Task-Oriented Intelligent Solution to Measure Parkinson’s Disease Tremor Severity

Tremor is a common symptom of Parkinson’s disease (PD). Currently, tremor is evaluated clinically based on MDS-UPDRS Rating Scale, which is inaccurate, subjective, and unreliable. Precise assessment of tremor severity is the key to effective treatment to alleviate the symptom. Therefore, several objective methods have been proposed for measuring and quantifying PD tremor from data collected while patients performing scripted and unscripted tasks. However, up to now, the literature appears to focus on suggesting tremor severity classification methods without discrimination tasks effect on classification and tremor severity measurement. In this study, a novel approach to identify a recommended system is used to measure tremor severity, including the influence of tasks performed during data collection on classification performance. The recommended system comprises recommended tasks, classifier, classifier hyperparameters, and resampling technique. The proposed approach is based on the above-average rule of five advanced metrics results of four subdatasets, six resampling techniques, six classifiers besides signal processing, and features extraction techniques. The results of this study indicate that tasks that do not involve direct wrist movements are better than tasks that involve direct wrist movements for tremor severity measurements. Furthermore, resampling techniques improve classification performance significantly. The findings of this study suggest that a recommended system consists of support vector machine (SVM) classifier combined with BorderlineSMOTE oversampling technique and data collection while performing set of recommended tasks, which are sitting, stairs up and down, walking straight, walking while counting, and standing.

A Novel Structure of Highly Interpretable Fuzzy Rules Extraction

Introduction: Extracting effective rules from medical data with two indicators of accuracy and high interpretability is essential to increase the accuracy and speed of diagnosis by specialists. As a result, the production of medical assistant systems that are able to detect the rules governing the data plays a vital role in early detection of the disease and thus increase the chances of treatment, disease control and maintaining the quality of life of patients.Material and Methods: In this paper, a system of automatic extraction of rules from medical data by a new hybrid method based on fuzzy logic and genetic algorithm is presented. Genetic algorithms are used to automatically generate these rules. The Parkinson UCI dataset including 195 records and 23 variables was used to evaluate the proposed method based on the criteria of interpretability, accuracy, sensitivity and specificity.Results: The evaluation of the proposed model on the Parkinson's dataset was the accuracy of 84.62%. This accuracy is supported by 4 fuzzy rules with an average rule length of 2 and using 7 linguistic terms extremely low, very low, low, normal, high, very high and extremely high. All fuzzy membership functions that represent each term have the same width.Conclusion: The proposed method, based on the three criteria of low number of rules, short rule length and symmetric membership functions with equal width for all variables, is quite suitable for automatic production of accurate and compact rules with high interpretability in medical data. . A 90% dimensionality reduction in the experimental evaluation showed that this model could be used to implement real-time systems.

Kompetensi Kemahiran Berbahasa Mahasiswa Program Studi Pendidikan Bahasa dan Sastra Indonsia Universitas Islam Riau

This study aimed to analyze the literacy competencies of students' language proficiency in the aspects of listening, responding to the rules, reading and writing. Literacy competence is a competency that must be considered by educators in honing language proficiency which is an important issue, especially in the development of language skills in students. This research used a quantitative-descriptive method. The data obtained from this study were the results of the Indonesian language proficiency test (UKBI) of students in the Indonesian Language and Literature Education study program. The population used in this study were students of the Indonesian Language and Literature Education study program, while the sample who had taken the UKBI test was 24 students. The results of this study indicated that the students' language proficiency literacy competence in the listening aspect obtains an average of 538, responds to the average rule of 464, reads an average of 519, and writes an average of 596. The overall average of language proficiency literacy competencies was 529. Twenty-five was in the middle-ranking, indicating that students have adequate proficiency in communicating using Indonesian, both oral and written. With these skills, the student concerned can understand factual information, properly capture and re-reveal information.

A cointegrating stock trading strategy: application to listed tanker shipping companies

In the current paper, we propose a strategy to trade a portfolio of listed shipping companies in the US market. In particular, we estimate a co-integrating relationship between the weekly stock market returns of a portfolio of tanker shipping companies and the Baltic Tanker Index, exploiting the close relationship between freight rates and the stock market performance of shipping companies. Our results suggest that a trading strategy on the basis of a co-integrating relationship and a simple moving average rule outperforms, by approximately 50%, a standard buy-and-hold strategy in various investment horizons, often by a very wide margin. Given the latter, the results allow us to enhance the current literature on shipping finance by providing evidence of how simple investment strategies can benefit both retail and institutional investors who do not have direct exposure or experience in the shipping industry by allowing them to include shipping stocks in their portfolios.

