Papers by Muhammad Asif Razzaq
A Novel Mutual Trust Evaluation Method for Identification of Trusted Devices in Smart Environment
2022 16th International Conference on Ubiquitous Information Management and Communication (IMCOM)
With the technological tsunami, the Internet of Things (IoT) has evolved our life with smart serv... more With the technological tsunami, the Internet of Things (IoT) has evolved our life with smart services such as healthcare, transportation, homes, and industries. Along with these benefits, different security and privacy issues have become a part of our daily life. Researchers from around the world have proposed efficient and reliable solutions to mitigate these challenges. However, limited studies have considered insider threats. In this paper, we have proposed a trust evaluation method, which considered the root cause of trust-relevant attacks such as self-promotion, bad-mouthing, ballot stuffing, and on- off attacks. The proposed approach uses low computation for calculating the trust score. Therefore, it can be deployed on IoT devices, fog nodes, and gateways to ensure mutual trust among the communicating entities.
IEEE Access, 2020
In the era of digital well-being, smart gadgets are the unobtrusive sources of acquiring informat... more In the era of digital well-being, smart gadgets are the unobtrusive sources of acquiring information. A variety of personalized wellness applications support self-quantification based recommendations to provide wellness status for achieving personalized targets. However, these applications are unable to promote the induction of new healthy habits and thus are not too much effective for long term as users tend to loose their interest. Thus, we have proposed a methodology for User-Centric Adaptive Intervention based on behavior change theory for maintaining end-users' interest. The methodology consists of four steps: (1) quantification of behavior based on contributing factors governed by expert-driven rules; (2) behavior-context based mapping for the identification of behavior status of the user; (3) selection of appropriate way of intervention to get fruitful outcomes; and finally (4) feedback based evaluation on the basis of recorded activities and questionnaires for satisfaction. A comprehensive healthy behavior indexbased quantification supports the machine learning-based prediction model for behavior-context mapping. Furthermore, the evaluation is performed through implicit and explicit feedback analysis along with the accuracy of the behavior-context prediction model through multiple scenarios to cover comprehensive situations. The ensemble classifier suggests the accuracy of 98.02% for the behavior-context prediction model, which is higher than the other classifiers. The gain in behavior change is drawn from implicit feedback, which depicts that behavior context-based methods have improved the adaptation in behavior at a steady pace for the long term. The explicit feedback from 99 end-users of wellness application based on the proposed methodology obtained Good and Desired status for widely used System Usability Score and AttrakDiff tools respectively.
Enhanced Quality of Life and Smart Living, 2017
A revolutionized wave of intelligent assistants has emerged in daily life of human over the recen... more A revolutionized wave of intelligent assistants has emerged in daily life of human over the recent years, therefore huge progress has been witnessed for development of healthcare assistants having the capability to communicate with users. However, the conversational complexities demand building more personalized and user-oriented dialogue process systems. To support human-computer dialogue process many models have been proposed. Considering personalization aspect, this research work presents novel Context-aware Dialogue Manager (CADM) model with its foundation based on well-known JDL fusion model. The proposed model addresses modern techniques for multi-turn dialogue process, by identifying dialogue intents, contexts and fusing personalized contexts over them. The model also maintains the dialogue context for progressing complex and multi-turn dialogue. It also helps using intent-context relationship in identifying optimized knowledge source for accurate dialogue expansion and its coherence. CADM functionality is discussed using support of Intelligent Medical Assistant in healthcare domain, which has the speech-based capability to communicate with users.
Context-Based Lifelog Monitoring for Just-in-Time Wellness Intervention
These days adoption of healthy behavior can be quantified through Ubiquitous computing and smart ... more These days adoption of healthy behavior can be quantified through Ubiquitous computing and smart gadgets. This digital technology has revolutionized the self-quantification to monitor activities for improving lifestyle. Context based lifelog monitoring is among the processes of tracking individualās lifestyle in an effective manner. We have proposed a methodology for context-based monitoring of an individualās prolonged sedentary physical activity and unhealthy dietary behavior in the domain of wellness and give just-in-time intervention to adapt healthy behavior. It detects multiple unhealthy activities of its users and verifies the context for intervention generation. The results depict that the average response of the context-based just-in-time interventions is about 75%.
