Asad Masood Khattak

Activity Recognition on Smartphones via Sensor-Fusion and KDA-Based SVMs

Although human activity recognition (HAR) has been studied extensively in the past decade, HAR on smartphones is a relatively new area. Smartphones are equipped with a variety of sensors. Fusing the data of these sensors could enable applications to recognize a large number of activities. Realizing this goal is challenging, however. Firstly, these devices are low on resources, which limits the number of sensors that can be utilized. Secondly, to achieve optimum performance efficient feature extraction, feature selection and classification methods are required. This work implements a smartphone-based HAR scheme in accordance with these requirements. Time domain features are extracted from only three smartphone sensors, and a nonlinear discriminatory approach is employed to recognize 15 activities with a high accuracy. This approach not only selects the most relevant features from each sensor for each activity but it also takes into account the differences resulting from carrying a phone at different positions. Evaluations are performed in both offline and online settings. Our comparison results show that the proposed system outperforms some previous mobile phone-based HAR systems.

Secured WSN-Integrated Cloud Computing for u-Life Care

This paper presents a Secured Wireless Sensor Network-integrated Cloud computing for u-Life Care (SC3). SC3 monitors human health, activities, and shares information among doctors, care-givers, clinics, and pharmacies in the Cloud, so that users can have better care with low cost. SC3 incorporates various technologies with novel ideas including; sensor networks, Cloud computing security, and activities recognition.

Precise tweet classification and sentiment analysis

The rise of social media in couple of years has changed the general perspective of networking, socialization, and personalization. Use of data from social networks for different purposes, such as election prediction, sentimental analysis, marketing, communication, business, and education, is increasing day by day. Precise extraction of valuable information from short text messages posted on social media (Twitter) is a collaborative task. In this paper, we analyze tweets to classify data and sentiments from Twitter more precisely. The information from tweets are extracted using keyword based knowledge extraction. Moreover, the extracted knowledge is further enhanced using domain specific seed based enrichment technique. The proposed methodology facilitates the extraction of keywords, entities, synonyms, and parts of speech from tweets which are then used for tweets classification and sentimental analysis. The proposed system is tested on a collection of 40,000 tweets. The proposed methodology has performed better than the existing system in terms of tweets classification and sentiment analysis. By applying the Knowledge Enhancer and Synonym Binder module on the extracted information we have achieved increase in information gain in a range of 0.1% to 55%. The increase in information gain has enabled our proposed system to better summarize the twitter data for user sentiments regarding a keyword from a particular category.

Change management in evolving web ontologies

Knowledge constantly grows in scientific discourse and is revised over time by different stakeholders, either collaboratively or through institutionalized efforts. The body of knowledge gets structured and refined as the Communities of Practice concerned with a field of knowledge develop a deeper understanding of the issues. As a result, the knowledge model moves from a loosely clustered terminology to a semi-formal or even formal ontology. Change history management in such evolving knowledge models is an important and challenging task. Different techniques have been introduced in the research literature to solve the issue. A comprehensive solution must address various multi-faceted issues, such as ontology recovery, visualization of change effects, and keeping the evolving ontology in a consistent state. More so because the semantics of changes and evolution behavior of the ontology are hard to comprehend. This paper introduces a change history management framework for evolving ontologies; developed over the last couple of years. It is a comprehensive and methodological framework for managing issues related to change management in evolving ontologies, such as versioning, provenance, consistency, recovery, change representation and visualization. The Change history log is central to our framework and is supported by a semantically rich and formally sound change representation scheme known as change history ontology. Changes are captured and then stored in the log in conformance with the change history ontology. The log entries are later used to revert ontology to a previous consistent state, and to visualize the effects of change on ontology during its evolution. The framework is implemented to work as a plug-in for ontology repositories, such as Joseki and ontology editors, such as Protege. The change detection accuracy of the proposed system Change Tracer has been compared with that of Changes Tab, Version Log Generator in Protege; Change Detection, and Change Capturing of NeOn Toolkit. The proposed system has shown better accuracy against the existing systems. A comprehensive evaluation of the methodology was designed to validate the recovery operations. The accuracy of Roll-Back and Roll-Forward algorithms was conducted using different versions of SWETO Ontology, CIDOC CRM Ontology, OMV Ontology, and SWRC Ontology. Experimental results and comparison with other approaches shows that the change management process of the proposed system is accurate, consistent, and comprehensive in its coverage.

