Future Computing and Informatics Journal最新文献

IoT diverse applications face many challenges. The main challenge is to have efficient energy aware communication protocols that utilize the diversity and heterogeneity of the connected things through Internet. Saving energy is a vital requirement in the limited battery energy nodes and also for the outsourced energy nodes for green computing. IoT milieu has many diverse devices that are heterogeneous in their energies, their Internet availability, etc. These devices are usually distributed into regions with different heterogeneity levels; ranging from homogeneous to near homogenous, till reaching to the high heterogeneous regions. Many existed protocols efficiently treated either the homogenous devices or heterogeneous devices. This paper defeats the gap between the physical wireless sensor network environment and the real heterogeneous Cyber IoT milieu. This paper targets not only providing an efficient hybrid energy aware clustering communication protocol for green IoT network computing; Hy-IoT, but also provides a real IoT network architecture for examining the proposed protocol compared to commonly existed protocols. Efficient cluster-head selection boosts the utilization of the nodes energy contents and consequently increases the network life time as well as the packets transmission rate to the base station. Hy-IoT uses different weighted election probabilities for selecting a Cluster-head based on heterogeneity level of the region. Simulation shows that Hy-IoT prolongs the network life time and increases the throughput compared to the SEP, LEACH and Z-SEP. Hy-IoT provides prolonging for the network life time ranging from 47.8% to 92.5% based on the heterogeneity level and also the average throughput was boosted ranging from 11.5% to 70.1% based on the heterogeneity level.

Decision tree is a well-known classifier which is widely used in real-world applications. It is easy to interpret, however it suffers from instability and lower classification performance for high-dimensionality datasets due to curse of dimensionality. Feature set partitioning is a novel concept to address the higher dimensionality problem by dividing the feature set into subsets (blocks). Many of the existing partitioning based decision tree approaches are sequential in nature, which lack logical relationships amongst the features. In this work, we propose novel non-sequential feature set partitioning methods by exploiting the ideas of Ferrer Diagram and Bell Triangle to create feature blocks with a mix of low, medium, and high correlation features. The experimental results on 11 UCI and KEEL datasets demonstrate the superiority of the proposed partitioning methods, upto 5% higher classification accuracy, over NBTree, BFTree, Serial-CMFP partitioning method, and classical decision tree techniques. The proposed methods also exhibit improved stability as compared to other decision tree methods.

The successful implementation of customer relationship management (CRM) is not easy and seems to be a complex task. Almost about 70% of all CRM implementation projects fail to achieve their expected objectives. Therefore, most researchers and information systems developers concentrate on the critical success factors approach which can enhance the success of CRM implementation and turn the failure and drawbacks faced CRM into successful CRM systems adoption and implementation. In this paper, the number of the previous studies is reviewed to demonstrate the barriers behind this high failure rate. In addition, an extensive review is conducted in order to identify and prioritize the critical success factors (CSFs) that if the organizations are aware of and have knowledge of them properly; they will achieve success and will obtain the expected benefits of their CRM initiative. And then, an extensive CSFs classification is proposed. Finally, the work proposes an extensive list of metrics as the means to help in measuring these critical success factors.

One of the significant data mining techniques is clustering. Due to expansion and digitalization of each field, large datasets are being generated rapidly. Such large dataset clustering is a challenge for traditional sequential clustering algorithms due to huge processing time. Distributed parallel architectures and algorithms are thus helpful to achieve performance and scalability requirement of clustering large datasets. In this study, we design and experiment a parallel k-means algorithm using MapReduce programming model and compared the result with sequential k-means for clustering varying size of document dataset. The result demonstrates that proposed k-means obtains higher performance and outperformed sequential k-means while clustering documents.

Heterogeneous computing supply various and scalable resources for many applications requirements. Its structure is based on interconnecting machines with several processing capacity spread over networks. The scientific bioinformatics and many other applications demand service flow processing in which services have dependencies execution. The environments of this computing are suitable for huge computational needs that contains diverse groups of services. Managing and mapping services of service flow to the suitable candidates who provides the service is classified as NP-complete problem. The managing such interdependent services on heterogeneous environments also takes the Quality of Service (QoS) requirements from users into account. This paper firstly proposes a model of service flow management with service cost quality requirement in heterogeneous computing. After that a service flow mapping algorithm named genetic to reduce the consumed cost of an application in heterogeneous environments is proposed. This algorithm gives a robust search technique that allow a soft cost solution to be derived from a huge search space of solutions by inheriting the evolution concepts. The obtained results from the applied experiments prove that genetic can save more than fifteen percent from the cost and also outperforms the compared algorithms in the metric of speedup and SLR.

Transition region based approaches are recent hybrid segmentation techniques well known for its simplicity and effectiveness. Here, the segmentation effectiveness depends on robust extraction of transition regions. So, we have proposed clustering approach based transition region extraction method for image segmentation. The proposed method initially uses the local variance of the input image to get the variance feature image. Fuzzy C-means clustering is applied to the variance feature image to separate the transitional features from the feature image. Further, Otsu thresholding is applied to the transitional feature image to extract the transition region. For extracting the exact edge image, morphological thinning operation is performed. The edge image extracted in former step is closed in nature. The morphological cleaning and region filling operation is performed on an edge image to get the object regions. Finally, objects are extracted via these object regions. The proposed method is compared with different image segmentation methods. An experimental result reveals that the proposed method outperforms other methods for segmentation of images containing single and multiple objects.

