A5101906419- Remote-Sensing Image Classification
- Spacecraft Design and Technology
- Infrared Target Detection Methodologies
- Advanced Chemical Sensor Technologies
- Biosensors and Analytical Detection
- Fractal and DNA sequence analysis
- Multimodal Machine Learning Applications
- Identification and Quantification in Food
- Shape Memory Alloy Transformations
- Electrospun Nanofibers in Biomedical Applications
- Radio Astronomy Observations and Technology
- Satellite Image Processing and Photogrammetry
- Calibration and Measurement Techniques
- Energy Efficient Wireless Sensor Networks
- Sparse and Compressive Sensing Techniques
- Domain Adaptation and Few-Shot Learning
- Speech and dialogue systems
- Advanced Sensor and Energy Harvesting Materials
- Hydrogels: synthesis, properties, applications
- GNSS positioning and interference
- Advanced Multi-Objective Optimization Algorithms
- Transition Metal Oxide Nanomaterials
- Advanced Memory and Neural Computing
- Sentiment Analysis and Opinion Mining
- Advanced Image Fusion Techniques
Amazon (Germany)
2022
Tufts University
2015-2020
South China University of Technology
2012-2015
Epidermal pH is an indication of the skin's physiological condition. For example, wound can be correlated to angiogenesis, protease activity, bacterial infection, etc. Chronic nonhealing wounds are known have elevated alkaline environment, while healing process occurs more readily in acidic environment. Thus, dermal patches capable continuous measurement used as point‐of‐care systems for monitoring skin disorder and process. Here, pH‐responsive hydrogel fibers presented that long‐term...
In this work, we present a disposable paper-based optical sensor arranged as barcode for monitoring food spoilage. The color-changing is embedded in the packaging and monitored using smart phone. color change of different sensing dyes that make up due to emission volatile organic compounds (VOCs) from food. Different geometric shapes are assigned each dye identification. fabrication low-tech easy perform. A phone quantifies sensor, which provides non-contact metric freshness/spoilage.
Economical sensing and recording of temperature are important in the transportation management sensitive goods such as medicine. Existing approaches measure entire profile using electronic devices running on a continuous power source. This letter presents simple, intelligent, battery-free solution for capturing informative events natural thermo-mechanical state shape memory alloy (SMA). approach utilizes temperature-induced irreversible mechanical deformation SMA way to capture history...
On page 711 S. Sonkusale, A. Khademhosseini, and co-workers present pH-responsive hydrogel fibers that can be used for long-term monitoring of epidermal wound conditions. dyes are loaded into mesoporous microparticles, which then embedded developed through microfluidic spinning. The fabricated microfibers flexible create conformal contact with skin. Images the pH-sensing during real-time pH measurement captured a smart phone camera convenient readout on-site.
In recent years, CubeSats have emerged as a platform of intense interest for wide range applications, including remote sensing. Of specific in this paper are data processing challenges associated with the MIT's Microwave Atmospheric Satellite (MicroMAS). Due to motion MicroMAS and geometry acquisition process, measurements not collected on regular grid spatial locations required by most applications. Thus, fundamental problem these is that interpolation. The further complicated fact collects...
With their greatly reduced sizes, low development cost, and rapid construction time, CubeSats have merged as a platform of considerable interest for wide range applications, including remote sensing. Many applications require the interpolation sensor data into regularly spaced grid downstream scientific products. This problem is complicated CubeSat platforms due to potentially significant uncertainties associated with spatial position satellite. In this paper, we present probabilistic...
Recent years have seen significant advances in multi-turn Spoken Language Understanding (SLU), where dialogue contexts are used to guide intent classification and slot filling. However, how selectively incorporate contexts, such as previous utterances acts, into SLU still remains a substantial challenge. In this work, we propose novel contextual model for filling tasks. We introduce an adaptive global-local context fusion mechanism integrate our model. The local aligns each using multi-head...
In recent years, Smart Home Assistants have expanded into tens of thousands devices and transformed from a voice only assistant to much more versatile smart assistant, that uses connected display provide multi-modal customer experience. order further improve on the multi-modality experience, comprehension systems need models can work with multisensory inputs. We focus problem visual grounding, which allows customers interact manipulate items displayed screen via voice. propose novel learning...
Recently, pattern classification and recognition based on sparse representation have seen a surge of interest in many applications. In this article, we present method hyperspectral imagery via expanded dictionary. The original spectral signatures are transformed with 1-D dyadic wavelet transform. Then these features combined the to form an Finally, linear programming is employed calculate solution such dictionary which was further substituted into related decision rule. Results experiment...
With the recent development of CubeSats, several ultracompact, low cost, and rapidly deployable satellites have been developed for earth observation missions. Because geometry acquisition process, measurements are irregularly sampled, whereas in meteorological applications, data preferred on a regular grid. This problem is further complicated by fact that, due to CubeSats' compact sizes constraints, such as limited power, errors occur geolocation calibration, resulting positional errors. In...
Anomaly detection is very useful for hyperspectral with no a priori information of spectral signature. However, most prevailing anomaly detectors are applied directly to the all-bands data without considering characteristics imagery in local spectrum range and some computation problem incurred from high dimensional data. In this paper, Dezert-Smarandache Theory (DSmT) based detector presented handle these problems. The first partitioned into several lower band-subsets. Then generalized basic...
With their greatly reduced sizes, low development cost and rapid construction times, CubeSats have emerged as a platform of intense interest for wide range applications, including remote sensing. However, due to compact form factor, performance tradeoffs relative larger existing platforms been encountered. Of specific in this paper are data processing challenges associated with the Micro-MAS platform. In meteorological radiometer samples preferred on regularly spaced grid generating...