Accelerating SPARQL queries by exploiting hash-based locality and adaptive partitioning

State-of-the-art distributed RDF systems partition data across multiple computer nodes (workers). Some systems perform cheap hash partitioning, which may result in expensive query evaluation. Others try to minimize inter-node communication, which requires an expensive data preprocessing phase, leading to a high startup cost. Apriori knowledge of the query workload has also been used to create partitions, which, however, are static and do not adapt to workload changes. In this paper, we propose AdPart, a distributed RDF system, which addresses the shortcomings of previous work. First, AdPart applies lightweight partitioning on the initial data, which distributes triples by hashing on their subjects; this renders its startup overhead low. At the same time, the locality-aware query optimizer of AdPart takes full advantage of the partitioning to (1) support the fully parallel processing of join patterns on subjects and (2) minimize data communication for general queries by applying hash distribution of intermediate results instead of broadcasting, wherever possible. Second, AdPart monitors the data access patterns and dynamically redistributes and replicates the instances of the most frequent ones among workers. As a result, the communication cost for future queries is drastically reduced or even eliminated. To control replication, AdPart implements an eviction policy for the redistributed patterns. Our experiments with synthetic and real data verify that AdPart: (1) starts faster than all existing systems; (2) processes thousands of queries before other systems become online; and (3) gracefully adapts to the query load, being able to evaluate queries on billion-scale RDF data in subseconds.     

A simple and accurate method for calibrating the oscillation amplitude of tuning-fork based AFM sensors

We have developed a simple and accurate method for calibrating the amplitude of vibration of quartz tuning fork sensors commonly used in atomic force- and near field optical-microscopy. Unlike interferometric methods, which require a complex optical setup, the method we present requires only a simple measurement of the electro-mechanical properties of the tuning-fork oscillator and can be performed in a matter of minutes without disturbing the experimental setup. Comparison with interferometric methods shows that an accuracy of better than few percent can be routinely achieved.     

Optimal Machine Learning Enabled Performance Monitoring for Learning Management Systems

Learning Management System (LMS) is an application software that is used in automation, delivery, administration, tracking, and reporting of courses and programs in educational sector. The LMS which exploits machine learning (ML) has the ability of accessing user data and exploit it for improving the learning experience. The recently developed artificial intelligence (AI) and ML models helps to accomplish effective performance monitoring for LMS. Among the different processes involved in ML based LMS, feature selection and classification processes find beneficial. In this motivation, this study introduces Glowworm-based Feature Selection with Machine Learning Enabled Performance Monitoring (GSO-MFWELM) technique for LMS. The key objective of the proposed GSO-MFWELM technique is to effectually monitor the performance in LMS. The proposed GSO-MFWELM technique involves GSO-based feature selection technique to select the optimal features. Besides, Weighted Extreme Learning Machine (WELM) model is applied for classification process whereas the parameters involved in WELM model are optimally fine-tuned with the help of Mayfly Optimization (MFO) algorithm. The design of GSO and MFO techniques result in reduced computation complexity and improved classification performance. The presented GSO-MFWELM technique was validated for its performance against benchmark dataset and the results were inspected under several aspects. The simulation results established the supremacy of GSO-MFWELM technique over recent approaches with the maximum classification accuracy of 0.9589.     

A Framework of Deep Learning and Selection-Based Breast Cancer Detection from Histopathology Images

Breast cancer (BC) is a most spreading and deadly cancerous malady which is mostly diagnosed in middle-aged women worldwide and effecting beyond a half-million people every year. The BC positive newly diagnosed cases in 2018 reached 2.1 million around the world with a death rate of 11.6% of total cases. Early diagnosis and detection of breast cancer disease with proper treatment may reduce the number of deaths. The gold standard for BC detection is biopsy analysis which needs an expert for correct diagnosis. Manual diagnosis of BC is a complex and challenging task. This work proposed a deep learning-based (DL) solution for the early detection of this deadly disease from histopathology images. To evaluate the robustness of the proposed method a large publically available breast histopathology image database containing a total of 277524 histopathology images is utilized. The proposed automatic diagnosis of BC detection and classification mainly involves three steps. Initially, a DL model is proposed for feature extraction. Secondly, the extracted feature vector (FV) is passed to the proposed novel feature selection (FS) framework for the best FS. Finally, for the classification of BC into invasive ductal carcinoma (IDC) and normal class different machine learning (ML) algorithms are used. Experimental outcomes of the proposed methodology achieved the highest accuracy of 92.7% which shows that the proposed technique can successfully be implemented for BC detection to aid the pathologists in the early and accurate diagnosis of BC.     

