This research-to-practice full paper presents our innovative approach to integrating Generative Artificial Intelligence (GAI) chatbots into selected BSCS courses. These courses operate within an Online Learning Environment (OLE) based on asynchronous communication. We have detailed two distinct approaches to implement Retrieval-Augmented Generation (RAG) model-based GAI chatbots. The first approach utilizes Microsoft Copilot Studio, allowing us to create customized chatbots without the need for coding. The second approach involves Python coding to develop more advanced GAI chatbots. Both methods are straightforward and cost-effective, leveraging the latest advancements to enhance communication between students and faculty. By incorporating frequently asked questions and answers from various BSCS courses into these chatbots, we can enrich the learning experience and aid both students and faculty in achieving their goals. Our preliminary results suggest that with careful planning, design, and implementation, these chatbots can circumvent common issues such as misinformation, inaccuracy, ethical and safety concerns, and lack of contextual understanding, thereby enhancing the effectiveness of student learning in an asynchronous communication-based OLE.

During the last two and half years, the Covid-19 Pandemic has made online learning environment (OLE) a necessary modality for all educational degree programs globally. However, migrating a conventional ground campus only Bachelor of Science in Computer Engineering (BSCE) degree program into an online modality is a project more complicated than simply replicating what is common in an on-ground classroom into a virtual classroom. The major challenges include how to maintain instructional effectiveness in an online modality, how to enable students accessing lab equipment to conduct hands-on experiments in an OLE, how to support students expeditiously when they encounter difficulties in an asynchronous communication based OLE, and how to assess students work produced in an OLE, etc. In this paper, we share our experience on how we applied a systematic approach, guided by various learning pedagogies, migrating a ground campus only ABET accredited BSCE degree program into the online modality successfully. Our practice has demonstrated that this approach can assist us to quickly identify solutions, quite often unique to the OLE, based on the specific characteristics of online modality to effectively address various typical challenges encountered during the process of migration.

Along with the growing popularity of the adaptive learning platform software in STEM education programs, further enhancing the ability of the adaptive learning platform to support learning effectiveness has become a priority. A common goal of all the adaptive learning platform software is to identify gaps in a student's knowledge, and provide relevant learning materials based on the result of the assessment of the student's exiting knowledge towards to the targeted subject, to increase the learning effectiveness. However, the student's existing knowledge is only one learning attribute, and it cannot reflect all the aspects that have an impact to the student's learning effectiveness. A natural solution to overcome this weakness is to make the adaptive learning decision making algorithm capable to process the dataset of multiple learning attributes of the student efficiently. This paper presents a machine learning algorithm to efficiently process the dataset of a student's multiple learning attributes. The main enabling foundation for this new algorithm is a data structure called “student learning attributes index” which represents every learning attribute as a tuple of three elements: the “learning-attribute-If)”, the “weight” of the learning attribute among all the learning attributes, and the “efficiency” of the contribution to the student's learning effectiveness made by the learning attribute. This study has applied unequal weight to each of the learning attributes, more accurately reflecting that different learning attributes will have different impacts on a student's learning effectiveness. This new algorithm enables various learning support applications to become more practical and accurate in supporting student learning.

In recent years, to meet the growing needs of upgrading computer-related competence of working adults, many online Bachelor of Science of Computer Science (BSCS) or Bachelor of Science of Information Technology (BSIT) degree programs have been created. However, how to effectively support these online students is still a challenge. This is due to special needs such as customizing the learning to individual backgrounds, supporting various programming and technical hands-on labs, and promoting teamwork engagement, etc. We have conducted a project integrated three initiatives to create an Online Learning Environment (OLE) suited to BSCS and BSIT degree programs: (a) using the adaptive learning software to customize the learning content based on each student's existing academic foundation; (b) using Amazon's Web Services to set up the hands-on labs; and (c) using discussion board assignments to promote the engagement of student-student and student-faculty, to train students to be competent in teamwork. The initial results of our project have consistently shown that all three initiatives mentioned above have a positive effect on students' learning. Our work has demonstrated that it is possible to create an OLE, which is not only cost-effective but also functionality proper, to the online BSCS and BSIT degree programs.

