated a local Arabic handwritten digit dataset from the spotted numerals by selecting uni-digit ones and tested the Deep Transfer Learning method from large open Arabic handwritten digit datasets for digit recognition. We achieved promising results for recognizing digits in these historical documents.

Historical document analysis systems gain importance with the increasing efforts in the digitalization of archives. Page segmentation and layout analysis are crucial steps for such systems. Errors in these steps will affect the outcome of handwritten text recognition and Optical Character Recognition (OCR) methods, which increase the importance of the page segmentation and layout analysis. Degradation of documents, digitization errors, and varying layout styles are the issues that complicate the segmentation of historical documents. The properties of Arabic scripts such as connected letters, ligatures, diacritics, and different writing styles make it even more challenging to process Arabic script historical documents. In this study, we developed an automatic system for counting registered individuals and assigning them to populated places by using a CNN-based architecture. To evaluate the performance of our system, we created a labeled dataset of registers obtained from the first wave of population registers of the Ottoman Empire held between the 1840s and 1860s. We achieved promising results for classifying different types of objects and counting the individuals and assigning them to populated places.

Chronic stress leads to poor well-being, and it has effects on life quality and health. Society may have significant benefits from an automatic daily life stress detection system using unobtrusive wearable devices using physiological signals. However, the performance of these systems is not sufficiently accurate when they are used in unrestricted daily life compared to the systems tested in controlled real-life and laboratory conditions. To test our stress level detection system that preprocesses noisy physiological signals, extracts features, and applies machine learning classification techniques, we used a laboratory experiment and ecological momentary assessment based data collection with smartwatches in daily life. We investigated the effect of different labeling techniques and different training and test environments. In the laboratory environments, we had more controlled situations, and we could validate the perceived stress from self-reports. When machine learning models were trained in the laboratory instead of training them with the data coming from daily life, the accuracy of the system when tested in daily life improved significantly. The subjectivity effect coming from the self-reports in daily life could be eliminated. Our system obtained higher stress level detection accuracy results compared to most of the previous daily life studies.

Objectives: The aim of this study was to report the clinical features, management, and outcome of patients with paranasal sinus mucocele with intraorbital extension. Materials and Methods: Eleven patients who were diagnosed and treated for paranasal sinus mucocele with intraorbital extension between 2005-2012 were included in this retrospective study. The clinical characteristics, treatment modalities, and complications were recorded and analyzed. Results: The records of 11 patients (aged 25 to 69, mean 47.6±15.6 years) with orbital mucocele were included in this study. The most frequent initial symptoms and findings were proptosis in 7 patients (63.6%), diplopia in 6 patients (54.5%), and ocular movement limitation in 6 patients (54.5%). The origin of the orbital mucocele was frontal sinus in 6 patients (54.5%), ethmoidal sinus in 3 patients (27.3%), and maxillary sinus in 2 patients (18.2%). Eight patients whose mucoceles were approachable with endoscopy (72.7%) were treated with functional endoscopic sinus surgery (ESS) and marsupialization of the sinus to the nasal cavity. Three patients’ mucoceles (27.3%) were located in the lateral side of the frontal sinus and were unapproachable with endoscopy. In these patients, the endoscopic approach was combined with the osteoplastic flap technique by external approach. After surgery, all the patients’ findings and symptoms improved; only one patient who had recurrent bilateral mucoceles required additional surgery. This recurrence was regressed by endoscopic surgery and no additional complications were observed. Conclusion: The frontal and ethmoidal sinuses were the most common origin of orbital mucoceles. Proptosis, limitation of eye movements, and diplopia were the most frequently detected signs in patients with orbital mucocele. Endoscopic sinus surgery produced favorable results in patients with an endoscopically approachable mucocele, and the osteoplastic flap technique with external approach led to successful results in patients with endoscopically unapproachable mucoceles. (Turk J Ophthalmol 2014; 44: 297-300)

The negative effects of mental stress on human health has been known for decades. High-level stress must be detected at early stages to prevent these negative effects. After the emergence of wearable devices that could be part of our lives, researchers have started detecting extreme stress of individuals with them during daily routines. Initial experiments were performed in laboratory environments and recently a number of works took a step outside the laboratory environment to the real-life. We developed an automatic stress detection system using physiological signals obtained from unobtrusive smart wearable devices which can be carried during the daily life routines of individuals. This system has modality-specific artifact removal and feature extraction methods for real-life conditions. We further tested our system in a real-life setting with collected physiological data from 21 participants of an algorithmic programming contest for nine days. This event had lectures, contests as well as free time. By using heart activity, skin conductance and accelerometer signals, we successfully discriminated contest stress, relatively higher cognitive load (lecture) and relaxed time activities by using different machine learning methods.

Aim: To compare the effects of intravitrealbevacizumab (IVB) and intravitreal triamcinolone acetonide (IVT) in the treatment of macular edema (ME) secondary to central retinal vein occlusion (CRVO). Materials and Methods: There were 20 patients treated with IVB (1.25 mg/0.05 mL) and 16 treated with IVT (4 mg/0.1 mL). The two groups were compared with regard to best-corrected visual acuity (BCVA), central macular thickness (CMT) on optical coherence tomography (OCT), slit-lamp biomicroscopy and fundus fluorescein angiography results, intraocular pressure (IOP), numbers of injections, and adverse events. Results: The mean follow-up times in the IVB and IVT groups were 17.45±8.1 months (range: 8-33 months) and 19.94±10.59 months (range: 6-40 months), respectively (P = 0.431). Visual acuity increased and CMT decreased significantly within both groups, but no differences were observed between the groups (P = 0.718). The percentages of patients with increased IOP and iatrogenic cataracts were significantly higher in the IVT group than in the IVB group. Conclusions: Treatment with IVB and IVT both resulted in significant improvement in visual acuity and a decrease in CMT in patients with ME secondary to non-ischemic CRVO, with no difference between the two treatments. The incidence of adverse events, however, was significantly greater in the IVT group than in the IVB group. IVB may be preferred over IVT for the treatment of ME in patients with non-ischemic CRVO.

