Muhammad Habib ur Rehman

Big data reduction framework for value creation in sustainable enterprises

Value creation is a major sustainability factor for enterprises, in addition to profit maximization and revenue generation. Modern enterprises collect big data from various inbound and outbound data sources. The inbound data sources handle data generated from the results of business operations, such as manufacturing, supply chain management, marketing, and human resource management, among others. Outbound data sources handle customer-generated data which are acquired directly or indirectly from customers, market analysis, surveys, product reviews, and transactional histories. However, cloud service utilization costs increase because of big data analytics and value creation activities for enterprises and customers. This article presents a novel concept of big data reduction at the customer end in which early data reduction operations are performed to achieve multiple objectives, such as (a) lowering the service utilization cost, (b) enhancing the trust between customers and enterprises, (c) preserving privacy of customers, (d) enabling secure data sharing, and (e) delegating data sharing control to customers. We also propose a framework for early data reduction at customer end and present a business model for end-to-end data reduction in enterprise applications. The article further presents a business model canvas and maps the future application areas with its nine components. Finally, the article discusses the technology adoption challenges for value creation through big data reduction in enterprise applications.

Mining personal data using smartphones and wearable devices: a survey.

The staggering growth in smartphone and wearable device use has led to a massive scale generation of personal (user-specific) data. To explore, analyze, and extract useful information and knowledge from the deluge of personal data, one has to leverage these devices as the data-mining platforms in ubiquitous, pervasive, and big data environments. This study presents the personal ecosystem where all computational resources, communication facilities, storage and knowledge management systems are available in user proximity. An extensive review on recent literature has been conducted and a detailed taxonomy is presented. The performance evaluation metrics and their empirical evidences are sorted out in this paper. Finally, we have highlighted some future research directions and potentially emerging application areas for personal data mining using smartphones and wearable devices.

Toward secure group communication in wireless mobile environments

Group communication has been increasingly used as an efficient communication mechanism for facilitating emerging applications that require packet delivery from one or many sources to multiple recipients. Due to insecure communication channel, group key management which is a fundamental building block for securing group communication, has received special attention recently. Developing group key management in highly dynamic environments particularly in wireless mobile networks due to their inherent characteristics faces additional challenges. On one hand, the constraint of wireless devices in terms of resources scarcity, and on the other hand the mobility of group members increase the complexity of designing a group key management scheme. The article illustrates a survey of existing group key management schemes that specifically consider the host mobility issue in secure group communication in wireless mobile environments. The primary constraints and challenges introduced by wireless mobile environments are identified in order to show their critical influence in designing a secure group communication. The investigated schemes are then compared and analyzed against some pertinent criteria. Finally, the remaining challenges that should be tackled are outlined, and future research directions are also discussed. Categorizing group key management schemes in different design approaches.Pros and cons of different group key management approachs.Design constraints of secure group communications in wireless mobile environments.Review of existing group key management schemes in wireless mobile environments.Future challenges in developing secure group communications.

Big Data Reduction Methods: A Survey

Abstract Research on big data analytics is entering in the new phase called fast data where multiple gigabytes of data arrive in the big data systems every second. Modern big data systems collect inherently complex data streams due to the volume, velocity, value, variety, variability, and veracity in the acquired data and consequently give rise to the 6Vs of big data. The reduced and relevant data streams are perceived to be more useful than collecting raw, redundant, inconsistent, and noisy data. Another perspective for big data reduction is that the million variables big datasets cause the curse of dimensionality which requires unbounded computational resources to uncover actionable knowledge patterns. This article presents a review of methods that are used for big data reduction. It also presents a detailed taxonomic discussion of big data reduction methods including the network theory, big data compression, dimension reduction, redundancy elimination, data mining, and machine learning methods. In addition, the open research issues pertinent to the big data reduction are also highlighted.

Towards native code offloading based MCC frameworks for multimedia applications

A number of resource-intensive applications, such as augmented reality, natural language processing, object recognition, and multimedia-based software are pushing the computational and energy boundaries of smartphones. Cloud-based services augment the resource-scare capabilities of smartphones while offloading compute-intensive methods to resource-rich cloud servers. The amalgam of cloud and mobile computing technologies has ushered the rise of Mobile Cloud Computing (MCC) paradigm which envisions operating smartphones and modern mobile devices beyond their intrinsic capabilities. System virtualization, application virtualization, and dynamic binary translation (DBT) techniques are required to address the heterogeneity of smartphone and cloud architectures. However, most of the current research work has only focused on the offloading of virtualized applications while giving limited consideration to native code offloading. Moreover, researchers have not attended to the requirements of multimedia based applications in MCC offloading frameworks. In this study, we present a survey and taxonomy of state-of-the-art MCC frameworks, DBT techniques for native offloading, and cross-platform execution techniques for multimedia based applications. We survey the MCC frameworks from the perspective of offload enabling techniques. We focus on native code offloading frameworks and analyze the DBT and emulation techniques of smartphones (ARM) on a cloud server (x86) architectures. Furthermore, we debate the open research issues and challenges to native offloading of multimedia based smartphone applications. We deliberate on DBT techniques for cross-platform heterogeneous smartphone and cloud architectures. DBT and emulation techniques are an essential part of native code based MCC offloading frameworks.We discuss techniques of cross-platform SIMD instruction translation and porting for multimedia based MCC applications.We provide a detailed taxonomy and parametric comparison of all the state-of-the-art studies discussed in the aforementioned directions.We identify research issues in current MCC offloading techniques, DBT optimization for process code migration based MCC offloading, and DBT optimizations for translation of SIMD instructions

