1393 research outputs found
Sort by
Adverse Health Effects of Kratom: An Analysis of Social Media Data
Get PDFThis study investigates the adverse healthcare effects associated with the use of kratom. Using machine learning techniques, we analyzed a total of 36,516 users’ posts related to kratom. The results and analysis showed that social media could help identify important insights related to the use of kratom. The sentiment and emotion analyses showed that the kratom experience was negative and largely associated with anger, fear, disgust, and sadness. The results from topic modeling showed that kratom is associated with a number of healthcare issues such as rashes and itching, urination, constipation, loss of appetite/weight, dry mouth, seizures, nausea, heartburn, dehydration, hot flashes, and loss of libido. The results indicated that 26% of users’ posts discussed multiple kratom side effects. Also, results showed the prevalence and dominance of loss of libido followed by heartburn, dry mouth, dehydration, and constipation
Automobile Autonomy vs the Social Impact of Human Trust
Get PDFThroughout human history, transportation has had a significant connection to the technology of that age. The evolution of modern transportation from horse drawn buggies to the current automobile can be attributed to a massive advancement in technology. As technology is increasingly evolving, so are the transportation systems. The next step for current transportation systems is the inclusion of autonomous driving, or self-driving automobiles. Researchers like Charlie Hewitt suggest that poor public perception of self-driving vehicles influences consumers to prefer traditional driven automobiles over their autonomous counterparts.1 As the automotive industry keeps moving forward with autonomous technology, they have progressed past the potential consumer market by adventuring outside the comfort zones of the consumers. The purpose of this thesis is to analyze the current world of autonomous automobiles and discuss some of the possible reasons for the lack of growth in potential consumer demand
JRevealPEG: A Semi-Blind JPEG Steganalysis Tool Targeting Current Open-Source Embedding Programs
Get PDFSteganography in computer science refers to the hiding of messages or data within other messages or data; the detection of these hidden messages is called steganalysis. Digital steganography can be used to hide any type of file or data, including text, images, audio, and video inside other text, image, audio, or video data. While steganography can be used to legitimately hide data for non-malicious purposes, it is also frequently used in a malicious manner. This paper proposes JRevealPEG, a software tool written in Python that will aid in the detection of steganography in JPEG images with respect to identifying a targeted set of open-source embedding tools. It is hoped that JRevealPEG will assist in furthering the research into effective steganalysis techniques, to ultimately help identify the source of hidden and possibly sensitive or malicious messages, as well as contribute to efforts at thwarting the activities of bad actors
Design Principles for Multiple Sclerosis Mobile Self-Management Applications: A Patient-Centric Perspective
No full textThis research aims to explore the users’ reactions and perception towards mobile applications for Multiple Sclerosis (MS) self-management mobile applications. The emphasis is on identifying design principles that can inform the development of successful and responsive MS self-management interventions. We employ a grounded theory approach to analyze user reviews of MS mobile applications available in the Apple and Google Play app stores. A total of 33 MS mobile applications and 1,378 user reviews and ratings were extracted from these stores. Using the results from grounded theory approach, as building blocks, we generated a domain ontology for design principles in the case of MS mobile applications. This research sheds light into design principles from a patient perspective and provides design recommendations for the usability of the MS mobile applications. The findings could extend to other conditions that share characteristics with MS
Transfer-Learned Pruned Deep Convolutional Neural Networks for Efficient Plant Classification in Resource-Constrained Environments
Get PDFTraditional means of on-farm weed control mostly rely on manual labor. This process is time-consuming, costly, and contributes to major yield losses. Further, the conventional application of chemical weed control can be economically and environmentally inefficient. Site-specific weed management (SSWM) counteracts this by reducing the amount of chemical application with localized spraying of weed species. To solve this using computer vision, precision agriculture researchers have used remote sensing weed maps, but this has been largely ineffective for early season weed control due to problems such as solar reflectance and cloud cover in satellite imagery. With the current advances in artificial intelligence, past research on weed detection in SSWM has used a large deep convolutional neural network (DCNN) for weed detection. These models are, however, computationally expensive and prone to overfitting on smaller datasets. Consequently, although DCNNs have shown continuous accuracy improvements in research settings, they remain relatively unused for practical purposes in precision agriculture due to their large number of parameters and the difficulty to implement on resource-constrained devices. Accordingly, this research investigated the use of model compression to reduce complexity and increase the efficiency of DCNNs in low-resource conditions. The proposed approach involves stacking two pre-trained DCNN models – Xception and DenseNet – to reduce the effect of performance degradation during the model compression process. A performance evaluation of the resulting XD-Ensemble indicated that the model outperformed both state-of-the-art DCNNs and a lightweight EfficientNet-B1 model in a resource-constrained environment in terms of prediction accuracy, model size, and inference speed. The current study contributes to enhancing viability while minimizing the environmental footprint of agricultural technologies as well as maximizing their production efficiency
Health Information systems capabilities and Hospital performance – An SEM analysis
No full textThe evaluation of the value generated by IT applications in general and hospital IT/IS, in particular, is an essential aspect of the research within the IS discipline. IT investment and IS capability as its functional manifestation can help improve the performance of hospitals. However, the estimated and expected efficiencies and improvement in care quality remain evasive and have yielded mixed evidence. One key finding that emerges from the research is that IT does bring value to organizations, but not in isolated cases. Instead, IT can create a synergic relationship that improves business performance by creating a process in an organization when coupled with organizational factors. We introduce hospital function efficiency as an intermediate business process that mediates HIT and hospital performance. Thus, our research investigates the impact of HIT capabilities on hospital quality of care through the hospital functional efficiency as a mediating variable using a structural equational modeling approach
Mental Health and the COVID-19 Pandemic: Analysis of Twitter Discourse
Get PDFThis study analyzed Twitter discourse to understand the association of the COVID-19 pandemic with mental health. The study compared tweets’ volume over time, tweets’ volume per mental health category, emotions, and the top hashtags on mental health before and after November 2019, the month on which the first COVID-19 case was reported. We analyzed a total of 273 million English tweets on mental health collected from 56 million unique users. Results and analysis showed a significant shift in trend for the volume of tweets on mental health over time. There was also a notable increase in the volume of tweets on depression, anxiety, stress, and suicide mental health groups. The volume of tweets posted by males and females was comparable. Finally, there was a noticeable increase in the average daily tweets that mention suicide prevention and mental health during the COVID-19 pandemic