Customized Rule-Based Model to Identify At-Risk Students and Propose Rational Remedial Actions

Detecting at-risk students provides advanced benefits for reducing student retention rates, effective enrollment management, alumni engagement, targeted marketing improvement, and institutional effectiveness advancement. One of the success factors of educational institutes is based on accurate and timely identification and prioritization of the students requiring assistance. The main objective of this paper is to detect at-risk students as early as possible in order to take appropriate correction measures taking into consideration the most important and influential attributes in students’ data. This paper emphasizes the use of a customized rule-based system (RBS) to identify and visualize at-risk students in early stages throughout the course delivery using the Risk Flag (RF). Moreover, it can serve as a warning tool for instructors to identify those students that may struggle to grasp learning outcomes. The module allows the instructor to have a dashboard that graphically depicts the students’ performance in different coursework components. The at-risk student will be distinguished (flagged), and remedial actions will be communicated to the student, instructor, and stakeholders. The system suggests remedial actions based on the severity of the case and the time the student is flagged. It is expected to improve students’ achievement and success, and it could also have positive impacts on under-performing students, educators, and academic institutions in general.

Does your partnership deed address performance?

Justin Cumberlege from specialist healthcare law firm Hempsons, provides some guidance on how to address under-performing partners, or conduct issues, in a partnership deed

Diagnosis and Treatment of Hypertension Among People Aged 45 Years and Over in India: A Sub-national Analysis of the Variation in Performance of Indian States

Introduction: Cardiovascular disease (CVD) is the single largest contributor to non-communicable disease (NCD) deaths, with hypertension contributing to a significant proportion of these deaths. This study aims to provide estimates of the prevalence, awareness, treatment and control of hypertension at sub-national levels in India and identifies well and under-performing states with respect to the diagnosis and treatment of hypertension.Methods: The study utilises data from the Longitudinal Study of Ageing in India (LASI), a nationally representative survey of more than 72,000 individuals. Age-sex adjusted prevalence rates of self-reported hypertension was calculated using the direct standardisation method. Multivariable logistic regression was performed to assess the association of self-reported hypertension with the various individual co-morbidity, lifestyle, and household factors. Self-reported prevalence was compared with an objective measure of hypertension for each state, and funnel plots were constructed to assess the performance of states.Results: Our findings suggest that the overall prevalence of age-sex adjusted self-reported hypertension was 25.8% in India with significant variation among states. Results based on logistic regression confirm that those individuals who are elderly, obese, belong to a higher socio-economic group and have associated co-morbidities are at increased odds of reporting hypertension. Overall, 4 out of 10 adults over 45 years of age in India are not aware of their hypertensive condition, and of those who are aware, 73% are currently taking medication, and only 10% of these have their hypertension under control. Based on the performance, states were classified into high and low performing categories. States with an increased proportion of population below the poverty line had significantly lower performance with respect to the diagnosis of hypertension, whereas states with higher literacy rates and greater availability of specialist doctors at community health centres (CHCs) had significantly better performance with respect to treatment-seeking behaviour.Conclusion: The findings of this study and its policy implications are discussed. Based on state performance, strategies are proposed in terms selective targeting vs. population-based strategies. High impact states and sub-groups are identified where intense efforts are needed to tackle the growing menace of hypertension in India.

The Influence of Servant Leadership and Motivation on the Service of Health Care Units in Way Kanan Regency

The results of evaluation program by The Way Kanan Health Department in late 2013 shows 47 cases of death among toddlers, 7 cases of malnutrition, 2 cases of paralysis with withered body. This might have been an indication of the presence of under-performing servants in health care units. Two of the many factors influencing their performance are leadership and motivation. This study aims to analyse the influence of servant leadership and motivation on the general performance of a health care unit in Way Kanan Regency, Lampung, Indonesia. Cross sectional approach and survey analysis method were used. 122 officers of Baradatu Health Care Unit and Pisang Baru Health Care Unit 122 people were taken as the population. The result shows significant relationship between servant leadership and motivation to the performance (p <0.05). The servant leadership variable has got the greatest influence on the accuracy of clinical decision making than the professional knowledge and behaviour with OR = 4,476. It is suggested that the District Health Office of Way Kanan Regency create: a model of servant leadership as an alternative to the existing leadership models, tighten the control on the program, and conduct more training to improve the quality of human resources and their performance at the health care units. Keywords: servant leadership, motivation, performance..

Ensemble Stock Market Prediction using SVM,LSTM, and Linear Regression

<div>Abstract: Stock forecasting is challenging because of stock volatility and dependability on external factors, such as economic, social, and political factors. This motivates investors to seek tools to identify stock trends to reap profits.</div><div><div>In this research, we compared several heterogeneous ensembles for financial forecasting, including averaging, weighted, stacking, and blending ensembles. In addition, we used a random forest regressor as the baseline.<br></div><div>Regression was used to predict the next day’s closing stock price. We used classification to label closing stock value as HIGH or LOW by comparing with the opening stock value of a particular company. We used Long Short Term Memory (LSTM) models, Linear Regression, and Support Vector Machines (SVM) as individual models. Further, we analyzed 10 years of historical data of the most active 20 companies of the NASDAQ stock exchange for implementing ensemble models.<br></div><div>In conclusion, experimental results depict blending ensembles perform the best out of compared ensembles in financial forecasting. Further, they reveal SVM is under-performing, LSTM outputs are satisfactory, while linear regression produced promising results.<br></div></div><div>Data: Data for this research was gathered from online available sources from the NASDAQ American stock exchange.</div><div>We gathered data for most active 20 companies and 10 years of historical data from 21st September 2019 backwards. We used 40044 data points in total.</div>

