Rules-based Approach Research Articles

Sentimental Analysis on Twitter: Insights from Supervised Learning

Sentimental analysis is use for analyzing the text so that it can determine theemotions what is in the message which can be positive, negative, or neutral. Social media platforms such as twitter, Instagram, Facebook, etc. where public opinions have been expressed a lot. Other sentimental analysis algorithms include the rules-based and hybrid approach for data processing. Sentiment algorithms are also analysed accordingly with in forms of text like sentences, It also contains relevantinterpretations through the information that was provided. In this study, a baseline model was first established, achieving an accuracy to serve as a comparison point for more sophisticated models. The Logistic Regression model outperformed the baseline significantly, demonstrating its effectiveness in accurately classifying sentiments. The Decision Tree Classification model, while an improvement over the baseline was less accurate than Logistic Regression, suggesting potential issues with overfitting and data dependency. The Random Forest Classification model provided a robust alternative, matching the performance of Logistic Regression and benefiting from the ensemble approach to handle diverse patterns in the sentiment data. Keywords: Sentimental analysis, Machine learning, supervised learning, twitter

Reducing Wait Times at Customs to Boost Trade: How Implementing the Trade Facilitation Agreement Can Expand Trade among AfCFTA Countries?

Abstract All WTO members participate in the Trade Facilitation Agreement (TFA), a rules-based bottom-up approach built on monitorable provisions (e.g., the publication of information, advance rulings, appeal or review of decisions, transparency and border agency cooperation) aimed at reducing time in customs. The paper draws on the OECD indicators of the state of implementation of provisions in the TFA summarised in a TFI (Trade Facilitation Index) to estimate the reduction in waiting time at customs for a large sample of 160 countries. Implementing the TFA could be a significant complement to the African Continental Free Trade Area (AfCFTA)'s objectives. The paper's estimates suggest that a realistic implementation of TFA measures could reduce time in customs for imports by 3.7 days and by 1.9 days for exports. Using extraneous estimates from customs-level transactions, this translates to a reduction tariff Ad-Valorem Equivalent (AVE) in the range 3.5%–7% for imports and 8% extra growth for exports. The large differences in interests across AfCFTA participants—landlocked-coastal, resource-rich and resource-poor, large-small—suggest large gains from reducing tariffs on intra-African trade. However, tariff reductions face the zero-sum hurdle of negotiations involving rent transfers across and within countries. By avoiding rent-transfer issues, this paper suggests that taking seriously the TFA provisions would be a powerful complement to the AfCFTA's tariff-reduction agenda.

Interpretable machine learning predicts postpartum hemorrhage with severe maternal morbidity in a lower-risk laboring obstetric population

BackgroundEarly identification of patients at increased risk for postpartum hemorrhage (PPH) associated with severe maternal morbidity (SMM) is critical for preparation and preventative intervention. However, prediction is challenging in patients without obvious risk factors for postpartum hemorrhage with severe maternal morbidity. Current tools for hemorrhage risk assessment use lists of risk factors rather than predictive models. ObjectiveTo develop, validate (internally and externally), and compare a machine learning model for predicting PPH associated with SMM against a standard hemorrhage risk assessment tool in a lower risk laboring obstetric population. Study DesignThis retrospective cross-sectional study included clinical data from singleton, term births (>=37 weeks’ gestation) at 19 US hospitals (2016–2021) using data from 58,023 births at 11 hospitals to train a generalized additive model (GAM) and 27,743 births at 8 held-out hospitals to externally validate the model. The outcome of interest was PPH with severe maternal morbidity (blood transfusion, hysterectomy, vascular embolization, intrauterine balloon tamponade, uterine artery ligation suture, uterine compression suture, or admission to intensive care). Cesarean birth without a trial of vaginal birth and patients with a history of cesarean were excluded. We compared the model performance to that of the California Maternal Quality Care Collaborative (CMQCC) Obstetric Hemorrhage Risk Factor Assessment Screen. ResultsThe GAM predicted PPH with an area under the receiver-operating characteristic curve (AUROC) of 0.67 (95% CI 0.64–0.68) on external validation, significantly outperforming the CMQCC risk screen AUROC of 0.52 (95% CI 0.50–0.53). Additionally, the GAM had better sensitivity of 36.9% (95% CI 33.01–41.02) than the CMQCC screen sensitivity of 20.30% (95% CI 17.40–22.52) at the CMQCC screen positive rate of 16.8%. The GAM identified in-vitro fertilization as a risk factor (adjusted OR 1.5; 95% CI 1.2–1.8) and nulliparous births as the highest PPH risk factor (adjusted OR 1.5; 95% CI 1.4–1.6). ConclusionOur model identified almost twice as many cases of PPH as the CMQCC rules-based approach for the same screen positive rate and identified in-vitro fertilization and first-time births as risk factors for PPH. Adopting predictive models over traditional screens can enhance PPH prediction.

