Site-wide links

Engineering, Science, & Technology

Creating, innovating, addressing challenges, solving problems, and improving the quality of lives in society.

Solder paste printing is the most common method for attaching surface mount devices to printed circuit boards and it has been reported that a majority of all assembly defects occur during the stencil printing process. It is also recognized that the solder paste printing... READ MORE
Hierarchical temporal memory (HTM) is a biomimetic machine learning algorithm focused upon modeling the structural and algorithmic properties of the neocortex. It is comprised of two components, realizing pattern recognition of spatial and temporal data, respectively. HTM research has gained momentum in recent years, leading... READ MORE
This project examined estimated emission reductions from implementing advanced control technologies in heavy duty diesel engines and to assess potential emission impacts from trucks supporting the High Volume Hydraulic Fracturing (HVHF) industry in Pennsylvania’s portion of the Marcellus Shale Formation. Models were run... READ MORE
Color Doppler Ultrasound (CDUS) is a method of non-invasive fluid velocity measurement that is used for regular cardiac screenings as well as during complex surgeries such as valve replacements. A Color Doppler image is a contour map of the velocity field and can thereby... READ MORE
Solar crop drying is a cheap and effective way to preserve food material, especially in developing countries where fuel and electricity are expensive or unavailable. Some tropical fruits are difficult to transport and store leading to significant spoilage. Without access to fuel and large... READ MORE
Current research in computer vision and machine learning has demonstrated some great abilities at detecting and recognizing objects in natural images. Current state-of-the-art results in object detection, classification and localization in ImageNet Challenges have the validation accuracy for top 5 predictions for classification to... READ MORE
Wind power is one of the fastest growing power sources worldwide. Large installations of wind power generation are prominent in Asia, Europe and the United States. The gear boxes and bearings of large wind turbines continue to be huge liabilities and fail well short... READ MORE
With the continuous scaling of device dimensions, the number of cores on a single die is constantly increasing. This integration of hundreds of cores on a single die leads to high power dissipation and thermal issues in modern Integrated Circuits (ICs). This causes problems... READ MORE
The purpose of this paper was to develop a new test method for packaging perforation evaluation to replace the current test method due to the human variables during test and the inconsistency of test results. First, an end user survey was conducted to find out... READ MORE
With increasing environmental concerns, recovery of used products through various options has gained significant attention. In order to collect, categorize and reprocess used products in a cost and time efficient manner, a pre-evaluated network infrastructure is needed in addition to existing traditional forward logistics... READ MORE
Solar energy is abundant and is distributed all over the earth. While all renewable energy resources are important, solar energy has the potential to meet high levels of energy demand [1]. Silicon occupies 90% of the PV market and single crystalline silicon solar cells account... READ MORE
Inverse problems have been studied in great detail and optimization methods using objective functionals such as output least-squares (OLS) and modified output least-squares (MOLS) are well understood. However, the existing literature has only dealt with identifying parameters that appear linearly in systems of partial differential... READ MORE
The goal of this thesis is to develop a voice-controlled human-robot interface (HRI) which allows a person to control and communicate with a robot. Dragon NaturallySpeaking, a commercially available automatic speech recognition engine, was chosen for the development of the proposed HRI. In order... READ MORE
In this thesis, renewal theory is used to analyze patterns of outcomes for discrete random variables. We start by introducing the concept of a renewal process and by giving some examples. It is then shown that we may obtain the distribution of the number... READ MORE
Ensemble learning is a widely used technique in Data Mining, this method allows us to aggregate models to reduce prediction error. There are many methods on how to perform model aggregation, one of them is known as Random Subspace Learning, which consists of building... READ MORE