مطالب

The use of mobile medical apps in clinical settings has recently received considerable attention. While some practitioners are using this technology to optimize decision making, others, on the other hand, are indifferent about its usage. Therefore, this study has utilized a modified UTAUT2 model to determine factors that influence the acceptance and use of mobile medical apps among professional nurses in the Ghanaian setting. A web-based data collection tool (Google Forms) was used to solicit data from 216 health professionals. Of the 216 respondents, 126 (58.33%) of them were Public Health Nurses, with 85 (39.35%) being General Nurses, and the remaining 5 (2.32%) were midwives, resulting in an average age of 31.57±4.14 years. The study used a previously validated self-administered questionnaire (UTAUT 2) to find out factors that informed respondents to adopt and use mobile medical apps. The findings established that professional qualification, gender, and the number of years that the individual had used smartphones were key determinants in accepting and using mobile medical apps. That is why this study makes the case that using technology in clinical practice has enormous advantages. It is, however, important to understand the factors that will influence the intention to adopt such technologies and their possible use.

A logo epitomizes a brand and depicts the picture of a product; consequently, attention, as an initial step of the AIDA model, to the logo is a good-looking index to survey the cognitive processing during consumers’ decision-making. Eye tracker extracts the visual attention data. For these reasons and appreciated from fixation duration, in the present study, the process of visual attention to the logo of a brand during decision-making was studied. To analyze the effects of the popularity of a brand on consumers’ decision-making, visual attention of 53 undergraduate students was studied. The brands were selected from two categories of beverages: soft drinks and non-alcoholic beers. Prior to the test, the participants had declared their favorite categories. The results showed that 75% of the participants selected a popular brand of their unfavorite categories. On the other hand, the difference of fixation duration between logos of popular and unknown brands did not directly relate to the choices of the participants. Therefore, these results did not correspond with the AIDA model. Additionally, cognitive processing toward the unknown brands’ logos was more than the popular brands’ logos. Moreover, the consumers who changed their decision were subjected to more cognitive processing compared to the consumers who insisted on their selection. In contrast to the AIDA model which implies that decision-making is triggered by attention, the present study indicated that decision making can also be influenced by the popularity of the brand. This can be due to optimization of the working memory usage by the brain. Finally, these results could be helpful in creating a new brand. According to the AIDA model, the more attractive logo and package of the brand, the more chance for being selected by the customers. However, our findings emphasize the importance of the popularity of the brand.

Handwriting Analysis has been used for a very long time to analyze an individual’s suitability for a job, and is in recent times, gaining popularity as a valid means of a person’s evaluation. Extensive Research has been done in the field of determining the Personality Traits of a person through handwriting. We intend to analyze an individual’s personality by breaking it down into the Big Five Personality Traits using their handwriting samples. We present a dataset that links personality traits to the handwriting features. We then propose our algorithm - consisting of one ANN based model and PersonaNet, a CNN based model. The paper evaluates our algorithm’s performance with baseline machine learning models on our dataset. Testing our novel architecture on this dataset, we compare our algorithm based on various metrics, and show that our novel algorithm performs better than the baseline Machine Learning models.

Corona Virus (COVID-19) is a major problem among people, and it causes suffering worldwide. Yet, the traditional prediction models are not yet suitably efficient in catching the fundamental expertise as they cannot visualize the difficulty in the health's representation problem areas. This paper states prediction mechanism that uses a model of deep learning called Long Short-Term Memory (LSTM). We have carried this model out on corona virus dataset that obtained from the records of infections, deaths, and recovery cases across the world. Furthermore, producing a dataset which includes features of geographic regions (temperature and humidity) that have experienced severe virus outbreaks, risk factors, spatio-temporal analysis, and social behavior of people, a predictive model can be developed for areas where the virus is likely to spread. However, the outcomes of this study are justifiable to alert the authorities and the people to take precautions.

Today, news texts can be created automatically and presented to readers without human participation through technologies and methods such as big data, deep learning, and natural language generation. With this research, we have developed an application that can contribute to the literature regarding The Studies on Robot Journalism Applications with a technology-reductionist perspective. Robot journalism application named Robottan Al Haberi (the English equivalent of the application name is “get the news from the robot”) produces news text by placing weather, exchange rates, and earthquake data in certain templates. The news texts, which are produced by placing the data in appropriate spaces on the template and with a maximum length of 280 characters, are automatically shared via the Twitter account @robottanalhaber. The weather information is shared once a day, the exchange rate information is shared three times a day, and the earthquake information is shared instantly. Here, we aim to produce automatic and short news by using the available structured data by placing them in specific news templates suggesting different options or a combination of them for different situations.

Deep learning techniques have become very popular among Artificial Intelligence (AI) techniques in many areas of life. Among many types of deep learning techniques, Convolutional Neural Networks (CNN) can be useful in image classification applications. In this work, a hybridized approach has been followed to classify lung nodule as benign or malignant. This will help in early detection of lung cancer and help in the life expectancy of lung cancer patients thereby reducing the mortality rate by this deadly disease scourging the world. The hybridization has been carried out between handcrafted features and deep features. The machine learning algorithms such as SVM and Logistic Regression have been used to classify the nodules based on the features. The dimensionality reduction technique, Principle Component Analysis (PCA) has been introduced to improve the performance of hybridized features with SVM. The experiments have been carried out with 14 different methods. It has been found that GLCM + VGG19 + PCA + SVM outperformed all other models with an accuracy of 94.93%, sensitivity of 90.9%, specificity of 97.36% and precision of 95.44%. The F1 score was found to be 0.93 and the AUC was 0.9843. The False Positive Rate was found to be 2.637% and False Negative Rate was 9.09%.