5153 research outputs found
Sort by
Intrusion Detection: Embedded Software Machine Learning and Hardware Rules Based Co-Designs
No full textSecurity of innovative technologies in future generation networks such as (Cyber Physical Systems (CPS) and Wi-Fi has become a critical universal issue for individuals, economy, enterprises, organizations and governments. The rate of cyber-attacks has increased dramatically, and the tactics used by the attackers are continuing to evolve and have become ingenious during the attacks. Intrusion Detection is one of the solutions against these attacks. One approach in designing an intrusion detection system (IDS) is software-based machine learning. Such approach can predict and detect threats before they result in major security incidents. Moreover, despite the considerable research in machine learning based designs, there is still a relatively small body of literature that is concerned with imbalanced class distributions from the intrusion detection system perspective. In addition, it is necessary to have an effective performance metric that can compare multiple multi-class as well as binary-class systems with respect to class distribution. Furthermore, the expectant detection techniques must have the ability to identify real attacks from random defects, ingrained defects in the design, misconfigurations of the system devices, system faults, human errors, and software implementation errors. Moreover, a lightweight IDS that is small, real-time, flexible and reconfigurable enough to be used as permanent elements of the system's security infrastructure is essential. The main goal of the current study is to design an effective and accurate intrusion detection framework with minimum features that are more discriminative and representative. Three publicly available datasets representing variant networking environments are adopted which also reflect realistic imbalanced class distributions as well as updated attack patterns. The presented intrusion detection framework is composed of three main modules: feature selection and dimensionality reduction, handling imbalanced class distributions, and classification. The feature selection mechanism utilizes searching algorithms and correlation based subset evaluation techniques, whereas the feature dimensionality reduction part utilizes principal component analysis and auto-encoder as an instance of deep learning. Various classifiers, including eight single-learning classifiers, four ensemble classifiers, one stacked classifier, and five imbalanced class handling approaches are evaluated to identify the most efficient and accurate one(s) for the proposed intrusion detection framework. A hardware-based approach to detect malicious behaviors of sensors and actuators embedded in medical devices, in which the safety of the patient is critical and of utmost importance, is additionally proposed. The idea is based on a methodology that transforms a device's behavior rules into a state machine to build a Behavior Specification Rules Monitoring (BSRM) tool for four medical devices. Simulation and synthesis results demonstrate that the BSRM tool can effectively identify the expected normal behavior of the device and detect any deviation from its normal behavior. The performance of the BSRM approach has also been compared with a machine learning based approach for the same problem. The FPGA module of the BSRM can be embedded in medical devices as an IDS and can be further integrated with the machine learning based approach. The reconfigurable nature of the FPGA chip adds an extra advantage to the designed model in which the behavior rules can be easily updated and tailored according to the requirements of the device, patient, treatment algorithm, and/or pervasive healthcare application
Arduino-based Smart Attic Fan System
No full textResearch indicates that on a hot summer day with outdoor temperatures around 80◦F, the temperature measured inside an attic could be around 135◦F or more. Extreme heat causes a homeowner’s electric bill for cooling to rise and the shingles of the house to crack and fall off. Such problems make houses unsafe to live in. Due to the cracked shingles, water leaks through the rooftop causing damages like mildew and mold. In this poster, we designed and implemented an Arduino-based smart attic fan system. It uses temperature and humidity sensors to monitor the status inside the attic. If the temperature inside the attic goes too high, or excessive moisture is detected inside the attic, the Arduino controller is going to automatically turn on the attic fan. The built-in camera can take videos inside attic and use wireless communication to upload it to cloud server. The homeowner can use their smart phones to “see” the status inside the attic remotely without the need to actually climb up into the attic. In case there is a fire, the smoke detector could also sense the situation and send out alarm to homeowner’s smart phone. This can help homeowners to detect rain leakage or other hazardous situation inside the attic and take actions on time to prevent further damage to the house. Our smart attic fan system utilizes Internet-of-Things (IoT) technology to extend the life of every roof, to lessen roof repair cost, and possibly make attics habitable
Artificial Intelligence in Human Resource Management: A game changer in talent acquisition
No full textArtificial intelligence (AI) seems to be everywhere these days and has become a part of our daily life. Talent acquisition is a critical aspect of human resource management. It is a fast-growing area for AI since a recruitment process stores significant amounts of data such as resumes, interview notes, assessments results, and compensation details for jobs and candidates. AI is transforming hiring by assisting recruiters in different talent acquisition processes, from identifying the right talent to screening and assessing specific behavior of candidates. AI is useful in streamlining and automating workflow in talent acquisition processes. It certainly helps organizations engage with the appropriate job candidates faster. This research suggests a decision methodology on where and when to use AI in talent acquisition to assist organizations in their human resource investment decisions