ģ¢
ķ©ģ ģø ģ¬ģ©ģ ģ»Øķ
ģ¤ķø ģøģ§ ė° ģ¶ė” ģģ¤ķ
źµ¬ķ
An ontology-based hybrid approach for accurate context reasoning
2017 19th Asia-Pacific Network Operations and Management Symposium (APNOMS), 2017
The combination of ontology based context-awareness and machine learning context classification i... more The combination of ontology based context-awareness and machine learning context classification is an interesting research area. The determined contexts are obtained using semantic reasoning based on context ontology developed by expert using domain specific rules. This reasoning suffer challenges of soundness and completeness in real-time deployment. This paper addresses the aforementioned challenges from semantic reasoning by embracing machine learning modeling and classification benefits. Machine learning relies on data, for this we developed training and deployment phase for ontological ABox assertions. Approximately 99.99% precision through machine learning approach was achieved over 91.5% accuracy with semantic reasoning. The statistical evaluation proves the improvement in terms of accuracy for context prediction and overall performance.
A Semantic Reasoning Model for Fortifying Decisions in Smart CDSS
The emergence of smartness in many domains for facilitating the life has boomed in recent years, ... more The emergence of smartness in many domains for facilitating the life has boomed in recent years, one of prominent area is Healthcare. Many of the developed applications for healthcare, use diagnosis/recommendation mechanism for facilitating physicians and patients. We propose a novel approach that reinforces physician diagnosis, guidelines and recommendation by Semantic knowledge inferencing. Upon receiving any diagnosis/recommendation our model unveils hidden knowledge through reasoning over Domain Specific Clinical Model DSCM thus enhancing authenticity of clinical decisions. This approach provides first-time ever combination of rule-based reasoning, automatic reasoner selection and updation of DSCMs. The clinical domain consists of heterogeneous DSCMs also termed as Ontologies.
MMOU-AR: Multimodal Obtrusive and Unobtrusive Activity Recognition Through Supervised Ontology-Based Reasoning
The aging population, prevalence of chronic diseases, and outbreaks of infectious diseases are so... more The aging population, prevalence of chronic diseases, and outbreaks of infectious diseases are some of the major healthcare challenges. To address these unmet healthcare challenges, monitoring and Activity Recognition (AR) are considered as a subtask in pervasive computing and context-aware systems. Innumerable interdisciplinary applications exist, underpinning the obtrusive sensory data using the revolutionary digital technologies for the acquisition, transformation, and fusion of recognized activities. However, little importance is given by the research community to make the use of non-wearables i.e. unobtrusive sensing technologies. The physical state of human pervasively in daily living for AR can be seamlessly presented by acquiring health-related information by using unobtrusive sensing technologies to enable long-term health monitoring without violating an individualās privacy. This paper aims to propose and provide supervised recognition of Activities of Daily Livings (ADLs)...
Applied Sciences, 2020
Virtual assistants are involved in the daily activities of humans such as managing calendars, mak... more Virtual assistants are involved in the daily activities of humans such as managing calendars, making appointments, and providing wake-up calls. They provide a conversational service to customers around-the-clock and make their daily life manageable. With this emerging trend, many well-known companies launched their own virtual assistants that manage the daily routine activities of customers. In the healthcare sector, virtual medical assistants also provide a list of relevant diseases linked to a specific symptom. Due to low accuracy and uncertainty, these generated recommendations are untrusted and may lead to hypochondriasis. In this study, we proposed a Medical Instructed Real-time Assistant (MIRA) that listens to the userās chief complaint and predicts a specific disease. Instead of informing about the medical condition, the user is referred to a nearby appropriate medical specialist. We designed an architecture for MIRA that considers the limitations of existing virtual medical ...
