Digital Commons @ Harrisburg University of Science and Technology
Not a member yet
435 research outputs found
Sort by
A Multi-Modal Approach for Gender-Based Violence Detection
No full textThe impact of living in an unhealthy and unsafe environment leads to perpetuated aggressive and violent behavior. Many organizations have conducted research to identify that violence against women is a deep-rooted issue and has existed for many years. Institutions and women-led groups have gathered to provide assistance and governments have done a lot to least to support the cause. But the severity of this social pandemic is still unresolved across the globe. Research shows that contact with nature reduces the incidence of aggression and violence within family members in a household. Research also shows that air pollution and aggressive behavior are correlated. This paper provides a multi-modal approach to measure Gender-Based Violence Index (GBVI) by detecting the coverage of green canopies using satellite imagery in addition to sensing the level of atmospheric pollution to calculate violence occurrences before they even happen in a given neighborhood. To support the identification process, computer vision technique will be applied to satellite imagery to measure and map out the Vegetation Index (VI) on a scale of 0-100 in a neighborhood along with using air pollution sensors and Internet of Things (IoT) to detect the level of intoxicants that aggravate the cause of violence against women. The result of this approach is promising for organizations like the United Nations, World Health Organization, and government bodies to create rapid response efforts in the interest of women rights, humanitarians, and security communities
Evaluating Recommender Systems Effect on Content Diversity: An agent-based framework
No full textDigital markets depend on recommender systems that facilitate interactions among suppliers, distributors, and consumers, ultimately increasing sales volume and allegedly increasing user utility. Beyond this operational cornerstone, recommender systems also have a passive role in how these markets organize and behave (e.g., funneling consumers into few suppliers or promoting obscure products and services that can better satisfy consumer needs). Te potential effect of recommendations appears to be larger on cultural or entertainment and media industries, where a product’s uncertainty is usually high. As such, cultural diversity and market concentration on content platforms (e.g., YouTube, Spotify) are susceptible to the effect of recommendation system algorithms. Te study of diversity has been a focal topic for individual recommendation optimizations, but little attention has been given to aggregated measures of diversity. Previous work on this area states that collaborative-based recommender systems have an impact on sales diversity. I expand on this, presenting an agent-based model to test the impacts of recommender systems on cultural markets. Te model offers a framework to estimate the effects of state-of-the-art content-based and collaborative filtering algorithms on diversity. Early results confirm previous work. Next steps include the use of machine learning algorithms, social influence, and adaptive behavior of users. Current and future work will provide useful insights for marketing modeling, content platform policy, and the use of recommenders in market design
Choice rates are independent from perceived patterns (when patterns are not obvious): A reply to Plonsky and Teodorescu
No full textIn Ashby, Konstantinidis, and Yechiam (2017) we argued that the variance in people\u27s choices in decisions from experience stems from uncertainty about preferences. This was confirmed by high correlations between the variance in experiential choices and subsequent one-shot policy decisions: both showing considerable diversification. In the present paper we address a comment regarding our paper by Plonsky and Teodorescu (2020). These authors suggested that variance in experiential choices is driven by responses to perceived patterns in prior outcomes (rather than individuals\u27 preferences), and that these responses can also drive subsequent policy decisions. This was supported by an apparent “wavy recency” effect in our data indicatory of responses to patterns, and by an experiment showing that outcome patterns affected subsequent policy decisions. We demonstrate that our study results do not in fact show a significant wavy recency. We do find positive recency but it is very poorly correlated with the overall choice rates. Hence, we contend that the variance in choice rates mostly reflects one\u27s preferences when there are no obvious patterns. Moreover, we argue that because Plonsky and Teodorescu\u27s experimental manipulation was confounded with the frequency of relatively positive/negative outcomes, their results do not conclusively show an effect of response to patterns on subsequent policies
Perception of Healthcare Providers on Mirror Therapy for Stroke
Get PDFStroke is a very important health problem faced worldwide with high mortality and incidence. The majority of stroke survivors suffer temporary or permanent disabilities of which hemiparesis is one of the most common. Hemiparesis makes it difficult for patients to perform their activities of daily living and often they have declining quality of life. Mirror therapy (MT) is a an inexpensive, easy and safe intervention which has been proven to be very effective to improve the motor function in hemiparetic stroke. Despite this, it is not often employed. Hence, the purpose of this study was to explore the awareness and perception of the various healthcare providers of MT for stroke and to define the value of MT in their opinion. The study was conducted using an anonymous online survey, and the data was collected and analysed using Microsoft Excel. It was found that a majority of the responding health care providers are aware of MT and some find it of value as an effective intervention
Study of Satisfaction of Inpatient Discharge Based on Nurses’ Perceptions
Get PDFPatient satisfaction plays an important role in providing quality health care, and discharge satisfaction is part of overall patient satisfaction since it reveals how patients feel about their stay. In this paper, we evaluated inpatient discharge satisfaction based on nurses’ perceptions. An anonymous survey was used to evaluate how satisfied the patients were when being discharged from the acute care hospital with survey questions answered by nurses who work on medical-surgical floors. Data was collected from the questionnaires and analyzed using Excel
Building Something with the Raspberry Pi
Get PDFIn 2017 Ryan Korn and I submitted a grant proposal in the annual Harrisburg University President’s Grant process. Our proposal was to partner with a local high school to install a classroom of 20 Raspberry Pi’s, along with the requisite peripherals. In that classroom students would be challenged to design something that combined programming with physical computing. In our presentation to the school we suggested that this project would give students the opportunity to be “amazing.”
As part of the grant, the top three students would be given scholarships to HU and the top five finalists would all be permitted to keep the Pi they used for their project. All students involved in the project would be invited to meet with the admissions team during the showcase.
It took until May of 2020 to complete the work on this grant. There have been some very satisfying moments, and more than a few interesting challenges. The purpose of this article is to trace some of the steps for those who might be interested in retracing the activities of our grant and putting Raspberry Pi’s in classrooms in their own schools
A tool for securities analysis and trading strategy back-testing
Get PDFThe platform created in this project will help users to analyze stock/ETF performance, define and improve their asset allocation plans and trade ideas. Using real market data, user can do a deep dive into securities performance, historical correlation, risk and return. Furthermore, user can use the platform back test their trade ideas, modify the parameters, including percentage allocation, risk limits and rebalancing frequency, and create the best strategy which suits their risk/return criteria and long-term wealth management goals
Deep Learning Framework of Vehicle Detection and Tracking System
Get PDFIn the last semester, I designed a system to detect and track vehicle system on the highway. The system is based on the public deep learning framework and utilize pre-trained model to implement the functions of this system. In this paper, I will use my own framework to implement this system. This try will help us better understand the details of deep learning framework. I will public the code of deep learning framework and make sure everyone can modify it.
This semester will focus on the researching of Naïve Convolutional Neural Networks. Neural networks are commonlyused for the analysis of visual images of high class of neural networks. Concerning the architecture from their general, and unchangeable, from the properties of the conductive hurdle weighted with stones, and they are, who is said to be artificial, according to the magnitude of the, or unchangeable. Those who are in the acknowledgment of the image and video recording systems review. The arrangement of images and medical image analysis, natural language processing and financial time series.
For my project in the last semester. I designed a tracking system used for tracking vehicles on the highway. The tracking system is based on the deep learning model. I used the open lib from coco-data base. In this semester, I will design the deep learning model by myself. In this paper, I will introduce my method to design the deep learning model. In this paper, I will introduce the blueprint, the details of method and my test cases