EU’s sustainable finance disclosure regulation: does the hybrid reporting regime undermine the goal to reorient capital to climate action?

ABSTRACT Disclosure and reporting are cornerstones of the European Union’s sustainable finance agenda with the goals of reorienting capital flows towards climate and other sustainable investments and minimizing greenwashing. A key component of the regulatory framework is the Sustainable Finance Disclosure Regulation (SFDR), which requires fund managers to calculate and disclose a ‘sustainable investment’ (SI) percentage, aggregating exposure to activities contributing to climate mitigation and adaptation and the other environmental and social sustainability objectives of the European Union. In turn, financial advisors must use SI percentages when advising customers under the Markets in Financial Instruments Directive II. Defining ‘sustainable investments’ in a robust and consistent way is crucial to the effectiveness of SFDR. Based on a review of the regulatory texts and financial sector participant observations this policy analysis article explores the overlapping guidelines framing how market participants are allowed to define sustainable investments, and the implications for achieving the goals of the sustainable finance agenda. The analysis suggests that the ‘unintentionally hybrid’ SFDR regime may perversely incentivize fund managers to forgo the use of the highly detailed EU Taxonomy rules-based approach that precisely defines climate-related ‘substantial contributions’ and apply the vague principles-based approach found in SFDR Article 2.17. This would allow each financial actor to define and determine independently what constitutes a sustainable investment, circumventing the robust, if imperfect, climate-related rules of the EU Taxonomy. The SFDR regime therefore risks undermining the European Commission’s stated goals of increasing capital allocation to sustainable activities and eliminating greenwashing. Key policy insights: A sustainability disclosure regime allowing the choice between robust rules and vague principles risks creating opportunities for greenwashing and reduced comparability. Fund managers are likely to select definitions that are least difficult to apply and maximize Sustainable Investment percentages. The current EU regime risks tacitly sanctioning the use of weak metrics, in turn slowing the reorientation of capital towards climate-related and other sustainable investments. The EU must at a minimum provide binding guidance on interpreting Article 2.17, require equal prominence for both SI percentages and EU Taxonomy-alignment scores, as well as address the usability issues of the existing Taxonomy.

Comparing social responses to Ebola and Covid-19 in Sierra Leone: an institutional analysis.

This paper compares community responses to Ebola and Covid-19 in two regions of southern and eastern Sierra Leone with reference to the theory of institutional dynamics proposed by the anthropologist Mary Douglas. Institutions, Douglas argued, are conveyed by styles of thought, shaped by the ways human communities, through everyday practices, reinforce systems of classification and denotation. Pandemic advice to 'follow the science' proved problematic, since there is no single institution of science, and institutions never stand alone but are bundled with other institutions, reflecting the manifold and intertwined practices of human social life. The paper explores some of the ways a traumatic epidemic of Ebola Virus Disease in Sierra Leone shaped a distinctive local response to this deadly infectious disease in the absence of an effective vaccine. This local approach emphasised social rules based on ideas about sequestration and testing. Communities then proposed to continue this rules-based approach to the pandemic of Covid-19 and showed little initial enthusiasm for vaccination. With Ebola, the adoption of rules resulted in dramatic drops in infection rates. But Covid-19 spreads in different ways, and good results from the application of social rules were much less apparent. The paper shows how communities began to grapple with this new situation. In some cases, vaccine hesitation was overcome by treating the requirement for vaccination as a new form of social discipline. More generally, it is concluded that epidemiologists need to pay specific attention to institutions and institutional dynamics in order to better understand and anticipate public reactions to new disease threats.