Construction Project Performance: Inhibiting Factors for Stakeholder

Globally, the construction industry is a catalyst for economic development. This is because it is the bedrock for economic activities. Over the years, the construction industry has been criticised for under-performing which brings about a decline in productivity. In order to improve construction project performance for infrastructural delivery, there are factors to be considered, inter alia, construction material related factors, construction machinery related factors, and project management related factors. In achieving this objective, a questionnaire survey was expedited to purposive practioners to evaluate the relative importance index of these factors. The paper reveals that in the category of construction material related factors, unsuitable locations for material and late delivery of construction materials topped the list with a MS value of 4.53 and 4.15, respectively; in the category of construction machinery related factors, poor maintenance of tools and machinery and difficulties in hiring construction tools and machinery topped the list with a MS value of 4.54 and 4.50, respectively; while in the category of project management related factors, efficient time management and project quality management topped the list with a MS value of 4.83 and 4.70, respectively. In addition, performance improvement factors were also highlighted.

The role of knowledge networks in facilitating the creation of climate information services

&lt;p&gt;Knowledge networks are collections of individuals and teams who work together across organizational, spatial and disciplinary boundaries to invent and share a body of knowledge. Climate services are tools and application that support decision-making by transforming raw climate data into tailored information. They call for co-development practices in place and for successful collaboration between different stakeholders. Knowledge networks for climate services are intermediaries that facilitate the interaction between upstream (&lt;em&gt;providers&lt;/em&gt;) and downstream (&lt;em&gt;user&lt;/em&gt;) actors operating at various scales (local, national, regional and supranational). They assist the decision-making process of a wide set of users by creating windows of opportunity and by delivering usable climate information. The aim of this work is to frame and assess the efficiency of knowledge networks for climate services in promoting innovation and facilitate its diffusion. First, we characterize knowledge networks learning from insights of a multidisciplinary literature. Second, we analyse the purpose, the process and the audience of each knowledge network for climate services by screening their programmatic documents. We then assess the efficiency of knowledge networks by performing content analysis of interviews with knowledge network managers and by checking for the existence of inconsistencies or gaps with the initial objectives. We find knowledge networks for climate services pursue four objectives: coordination, innovation promotion, science-policy interface and support to members. We also find inadequate tools to monitor the members activities, but a strong positioning within the climate services domain. On the communication side, knowledge networks for climate services mostly interact with developers of climate services but they face challenges in sharing the members&amp;#8217; activities with users. Our work fills a significant knowledge gap and helps providing new tools of performance assessment in absence of a clearly defined methodology. The identification of bottlenecks and under-performing mechanisms in the climate information services sphere allows the elaboration of strategies to improve the status quo and facilitates the diffusion of these innovations.&lt;/p&gt;

Managing teaching and learning: integrating instructional and transformational leadership in South African schools context

PurposeThe purpose of this study was to examine the integration of instructional and transformational leadership models of leadership in sustaining quality teaching and learning in schools. The study sought to establish how principals integrate instructional and transformational leadership in enhancing learner performance.Design/methodology/approachThe study employed qualitative methods of collecting and analysing data. The principal sources of data were six face-to-face semi-structured interview questions with school principals from selected schools in rural South Africa. Qualitative evidence was collected from six principals selected through purposive sampling. The selection of participants was based on the criteria that there was evidence of employing instructional and transformational leadership.FindingsFindings from the study provided evidence that instructional and transformational leadership approaches were used to change under performing schools. There was evidence of individualised consideration and principals supporting teachers through providing rewards and motivation. It was established that principals build a school culture that promotes successful academic improvement. The study showed that the integration of instructional and transformational models of leadership leads to a climate that promotes a culture of teaching and learning.Research limitations/implicationsThe study covered six schools in South Africa. Findings from the study have implications that principals are cornerstones to achieving quality teaching and learning in schools.Practical implicationsThe study was conducted in schools that were seen to adopt instructional and transformational leadership. This study is among the most important studies that were conducted in South Africa on the role of leadership in enhancing a culture of teaching and learning.Social implicationsThe study has critical implications for policy making and influences on school leadership in general and the adoption of strategies, policies and models that can improve teaching and learning. The study highlights the importance of integrating leadership models.Originality/valueThis is an original study conducted in South Africa and data was conducted through face-to-face interviews to seek for opinions from participants in their original settings.

Real-Time Obstacle Detection Based on Image Semantic Segmentation and Fusion Network

During fruit production, the robots must walk stably across the orchard, and detect the obstacles in real time on its path. With the rapid process of deep convolutional neural network (CNN), it is now a hot topic to enable orchard robots to detect obstacles through image semantic segmentation. However, most such obstacle detection schemes are under performing in the complex environment of orchards. To solve the problem, this paper proposes an image semantic fusion network for real-time detection of small obstacles. Two branches were set up to extract features from red-green-blue (RGB) image and depth image, respectively. The information extracted by different modules were merged to complement the image features. The proposed network can operate rapidly, and support the real-time detection of obstacles by orchard robots. Experiments on orchard scenarios show that our network is superior to the latest image semantic segmentation methods, highly accurate in the recognition of high-definition images, and extremely fast in reasoning.

Undergraduate Students Academic Progress Reporting Using UPReS: A Feed Forward Approach

Academic performance monitoring is traditionally based on feedback approach. A disadvantage of this approach is that any remedial action would be too late to be implemented. Given that higher education institutions are striving towards achieving graduate on time objectives, an innovative feed forward approach is highly needed. Undergraduate Progress Reporting System (UPReS) is an innovative monitoring and reporting system to monitor academic performance among undergraduate students using electronic spreadsheet. UPReS enables users to forecast academic performance and to identify under-performing students which allows for early intervention programs to be implemented. Using qualitative methodology, this research found that UPReS is able to overcome the limitations of current academic progress monitoring system and offers benefits to students, lecturers and higher education institutions.