An Adaptive Semantic based Mediation System for Data Interoperability among Health Information Systems

Heterogeneity in the management of the complex medical data, obstructs the attainment of data level interoperability among Health Information Systems (HIS). This diversity is dependent on the compliance of HISs with different healthcare standards. Its solution demands a mediation system for the accurate interpretation of data in different heterogeneous formats for achieving data interoperability. We propose an adaptive AdapteRInteroperability ENgine mediation system called ARIEN, that arbitrates between HISs compliant to different healthcare standards for accurate and seamless information exchange to achieve data interoperability. ARIEN stores the semantic mapping information between different standards in the Mediation Bridge Ontology (MBO) using ontology matching techniques. These mappings are provided by our System for Parallel Heterogeneity (SPHeRe) matching system and Personalized-Detailed Clinical Model (P-DCM) approach to guarantee accuracy of mappings. The realization of the effectiveness of the mappings stored in the MBO is evaluation of the accuracy in transformation process among different standard formats. We evaluated our proposed system with the transformation process of medical records between Clinical Document Architecture (CDA) and Virtual Medical Record (vMR) standards. The transformation process achieved over 90 % of accuracy level in conversion process between CDA and vMR standards using pattern oriented approach from the MBO. The proposed mediation system improves the overall communication process between HISs. It provides an accurate and seamless medical information exchange to ensure data interoperability and timely healthcare services to patients.

Privacy-aware searching with oblivious term matching for cloud storage

Encryption ensures confidentiality of the data outsourced to cloud storage services. Searching the encrypted data enables subscribers of a cloud storage service to access only relevant data, by defining trapdoors or evaluating search queries on locally stored indexes. However, these approaches do not consider access privileges while executing search queries. Furthermore, these approaches restrict the searching capability of a subscriber to a limited number of trapdoors defined during data encryption. To address the issue of privacy-aware data search, we propose Oblivious Term Matching (OTM). Unlike existing systems, OTM enables authorized subscribers to define their own search queries comprising of arbitrary number of selection criterion. OTM ensures that cloud service provider obliviously evaluates encrypted search queries without learning any information about the outsourced data. Our performance analysis has demonstrated that search queries comprising of 2 to 14 distinct search criteria cost only 0.03 to 1.09

Towards Smart Homes Using Low Level Sensory Data

per 1000 requests.

Context-aware Human Activity Recognition and decision making

Ubiquitous Life Care (u-Life care) is receiving attention because it provides high quality and low cost care services. To provide spontaneous and robust healthcare services, knowledge of a patient’s real-time daily life activities is required. Context information with real-time daily life activities can help to provide better services and to improve healthcare delivery. The performance and accuracy of existing life care systems is not reliable, even with a limited number of services. This paper presents a Human Activity Recognition Engine (HARE) that monitors human health as well as activities using heterogeneous sensor technology and processes these activities intelligently on a Cloud platform for providing improved care at low cost. We focus on activity recognition using video-based, wearable sensor-based, and location-based activity recognition engines and then use intelligent processing to analyze the context of the activities performed. The experimental results of all the components showed good accuracy against existing techniques. The system is deployed on Cloud for Alzheimer’s disease patients (as a case study) with four activity recognition engines to identify low level activity from the raw data captured by sensors. These are then manipulated using ontology to infer higher level activities and make decisions about a patient’s activity using patient profile information and customized rules.

Short Communication: Time efficient reconciliation of mappings in dynamic web ontologies

Ubiquitous Life Care (u-Life care) nowadays becomes more attractive to computer science researchers due to a demand on a high quality and low cost of care services at anytime and anywhere. Many works exploit sensor networks to monitor patients health status, movements, and real-time daily life activities to provide care services to them. Context information with real-time daily life activities can help in better services, service suggestions, and change in system behavior for better healthcare. Our proposed Secured Wireless Sensor Network - integrated Cloud Computing for ubiquitous - Life Care (SC3) monitors human health as well as activities. In this paper we focus on Human Activity Recognition Engine (HARE) framework architecture, backbone of SC3 and discussed it in detail. Camera-based and sensor-based activity recognition engines are discussed in detail along with the manipulation of recognized activities using Context-aware Activity Manipulation Engine (CAME) and Intelligent Life Style Provider (i-LiSP). Preliminary results of CAME showed robust and accurate response to medical emergencies. We have deployed five different activity recognition engines on Cloud to identify different set of activities of Alzheimers disease patients.

Ontology Evolution: A Survey and Future Challenges

Mappings are established among ontologies for resolving the terminological and conceptual incompatibilities among information networks and information systems. Accommodating new knowledge in domain ontology causes the ontology to change from one consistent state to another. This consequently makes existing mappings among ontologies unreliable and stale due to the changes in resources. Mapping evolution eliminates discrepancies in the existing mappings. The proposed approach offers the benefits of re-establishing mappings among the updated ontologies in less time than is required with existing systems. It only considers the changed resources and eliminates staleness from the mappings. This approach uses the change history to drastically reduce the time required for reconciling mappings among ontologies, as shown in the results.