Search

Grapevine leaves are utilized worldwide in a vast range of traditional cuisines. As their price and flavor differ from kind to kind, recognizing various species of grapevine leaves is becoming an essential task. In addition, the differentiation between grapevine leaf types by human sense is difficult and time-consuming. Thus, building a machine learning model to automate the grapevine leaf classification is highly beneficial. Therefore, this is the primary focus of this work. This paper uses a CNN-based model to classify grape leaves by adapting DenseNet201. This study investigates the impact of layer freezing on the performance of DenseNet201 throughout the fine-tuning process. This work used a public dataset consist of 500 images with 5 different classes (100 images per class). Several data augmentation methods used to expand the training set. The proposed CNN model, named DenseNet-30, outperformed the existing grape leaf classification work that the dataset borrowed from by achieving 98% overall accuracy.

Background Motor impairment after stroke is due not only to direct tissue loss but also to disrupted connectivity within the motor network. Mixed results from studies attempting to enhance motor recovery with Transcranial Magnetic Stimulation (TMS) highlight the need for a better understanding of both connectivity after stroke and the impact of TMS on this connectivity. This study used TMS-EEG to map the causal information flow in the motor network of healthy adult subjects and define how stroke alters these circuits. Methods Fourteen stroke patients and 12 controls received TMS to two sites (bilateral primary motor cortices) during two motor tasks (paretic/dominant hand movement vs. rest) while EEG measured the cortical response to TMS pulses. TMS-EEG based connectivity measurements were derived for each hemisphere and the change in connectivity (ΔC) between the two motor tasks was calculated. We analyzed if ΔC for each hemisphere differed between the stroke and control groups or across TMS sites, and whether ΔC correlated with arm function in stroke patients. Results Right hand movement increased connectivity in the left compared to the right hemisphere in controls, while hand movement did not significantly change connectivity in either hemisphere in stroke. Stroke patients with the largest increase in healthy hemisphere connectivity during paretic hand movement had the best arm function. Conclusions TMS-EEG measurements are sensitive to movement-induced changes in brain connectivity. These measurements may characterize clinically meaningful changes in circuit dynamics after stroke, thus providing specific targets for trials of TMS in post-stroke rehabilitation.

Current guidelines regarding treatment for germ-cell tumors (GCTs) emphasizes cautious progression focusing on stage-specific treatments. Presented herein is the case of a 30-year-old man who, through monitoring of serum alpha-fetoprotein (AFP) levels and surveillance imaging, avoided excessive treatment. This case demonstrates how an experienced clinician, familiar with natural history of GCTs, can appropriately classify level of risk and allow a patient to preserve natural fertility. Furthermore, we highlight the potential for miRNA analysis in staging and management of GCTs. This case serves to underscore the importance of acting with caution in the pursuit of the best outcome for our patients.

The current covid-19 pandemic has transferred educational, work and other activities on-line and made it essential to be able to use videoconferencing tools. This raises many issues for disabled people, including the accessibil-ity and usability of these tools. However, studies evaluating accessibility and usability of these tools seem to be lacking and this paper contributes to filling this gap. It has three main contributions: (i) the presentation of crite-ria to be used in this valuation; (ii) a preliminary study of the experiences of the two disabled authors; (iii) preliminary recommendations for tool de-velopers.

Objective Primary objective is to determine the rate of intubation with inappropriately sized endotracheal tubes (ETTs) in a pediatric intensive care unit (PICU) in El Salvador. Secondary objective is to determine effectiveness of a video-based curriculum to teach local providers on pediatric advanced airway management and surgical approach to patients requiring airway reconstruction. Methods Data for 296 intubated pediatric patients was collected over a six month period in a 16-bed PICU in El Salvador. Results of a learning behavior assessment survey completed by local healthcare workers informed a curriculum to complement on-site education during annual surgical airway mission trips. The video-based curriculum addressed proper sizing and use of cuffed endotracheal tubes, care of the intubated child and perioperative considerations of the surgical airway patient. Providers completed pre and post-curriculum quizzes to measure knowledge acquisition. Results Over 6-months, 281 patients were intubated. Sixty-three percent had improperly sized ETTs. Thirty-one percent had a failed or accidental extubation. All-cause mortality was 24%. One hundred and fifty-nine Salvadorian providers completed a learning behavior survey informing a video-based curriculum. Sixty-four providers completed the curriculum. Post-curriculum quiz scores increased by 18.7%. Surgeons, anesthesiologist, intensivists and speech pathologists demonstrated significant improvement (p Conclusion Nearly two-thirds of intubated patients in a PICU in El Salvador have improperly sized ETTs and one-third require reintubation following planned or accidental extubation. The development of this first of its kind video-based curriculum for critical care and surgical training regarding how to properly care for the intubated child is coupled with the development of a longitudinal database to record pediatric airway related morbidity and mortality in the largest pediatric hospital in El Salvador. This model and system can be used to track the reduction in airway related morbidity and mortality directly related to a systems based intervention both in El Salvador and then elsewhere.

This research is motivated by the importance of science, technology, engineering and mathematics (STEM), including for many careers, understanding increasingly important public debates and policy formulation on issues such as cybersecurity/ privacy management and genetically modified organisms and for personal life e.g. budgeting. STEM accessibility seems to have received less attention than that of other subjects. Particular areas of difficulty/ exclusion are laboratories, fieldwork and access to formulae. This presentation will focus on laboratories.

The paper presents the preliminary results of an ongoing survey of the use of computers and mobile devices, interest in recommender apps and knowledge and concerns about privacy issues amongst English and Italian speaking disabled people. Participants were found to be regular users of computers and mobile devices for a range of applications. They were interested in recommender apps for household items, computer software and apps that met their accessibility and other requirements. They showed greater concerns about controlling access to personal data of different types than this data being retained by the computer or mobile device. They were also willing to make tradeoffs to improve device performance.

This paper discusses the role of technology in overcoming existing barriers to education and employment faced by people with specific learning disabilities and illustrates the discussion by the example of the Learnmaths toolbox for people with specific learning disabilities in mathematics. The context of the toolbox is respect for equality and diversity and consequently the recognition that different approaches to learning are equally valid and that the cognitive processes of people with specific learning disabilities can lead to creativity and innovation.