Machine learning approaches are powerful techniques commonly employed for developing cancer prediction models using associated gene expression and mutation data. Our survey provides a comprehensive review of recent cancer studies that have employed gene expression data from several cancer types (breast, lung, kidney, ovarian, liver, central nervous system and gallbladder) for survival prediction,tumor identification and stratification. We also provide an overview of biomarker studies that are associated with these cancer types. The survey captures multiple aspects of machine learning associated cancer studies,including cancer classification, cancer prediction, identification of biomarker genes, microarray, and RNA-Seq data.We discuss the technical issues with current cancer prediction models and the corresponding measurement tools for determining the activity levels of gene expression between cancerous tissues and noncancerous tissues. Additionally, we investigate how identifying putative biomarker gene expression patterns can aid in predicting future risk of cancer and inform the provision of personalized treatment.

In higher education institutions, a high number of studies show that the use of predictive learning analytics can positively impact student retention and the other aspects which lead to student success. Predictive learning analytics examines the learning data for intervening or improving the process itself that positively reflects on student performance. In our survey, we are considering the most recent research papers focusing on predictive learning analytics and how that affects the final student outcome in educational institutions. The process of predictive learning analytics, such as data collection, data preprocessing, data mining, and others, has been illustrated in detail. We have identified factors that affect student performance. Several machine learning approaches have also been compared to provide a clear view of the most suitable algorithms and tools used for implementing the learning analytics.

In the pursuit of better cancer classification, many studies have been conducted to identify the genes associated with cancer. However, the high dimensionality of gene expression data and the limited relevance of a few genes pose significant challenges to this endeavor. Existing gene selection methods yield divergent gene lists, further complicating the classification process. To overcome this issue, we developed a novel approach called Fuzzy Gene Selection (FGS), which combines the strengths of various gene selection methods in the field. FGS was developed using three feature selection techniques (Mutual Information, F-ClassIf, and Chi-squared) to rank genes based on their importance. These methods generated scores and rankings for each gene. Fuzzification and Defuzzification techniques were then applied to combine these scores into a single best score for each gene. This approach aids in identifying genes of significance in cancer classification, especially in multi-class scenarios. Classifiers often produce convergent decisions in such cases, where the predicted probabilities for different classes do not always correspond to the correct predicted class with the highest probability. To address this, we developed a novel Fuzzy classifier that leverages the contributions from each node’s traditional deep classifier. This novel approach combines the strengths of traditional deep classifiers at individual nodes, enabling the Fuzzy classifier to make more robust and informed predictions. The Fuzzy classifier (FC) has demonstrated improvements in accuracy and the generalization of the proposed algorithm to accurately classify different cancer types.

The Designers' Workbench is a system developed by the Advanced Knowledge Technologies Consortium to support designers in large organizations, such as Rolls-Royce, to ensure that the design is consistent with the specification for the particular design as well as with the company's design rule book(s). In the principal application discussed here, the evolving design is described using a jet engine ontology. Design rules are expressed as constraints over the domain ontology. Currently, to capture the constraint information, a domain expert (design engineer) has to work with a knowledge engineer to identify the constraints, and it is then the task of the knowledge engineer to encode these into the Workbench's knowledge base. This is an error-prone and time-consuming task. It is highly desirable to relieve the knowledge engineer of this task, so we have developed a system, ConEditor+, that enables domain experts themselves to capture and maintain these constraints. Further, we hypothesize that to appropriately apply, maintain, and reuse constraints, it is necessary to understand the underlying assumptions and context in which each constraint is applicable. We refer to them as “application conditions,” and these form a part of the rationale associated with the constraint. We propose a methodology to capture the application conditions associated with a constraint and demonstrate that an explicit representation (machine interpretable format) of application conditions (rationales) together with the corresponding constraints and the domain ontology can be used by a machine to support maintenance of constraints. Support for the maintenance of constraints includes detecting inconsistencies, subsumption, redundancy, fusion between constraints, and suggesting appropriate refinements. The proposed methodology provides immediate benefits to the designers, and hence, should encourage them to input the application conditions (rationales).

There has been a strong focus on the evaluation of Quality of Service (QoS) and multimedia transmission over protocols of internet protocol (IP). The main goal of this paper is to evaluate the performance of QoS in real implementation, also a comparison of an appropriate video and voice (CODECS) over IP schemes depending on the SIP and IAX2 protocols based on the Asterisk PBX server(s), an open source communication platform. The network was implemented within various private networks, such as Wire and Wi-Fi, which serves as a local exchange for placing various calls. Quality has been evaluated based on some QoS parameters such as bandwidth, jitter and delay to investigate the performance of different codecs in video and voice over IP (VVoIP) network. The VVoIP codecs used in the measurements are: G.711 (ulaw&alaw), GSM, G.722, Speex, H.263, H.264, H.261 and H.263P. Evaluation of performance results will give network Planners and Multimedia protocols developers an opportunity to select the codec for VVoIP performance enhancement, which can lead to improved customer satisfaction.

Education providers are increasingly using artificial techniques for predicting students' performance based on their interactions in Virtual Learning Environments (VLE). In this paper, the Open University Learning Analytics Dataset (OULAD), which contains student demographic information, assessment scores, number of clicks in the virtual learning environment and final results, etc, has been used to predict student performance. Various techniques such as standardisation and normalisation have been employed in the pre-processing stage. Spearman's correlation coefficient is used to measure the correlation between the activity types and the students' final results to determine the importance of the activities. Deep learning has been utilised to predict students' performance based on their engagement in the VLE. The empirical results show that our model has the ability to accurately predict student academic performance.