Multimedia Systems, 2020
Human activity recognition (HAR) is an important branch of human-centered research. Advances in w... more Human activity recognition (HAR) is an important branch of human-centered research. Advances in wearable and unobtrusive technologies offer many opportunities for HAR. While much progress has been made in HAR using wearable technology, it still remains a challenging task using unobtrusive (non-wearable) sensors. This paper investigates detection and tracking of multi-occupant HAR in a smart-home environment, using a novel low-resolution Thermal Vision Sensor (TVS). Specifically, the research presents the development and implementation of a two-step framework, consisting of a Computer Vision (CV) based method to detect and track multiple occupants combined with Convolutional Neural Network (CNN) based HAR. The proposed algorithm uses frame-difference over consecutive frames for occupant detection, a set of morphological operations to refine identified objects, and features are extracted before applying a Kalman filter for tracking. Laterally, a 19-layer CNN architecture is used for HAR and afterward the results from both methods are fused using time interval based sliding window. This approach is evaluated through a series of experiments based on benchmark Thermal Infrared datasets (VOT-TIR2016) and multi-occupant data collected from TVS. Results demonstrate that the proposed framework is capable of detecting and tracking 88.46% of multi
Computing, 2020
The proliferation of semantic big data has resulted in a large amount of content published over t... more The proliferation of semantic big data has resulted in a large amount of content published over the Linked Open Data (LOD) cloud. Semantic Web applications consume these data by issuing SPARQL queries. One of the main challenges faced by querying the LOD web cloud on account of the inherent distributed nature of LOD is its high search latency and lack of tools to connect the SPARQL endpoints. In this paper, we propose an Adaptive Cache Replacement strategy (ACR) that aims to accelerate the overall query processing of the LOD cloud. ACR alleviates the burden on SPARQL endpoints by identifying subsequent queries learned from clients historical query patterns and caching the result of these queries. For cache replacement, we propose an exponential smoothing forecasting method to replace the less valuable cache content. In the experimental study, we evaluate the performance of the proposed approach in terms of hit rates, query time and overhead. The proposed approach is found to outperform existing state-of-the-art approaches, increase hit rates by 5.46%, and reduce the query times by 6.34%.
Sensors, 2020
The recognition of activities of daily living (ADL) in smart environments is a well-known and an ... more The recognition of activities of daily living (ADL) in smart environments is a well-known and an important research area, which presents the real-time state of humans in pervasive computing. The process of recognizing human activities generally involves deploying a set of obtrusive and unobtrusive sensors, pre-processing the raw data, and building classification models using machine learning (ML) algorithms. Integrating data from multiple sensors is a challenging task due to dynamic nature of data sources. This is further complicated due to semantic and syntactic differences in these data sources. These differences become even more complex if the data generated is imperfect, which ultimately has a direct impact on its usefulness in yielding an accurate classifier. In this study, we propose a semantic imputation framework to improve the quality of sensor data using ontology-based semantic similarity learning. This is achieved by identifying semantic correlations among sensor events t...
International Journal of Medical Informatics, 2020
This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
Proceedings, 2018
Activity recognition (AR) is a subtask in pervasive computing and context-aware systems, which pr... more Activity recognition (AR) is a subtask in pervasive computing and context-aware systems, which presents the physical state of human in real-time. These systems offer a new dimension to the widely spread applications by fusing recognized activities obtained from the raw sensory data generated by the obtrusive as well as unobtrusive revolutionary digital technologies. In recent years, an exponential growth has been observed for AR technologies and much literature exists focusing on applying machine learning algorithms on obtrusive single modality sensor devices. However, University of JaƩn Ambient Intelligence (UJAmI), a Smart Lab in Spain has initiated a 1st UCAmI Cup challenge by sharing aforementioned varieties of the sensory data in order to recognize the human activities in the smart environment. This paper presents the fusion, both at the feature level and decision level for multimodal sensors by preprocessing and predicting the activities within the context of training and test...
International journal of medical informatics, 2018
Medical students should be able to actively apply clinical reasoning skills to further their inte... more Medical students should be able to actively apply clinical reasoning skills to further their interpretative, diagnostic, and treatment skills in a non-obtrusive and scalable way. Case-Based Learning (CBL) approach has been receiving attention in medical education as it is a student-centered teaching methodology that exposes students to real-world scenarios that need to be solved using their reasoning skills and existing theoretical knowledge. In this paper, we propose an interactive CBL System, called iCBLS, which supports the development of collaborative clinical reasoning skills for medical students in an online environment. The iCBLS consists of three modules: (i) system administration (SA), (ii) clinical case creation (CCC) with an innovative semi-automatic approach, and (iii) case formulation (CF) through intervention of medical students' and teachers' knowledge. Two evaluations under the umbrella of the context/input/process/product (CIPP) model have been performed wit...