Breast cancer is a malignant tumor that starts in the cells of the breast. A malignant tumor is a group of cancer cells that can grow into near tissues or invading the distant areas of the body. The disease occurs almost entirely in women, but men can get it, too. Survival rate, recurrence detection and disease-free survival rate (DFS) are the main patient's outcome and prognosis measures. Breast cancer outcomes are vary among different stages of the disease. There are five stages of breast cancer named as 0, 1, 2, 3, and 4. Prognosis helps doctors to save patients' lives by estimating how patient will progress in the therapy plan by comparing the patient's results with another patient's has the same disease characteristics and completed his therapy plan. In Egypt breast cancer represented 21.6% of 33,000 women cancer deaths Ibrahim et al.,2014, with incidence rate (48.8/100,000) and mortality rate (19.2/100,000). We selected a sample about 1692 cases were diagnosed as breast cancer patients at the period from 2010 to 2012 taken from the cases recorded in the Tumors Hospital and Institute of First Settlement one of the National Cancer Institute “NCI” cancer hospitals in Egypt. NCI is the central cancer institute in Egypt. We select the main sufficient attributes to building a prognosis predictive model 0.1471 records have been selected form the whole sample. The data set we select is used to compute and predict the three main outcome of prognosis measure at two level, data level for the complete data set, stage level for every stage of breast cancer separately. The study uses efficient five prediction models with highest accuracy. Results shows that the 5-years survival rate and local recurrence was in continuous decreasing since 2010 to 2012. Metastatic as a type of breast cancer recurrence was 20.74% in 2010, 17.59% in 2011 and 22.35% in 2012.The DFS (Disease-Free Survival) have the worst rate ever in 2012 as 7.13% after it was 30.37% in 2010.Prognosis predictive models results shows that the SVM classifiers is the most accurate model to predict the three prognosis measures at the two data level.

The aim of this project is to design and implement a low cost Autonomous Unmanned Ground Vehicle (AUGV), a vehicle that can be controlled remotely without an onboard human presence. The AUGV is also able to move autonomously while automatically detecting and avoiding obstacles. The vehicle also reads directions from QR codes, calculates the shortest path to its destination and autonomous move towards its final destination. A Raspberry Pi 3 has been used as the brain of the vehicle together with other components such as DC and Servo motors, Ultrasonic and Infrared sensors, webcam, batteries, power bank, motor controller and a smartphone. Python, Java and PHP have been used to implement the prototype which currently focusses on indoor navigation. There exists several potential practical applications of the UAGV such as an autonomous wheel chair for handicapped persons allowing them to move around autonomously without relying on any other persons. The idea can be extended to fit into the untapped indoor commercial market such as malls, hotels, banks, nursing homes, hospitals, offices, stores, schools, museums and many more.

Breast cancer is one of the dreadful diseases that affect women globally. The occurrences of breast masses in the breast region are the main cause for women to develop a breast cancer. Early detection of breast mass will increase the survival rate of women and hence developing an automated system for detection of the breast masses will support radiologists for accurate diagnosis. In the pre-processing step, the images are pre-processed using Gaussian filtering. An automated detection method of breast masses is proposed using an optimized region growing technique where the initial seed points and thresholds are optimally generated using a swarm optimization technique called Dragon Fly Optimization (DFO). The texture features are extracted using GLCM and GLRLM techniques from the segmented images and fed into a Feed Forward Neural Network (FFNN) classifier trained using back propagation algorithm which classifies the images as benign and malignant. The performance of the proposed detection technique is evaluated using the images obtained from DDSM database. The results achieved by the proposed pixel-based technique are compared to other region growing methods using ROC analysis. The sensitivity of the proposed system reached up to 98.1% and specificity achieved is 97.8% in which 300 images are used for training and testing purposes.

Bio-inspired computing represents the umbrella of different studies of computer science, mathematics, and biology in the last years. Bio-inspired computing optimization algorithms is an emerging approach which is based on the principles and inspiration of the biological evolution of nature to develop new and robust competing techniques. In the last years, the bio-inspired optimization algorithms are recognized in machine learning to address the optimal solutions of complex problems in science and engineering. However, these problems are usually nonlinear and restricted to multiple nonlinear constraints which propose many problems such as time requirements and high dimensionality to find the optimal solution. To tackle the problems of the traditional optimization algorithms, the recent trends tend to apply bio-inspired optimization algorithms which represent a promising approach for solving complex optimization problems. This paper presents state-of-art of nine of recent bio-inspired algorithms, gap analysis, and its applications namely; Genetic Bee Colony (GBC) Algorithm, Fish Swarm Algorithm (FSA), Cat Swarm Optimization (CSO), Whale Optimization Algorithm (WOA), Artificial Algae Algorithm (AAA), Elephant Search Algorithm (ESA), Chicken Swarm Optimization Algorithm (CSOA), Moth flame optimization (MFO), and Grey Wolf Optimization (GWO) algorithm. The previous related works are collected from Scopus databases are presented. Also, we explore some key issues in optimization and some applications for further research. We also analyze in-depth discussions the essence of these algorithms and their connections to self-organization and its applications in different areas of research are presented. As a result, the proposed analysis of these algorithms leads to some key problems that have to be addressed in the future.