This Innovative Practice Full Paper presents our work on how to apply data analytics to schedule best-suited classes for students, especially the working adult students, with different academic histories. In this computer-technology-driven economy, many working adults are going back to school to complete their college degrees. They usually bring various numbers of transfer credits with them. Often a group of students enrolled at the same time will end up in different classes. The working adult students with different needs make schools with a limited number of classrooms difficult to predict their course schedule. Also, manually scheduling courses for such students not only consumes a large amount of time, but also increases the chance for human error in the scheduling process. The paper will present our software's architecture, functionality, algorithm, as well as the results of some Use Cases. The future work will allow admission staff to evaluate the “what-if” scenarios of working adult students based on their future working and/or family situations to foresee how they might plan ahead for their schooling, so that they can balance both educational goals and other priorities. All of these will effectively support student-centered education and have a positive impact on student retention.

E-Learning is gaining more traction as it is accepted and used by more students, as it provides time convenience, cost effectiveness, and location flexibility. E-Learning's key weakness is lacking of a cost effective way to support instructors to provide synchronous feedback to students. In addition, the help provided is usually not in real time and is missing an instructor's influence to a student's affective status in the feedback, which creates a practicality gap between e-Learning and feedback effectiveness. This paper proposes an e-Tutor framework for math word problem, and discusses various aspects of feedback effectiveness which is the central design concept of the e-Tutor.

The signature-based malware-detection method is the most popular one used in anti-malware software. However, given advanced malware capabilities, the database of traditional signature-based antimalware software is becoming bloated to support identification of every variant. The increase in signatures slows the detection process and, in some cases, exceeds the resource availability of the platforms that need it most. With the expansion of the smaller platforms with limited computing resources, such as some mobile devices and various types of sensor networks, including Internet-of-Things (IoT), anti-malware's capability needs to be refined to support these platforms. Behavior-based signatures might provide that much-needed reduction in the number of signatures found in a signature set while retaining the full spectrum of malware variants.

To avoid failure and achieve higher availability, replication scheme is now widely used in distributed Cloud storage systems [25]. However, most of them only statically replicate data on some randomly chosen nodes for a fixed number of times and it is obviously not enough for more reasonable resource allocation. Moreover, query load for Web application is highly irregular. It throws us into a dilemma to always maintain maximum number of replicas in case of explosive query load outburst or save resources with fewer replicas at the expense of performance. In this paper, we present a Resilient, Fault-tolerant and High-efficient global replication algorithm (RFH) for distributed Cloud storage systems. RFHis especially efficient facing 'flash crowd' problem. Each data partition is represented by a virtual node. Each virtual node itself decides whether to replicate, migrate or suicide by weighing up the pros and cons. It is based on the evaluation of traffic load of all nodes, and selects among physical nodes with the most traffic (traffic hub) to replicate or migrate on. After that, it takes into account blocking probability to achieve quicker response and better load balance performance. Extensive simulations have been conducted and the results have demonstrated that the proposed scheme RFH outperforms the main existing algorithms the request-oriented algorithms[16] [5], the owner-oriented algorithms [7] [11] [12] [13] and the random algorithms [4] [21] [22] in terms of high replica utilization rate, high query efficiency and reasonable path length at a low cost while maintaining high availability.

Summary form only given. Managers must make decisions based on limited budgets on how best to protect their networks. Resources should be allocated across three different areas: Protect, Detect, and Response. Often what might seem as an obvious solution is not the best solution for resource allocation and networks. A model using logistic regression can help a manager determine the level of probability, based on the allocation of resources, organization objectives and certain attack characteristics that the network will be within an acceptable level of risk.

The emergence of cloud computing services has created an additional dimension in the decision for creating a new business plan which requires computing resources. Although quite a few of the recent published analytical models have provided some very good ground work for assessing the cost difference between in-house systems and leasing cloud services for the same set of computing requirements, there is a need for research towards providing a company with risk analysis tools that will allow business managers to assess the viability of migrating business applications to the cloud with broader considerations. This article consolidates several genres of analysis on cloud computing risk. We derive an new analytical model that takes into account business economics, and other business requirements such as various considerations on security and availability. This model applies these considerations to the already well researched buy-or-lease models currently used by business management professionals which allows for an easy transition to this more thorough model. We made a comparison research through evaluating the service requirement situation from published research against two service providers. The results of this research demonstrates the veracity of our model. The rationale for this research is to provide a more complete and robust model that encompasses the entire spectrum of considerations yet holds a high degree of precision.

System architecture of distributed enterprise data warehouse should ensure quality attributes such as separation, scalability, extensibility, security, and manageability. However, all existing distributed enterprise data warehouse system architectures have failed to address security at the architecture level. We propose that adding a virtualized proxy component to the system architecture will greatly enhance the security of the distributed enterprise data warehouse system.