Semantic interoperability for big-data in heterogeneous IoT infrastructure for healthcare

Ullah, Farhan,Habib, Muhammad Asif,Farhan, Muhammad,Khalid, Shehzad,Durrani, Mehr Yahya,Jabbar, Sohail Elsevier 2017 Sustainable cities and society Vol.34 No.-

<P><B>Abstract</B></P> <P>Interoperability remains a major burden to the developers of Internet of Things systems. It is due to IoT devices are extremely heterogeneous regarding basic communication protocols, data formats, and technologies. Furthermore, due to the absence of worldwide satisfactory standards, Interoperability tools remains imperfect. In this paper, we have proposed Semantic Interoperability Model for Big-data in IoT (SIMB-IoT) to deliver semantic interoperability among heterogeneous IoT devices in health care domain. This model is used to recommend medicine with side effects for different symptoms collected from heterogeneous IoT sensors. Two datasets are taken for the analysis of big-data. One dataset contains diseases with drug details and the second dataset contains medicines with side effects. Information between physician and patient are semantically annotated and transferred in a meaningful way. A Lightweight Model for Semantic annotation of Big-data using heterogeneous devices in IoT is proposed to provide annotations for big data. Resource Description Framework (RDF) is a semantic web framework that is recycled to communicate things using Triples to make it semantically significant. RDF annotated patients’ data and made it semantically interoperable. SPARQL query is used to extract records from RDF graph. Tableau, Gruff-6.2.0, and Mysql tools are used in simulation in this article.</P> <P><B>Highlights</B></P> <P> <UL> <LI> A Lightweight SIMB-IoT model is proposed for heterogeneous IoT devices for semantic interoperability in healthcare domain. </LI> <LI> Intelligent health cloud recommends drugs and their side effects against the input of different diseases’ symptoms. </LI> <LI> Semantic data analytics is used to expose hidden patterns from a large volume of the big dataset. </LI> <LI> SPARQL is used to interact with the document, indexed by MedDRA repository’s keywords. </LI> </UL> </P>

CDASA-CSMA/CA: Contention Differentiated Adaptive Slot Allocation CSMA-CA for Heterogeneous Data in Wireless Body Area Networks

( Fasee Ullah ),( Abdul Hanan Abdullah ),( Gaddafi Abdul-Salaam ),( Marina Md Arshad ),( Farhan Masud ) 한국인터넷정보학회 2017 KSII Transactions on Internet and Information Syst Vol.11 No.12

The implementation of IEEE 802.15.6 in Wireless Body Area Network (WBAN) is contention based. Meanwhile, IEEE 802.15.4 MAC provides limited 16 channels in the Superframe structure, making it unfit for N heterogeneous nature of patient’s data. Also, the Beacon-enabled Carrier-Sense Multiple Access/Collision-Avoidance (CSMA/CA) scheduling access scheme in WBAN, allocates Contention-free Period (CAP) channels to emergency and non-emergency Biomedical Sensors (BMSs) using contention mechanism, increasing repetition in rounds. This reduces performance of the MAC protocol causing higher data collisions and delay, low data reliability, BMSs packet retransmissions and increased energy consumption. Moreover, it has no traffic differentiation method. This paper proposes a Low-delay Traffic-Aware Medium Access Control (LTA-MAC) protocol to provide sufficient channels with a higher bandwidth, and allocates them individually to non-emergency and emergency data. Also, a Contention Differentiated Adaptive Slot Allocation CSMA-CA (CDASA-CSMA/CA) for scheduling access scheme is proposed to reduce repetition in rounds, and assists in channels allocation to BMSs. Furthermore, an On-demand (OD) slot in the LTA-MAC to resolve the patient’s data drops in the CSMA/CA scheme due to exceeding of threshold values in contentions is introduced. Simulation results demonstrate advantages of the proposed schemes over the IEEE 802.15.4 MAC and CSMA/CA scheme in terms of success rate, packet delivery delay, and energy consumption.

