Internet of Things and Big Data as enablers for business digitalization strategies

Task scheduling in cloud computing can directly affect the resource usage and operational cost of a system. To improve the efficiency of task executions in a cloud, various metaheuristic algorithms, as well as their variations, have been proposed to optimize the scheduling. In this article, for the first time, we apply the latest metaheuristics whale optimization algorithm (WOA) for cloud task scheduling with a multiobjective optimization model, aiming at improving the performance of a cloud system with given computing resources. On that basis, we propose an advanced approach called I mproved W OA for C loud task scheduling (IWC) to further improve the optimal solution search capability of the WOA-based method. We present the detailed implementation of IWC and our simulation-based experiments show that the proposed IWC has better convergence speed and accuracy in searching for the optimal task scheduling plans, compared to the current metaheuristic algorithms. Moreover, it can also achieve better performance on system resource utilization, in the presence of both small and large-scale tasks.

/pdf/a-woa-based-optimization-approach-for-task-scheduling-in-1u15zqfjzh.pdf

A WOA-Based Optimization Approach for Task Scheduling in Cloud Computing Systems

With the growth in computing technologies, cloud computing has added a new paradigm to user services that allows accessing Information Technology services on the basis of pay-per-use at any time and any location. Owing to flexibility in cloud services, numerous organizations are shifting their business to the cloud and service providers are establishing more data centers to provide services to users. However, it is essential to provide cost-effective execution of tasks and proper utilization of resources. Several techniques have been reported in the literature to improve performance and resource use based on load balancing, task scheduling, resource management, quality of service, and workload management. Load balancing in the cloud allows data centers to avoid overloading/underloading in virtual machines, which itself is a challenge in the field of cloud computing. Therefore, it becomes a necessity for developers and researchers to design and implement a suitable load balancer for parallel and distributed cloud environments. This survey presents a state-of-the-art review of issues and challenges associated with existing load-balancing techniques for researchers to develop more effective algorithms.

Issues and Challenges of Load Balancing Techniques in Cloud Computing: A Survey

In a contemporary data center, Linux applications often generate a large quantity of real-time system call traces, which are not suitable for traditional host-based intrusion detection systems deployed on every single host. Training data mining models with system calls on a single host that has static computing and storage capacity is time-consuming, and intermediate datasets are not capable of being efficiently handled. It is cumbersome for the maintenance and updating of host-based intrusion detection systems (HIDS) installed on every physical or virtual host, and comprehensive system call analysis can hardly be performed to detect complex and distributed attacks among multiple hosts. Considering these limitations of current system-call-based HIDS, in this article, we provide a review of the development of system-call-based HIDS and future research trends. Algorithms and techniques relevant to system-call-based HIDS are investigated, including feature extraction methods and various data mining algorithms. The HIDS dataset issues are discussed, including currently available datasets with system calls and approaches for researchers to generate new datasets. The application of system-call-based HIDS on current embedded systems is studied, and related works are investigated. Finally, future research trends are forecast regarding three aspects, namely, the reduction of the false-positive rate, the improvement of detection efficiency, and the enhancement of collaborative security.

Host-Based Intrusion Detection System with System Calls: Review and Future Trends

Agricultural pests cause between 20 and 40 percent loss of global crop production every year as reported by the Food and Agriculture Organization (FAO). Therefore, smart agriculture presents the best option for farmers to apply artificial intelligence techniques integrated with modern information and communication technology to eliminate these harmful insect pests. Consequently, the productivity of their crops can be increased. Hence, this article introduces a new mobile application to automatically classify pests using a deep-learning solution for supporting specialists and farmers. The developed application utilizes faster region-based convolutional neural network (Faster R-CNN) to accomplish the recognition task of insect pests based on cloud computing. Furthermore, a database of recommended pesticides is linked with the detected crop pests to guide the farmers. This study has been successfully validated on five groups of pests; called Aphids, Cicadellidae, Flax Budworm, Flea Beetles, and Red Spider. The proposed Faster R-CNN showed highest accurate recognition results of 99.0% for all tested pest images. Moreover, our deep learning method outperforms other previous recognition methods, i.e., Single Shot Multi-Box Detector (SSD) MobileNet and traditional back propagation (BP) neural networks. The main prospect of this study is to realize our developed application for on-line recognition of agricultural pests in both the open field such as large farms and greenhouses for specific crops.

A new mobile application of agricultural pests recognition using deep learning in cloud computing system

/pdf/analysis-and-outcome-prediction-of-crowdfunding-campaigns-2zsnypw68x.pdf

Analysis and Outcome Prediction of Crowdfunding Campaigns

Enormous amounts of unstructured data such as images, videos, emails, sensors’ data and documents of multiple types are being generated daily by varied applications. Apart from the challenges related to collection or processing of this data, its efficient storage is also a significant challenge since this data do not conform to any predefined storage model. Therefore, any enterprise dealing with huge unstructured data requires a scalable storage system that can provide data durability and availability at a low cost. The paper proposes a tenant-centric approach to develop an object-based software defined storage system for SaaS multi-tenant applications. We present TOSDS (Tenant-centric Object-based Software Defined Storage), a system that can efficiently meet the storage requirements of users or tenants with diverse needs who are using a multitenant SaaS application. The experimental verification of TOSDS illustrates its effectiveness in storage utilization as well as tenant isolation.

/pdf/tosds-tenant-centric-object-based-software-defined-storage-3mob2hw0p0.pdf

TOSDS: Tenant-centric Object-based Software Defined Storage for Multitenant SaaS Applications

The paper presents a comprehensive approach for the detection of symptoms of depression in individuals based on their data from a social media network, Twitter. This data is combined with a historical labelled data set for gaining proper insights about users. Apart from its large size, data of user tweets is of an unstructured form and hence, the work employs a MongoDB based Big Data framework for storing and processing this data. Naïve Bayes' and Long Short-Term Memory (LSTM) classifiers are used to classify tweets as belonging to depressed users or not. Subsequently, topics are extracted from the tweets using Latent Dirichlet Allocation (LDA) to understand the key terms in depressed users' tweets. Lastly, a chatbot based solution is presented for helping the depressed users.

Depression Detection on Social Media

Efficient Clustering of Transactional Data for Privacy-Preserving Data Publishing

Existing fault tolerance approaches in the cloud are broadly based on replication and checkpointing. Each of these approaches has its advantages and limitations. This paper presents an adaptable fault tolerance method for determining which of the two approaches will be appropriate for the successful execution of a task in the given cloud conditions. The proposed method classifies the failure risk of host machines available for task execution based on their failure history. Subsequently, fuzzy logic is used to determine the appropriate fault tolerance approach by considering a host's failure risk, user-defined task's priority, and level of resource redundancy. Setting a task's priority provides a user with control to solicit a desired fault tolerance level while the availability of resources reflects a cloud provider's capability to offer fault tolerance. Simulation experiments have verified that the proactive selection of a fault-tolerance method increases the number of tasks that complete successfully.

Parmeet Kaur

Papers

Analysis and Outcome Prediction of Crowdfunding Campaigns

TOSDS: Tenant-centric Object-based Software Defined Storage for Multitenant SaaS Applications

Depression Detection on Social Media

Efficient Clustering of Transactional Data for Privacy-Preserving Data Publishing

An Adaptable Approach to Fault Tolerance in Cloud Computing