ANALYSIS OF MAGIC FORMULA FOR INVESTMENT RETURN IN INDIAN STOCK

Magic Formula Investing, popularized by Joel Greenblatt, is a strategy that focuses on selecting stocks based on two main criteria: high earnings yield and high return on capital. Earnings yield is the ratio of a company's earnings per share to its stock price, indicating how much profit a company is generating relative to its price. Return on capital, on the other hand, measures how efficiently a company is using its capital to generate profits. The goal of this strategy is to identify undervalued companies that exhibit strong financial performance. By targeting stocks with high earnings yield and return on capital, investors aim to uncover hidden gems in the stock market that may be overlooked by others. This methodical approach to value investing has garnered attention for its relative simplicity and effectiveness in outperforming the market. One of the key advantages of the Magic Formula is its straightforward nature, which makes it accessible to a wide range of investors. Unlike more complex investment strategies that require in-depth financial analysis, the Magic Formula provides a clear and systematic way to identify potential investment opportunities. Overall, Magic Formula Investing offers investors a disciplined and rules-based approach to stock selection, with the aim of achieving superior returns compared to the broader market. While past performance is not indicative of future results, the Magic Formula's track record

The role of ethical leadership in resilient corporations

This paper suggests that to ensure resilient and sustainable organisations, ethical leadership needs to go beyond strict rule compliance, using a four-pronged approach: 1. Collect and monitor broad indicators, quantitative and qualitative, that may signal an increase in ethical risks; 2. Create an open and safe dialogue culture where voicing risks and concerns is actively encouraged. 3. Develop a values-based corporate culture where duty of care, in its widest conception, guides policies and decision making by all members of the organisation. This implies actively supporting those who (i) show genuine concern and care for the organisation; (ii) care for one another and for their staff; (iii) care for stakeholders, including clients and those that may be negatively affected by its operations; 4. Create trust in this values-based culture by ensuring a gradual, people-centred response to inappropriate conduct, away from the traditional rules-based legalistic approach that has fuelled distrust in the system's ability to heal internally.

Optimized Design of a H2-Powered Moped for Urban Mobility

Micro-mobility plays an increasingly important role in the current energy transition thanks to its low energy consumption and reduced contribution to urban congestion. In this scenario, fuel cell hybrid electric vehicles have several advantages over state-of-the-art battery electric vehicles, such as increased driving ranges and reduced recharge times. In this paper, we study the conversion of a commercial electric moped (Askoll eS3®) into a fuel cell hybrid electric vehicle by finding the optimal design of the components through an optimization methodology based on backward dynamic programming. This optimal design and operation strategy can also be implemented with a rules-based approach. The results show that a system composed of a 1 kW proton exchange membrane fuel cell, a 2000 Sl metal hydride hydrogen tank, and a 240 Wh buffer battery can cover the same driving range as the batteries in an electric moped (119 km). Such a hybrid system occupies considerably less volume (almost 40 L) and has a negligibly higher mass. The free volume can be used to extend the driving range up to almost three times the nominal value. Moreover, by using a high-pressure composite tank, it is possible to increase the mass energy density of the onboard energy storage (although compression can require up to 10% of the hydrogen’s chemical energy). The fuel cell hybrid electric vehicle can be recharged with green hydrogen that is locally produced. In detail, we analyze a residential scenario and a shared mobility scenario in the small Italian city of Viterbo.

A New Generation of Rules-based Approach: Mivar-based Intelligent Planning of Robot Actions (MIPRA) and Brains for Autonomous Robots

A New Generation of Rules-based Approach: Mivar-based Intelligent Planning of Robot Actions (MIPRA) and Brains for Autonomous Robots

Topic Identification in Voice Recordings

Abstract The paper shows the understanding of a topic recognition problem like the speech recognition system based on Natural Language Processing (NLP) and the steps of its implementation of a rules-based approach, which is able to classify given audio materials based on predefined topics in real-time. During implementation, a statistical vocabulary was developed. Google Speech API (Application Programming Interface) was employed for subtitling audio materials, and the most ideal time frame for reception was identified through several experiments. The motivation of this work is based on the deficiency of similar simple systems for Hungarian topic recognition, even though numerous international languages already utilize multiple Automatic Sound Recognition (ASR) systems.

