Search for: All records

High-resolution digital elevation models (HRDEMs), derived from LiDAR, are widely used for mapping hydrographic details in flat terrains. However, artificial flow barriers, particularly from roads, elevate terrain and prematurely end flowlines. Drainage barrier processing (DBP), such as HRDEM excavation, is employed to address this issue. However, there is a gap in quantitatively assessing the impact of DBP on HRDEM-derived flowlines, especially at finer scales. This study fills that gap by quantitatively assessing how DBP improves flowline quality at finer scales. We evaluated HRDEM-derived flowlines that were generated using different flow direction algorithms, developing a framework to measure the effects of flow barrier removal. The results show that the primary factor influencing flowline quality is the presence of flow accumulation artifacts. Quality issues also stem from differences between natural and artificial flow paths, unrealistic flowlines in flat areas, complex canal networks, and ephemeral drainage ways. Notably, the improvement achieved by DBP is demonstrated to be more than 6%, showcasing its efficacy in reducing the impact of flow barriers on hydrologic connectivity. 

This paper examines the challenges community college students encounter when transferring to four-year higher-education institutions, focusing on the gap between their transfer aspirations and actual success. Despite the availability of substantial financial aid in higher education, transfer students continue to face numerous challenges that impede their integration and success at new institutions. These obstacles arise from a combination of institutional factors and individual student characteristics. Utilizing Pascarella’s model, this study underscores the importance of support programs in raising institutional awareness of the diverse challenges transfer students face and the necessity for tailored strategies to facilitate their successful transition and retention. 

Due to long-standing barriers to healthcare access in rural areas, telehealth has been promoted as an effective means of delivering healthcare services. However, there is a general absence of quantitative data showing how geographic residence and race affect telehealth adoption. This study examines variations in telehealth adoption based on race and geographic residence in Southern Illinois using a mail survey. It finds that residents of urban Carbondale, compared to those in rural Cairo, have better access to broadband and are more likely to use telehealth. Respondents significantly differ from each other based on their geographic location of residence and race when it came to using telehealth to save money on travel and to save money on childcare. A significant barrier to telehealth adoption identified across all groups is privacy protection concern. The findings highlight the crucial role of broadband infrastructure in healthcare access and the need for trust in telehealth systems to ensure data privacy. 

This study delves into the adoption and challenges of telehealth services in rural settings, examining racial and locational influences on usage. Employing qualitative methods, it draws on 30 detailed interviews with both healthcare providers and patients in two racially diverse, economically disadvantaged towns in Southern Illinois from fall 2021 to spring 2023. Our findings indicate that insufficient internet access and lack of necessary devices are significant factors in the reluctance of rural residents to embrace telehealth services. Additionally, this study reveals a major barrier: a deep-seated mistrust in the telehealth infrastructure's ability to safeguard private medical information. Notably, our results show that Black participants have heightened concerns regarding the health care industry's capacity to maintain the confidentiality of their medical data. 

The past decade has seen a rise in the availability of modern information and communication technologies (ICTs) for developing smart societies and communities. However, the smart divide, characterized by inequalities in ICT infrastructures, software access, and individual capabilities, remains a significant barrier for rural communities. Limited empirical studies exist that explore what and how ICT infrastructures can be developed to bridge the smart divide. The paper aimed to address rural broadband access in the context of infrastructural dimensions of smart divide (i.e., smart infrastructural divide) in the United States, focusing on the wireless network infrastructure’s role in narrowing the gap. It examined the broadband specifications needed for smart applications like smart education and telehealth, emphasizing the importance of wireless network capabilities. While fixed broadband offers higher speeds, wireless networks can support many smart applications with decent flexibility and ease of access. To further understand the implications of wireless broadband to rural communities, we conducted a case study in Carbondale and Cairo, two rural towns in Southern Illinois, using on-site user-inspired speed testing. An Android application was developed to measure download/upload speeds and Reference Signal Received Power (RSRP) for broadband quality. Results suggest both Carbondale and Cairo experienced below-average speeds with high variability among census blocks, which highlights the need for improved wireless network infrastructure. The paper culminated in the technological and policy recommendations to narrow down the smart infrastructural divide. 

The accurate and efficient determination of hydrologic connectivity has garnered significant attention from both academic and industrial sectors due to its critical implications for environmental management. While recent studies have leveraged the spatial characteristics of hydrologic features, the use of elevation models for identifying drainage paths can be influenced by flow barriers. To address these challenges, our focus in this study is on detecting drainage crossings through the application of advanced convolutional neural networks (CNNs). In pursuit of this goal, we use neural architecture search to automatically explore CNN models for identifying drainage crossings. Our approach not only attains high accuracy (over 97% for average precision) in object detection but also excels in efficiently inferring correct drainage crossings within a remarkably short time frame (0.268 ms). Furthermore, we perform a detailed profiling of our approach on GPU systems to analyze performance bottlenecks. 

Embedded devices, constrained by limited memory and processors, require deep learning models to be tailored to their specifications. This research explores customized model architectures for classifying drainage crossing images. Building on the foundational ResNet-18, this paper aims to maximize prediction accuracy, reduce memory size, and minimize inference latency. Various configurations were systematically probed by leveraging hardware-aware neural architecture search, accumulating 1,717 experimental results over six benchmarking variants. The experimental data analysis, enhanced by nn-Meter, provided a comprehensive understanding of inference latency across four different predictors. Significantly, a Pareto front analysis with three objectives of accuracy, latency, and memory resulted in five non-dominated solutions. These standout models showcased efficiency while retaining accuracy, offering a compelling alternative to the conventional ResNet-18 when deployed in resource-constrained environments. The paper concludes by highlighting insights drawn from the results and suggesting avenues for future exploration.