Objective. To compare central macular thickness (CMT) of diabetic patients with type 2 diabetes without clinical retinopathy and healthy subjects. Materials and Methods. Optical coherence tomography (OCT) measurements were performed in 124 eyes of 62 subjects with diabetes mellitus without clinical retinopathy (study group: 39 females, 23 males; mean age: 55.06 ± 9.77 years) and in 120 eyes of 60 healthy subjects (control group: 35 females, 25 males; mean age: 55.78 ± 10.34 years). Blood biochemistry parameters were analyzed in all cases. The data for central macular thickness (at 1 mm), the levels of fasting plasma glucose, and glycosylated hemoglobin (HbA1c) were compared in both groups. Results. The mean central macular thickness was 232.12 ± 24.41 µm in the study group and 227.19 ± 29.94 µm in the control group. The mean HbA1c level was 8.92 ± 2.58% in the study group and 5.07 ± 0.70% in the control group (P=0.001). No statistically significant relationship was found between CMT, HbA1c, and fasting plasma glucose level in either group (P>0.05). Conclusions. Central macular thickness was not significantly thicker in patients with type 2 diabetes without clinical retinopathy than in healthy subjects.

Abstract Background The goal of this study was to evaluate the somatic and psychological effects by means of QUALITY OF LIFE (QOL) of surgical treatment of patients with oral squamous cell carcinoma. The factors gender, age, nicotine consumption, and tumour stage were taken into consideration. Methods 54 patients after surgical resection of oral squamous cell carcinomas (OSCC) were analysed from 01.09.2005 to 31.05.2008. Inclusion criteria for the study were: age at least 18 years, no indication or treatment of synchronous and metachronous tumours. German translations of the EORTC H&N-35 and EORTC QLQ-C-30 questionnaires, as well as a general socioeconomic patient history were used as measuring instruments. The questionnaires were completed independently by the patients. The answers were translated into scale values for statistical evaluation using appropriate algorithms. Results Analysis of the EORTC-QLQ-C-30 questionnaires demonstrated a tendency of more negative assessment of emotional function among the female participants, and a more negative evaluation of social function among the male participants. Greater tumour sizes showed significantly lower bodily function (p = 0.018). While a smaller tumour size was significantly associated with lower cognitive functioning (p = 0.031). Other cofactors such as age, nicotine consumption, and tumour stage only showed a tendency to influence the quality of sleep and daily life. Conclusions The data obtained within this investigation demonstrated that gender had the most significant power on the subjectively perceived postoperative quality of life. This factor is important e.g. in preoperative decision making regarding immediate microvascular reconstruction after e.g. mandibular resection and therefore QOL assessment should become integral component of the care of patients with OSCC.

Abstract Background Bisphosphonates are widely used in the clinical treatment of bone diseases with increased bone resorption. In terms of side effects, they are known to be associated with osteonecrosis of the jaw (BONJ). The objective of this study was to evaluate the effect of bisphosphonates on osteoblast proliferation by cell count and gene expression analysis of cyclin D1 in vitro. Furthermore, the gene expression of the extracellular matrix protein collagen type I was evaluated. Nitrogen-containing and non-nitrogen-containing bisphosphonates have been compared on gene expression levels. Methods Human osteoblast obtained from hip bone were stimulated with zoledronate, ibandronate and clodronate at concentrations of 5 × 10-5M over the experimental periods of 1, 2, 5, 10 and 14 days. At each point in time, the cells were dissolved, the mRNA extracted, and the gene expression level of cyclin D1 and collagen type I were quantified by Real-Time RT-PCR. The gene expression was compared to an unstimulated osteoblast cell culture for control. Results The proliferation appeared to have been influenced only to a small degree by bisphosphonates. Zolendronate led to a lower cyclin D1 gene expression after 10 days. The collagen gene expression was enhanced by nitrogen containing bisphosphonates, decreased however after day 10. The non-nitrogen-containing bisphosphonate clodronate, however, did not significantly influence cyclin D1 and collagen gene expression. Conclusions The above data suggest a limited influence of bisphosphonates on osteoblast proliferation, except for zoledronate. The extracellular matrix production seems to be initially advanced and inhibited after 10 days. Interestingly, clodronate has little influence on osteoblast proliferation and extracellular matrix production in terms of cyclin D1 and collagen gene expression.

Sulfide ions are regarded to be toxic to microorganisms in engineered methanogenic systems (EMS), where organic substances are anaerobically converted to products such as methane, hydrogen, alcohols, and carboxylic acids. A vast body of research has addressed solutions to mitigate process disturbances associated with high sulfide levels, yet the established paradigm has drawn the attention away from the multifaceted sulfide interactions with minerals, organics, microbial interfaces and their implications for performance of EMS. This brief review brings forward sulfide-derived pathways other than toxicity and with potential significance for anaerobic organic matter degradation. Available evidence on sulfide reactions with organic matter, interventions with key microbial metabolisms, and interspecies electron transfer are critically synthesized as a guidance for comprehending the sulfide effects on EMS apart from the microbial toxicity. The outcomes identify existing knowledge gaps and specify future research needs as a step forward towards realizing the potential of sulfide-derived mechanisms in diversifying and optimizing EMS applications., Competing Interests: Declaration of Competing Interest The authors declare that they have no conflict of interest., (Copyright © 2023 The Authors. Published by Elsevier Inc. All rights reserved.)