Browsing by Subject "Sensors"
Now showing 1 - 6 of 6
Results Per Page
Sort Options
Item Analyzing Social Media Texts and Images to Assess the Impact of Flash Floods in Cities(IEEE, 2017-06-15) Basnyat, Bipendra; Anam, Amrita; Singh, Neha; Gangopadhyay, Aryya; Roy, NirmalyaComputer Vision and Image Processing are emerging research paradigms. The increasing popularity of social media, micro- blogging services and ubiquitous availability of high-resolution smartphone cameras with pervasive connectivity are propelling our digital footprints and cyber activities. Such online human footprints related with an event-of-interest, if mined appropriately, can provide meaningful information to analyze the current course and pre- and post- impact leading to the organizational planning of various real-time smart city applications. In this paper, we investigate the narrative (texts) and visual (images) components of Twitter feeds to improve the results of queries by exploiting the deep contexts of each data modality. We employ Latent Semantic Analysis (LSA)-based techniques to analyze the texts and Discrete Cosine Transformation (DCT) to analyze the images which help establish the cross-correlations between the textual and image dimensions of a query. While each of the data dimensions helps improve the results of a specific query on its own, the contributions from the dual modalities can potentially provide insights that are greater than what can be obtained from the individual modalities. We validate our proposed approach using real Twitter feeds from a recent devastating flash flood in Ellicott City near the University of Maryland campus. Our results show that the images and texts can be classified with 67\% and 94\% accuracies respectively.Item Automated Functional and Behavioral Health Assessment of Older Adults with Dementia(IEEE, 2016-08-18) Alam, Mohammad Arif Ul; Roy, Nirmalya; Holmes, Sarah; Gangopadhyay, Aryya; Galik, ElizabethDementia is a clinical syndrome of cognitive deficits that involves both memory and functional impairments. While disruptions in cognition is a striking feature of dementia, it is also closely coupled with changes in functional and behavioral health of older adults. In this paper, we investigate the challenges of improving the automatic assessment of dementia, by better exploiting the emerging physiological sensors in conjunction with ambient sensors in a real field environment with IRB approval. We hypothesize that the cognitive health of older individuals can be estimated by tracking their daily activities and mental arousal states. We employ signal processing on wearable sensor data streams (e.g., Electrodermal Activity (EDA), Photoplethysmogram (PPG), accelerometer (ACC)) and machine learning algorithms to assess cognitive impairments and its correlation with functional health decline. To validate our approach, we quantify the score of machine learning, survey and observation based Activities of Daily Living (ADLs) and signal processing based mental arousal state, respectively for functional and behavioral health measures among 17 older adults living in a continuing care retirement community in Baltimore. We compare clinically observed scores with technology guided automated scores using both machine learning and statistical techniques.Item Developing a Quantitative Framework for Designing Responsive RNA Electrochemical Aptamer-Based Sensors and Applications(2015-01-01) Schoukroun-Barnes, Lauren R.; White, Ryan J; Chemistry & Biochemistry; ChemistryElectrochemical aptamer-based sensors utilizing structure-switching aptamers are specific, selective, sensitive, and widely applicable to the detection of a variety of targets. The specificity is achieved by the binding properties of an electrode-bound RNA or DNA aptamer biorecognition element that is a single-strand of DNA or RNA selected for in vitro to bind to a specific target molecule. Signaling in this class of sensors arises from changes in electron transfer efficiency upon target-induced changes in the conformation/flexibility of the aptamer probe. The changes in aptamer flexibility can be readily monitored electrochemically. The signaling mechanism enables several approaches to maximize the analytical attributes (i.e., sensitivity, limit of detection, and observed binding affinity) of the aptamer sensor. The work in this dissertations describes the quantitative effects of two different approaches to control sensor signaling in order to rationally tune sensor performance. The first part of this dissertations describes the effects of nucleic acid sequence and structure on the signaling of a representative small molecule aptamer-based sensor for the detection of aminoglycoside antibiotics. Modifying aptamer sequences to undergo large conformation changes upon target addition improves and maximizes E-AB sensor signaling because the collisional frequency and electron transfer rate of the 3?