A5001646142- Photonic and Optical Devices
- Image Retrieval and Classification Techniques
- Advanced Steganography and Watermarking Techniques
- Reinforcement Learning in Robotics
- Robotics and Sensor-Based Localization
- Digital Media Forensic Detection
- Face and Expression Recognition
- Remote-Sensing Image Classification
- Chaos-based Image/Signal Encryption
- Advanced Image and Video Retrieval Techniques
- Infrared Target Detection Methodologies
- Evolutionary Algorithms and Applications
- Medical Image Segmentation Techniques
- Gene expression and cancer classification
- Genomics and Phylogenetic Studies
- Robotic Path Planning Algorithms
- Multi-Agent Systems and Negotiation
- Advanced Vision and Imaging
- Advanced Optical Sensing Technologies
- Molecular Biology Techniques and Applications
- Metaheuristic Optimization Algorithms Research
- Simulation Techniques and Applications
- Distributed and Parallel Computing Systems
- Advanced Optical Imaging Technologies
- Face recognition and analysis
University of Massachusetts Lowell
2015-2024
Mapúa University
2017
University of Massachusetts Amherst
2010
University of Denver
1999-2001
Batch effects are the systematic non-biological differences between batches (groups) of samples in microarray experiments due to various causes such as sample preparation and hybridization protocols. Previous work focused mainly on development methods for effective batch removal. However, their impact cross-batch prediction performance, which is one most important goals microarray-based applications, has not been addressed. This paper uses a broad selection data sets from Microarray Quality...
Abstract To use next-generation sequencing technology such as RNA-seq for medical and health applications, choosing proper analysis methods biomarker identification remains a critical challenge most users. The US Food Drug Administration (FDA) has led the Sequencing Quality Control (SEQC) project to conduct comprehensive investigation of 278 representative data pipelines consisting 13 sequence mapping, three quantification, seven normalization methods. In this article, we focused on impact...
Cytosine modifications in DNA such as 5-methylcytosine (5mC) underlie a broad range of developmental processes, maintain cellular lineage specification, and can define or stratify types cancer other diseases. However, the wide variety approaches available to interrogate these has created need for harmonized materials, methods, rigorous benchmarking improve genome-wide methylome sequencing applications clinical basic research. Here, we present multi-platform assessment cross-validated...
Abstract Background Targeted sequencing using oncopanels requires comprehensive assessments of accuracy and detection sensitivity to ensure analytical validity. By employing reference materials characterized by the U.S. Food Drug Administration-led SEquence Quality Control project phase2 (SEQC2) effort, we perform a cross-platform multi-lab evaluation eight Pan-Cancer panels assess best practices for oncopanel sequencing. Results All demonstrate high across targeted high-confidence coding...
Abstract Accurate indel calling plays an important role in precision medicine. A benchmarking set is essential for thoroughly evaluating the performance of bioinformatics pipelines. reference sample with a known-positive variants was developed FDA-led Sequencing Quality Control Phase 2 (SEQC2) project, but known indels were limited. This project sought to provide enriched that would be more translationally relevant by focusing on additional cancer related regions. thorough manual review...
In this paper, we propose a system that automatically detects and recognizes road signs found in the United States, real time or close to real-time. The proposed has application intelligent autonomous unmanned vehicles for urban surveillance rescue. It is multi-layered hierarchical scheme composed of 3 parts: sign color segmentation, shape recognition, classification. robust invariant image translation, rotation scaling. can deal with situations where there partial occlusion, blurring image,...
Metagenomics is the study of microorganisms collected directly from natural environments. studies use DNA fragments obtained a environment using whole genome shotgun (WGS) sequencing. Sequencing random into taxa-based groups known as binning. Currently, there are two different methods binning: sequence similarity and composition methods. Sequence usually based on alignment to like BLAST, or MEGAN. As only very small fraction species available in current databases, do not yield good results....
Wide area surveillance and reconnaissance in many homeland security applications generally entails an airborne platform providing a desired view of the interest. The needs large critical infrastructures key resources that may span for miles, demand field exceeds provided by single sensor. Image registration aerial imagery can increase while panoramic view. This increases without any modification to optics, focal plane array, associated hardware. Some primary limitations existing image...
Chlorophyll fluorescence (ChlF), a plant response in time to stressors, has long been known be useful tool detect stress. Early and accurate stress detection is imperative enabling timely appropriate intervention. One major limitation of prior work that, general, only few key inflection points localized section chlorophyll signal are used calculate single index values. These values yield very limited insight into level or type. In this paper, we present method for classification that uses...
Similarity measures such as normalized cross correlation (NCC) are widely employed for applications pattern recognition and/or template matching which commonly used in image registration. This approach, however, is not immune to noise variations present the images especially case where multiple bands of interest dominated by both system and external sensor's field view. Thus can influence calculation coefficients produce erroneous results during matching. work proposes a metric identifies...
In this paper we deal with the design and analysis of an intelligent multi-agent-based architecture for synchronized real-time situational understanding, awareness, decision-making, control in a geographically networked distributed computing environment. particular, focus here on implementation middleware framework agent intra inter-node communication as well nodes synchronization. While proposed work finds applications many areas including chemical sensors, large key infrastructures...
In this paper, we present two high capacity information hiding schemes in which large amount of can be hidden gray level images with transparency using Tchebichef moments. particular, the is a image same size as original image. A watermark also for data authentication and tampering localization purposes. The novelty our work comes from combining both steganography digital watermarking one scheme. first scheme secure fragile capability. By mean that will distorted under any kind attack...
The main focus of this paper is on issues related to communications, load balancing, resource sharing and allocation in a distributed computing system, as applied battlefield simulation. We present architecture middleware algorithms for scheduling balancing. In the proposed nodes use Multi-Token Message Passing Interface (MPI) over message based Myrinet communication namely GM protocol, Gigabit switch communicate with each other. As we show here brings additional implementation challenges...
One of the main contributions this paper is to show that contrary common belief Tchebichef moments are more sensitive noise added image than Zernike moments. We by imposing different types and levels on various images measuring error due alone after reconstruction. To calculate alone, reconstruction subtracted from total error, which initially includes both errors. Another contribution present some analysis compare capability Legendre in free environments independent used. spectrally...