Improving Sheet Metal Processes Using Lean Manufacturing
No full textLean manufacturing is a branch of manufacturing, that finds out the optimized route for a process to be completed. It isn’t just about using tools or changing a few steps in our manufacturing processes. It changes the whole view of the business and it progress. Right from supply chain to the managers role, is taken into consideration in this process. Lean is also known as a cost cutting mechanism. It helps companies strive for increased efficiency, decreasing the losses. Mapping and analysis (statistical) are the main approaches to lean. Lean focuses on step by step analysis of waste reduction, keeping the process clean and optimized. This poster will give an insight about Kaizen or Continuous Improvement, which helped improving the production, and simultaneously increased efficiency. Key tools and techniques used in lean systems are: Six Sigma, Muda, Poka-yoke, Kaizen, Kanban, 5S
The UB-Discovery STEM on Wheels Project (Science, Technology, Engineering, & Mathematics)
No full textBridgeport Public Schools (BPS) in Connecticut serve 21,260 students from 39 minority groups in low performing schools. BPS have limited funds for curriculum improvements and resources necessary to address STEM achievement gaps. Thus, the University of Bridgeport (UB) has partnered with the Discovery Museum and Planetarium (DMP) to purchase and retrofit a bus that will bring STEM education and precious resources to high-needs K-12 schools in the community that are lagging behind. A city bus is transformed into a mobile classroom and laboratory and UB-DMP offer the required technical, logistical, and science literacy and pedagogy expertise that is essential in reaching targeted students. UB-DMP collectively brings space and astronomy themes (rocketry, satellites, mission control, high altitude ballooning, remote sensing, citizen science) as well as robotics, 3D printing, virtual reality, and renewable energy programming to students of all ages. In sum, STEM on Wheels: 1) offers STEM experiences to schools lacking resources, 2) provides K-12 students with hands-on, STEM-focused skills aligned with the Next Generation Science Standards (NGSS), and 3) trains UB engineering, science, and math students in effective teaching practices that communicate the excitement of STEM activities. This project is sponsored in part by the CHEFA Client Grant Program, The Greater Bridgeport Transit Authority, 21 Century Fox and NASA CT Space Grant Consortium
Use of Image processing technology for reporting: BIM Model comparison with Daily progress in Construction
No full textThe basis of a successful project in the world of construction is largely based on the financial outcome of the project. There are many variables affecting the financial outcome of a project, being able to control the project with daily progress reporting is a key point that enormously drives the successful completion of the project. The paper describes the use of image processing technology in drones to compare the completed coordinated BIM models with the daily progress that has been made on the job by different trades. The methodology implements use of deep learning techniques to compare data with “to be accomplished” model. More than 18% of labor factor is taken in account in bid of project only for report generation and following progress reporting
2019 College of Health Sciences Spring Commencement Ceremony (May 12 2019)
No full textThe College of Health Sciences Spring Commencement ceremony with a listing of every graduate and honorary degree recipients. President's message and Dean's message noted. Commencement speaker Tracy W. Gaudet, MD Executive director Veterans Health Administration Office of Patient Centered Care & Cultural Transformation noted
Current Outsourcing Industries Status in China
No full textChina as the second biggest economic country, it becomes an ideal place for companies that want to outsource their businesses. China places an important role in outsourcing industries. In this research, it proves the truth that China has the power to lead the way in different perspectives
Automated Beach Cleaner
No full textIn today's world of plastic, beaches all over the earth are suffering from litter and waste that inevitably reaches the shore and gets swept into the ocean and seas. Even today, litter such as plastic bags and cigarette butts are still a common sight in even some of the most remote beaches. The world responded to this by creating beach cleaners, which clear beaches at night from the leftover litter by visitors. These however are usually found to be large and expensive, as well as limited to utilization when there are no people around as it might be dangerous to operate during human activity. This project exploits the complications with these industrial sized beach cleaners and presents a comprehensive, automated beach cleaner that accounts for these challenges
Flourish: A Successful Homeless Transition Housing, Services, Social Connectedness, & Prevention
No full textHomelessness is a growing issue within the United States and proper shelter is not always accessible. This is a problem that is expected to escalate as the years progress. Improving the conditions of the shelter in which homeless individuals stay, could contribute to their overall well-being and rehabilitation. These conditions can be improved on a daily basis by providing adequate services to help with self esteem, hygiene, clothing, employment and education. Integrating the wellness factor into the building program itself would be beneficial in our Community