Impact of food-related conflicts on self-reported food insecurity

Food security is recognized as an inherent human right, enshrined within the principles of the Agenda 2030. The Global Report of Food Crises 2022 points out 193 million people facing severe food insecurity across 53 countries, posing challenges to decision-makers and institutions. Among the many causes of food crises, violent conflict, economic shocks, and environmental pressures are the most influential. In this work, we focus primarily on the conflict-related domain. Finding a stable relationship between conflict and food insecurity is complex for several reasons: first, the relationship is mutually reinforcing; second, the full impact of conflict on food insecurity may take time to have an effect; and third, conflict itself is a multidimensional phenomenon and can include multiple types of violent events. This research set out to comparatively assess the impact of different types of violence on self-reported food insecurity in three prominent food crisis contexts: Burkina Faso, Syria, and Yemen. A measure of food-related classifying events was developed using a rules-based approach. The analysis showed that this approach can effectively code and classify food-related conflict in diverse contexts. By refining the search string, it becomes possible to capture food-related conflict in various food systems. Our findings point out that the new-build measure of food-related conflict is more strongly correlated to subsequent self-reported insufficient food consumption than other forms of violence. The results demonstrate that this relationship is robust across a range of data collection windows and across discrete time periods of analysis. In summary, the research suggests that focusing on the use of food and food systems as tactics in conflict can be highly valuable for understanding and addressing food insecurity.

AIMEE: An Exploratory Study of How Rules Support AI Developers to Explain and Edit Models

In real-world applications when deploying Machine Learning (ML) models, initial model development includes close analysis of the model results and behavior by a data scientist. Once trained, however, models may need to be retrained with new data or updated to adhere to new rules or regulations. This presents two challenges. First, how to communicate how a model is making its decisions before and after retraining, and second how to support model editing to take into account new requirements. To address these needs, we built AIMEE (AI Model Explorer and Editor), a tool created to address these challenges by providing interactive methods to explain, visualize, and modify model decision boundaries using rules. Rules should benefit model builders by providing a layer of abstraction for understanding and manipulating the model and reduces the need to modify individual rows of data directly. To evaluate if this was the case, we conducted a pair of user studies totaling 23 participants to evaluate AIMEE's rules-based approach for model explainability and editing. We found that participants correctly interpreted rules and report on their perspectives of how rules are beneficial (and not), ways that rules could support collaboration, and provide a usability evaluation of the tool.

COVID-19 pandemic’s effect on the mental health among the Tunisian general population: Associated factors mining via machine learning

The emergence of COVID-19 pandemic has caused a brutal change in the lifestyle of citizens all around the world and greatly affected the mental health of individuals. In Tunisia, many psychological problems have been triggered during the first peak of the pandemic like anxiety, depression, sleep disturbances, and suicide risk. To overcome such disorders, it is crucial to identify the main factors leading to the mental disorders and then develop preventive strategies if a novel form of pandemic or a traumatic event appears. This paper proposes a novel association rules-based approach to characterize the profiles of citizens highly vulnerable to psychological disorders when confronted to traumatic events. The aim of this work is to use machine learning techniques in order to identify the major factors as well as the clusters of features leading to several psychiatric disorders during the COVID-19 pandemic in Tunisia. Many stressors were found to be associated with some psychiatric disorders. The stronger associations were found between doctor consultation and anxiety, COVID test and depression, quarantine and insomnia, and direct contact with a suspected case and peritraumatic distress and dissociation. In addition, it has been found that some factors, like female gender and regular worker, are not leading to mental disorders when they are treated alone, however, they present a high influence on the mental health when they are associated with other factors. For instance, this work discovered that women who have psychiatric history and who always drink coffee are exposed to depression during the pandemic. Other profile of citizens who are highly vulnerable to peritraumatic dissociation concerns students who are confined and who have recent symptoms. The characterization of such vulnerable profiles can provide considerable decision support for medical staff.

