Vietnam Journal of Computer Science

Breast cancer is the leading cause of high fatality among women population. Identification of the benign and malignant tumor at correct time plays a critical role in the diagnosis of breast cancer. In this paper, an attempt has been made to extract the valuable information by selecting the relevant features using our proposed EGWO-SVM (enhanced grey wolf optimization-support vector machine) approach. Grey wolf optimizer (GWO) has gained a lot of popularity among other swarm intelligence methods due to its various characteristics like few tuning parameters, simplicity and easy to use, scalable, and most importantly its ability to provide faster convergence by maintaining the right balance between the exploration and exploitation during the search. Therefore, an enhanced GWO has been proposed in combination with SVM to determine the optimum subset of tumor features for accurate identification of benign and malignant tumor. The proposed approach has been tested and compared with numerous existing, state-of-the-art as well as recently published breast cancer classification approaches on the standard benchmark Wisconsin Diagnostic Breast Cancer (WDBC) database. The proposed approach outperforms all the compared approaches by improving the classification accuracy to 98.24% demonstrating its effectiveness in identifying the breast cancer.

Fall detection is a serious problem in elder people. Constant inspection is important for this fall identification. Currently, numerous methods associated with fall detection are a significant area of research for safety purposes and for the healthcare industries. The objective of this paper is to identify elderly falls. The proposed method introduces keyframe based fall detection in elderly care system. Experiments were conducted on University of Rzeszow (UR) Fall Detection dataset, Fall Detection Dataset and MultiCam dataset. It is substantially proved that the proposed method achieves higher accuracy rate of 99%, 98.15% and 99% for UR Fall detection dataset, Fall Detection Dataset and MultiCam dataset, respectively. The performance of the proposed method is compared with other methods and proved to have higher accuracy rate than those methods.

It is a trend for the public organizations to digitalize and publish their large dataset as open linked data to the public users for queries and other applications for further utilizations. Different users’ queries with various frequencies over time create different workload patterns to the servers which cannot guarantee the QoS during peak usages. Materialization is a well-known effective method to reduce peaks, but it is not used by semantic webs, due to frequently evolving schema. This research is able to estimate workloads based on previous queries, analyze and normalize their structures to materialize views, and map the queries to the views with populated data. By analyzing how access patterns of individual views contribute to the overall system workload, the proposed model aims at selection of candidates offering the highest reduction of the peak workload. Consequently, rather than optimizing all queries equally, a system using the new selection method can offer higher query throughput when it is the most needed, allowing for a higher number of concurrent users without compromising QoS during the peak usage. Finally, two case studies were used to evaluate the proposed method.

An important part of the industry 4.0 concept is the horizontal and vertical integration of manufacturing systems.

Information exchange in traditional production environments happens through interfaces that are connections between strictly defined senders and receivers. This limits the possibility for changing and extending the manufacturing system. A possible approach to enable the information exchange between all system entities uniformly are information models. Such models are semantic descriptions of the available data. The creation of these models needs to follow the manufacturing process, but also requires certain standardization to improve efficiency. Another challenge is the actual technical integration of the information into a common address space.

This paper connects an approach for information modeling with a concept for dynamic aggregation. The approach is described with the help of a continuous example that uses OPC UA as a middleware technology.

Metaheuristic search algorithms are used to develop new protocols for optimal intravenous insulin infusion rate recommendations in scenarios involving hospital in-patients with Type 1 Diabetes. Two metaheuristic search algorithms are used, namely, Particle Swarm Optimization and Covariance Matrix Adaption Evolution Strategy. The Glucose Regulation for Intensive Care Patients (GRIP) serves as the starting point of the optimization process. We base our experiments on a methodology in the literature to evaluate the favorability of insulin protocols, with a dataset of blood glucose level/insulin infusion rate time series records from 16 patients obtained from the Waikato District Health Board. New and significantly better insulin infusion strategies than GRIP are discovered from the data through metaheuristic search. The newly discovered strategies are further validated and show good performance against various competitive benchmarks using a virtual patient simulator.

Nowadays, the Internet of Things (IoT) is a common word for the people because of its increasing number of users. Statistical results show that the users of IoT devices are dramatically increasing, and in the future, it will be to an ever-increasing extent. Because of the increasing number of users, security experts are now concerned about its security. In this research, we would like to improve the security system of IoT devices, particularly in IoT botnet, by applying various machine learning (ML) techniques. In this paper, we have set up an approach to detect botnet of IoT devices using three one-class classifier ML algorithms. The algorithms are: one-class support vector machine (OCSVM), elliptic envelope (EE), and local outlier factor (LOF). Our method is a network flow-based botnet detection technique, and we use the input packet, protocol, source port, destination port, and time as features of our algorithms. After a number of preprocessing steps, we feed the preprocessed data to our algorithms that can achieve a good precision score that is approximately 77–99%. The one-class SVM achieves the best accuracy score, approximately 99% in every dataset, and EE’s accuracy score varies from 91% to 98%; however, the LOF factor achieves lowest accuracy score that is from 77% to 99%. Our algorithms are cost-effective and provide good accuracy in short execution time.

In educational data mining, student classification is an important and popular task by predicting final study status of each student. In the existing works, this task has been considered in many various contexts at both course and program levels with different learning approaches. However, its real-world characteristics such as temporal aspects, data imbalance, data overlapping, and data shortage with sparseness have not yet been fully investigated. Making the most of deep learning, our work is the first one addressing those challenges for the program-level student classification task. In a simple but effective manner, convolutional neural networks (CNNs) are proposed to exploit their well-known advantages on images for temporal educational data. As a result, the task is resolved by our enhanced CNN models with more effectiveness and practicability on real datasets. Our CNN models outperform other traditional models and their various variants on a consistent basis for program-level student classification.