Semantic Interoperability in Heterogeneous IoT Infrastructure for Healthcare

Jabbar, Sohail,Ullah, Farhan,Khalid, Shehzad,Khan, Murad,Han, Kijun WILEY INTERSCIENCE 2017 WIRELESS COMMUNICATIONS AND MOBILE COMPUTING Vol.2017 No.-

<P>Interoperability remains a significant burden to the developers of Internet of Things’ Systems. This is due to the fact that the IoT devices are highly heterogeneous in terms of underlying communication protocols, data formats, and technologies. Secondly due to lack of worldwide acceptable standards, interoperability tools remain limited. In this paper, we proposed an IoT based Semantic Interoperability Model (IoT-SIM) to provide Semantic Interoperability among heterogeneous IoT devices in healthcare domain. Physicians communicate their patients with heterogeneous IoT devices to monitor their current health status. Information between physician and patient is semantically annotated and communicated in a meaningful way. A lightweight model for semantic annotation of data using heterogeneous devices in IoT is proposed to provide annotations for data. Resource Description Framework (RDF) is a semantic web framework that is used to relate things using triples to make it semantically meaningful. RDF annotated patients’ data has made it semantically interoperable. SPARQL query is used to extract records from RDF graph. For simulation of system, we used Tableau, Gruff-6.2.0, and Mysql tools.</P>

A Cross-Platform Malware Variant Classification based on Image Representation

( Hamad Naeem ),( Bing Guo ),( Farhan Ullah ),( Muhammad Rashid Naeem ) 한국인터넷정보학회 2019 KSII Transactions on Internet and Information Syst Vol.13 No.7

Recent internet development is helping malware researchers to generate malicious code variants through automated tools. Due to this reason, the number of malicious variants is increasing day by day. Consequently, the performance improvement in malware analysis is the critical requirement to stop the rapid expansion of malware. The existing research proved that the similarities among malware variants could be used for detection and family classification. In this paper, a Cross-Platform Malware Variant Classification System (CP-MVCS) proposed that converted malware binary into a grayscale image. Further, malicious features extracted from the grayscale image through Combined SIFT-GIST Malware (CSGM) description. Later, these features used to identify the relevant family of malware variant. CP-MVCS reduced computational time and improved classification accuracy by using CSGM feature description along machine learning classification. The experiment performed on four publically available datasets of Windows OS and Android OS. The experimental results showed that the computation time and malware classification accuracy of CP-MVCS was higher than traditional methods. The evaluation also showed that CP-MVCS was not only differentiated families of malware variants but also identified both malware and benign samples in mix fashion efficiently.

An Adaptive Control of Smart Appliances with Peak Shaving Considering EV Penetration

Zunaib Maqsood Haider,Farhan H. Malik,M. Kashif Rafique,Soon-Jeong Lee(이순정),Jun-Hyeok Kim(김준혁),Khawaja Khalid Mehmood,Saad Ullah Khan,Chul-Hwan Kim(김철환) 대한전기학회 2016 전기학회논문지 Vol.65 No.5

Electric utilities may face new threats with increase in electric vehicles (EVs) in the personal automobile market. The peak demand will increase which may stress the distribution network equipment. The focus of this paper is on an adaptive control of smart household appliances by using an intelligent load management system (ILMS). The main objectives are to accomplish consumer needs and prevent overloading of power grid. The stress from the network is released by limiting the peak demand of a house when it exceeds a certain point. In the proposed strategy, for each smart appliance, the customers will set its order/rank according to their own preferences and then system will control the household loads intelligently for consumer reliability. The load order can be changed at any time by the customer. The difference between the set and actual value for each load’s specific parameter will help the utility to estimate the acceptance of this intelligent load management system by the customers.

A New Hybrid Approach of Clustering Based Probabilistic Decision Tree to Forecast Wind Power on Large Scales

He Chuan,Mansoor Khan,Liu Tianqi,Ullah Farhan 대한전기학회 2021 Journal of Electrical Engineering & Technology Vol.16 No.2

The wind power forecasting plays a vital role in renewable energy production. Due to the dynamic and uncertain behavior of wind, it is really hard to catch the actual features of wind for accurate forecasting measures. The patchy and instability of wind leading to the assortment of training samples have a main infl uence on the forecasting accuracy. For this purpose, an accurate forecasting method is needed. This paper proposed a new hybrid approach of clustering based probabilistic decision tree to forecast wind power effi ciently. The collected data is screened for noisy information and selected those variables which mainly contribute in accurate predictions. Then, the wind data is normalized using mean and standard deviation to extract playing level fi elds for each feature. Based on the similarity of the data behavior, the K-means clustering algorithm is applied to classify the samples into diff erent groups which contain the historical wind data. Further, the Naïve Bayes (NB) tree is proposed to extract probabilities for each feature in the clusters. The NB tree is a hybrid model of C4.5 and NB methods that successfully applied on three big real-world wind datasets (hourly, monthly, yearly) collected from National Renewable Energy Laboratory (NREL). The forecasting accuracy exposed that the proposed method could forecast an accurate wind power from hours to years’ data. Comprehensive comparisons are made of the proposed method with the most popular state of the art techniques which show that this method provides more accurate prediction results.