Management of diversity and inbreeding when importing new stock into an inbred population.

This article relates to breeding programs that seek to manage genetic diversity. The method maximizes a multicomponent objective function, applicable across breeding scenarios. However, this paper focuses on breeding decisions following immigration of 10 unrelated individuals into a highly inbred simulated population (F ≈ 0.34). We use Optimal Contribution Selection to maximize retention of genetic diversity. However, some treatments add Coancestry Assortative Mating (CAM). This helps to avoid early dilution of immigrant genetic material, maximizing its ability to contribute to genetic diversity in the longer term. After 20 generations, this resulted in considerably increased genetic diversity, with mean coancestries 59% of what random pairing gave. To manage progeny inbreeding, common practice is to reject matings above an upper limit. As a suboptimal rules-based approach, this resulted in 26% decreased genetic diversity and 8% increased inbreeding in the long term, compared with random pairing. In contrast, including mean progeny inbreeding as a continuous variable in the overall objective function decreased final inbreeding by 37% compared with random pairing. Adding some emphasis on selection for a single trait resulted in a similar pattern of effects on coancestry and inbreeding, with 12% higher trait response under CAM. Results indicate the properties of alternative methods, but we encourage users to do their own investigations of particular scenarios, such as including inbreeding depression. Practical implementation of these methods is discussed: they have been widely adopted in domestic animal breeding and are highly flexible to accommodate a wide range of technical and logistical objectives and constraints.

Vegetation Cover Dynamics in the High Atlas Mountains of Morocco

Since the 1990s, Morocco’s agriculture has been characterized by the co-existence and transformation of both modern and traditional smallholder systems. In the Atlas Mountains, the effects of rural–urban transformation have led to intensified irrigated agriculture in some agricultural areas, while others were abandoned. To better understand these effects, this study aimed at (1) analyzing the land use and land cover (LULC) changes, (2) assessing the structure and dynamics of vegetation, and (3) comparing a Support Vector Machine (SVM) classification approach with a seasonal rules-based approach. We, therefore, employed a semi-automatic supervised classification of LULC using Landsat data from the 1990s to the 2020s to distinguish between Open Canopy Vegetation, Bareland, Forest, and Water. Overall accuracies achieved ranged from 88% to 90% in 1990, 2000, 2010, and 2020. SVM results indicated the share of Bareland as >80% of the landscape in all periods. With the seasonal rules-based approach, 10% less Bareland was detected than with the SVM approach. Our findings indicate the limitation of detecting vegetation reflectance in semi-arid mountainous regions such as that prevailing in Morocco using a single machine learning method.

Practical Applications of Tactical Asset Allocation, Risk Premia, and the Business Cycle: A Macro Regime Approach

In <b><i>Tactical Asset Allocation, Risk Premia, and the Business Cycle: A Macro Regime Approach</i></b>, from the March 2023 issue of <b><i>The Journal of Portfolio Management</i></b>, <b>Alessio de Longis</b> and <b>Dianne Ellis</b> of <b>Invesco</b> propose a tactical asset allocation methodology based on identifying key phases of the business cycle and tilting portfolios toward risk premiums that outperform during each phase. They provide a rules-based approach for predicting phases of the business cycle based on leading economic indicators and the global risk appetite. They focus on three risk premiums as the key elements for implementing the methodology: the term premium, the credit premium, and the equity premium. The authors demonstrate the use of their methodology with multiasset and fixed-income portfolio examples. The examples show a potential to generate excess returns, compared to a buy-and-hold benchmark, while maintaining an equivalent level of risk over the long term.

