- Data Management and Algorithms
- Advanced Database Systems and Queries
- Geographic Information Systems Studies
- Automated Road and Building Extraction
- Human Mobility and Location-Based Analysis
- Semantic Web and Ontologies
- Data Stream Mining Techniques
- Time Series Analysis and Forecasting
- Natural Language Processing Techniques
- Traffic Prediction and Management Techniques
- Advanced Text Analysis Techniques
- Energy Efficient Wireless Sensor Networks
- Advanced Data Storage Technologies
- Speech Recognition and Synthesis
- Cloud Computing and Resource Management
- IoT and Edge/Fog Computing
- Advanced Image and Video Retrieval Techniques
- Speech and dialogue systems
- Anomaly Detection Techniques and Applications
- Caching and Content Delivery
- Hand Gesture Recognition Systems
- Data Visualization and Analytics
- Algorithms and Data Compression
- Emergency and Acute Care Studies
- Wildlife-Road Interactions and Conservation
University of Washington Tacoma
2015-2024
University of Washington
2018-2024
British University in Egypt
2023
University of Maryland, College Park
2021
Canadian International College
2019
Washington Center
2018
University of British Columbia
2016
IHS Markit (United States)
2014
Microsoft Research (United Kingdom)
2010-2013
Microsoft (United States)
2010-2011
Event processing will play an increasingly important role in constructing enterprise applications that can immediately react to business critical events. Various technologies have been proposed recent years, such as event processing, data streams and asynchronous messaging (e.g. pub/sub). We believe these share a common model differ only target workload, including query language features consistency requirements. argue integrating is the next step natural progression. In this paper, we...
Highlights An AI-enabled web application was developed to classify insects on sticky traps. The AI models were trained images exposed real environmental conditions. Automated insect identification can enhance integrated pest management. This technology could be used in other applications. Abstract. Huanglongbing (HLB) disease has had a devastating impact several citrus production areas across the world. is associated with three phloem-limited bacteria of Candidatus Liberibacter group, which...
Many factors affect the precision and accuracy of location data. These include, but not limited to, environmental obstructions (e.g., high buildings forests), hardware issues malfunctioning poor calibration), privacy concerns users denying consent to fine-grained tracking). lead uncertainty about users’ which in turn affects quality location-aware services. This paper proposes a novel framework called UMove, stands for uncertain movements, manage trajectory moving objects under uncertainty....
Because financial applications rely on a continual stream of time-sensitive data, any data management system must be able to process complex queries the fly. Although many organizations turn custom solutions, systems can offer same low-latency processing with flexibility handle range applications.
Trajectory prediction techniques play a serious role in many location-based services such as mobile advertising, carpooling, taxi services, traffic management, and routing services. These rely on the object's motion history to predict future path(s). As consequence, these fail when is unavailable. The unavailability of might occur for several reasons as; be inaccessible, recently registered user with no preceding history, or previously logged data preserved confidentiality privacy. This...
Court orders may require supervising agencies (probation, parole, pre-trial or law enforcement) to monitor a specific set of offenders using ankle bracelets. These bracelets transmit the offender's GPS coordinates at regular intervals. The analysis data help: (1) detect unauthorized activities in real time and provide alerts community corrections officer, enforcement dispatcher control center, (2) mine for offenders' suspicious behavior predict probable future threats beforehand....
NoSQL data-stores are commonly used to provide flexibility and availability for big data handling. However, there is a lack of comprehensive studies about which data-store performs the best from two scalability aspects, (scale-up, scale-out), in distributed parallel processing environment. This paper compares popular (Cassandra, HBase, MongoDB) analyzes resulting performance. Our experiments measure throughput, latency, run-time evaluated on set that consist standard benchmarking workloads....
Earthen construction is known for its significant environmental benefits. It has been overshadowed by the growing popularity of industrial materials in industry, leading to a detrimental impact on environment. However, emergence 3D printing (3DP) techniques received much consideration using earth as material. Despite potential, durability 3D-printed earthen structure remains challenge that researchers are actively working overcome. This research focuses feasibility clay-based façades hot...
All online map service providers are working hard to maintain high-quality maps provide services. Example inaccuracies that can be encountered in the provided may include missing road segments, shifted connections, or incorrect turn restrictions, and mislabeling attributes like marking a directional as one-way. Maps also rapidly changing some areas due new constructions. While accuracy of various mapping systems, given by providers, is known high, even minor discrepancies underlying lead...
GPS data is noisy by nature. A typical location-based service would start filtering out the noise from raw points that are generated moving objects. Once locations of objects identified, provided. In this paper, we decide not to throw away noise. Instead, consider as an asset. We analyze various patterns under different conditions and region characteristics. More specifically, focus on one example where a lot experienced; which urban canyons. believe learning in supervised environment...
As any other type of data, GPS traces contain noise, anomaly, and sometimes unexpected values. Normally, researchers data engineers analysts would start dealing with by removing those noises outliers. However, in this work, we take the opposite direction. We focus on analyzing values rather than discarding them. Interestingly, discovered useful findings from an insight look at noise trajectories. The intuition behind discoveries is that when readings are observed several times around a...
Early transfusion can prolong life in injured patients awaiting definitive hemorrhage control. We conducted a community resources assessment of blood product availability at hospitals within the Washington State (WA) Regional Trauma System, with expectation that minority Level IV and V centers would have products routinely available for use resuscitation.We designed questionnaire soliciting information on unit quantities red cells (RBC), plasma, platelets, cryoprecipitate, and/or whole...
Map service providers are working hard to maintain high-quality maps more than three billion digital users. As each provider presents its unique routing engine and road network graph (RNG) mapping techniques, inconsistencies in services provided inevitable. These may be of two types- (1) RNG, including missing or shifted segments, turn restriction, mislabeled attributes; (2) arising from the algorithm (RA). Discovering those would improve efficiency. This paper a system, named GeoDart, that...
Scalability and energy management issues are crucial for sensor network databases. In this paper, we introduce the Sharing PArtitioning of Stream Spectrum (SPASS) protocol as a new approach to provide scalability with respect number sensors manage power consumption efficiently. The spectrum is range/distribution values read by that sensor. Close-by tend give similar readings and, consequently, exhibit spectra. We propose combine spectra into one global shared all contributing sensors. Then,...
Abstract: This paper introduces the Diacritic-Aware Segmentation and Alignment Model for Arabic (DASAM). Diacritics are vital pronunciation meaning in language but often ignored by current speech recognition systems. DASAM is designed word-level segmentation alignment unseen audio associating them with diacritic-marked text. The approach uses linguistic analysis based on intonation rules. then applies Dynamic Time Warping (DTW) to match reference word its position sentence audio. model...
This paper presents QRDiaRec, an advanced diacritization system for Arabic Quranic texts. In Arabic, linguistic style refers to the variations in diacritic markings used convey different pronunciations, dialects, meanings, and contextual understandings.QRDiaRec addresses challenge of interpreting diacritics across multiple styles, which is crucial accurate language processing. Unlike traditional systems that generate only one correct form diacritics, QRDiaRec can recognize produce valid...
This research introduces a novel framework for analyzing Arabic linguistic styles, focusing on the Quran as case study. Unlike previous studies that often focus single style or regional variations, ours examines unique features of multiple styles within text. Our approach addresses inconsistencies in character representation. creates standardized format text, ensuring consistent results. utilizes Provenance Tracker to connect different and document their lineage through narrators By text...