Fractal feature selection model for enhancing high-dimensional biological problems.

The integration of biology, computer science, and statistics has given rise to the interdisciplinary field of bioinformatics, which aims to decode biological intricacies. It produces extensive and diverse features, presenting an enormous challenge in classifying bioinformatic problems. Therefore, an intelligent bioinformatics classification system must select the most relevant features to enhance machine learning performance. This paper proposes a feature selection model based on the fractal concept to improve the performance of intelligent systems in classifying high-dimensional biological problems. The proposed fractal feature selection (FFS) model divides features into blocks, measures the similarity between blocks using root mean square error (RMSE), and determines the importance of features based on low RMSE. The proposed FFS is tested and evaluated over ten high-dimensional bioinformatics datasets. The experiment results showed that the model significantly improved machine learning accuracy. The average accuracy rate was 79% with full features in machine learning algorithms, while FFS delivered promising results with an accuracy rate of 94%.

Embedding patients confidential data in ECG signal for healthcare information systems.

In Wireless tele-cardiology applications, ECG signal is widely used to monitor cardiac activities of patients. Accordingly, in most e-health applications, ECG signals need to be combined with patient confidential information. Data hiding and watermarking techniques can play a crucial role in ECG wireless tele-monitoring systems by combining the confidential information with the ECG signal since digital ECG data is huge enough to act as host to carry tiny amount of additional secret data. In this paper, a new steganography technique is proposed that helps embed confidential information of patients into specific locations (called special range numbers) of digital ECG host signal that will cause minimal distortion to ECG, and at the same time, any secret information embedded is completely extractable. We show that there are 2.1475 × 10(9) possible special range numbers making it extremely difficult for intruders to identify locations of secret bits. Experiments show that percentage residual difference (PRD) of watermarked ECGs can be as low as 0.0247% and 0.0678% for normal and abnormal ECG segments (taken from MIT-BIH Arrhythmia database) respectively.

Compression-based aggregation model for medical web services.

Many organizations such as hospitals have adopted Cloud Web services in applying their network services to avoid investing heavily computing infrastructure. SOAP (Simple Object Access Protocol) is the basic communication protocol of Cloud Web services that is XML based protocol. Generally,Web services often suffer congestions and bottlenecks as a result of the high network traffic that is caused by the large XML overhead size. At the same time, the massive load on Cloud Web services in terms of the large demand of client requests has resulted in the same problem. In this paper, two XML-aware aggregation techniques that are based on exploiting the compression concepts are proposed in order to aggregate the medical Web messages and achieve higher message size reduction.

A new XML-aware compression technique for improving performance of healthcare information systems over hospital networks.

Most organizations exchange, collect, store and process data over the Internet. Many hospital networks deploy Web services to send and receive patient information. SOAP (Simple Object Access Protocol) is the most usable communication protocol for Web services. XML is the standard encoding language of SOAP messages. However, the major drawback of XML messages is the high network traffic caused by large overheads. In this paper, two XML-aware compressors are suggested to compress patient messages stemming from any data transactions between Web clients and servers. The proposed compression techniques are based on the XML structure concepts and use both fixed-length and Huffman encoding methods for translating the XML message tree. Experiments show that they outperform all the conventional compression methods and can save tremendous amount of network bandwidth.