Sensors (Basel, Switzerland), Jan 24, 2017
The emerging research on automatic identification of user's contexts from the cross-domain en... more The emerging research on automatic identification of user's contexts from the cross-domain environment in ubiquitous and pervasive computing systems has proved to be successful. Monitoring the diversified user's contexts and behaviors can help in controlling lifestyle associated to chronic diseases using context-aware applications. However, availability of cross-domain heterogeneous contexts provides a challenging opportunity for their fusion to obtain abstract information for further analysis. This work demonstrates extension of our previous work from a single domain (i.e., physical activity) to multiple domains (physical activity, nutrition and clinical) for context-awareness. We propose multi-level Context-aware Framework (mlCAF), which fuses the multi-level cross-domain contexts in order to arbitrate richer behavioral contexts. This work explicitly focuses on key challenges linked to multi-level context modeling, reasoning and fusioning based on the mlCAF open-source ont...
Digital Communications and Networks, 2017
Case-Based Learning (CBL) has become an effective pedagogy for student-centered learning in medic... more Case-Based Learning (CBL) has become an effective pedagogy for student-centered learning in medical education, which is founded on persistent patient cases. Flippped learning and Internet of Things (IoTs) concepts have gained significant attention in recent years. Using these concepts in conjunction with CBL can improve learning ability by providing real evolutionary medical cases. It also enables students to build confidence in their decision making, and efficiently enhances teamwork in the learning environment. We propose an IoT-based Flip Learning Platform, called IoTFLiP, where an IoT infrastructure is exploited to support flipped case-based learning in a cloud environment with state of the art security and privacy measures for personalized medical data. It also provides support for application delivery in private, public, and hybrid approaches. The proposed platform is an extension of our Interactive Case-Based Flipped Learning Tool (ICBFLT), which has been developed based on current CBL practices. ICBFLT formulates summaries of CBL cases through synergy between students' and medical expert knowledge. The low cost and reduced size of sensor device, support of IoTs, and recent flipped learning advancements can enhance medical students' academic and practical experiences. In order to demonstrate a working scenario for the proposed IoTFLiP platform, real-time data from IoTs gadgets is collected to generate a real-world case for a medical student using ICBFLT.
Sensors (Basel, Switzerland), Jan 29, 2016
Recent years have witnessed a huge progress in the automatic identification of individual primiti... more Recent years have witnessed a huge progress in the automatic identification of individual primitives of human behavior, such as activities or locations. However, the complex nature of human behavior demands more abstract contextual information for its analysis. This work presents an ontology-based method that combines low-level primitives of behavior, namely activity, locations and emotions, unprecedented to date, to intelligently derive more meaningful high-level context information. The paper contributes with a new open ontology describing both low-level and high-level context information, as well as their relationships. Furthermore, a framework building on the developed ontology and reasoning models is presented and evaluated. The proposed method proves to be robust while identifying high-level contexts even in the event of erroneously-detected low-level contexts. Despite reasonable inference times being obtained for a relevant set of users and instances, additional work is requi...
Sensors (Basel, Switzerland), Jan 10, 2016
There is sufficient evidence proving the impact that negative lifestyle choices have on people... more There is sufficient evidence proving the impact that negative lifestyle choices have on people's health and wellness. Changing unhealthy behaviours requires raising people's self-awareness and also providing healthcare experts with a thorough and continuous description of the user's conduct. Several monitoring techniques have been proposed in the past to track users' behaviour; however, these approaches are either subjective and prone to misreporting, such as questionnaires, or only focus on a specific component of context, such as activity counters. This work presents an innovative multimodal context mining framework to inspect and infer human behaviour in a more holistic fashion. The proposed approach extends beyond the state-of-the-art, since it not only explores a sole type of context, but also combines diverse levels of context in an integral manner. Namely, low-level contexts, including activities, emotions and locations, are identified from heterogeneous senso...
UCAmI 2018, 2018
In this work, we detail a methodology based on Convolutional Neural Networks (CNNs) to detect fal... more In this work, we detail a methodology based on Convolutional Neural Networks (CNNs) to detect falls from non-invasive thermal vision sensors. First, we include an agile data collection to label images in order to create a dataset that describes several cases of single and multiple occupancy. These cases include standing inhabitants and target situations with a fallen inhabitant. Second, we provide data augmentation techniques to increase the learning capabilities of the classification and reduce the configuration time. Third, we have defined 3 types of CNN to evaluate the impact that the number of layers and kernel size have on the performance of the methodology. The results show an encouraging performance in single-occupancy contexts, with up to 92 % of accuracy, but a 10 % of reduction in accuracy in multiple-occupancy. The learning capabilities of CNNs have been highlighted due to the complex images obtained from the low-cost device. These images have strong noise as well as unce...
Uploads
Papers by Muhammad Asif Razzaq