Multi-aging Effects on Vegetable Based Oils for Transformer Insulation in HV Systems

Khan Irfanullah,Abid Muhammad Ahtasham,Ullah Kaleem,Ullah Zahid,Haider Aun,Ahmad Farhan Ammar,Zia Zain,Ali Sahibzada Muhammad 대한전기학회 2021 Journal of Electrical Engineering & Technology Vol.16 No.5

Liquid insulation media is used for insulation and cooling purpose inside the transformer. Currently, transformers are using petroleum based mineral oil, which poses a serious hazardous environmental impact, since the mineral oil is non-renewable and non-biodegradable. Although, the increased cost and depleting nature of mineral oil cause an emergent need to use suitable alternatives to mineral oils that are biodegradable and environmentally friendly. In response to this resource issue, various vegetable oils, namely Sunfl ower oil, Soya bean oil, and a blend of Sunfl ower and Olive (BSO) oil are suitable alternatives for transformer insulation in high voltage systems. The afore-mentioned vegetable oils are subjected to multi-aging and comparative analysis is performed with mineral oil. Further, the dielectric and thermal properties of vegetable oils are tested before and after aging. Fourier Transform Infrared spectroscopy, water content, breakdown voltage, viscosity, fl ash point, tan delta, and pour point tests are performed on vegetable oils before and after aging. Finally, a comparative analysis of vegetable oils with mineral oil is provided to prove the effi cacy of the proposed vegetable oils. The BSO oil resulted in higher breakdown strength and good thermal behavior when subjected to the abovementioned various diagnostic measurement tests in comparison to other oils

A Hybrid Proposed Framework for Object Detection and Classification

Aamir, Muhammad,Pu, Yi-Fei,Rahman, Ziaur,Abro, Waheed Ahmed,Naeem, Hamad,Ullah, Farhan,Badr, Aymen Mudheher Korea Information Processing Society 2018 Journal of information processing systems Vol.14 No.5

The object classification using the images' contents is a big challenge in computer vision. The superpixels' information can be used to detect and classify objects in an image based on locations. In this paper, we proposed a methodology to detect and classify the image's pixels' locations using enhanced bag of words (BOW). It calculates the initial positions of each segment of an image using superpixels and then ranks it according to the region score. Further, this information is used to extract local and global features using a hybrid approach of Scale Invariant Feature Transform (SIFT) and GIST, respectively. To enhance the classification accuracy, the feature fusion technique is applied to combine local and global features vectors through weight parameter. The support vector machine classifier is a supervised algorithm is used for classification in order to analyze the proposed methodology. The Pascal Visual Object Classes Challenge 2007 (VOC2007) dataset is used in the experiment to test the results. The proposed approach gave the results in high-quality class for independent objects' locations with a mean average best overlap (MABO) of 0.833 at 1,500 locations resulting in a better detection rate. The results are compared with previous approaches and it is proved that it gave the better classification results for the non-rigid classes.

A Hybrid Proposed Framework for Object Detection and Classification

( Muhammad Aamir ),( Yi-fei Pu ),( Ziaur Rahman ),( Waheed Ahmed Abro ),( Hamad Naeem ),( Farhan Ullah ),( Aymen Mudheher Badr ) 한국정보처리학회 2018 Journal of information processing systems Vol.14 No.5

The object classification using the images’ contents is a big challenge in computer vision. The superpixels’ information can be used to detect and classify objects in an image based on locations. In this paper, we proposed a methodology to detect and classify the image's pixels' locations using enhanced bag of words (BOW). It calculates the initial positions of each segment of an image using superpixels and then ranks it according to the region score. Further, this information is used to extract local and global features using a hybrid approach of Scale Invariant Feature Transform (SIFT) and GIST, respectively. To enhance the classification accuracy, the feature fusion technique is applied to combine local and global features vectors through weight parameter. The support vector machine classifier is a supervised algorithm is used for classification in order to analyze the proposed methodology. The Pascal Visual Object Classes Challenge 2007 (VOC2007) dataset is used in the experiment to test the results. The proposed approach gave the results in high-quality class for independent objects’ locations with a mean average best overlap (MABO) of 0.833 at 1,500 locations resulting in a better detection rate. The results are compared with previous approaches and it is proved that it gave the better classification results for the non-rigid classes.