-attached redox molecule exhibits strong distance dependence. This dissertations also discusses the effects of stabilizing a folded structure of the aptamer to conserve the signal change, but reduce the binding affinity in order to shift the functional region of the sensor towards the therapeutic window of aminoglycoside antibiotics. Finally, with a newly developed family of aptamer sequences, tunable and predictable sensor responses achieved by employing different ratios of two aptamers with different affinities for the same target molecule on one sensor surface. The studies here were performed on a test bed aminoglycoside E-AB sensor, however the design criteria and framework established to tune sensor responses are generally applicable to any aptamer-based sensor. The second part of this dissertations explains the use of hydrogels to protect RNA E-AB sensors to enable use in complex media, such as whole blood, serum, plasma, etc.. The motivation is to bring the promising attributes of E-AB sensors to the clinic or bedside for real-time therapeutic drug monitoring. However, RNA E-AB sensor application has been limited as a result of degradation of the RNA sensing element in biological samples. To improve E-AB sensor function in complex samples, this work describes the development of a biocompatible hydrogel material to protect the oligonucleotides from degradation and inhibit non-specific absorption of proteins to the sensor surface ? both of which impede sensor function. Specifically, RNA sensors for aminoglycoside antibiotics were coated with a polyacrylamide hydrogel and tested in serum. Coating the RNA sensors with the hydrogel enabled sensor stability for a period of 3h in serum, which is a significant improvement from the uncoated sensors. The hydrogel coating also did not significantly affect E-AB sensor function based on the comparable titration curves of the uncoated and coated E-AB sensors. While sensor function and stability were tested specifically with aminoglycoside targets the technique employed to coat sensors with a hydrogel should be generally applicable to any small molecule E-AB sensor.Item Feasibility and mitigation of false data injection attacks in smart grid(IEEE, 2016-10-06) Khanna, Kush; Joshi, AnupamThe power grid is evolving rapidly. With the addition of micro-grids and renewable energy resources, and increasing automation in decision-making enabled by sensors, the grid has become very complex. Research in the area of smart grids shows that the grid is vulnerable to cyber-attacks. In particular, recent studies reveals how false data injection could lead to variety of problems in the smart grid operation. A well-crafted attack can pass the bad data detection systems during state estimation and affect the operation and control of the power grid. In this paper, we build on prior efforts in this space to describe how false data injection attacks can be alleviated using conventional techniques by protecting certain critical sensors in the power system. The feasibility of false data injection attacks with incomplete network knowledge is explained in this paper considering IEEE 14 bus test system. The assumptions for defining the attacking region are also validated with the help of different case studies. This paper depicts the importance of securing the power grid against cyber-attacks.Item SensePresence: Infrastructure-less Occupancy Detection for Opportunistic Sensing Applications(IEEE, 2015-09-14) Khan, Md Abdullah Al Hafiz; Hossain, H M Sajjad; Roy, NirmalyaPredicting the occupancy related information in an environment has been investigated to satisfy the myriad requirements of various evolving pervasive, ubiquitous, opportunistic and participatory sensing applications. Infrastructure and ambient sensors based techniques have been leveraged largely to determine the occupancy of an environment incurring a significant deployment and retrofitting costs. In this paper, we advocate an infrastructure-less zero-configuration multimodal smartphone sensor-based techniques to detect fine-grained occupancy information. We propose to exploit opportunistically smartphones' acoustic sensors in presence of human conversation and motion sensors in absence of any conversational data. We develop a novel speaker estimation algorithm based on unsupervised clustering of overlapped and non-overlapped conversational data to determine the number of occupants in a crowded environment. We also design a hybrid approach combining acoustic sensing opportunistically with locomotive model to further improve the occupancy detection accuracy. We evaluate our algorithms in different contexts, conversational, silence and mixed in presence of 10 domestic users. Our experimental results on real-life data traces collected from 10 occupants in natural setting show that using this hybrid approach we can achieve approximately 0.76 error count distance for occupancy detection accuracy on average.Item Unseen Activity Recognitions: A Hierarchical Active Transfer Learning Approach(IEEE, 2017-07-17) Alam, Mohammad Arif Ul; Roy, NirmalyaHuman activity recognition (AR) is an essential element for user-centric and context-aware applications. While previous studies showed promising results using various machine learning algorithms, most of them can only recognize the activities that were previously seen in the training data. We investigate the challenges of improving the recognition of unseen daily activities in smart home environment, by better exploiting the hierarchical taxonomy of complex daily activities. We first (a) design a hierarchical representation of complex activity taxonomy in terms of human-readable semantic attributes, and (b) develop a hierarchy of classifiers which incorporates a cluster tree built on the domain knowledge from training samples. Though this model is rich in recognizing complex activities that are previously seen in training data, it is not well versed to recognize unseen complex activities without new training samples. To tackle this challenge, we extend Hierarchical Active Transfer Learning (HATL) approach that exploits semantic attribute cluster structure of complex activities shared between seen (source) and unseen (target) activity domains. Our approach employs transfer and active learning to help label target domain unlabeled data by spawning the most effective queries. We evaluated our approach with two real-time smart home systems (IRB #HP-00064387) which corroborates radical improvements in recognizing unseen complex activities.