KARL: Knowledge Augmented Rule Learning for Informed Biomarker Discovery

Background: Ongoing molecular profiling studies enabled by advances in biomedical technologies are producing vast amounts of ‘omic’ data for early detection, monitoring, and prognosis of diverse diseases. A major common limitation is the scarcity of biological samples, necessitating integrative modeling frameworks that can make optimal use of available data for disease classification tasks. Related data sets are often available from different studies, but may have been generated using different technology platforms. Thus, there is a critical need for flexible modeling methods that can handle data from diverse sources to facilitate the discovery of robust biomarkers that underlie disease regulatory processes. Results: In this paper, we introduce a novel framework called Knowledge Augmented Rule Learning (KARL), which incorporates two sources of knowledge, domain, and data, for pattern discovery from small and high-dimensional datasets, such as transcriptomic data. We propose KARL as a transfer rule learning framework in which knowledge of the domain is transferred to the learning process on data in order to 1) improve the reliability of the discovered patterns, and 2) study the knowledge of the domain when used along with data for modeling. In this work, we generated KARL models on gene expression datasets for five types of cancer, including brain, breast, colon, lung, and prostate. As our knowledge of the domain, we used the Ingenuity Knowledge Base (IKB) to extract genes related to hallmarks of cancer and annotated these prior relationships before learning classifiers from these datasets. Conclusions: Our results show that KARL produces, on average, rule models that are more robust classifiers than the baseline without such background knowledge, for our tasks of cancer prediction using 25 publicly available gene expression datasets. Moreover, KARL helped us learn insights about previously known relationships in these gene expression datasets, along with new relationships not input as known, to enable informed biomarker discovery for cancer prediction tasks. KARL can be applied to modeling similar data from any other domain and classification task. Future work would involve extensions to KARL to handle hierarchical knowledge to derive more general hypotheses to drive biomedicine.

Theoretical and practical motivations for the use of the moving average rule in the stock market

This paper provides some theoretical foundations for using moving average (MA) rules in the stock market. In particular, the paper analyzes the conditional probability of price increments and examines how this probability varies over time. We prove under certain assumptions that the probability of being in an uptrend is greater than the probability of being in a downtrend. This demonstration partially justifies the common use of MA rules in the stock market. Finally, we propose an ex-post empirical analysis to evaluate and compare the performance of some MA rules and other portfolio strategies in the US stock market. In this context, we also suggest a methodology that incorporates these trading rules as alarm rules to predict potential market failures. Our ex-post results confirm the advantages of using these trading rules to predict market trends and crises.

Testing Technical Trading Rules: Evidence from SAARC Countries

Technical analysis is widely accepted tool in professional place which is frequently used for investment decisions. Technical analysis beliefs that there exist patterns and trends and by capturing trends and patterns one can bless with above average profits. We test two technical strategies: Moving averages and Trading Range to question, either these techniques can yield profitable returns with the help of historical data. Representative daily indices of Four countries namely Pakistan, India, Srilanka, Bangladesh ranging from 1997 to 2011 have been examined. In case of Moving Average Rule, both simple and exponential averages have been examined to test eleven different short term and long term rules with and without band condition. Our results delivered that buy signals generate consistent above average returns for the all sub periods and sell signals generate lower returns than the normal returns. Intriguing observation is that Exponential average generates higher returns than the Simple Average. The results of Trading Range Break strategy are parallel with Moving average Method. However, Trading Range Strategy found not to give higher average higher return when compared with Moving Averages Rules and degree of volatility in returns is higher when compared with moving Average rule. In attempt to conclude, there exist patterns and trends that yield above average and below average returns which justify the validity of technical analysis.

Better Rulesets by Removing Redundant Specialisations and Generalisations in Association Rule Mining

Association rule mining is a fundamental task in many data mining and analysis applications, both for knowledge extraction and as part of other processes (for example, building associative classifiers). It is well known that the number of associations identified by many association rule mining algorithms can be so large as to present a barrier to their interpretability and practical use. A typical solution to this problem involves removing redundant rules. This paper proposes a novel definition of redundancy, which is used to identify only the most interesting associations. Compared to existing redundancy based approaches, our method is both more robust to noise, and produces fewer overall rules for a given data (improving clarity). A rule can be considered redundant if the knowledge it describes is already contained in other rules. Given an association rule, most existing approaches consider rules to be redundant if they add additional variables without increasing quality according to some measure of interestingness. We claim that complex interactions between variables can confound many interestingness measures. This can lead to existing approaches being overly aggressive in removing redundant associations. Most existing approaches also fail to take into account situations where more general rules (those with fewer attributes) can be considered redundant with respect to their specialisations. We examine this problem and provide concrete examples of such errors using artificial data. An alternate definition of redundancy that addresses these issues is proposed. Our approach is shown to identify interesting associations missed by comparable methods on multiple real and synthetic data. When combined with the removal of redundant generalisations, our approach is often able to generate smaller overall rule sets, while leaving average rule quality unaffected or slightly improved.