Quantification of Climate Warming and Crop Management Impacts on Cotton Phenology

Understanding the impact of the warming trend on phenological stages and phases of cotton (Gossypium hirsutum L.) in central and lower Punjab, Pakistan, may assist in optimizing crop management practices to enhance production. This study determined the influence of the thermal trend on cotton phenology from 1980–2015 in 15 selected locations. The results demonstrated that observed phenological stages including sowing (S), emergence (E), anthesis (A) and physiological maturity (M) occurred earlier by, on average, 5.35, 5.08, 2.87 and 1.12 days decade−1, respectively. Phenological phases, sowing anthesis (S-A), anthesis to maturity (A-M) and sowing to maturity (S-M) were reduced by, on average, 2.45, 1.76 and 4.23 days decade−1, respectively. Observed sowing, emergence, anthesis and maturity were negatively correlated with air temperature by, on average, −2.03, −1.93, −1.09 and −0.42 days °C−1, respectively. Observed sowing-anthesis, anthesis to maturity and sowing-maturity were also negatively correlated with temperature by, on average, −0.94, −0.67 and −1.61 days °C−1, respectively. Applying the cropping system model CSM-CROPGRO-Cotton model using a standard variety in all locations indicated that the model-predicted phenology accelerated more due to warming trends than field-observed phenology. However, 30.21% of the harmful influence of the thermal trend was compensated as a result of introducing new cotton cultivars with higher growing degree day (thermal time) requirements. Therefore, new cotton cultivars which have higher thermal times and are high temperature tolerant should be evolved.

UniMiner: Towards a unified framework for data mining

Wearable devices and Smartphones generate huge data streams in pervasive and ubiquitous environments. Traditionally, big data systems collect all the data at a central data processing system (DPS). These data silos are further analyzed to generate approximated patterns for different application areas. This approach has one-sided utility (i.e. at big data processing end) but two main side-effects that lead towards users dissatisfaction and extra computational costs. These effects are: (1) since all the data is being collected at central DPS, user privacy is compromised and (2) the collection of huge raw data streams, most of which could be irrelevant, at central systems needs more computational and storage resources hence increases the overall operational cost. Keeping in view these limitations, we are proposing a unified framework that balances between utility and cost of big data system with increased user satisfaction. We studied different data mining systems and proposed a new framework, named as UniMiner, to leverage data mining systems with wearable devices, smartphones, and cloud computing technologies. The gist of UniMiner is the scalability of data mining tasks from resource-constraint devices to collaborative and hybrid execution models. This scalable unified data mining approach distinguishes UniMiner from existing systems by enabling maximum data processing near data sources. Finally, we assessed the feasibility of mobile devices using six frequent pattern mining algorithms. The results show that mobile devices could be adopted as data mining platforms by tuning some additional parameters.

Frequent pattern mining in mobile devices: A feasibility study

The availability of computational power in mobile devices is key-enabler for Mobile Data Mining (MDM) at user-premises. Alternately, resource-constraints like limited energy, narrow bandwidth, and small screens challenge in adoption of MDM. Currently, MDM is based on light-weight algorithms that are adaptive in resource-constrained environments but a study to evaluate the performance of general algorithms still lacks in the literature. To this end, we have studied six Frequent Pattern Mining (FPM) algorithms and deployed them in mobile devices to evaluate the feasibility and highlighted the associated challenges. The experiments were performed on real and synthetic data sets strictly in android-based mobile device and compared with PC-based setup. The experimental results show that FPM algorithms can leverage MDM after tuning some basic parameters.

Towards next-generation heterogeneous mobile data stream mining applications: Opportunities, challenges, and future research directions

Abstract The convergence of Internet of Things (IoTs), mobile computing, cloud computing, edge computing and big data has brought a paradigm shift in computing technologies. New computing systems, application models, and application areas are emerging to handle the massive growth of streaming data in mobile environments such as smartphones, IoTs, body sensor networks, and wearable devices, to name a few. However, the challenge arises about how and where to process the data streams in order to perform analytic operations and uncover useful knowledge patterns. The mobile data stream mining (MDSM) applications involve a number of operations for, 1) data acquisition from heterogeneous data sources, 2) data preprocessing, 3) data fusion, 4) data mining, and 5) knowledge management. This article presents a thorough review of execution platforms for MDSM applications. In addition, a detailed taxonomic discussion of heterogeneous MDSM applications is presented. Moreover, the article presents detailed literature review of methods that are used to handle heterogeneity at application and platform levels. Finally, the gap analysis is articulated and future research directions are presented to develop next-generation MDSM applications.

Opportunistic Computation Offloading in Mobile Edge Cloud Computing Environments

The dynamic mobility and limitations in computational power, battery resources, and memory availability are main bottlenecks in fully harnessing mobile devices as data mining platforms. Therefore, the mobile devices are augmented with cloud resources in mobile edge cloud computing (MECC) environments to seamlessly execute data mining tasks. The MECC infrastructures provide compute, network, and storage services in one-hop wireless distance from mobile devices to minimize the latency in communication as well as provide localized computations to reduce the burden on federated cloud systems. However, when and how to offload the computation is a hard problem. In this paper, we present an opportunistic computation offloading scheme to efficiently execute data mining tasks in MECC environments. The scheme provides the suitable execution mode after analyzing the amount of unprocessed data, privacy configurations, contextual information, and available on-board local resources (memory, CPU, and battery power). We develop a mobile application for online activity recognition and evaluate the proposed scheme using the event data stream of 5 million activities collected from 12 users for 15 days. The experiments show significant improvement in execution time and battery power consumption resulting in 98% data reduction.