Improving Lyme disease testing with data driven test design in pediatrics

Diagnostic advances have not kept pace with the expansion of Lyme disease caused by Borrelia burgdorferi and transmitted by ticks. Lyme disease clinical manifestations can overlap with many other diagnoses making Lyme disease a critical part of many differential diagnoses in endemic areas. Current diagnostic blood tests rely on a 2-tiered algorithm for which the second step is either a time-consuming western blot or a whole cell lysate immunoassay. Neither of these second step tests allow for rapid results of this critical rule out test. We hypothesized that using western blot confirmation information, we could create computational models to propose recombinant second-tier tests that would allow for more rapid, automated, and specific testing algorithms. We propose here a framework for assessing retrospective data to determine putative recombinant assay components. A retrospective pediatric cohort of 2755 samples submitted for Lyme disease screening was assessed using support vector machine learning algorithms to optimize tier 1 diagnostic thresholds for the Vidas IgG II assay and determine optimal tier 2 components for both a positive and negative confirmation test. In cases where the tier 1 screen was negative, but clinical suspicion was high, we found that 1 protein (L58) could be used to reduce false-negative results. For second-tier testing of screen positive cases, we found that 6 proteins could be used to reduce false-positive results (L18, L39M, L39, L41, L45, and L58) with a final machine learning classifier or 2 proteins using a final rules-based approach (L41, L18). This led to an overall accuracy of 92.36% for the proposed algorithm without a final machine learning classifier and 92.12% with integration of the machine learning classifier in the final algorithm when compared to the IgG western blot as the gold-standard. Use of this framework across multiple assays and institutions will allow for a data-driven approach to assay development to provide laboratories and patients with the improvements in turnaround time needed for this testing.

The EMory BrEast imaging Dataset (EMBED): A Racially Diverse, Granular Dataset of 3.4 Million Screening and Diagnostic Mammographic Images.

Supplemental material is available for this article. Keywords: Mammography, Breast, Machine Learning © RSNA, 2023.

Principles-based risk regulatory reforms and management control practices: a field study

PurposeGovernment reforms have seen shifts from rules-based to principles-based risk regulatory governance. This paper examines the effects of principles-based risk regulatory reforms on public sector risk management (RM) and management control practices in public sector organizations (PSOs).Design/methodology/approachThe principles-based regulation focuses on providing autonomy to PSOs while maintaining control over their actions without direct intervention. This resonates with Foucault's notion of how modern forms of governments operate. The research is informed by Foucault's concept of governmentality. The authors conducted a qualitative field study of an Australian PSO, gathering and analysing data from interviews, focus groups, and archival documents.FindingsThe findings show the capillary modes by which principles-based risk regulatory regime penetrates and works with management control practices in pursuit of regulatory goals within the PSO the authors studied. In addition, the authors find that the principles-based approach (focusing on autonomy) and rules-based approach (focusing on control) are not opposites in kind and effect but rather, autonomy should be understood as a central pillar of control. Furthermore, the findings show how cultural controls and formal controls are not in conflict but are interconnected in RM practices, with cultural controls providing control architecture for RM and formal control translating the control architecture into routines. Finally, the study provides insights into how enterprise risk management (ERM) provides capabilities for and routinizes RM practices in a PSO and the management control systems (MCS) that enabled this to occur.Originality/valueThe paper provides novel insights into how MCS are infiltrated, mobilized and deployed to enact principles-based risk regulatory reforms. These insights are useful for regulators, practitioners and researchers.

Recursive encoder network for the automatic analysis of STEP files

Automated tools which can understand and interface with CAD (computer-aided design) models are of significant research interest due to the potential for improving efficiency in manufacturing processes. At present, most research into the use of artificial intelligence to interpret three-dimensional data takes input in the form of multiple two-dimensional images of the object or in the form of three-dimensional grids of voxels. The transformation of the input data necessary for these approaches inevitably leads to some loss of information and limitations of resolution. Existing research into the direct analysis of model files in STEP (standard for the exchange of product data) format tends to follow a rules-based approach to analyse models of a certain type, resulting in algorithms without the benefits of flexibility and complex understanding which artificial intelligence can provide. In this paper, a novel recursive encoder network for the automatic analysis of STEP files is presented. The encoder network is a flexible model with the potential for adaptation to a wide range of tasks and finetuning for specific CAD model datasets. Performance is evaluated using a machining feature classification task, with results showing accuracy approaching 100% and training time comparable to that of existing multi-view and voxel-based solutions without the need for a GPU.