A Framework of Deep Optimal Features Selection for Apple Leaf Diseases Recognition

Identifying fruit disease manually is time-consuming, expert-required, and expensive; thus, a computer-based automated system is widely required. Fruit diseases affect not only the quality but also the quantity. As a result, it is possible to detect the disease early on and cure the fruits using computer-based techniques. However, computer-based methods face several challenges, including low contrast, a lack of dataset for training a model, and inappropriate feature extraction for final classification. In this paper, we proposed an automated framework for detecting apple fruit leaf diseases using CNN and a hybrid optimization algorithm. Data augmentation is performed initially to balance the selected apple dataset. After that, two pre-trained deep models are fine-tuning and trained using transfer learning. Then, a fusion technique is proposed named Parallel Correlation Threshold (PCT). The fused feature vector is optimized in the next step using a hybrid optimization algorithm. The selected features are finally classified using machine learning algorithms. Four different experiments have been carried out on the augmented Plant Village dataset and yielded the best accuracy of 99.8%. The accuracy of the proposed framework is also compared to that of several neural nets, and it outperforms them all.     

WiMA: Towards a Multi-Criterion Association in Software Defined Wi-Fi Networks

Despite the planned installation and operations of the traditional IEEE 802.11 networks, they still experience degraded performance due to the number of inefficiencies. One of the main reasons is the received signal strength indicator (RSSI) association problem, in which the user remains connected to the access point (AP) unless the RSSI becomes too weak. In this paper, we propose a multi-criterion association (WiMA) scheme based on software defined networking (SDN) in Wi-Fi networks. An association solution based on multi-criterion such as AP load, RSSI, and channel occupancy is proposed to satisfy the quality of service (QoS). SDN having an overall view of the network takes the association and reassociation decisions making the handoffs smooth in throughput performance. To implement WiMA extensive simulations runs are carried out on Mininet-NS3-Wi-Fi network simulator. The performance evaluation shows that the WiMA significantly reduces the average number of retransmissions by 5%–30% and enhances the throughput by 20%–50%, hence maintaining user fairness and accommodating more wireless devices and traffic load in the network, when compared to traditional client-driven (CD) approach and state of the art Wi-Balance approach.     

Analysis of Distribution of Nonmetallic Inclusions in Aluminum DC-Cast Billets and Slabs

Inclusion distribution was studied in commercial aluminum DC-cast billets and slabs using a newly developed deep-etching method. Analyses revealed a nonuniform distribution of nonmetallic inclusions across billet diameters and lengths, and also across slab thicknesses and widths. In as-cast billets, more inclusions were found at the beginning and end of the billet length; more were present near the cross-section center than near the surface. In slabs, inclusions were located mostly within 13 mm of the surface and in a band between the centerline and the surface. Few inclusions were found 60 to 100 mm from the slab surface or at the centerline. In addition, comparing slab quality after casting using three types of ceramic foam filters (CFFs; i.e., 30 ppi, 50 ppi, and 50 ppi + HF) revealed significant differences in inclusion size, number, and distribution. Casting slabs using a finer pore-size filter (50 ppi) reduced the number of non-metallic inclusions greatly. The inclusion distribution patterns observed in the solidified slabs are discussed in terms of melt flow during casting.     

Tea and coffee consumption in relation to vitamin D and calcium levels in Saudi adolescents

ABSTRACT: BACKGROUND: Coffee and tea consumption was hypothesized to interact with variants of vitamin D-receptor polymorphisms, but limited evidence exists. Here we determine for the first time whether increased coffee and tea consumption affects circulating levels of 25-hydroxyvitamin D in a cohort of Saudi adolescents. METHODS: A total of 330 randomly selected Saudi adolescents were included. Anthropometrics were recorded and fasting blood samples were analyzed for routine analysis of fasting glucose, lipid levels, calcium, albumin and phosphorous. Frequency of coffee and tea intake was noted. 25-hydroxyvitamin D levels were measured using enzyme-linked immunosorbent assays. RESULTS: Improved lipid profiles were observed in both boys and girls, as demonstrated by increased levels of HDL-cholesterol, even after controlling for age and BMI, among those consuming 9--12 cups of coffee/week. Vitamin D levels were significantly highest among those consuming 9--12 cups of tea/week in all subjects (p-value 0.009) independent of age, gender, BMI, physical activity and sun exposure. CONCLUSION: This study suggests a link between tea consumption and vitamin D levels in a cohort of Saudi adolescents, independent of age, BMI, gender, physical activity and sun exposure. These findings should be confirmed prospectively.     

Robust tools for prediction of variability and optimization in structural dynamics

The aims of this work were to quantify the effects of uncertainties of design parameters on the variability of linear and non-linear behaviour of mechanical structures that we wish to optimize, and to calculate optimal and robust solutions resulting from numerical simulations. We propose a method that takes into account the propagation of uncertainties in finite-element models in a multi-objective optimization procedure. This method is based on coupling the stochastic response surface method (SRSM) and the non-dominated sorting genetic algorithm (NSGA). SRSM is based on application of the stochastic finite-element method via the polynomial chaos expansion method or the modal perturbation method. This strategy avoids the use of Monte Carlo simulation, in which costs can become prohibitive in optimization problems, especially when the finite-element models are large and have a considerable number of design parameters. The robust design described here has been developed to obtain an optimum value that is insensitive to changes of design variables within a feasible range.