Logic Machine Research Articles

Improving the quality ofhospital sterilization process using failure modes andeffects analysis, fuzzy logic, andmachine learning: experience intertiary dental centre.

Activities practiced in the hospital generate several types of risks. Therefore, performing the risk assessment is one of the quality improvement keys in the healthcare sector. For this reason, healthcare managers need to design and perform efficient risk assessment processes. Failure modes and effects analysis (FMEA) is one of the most used risk assessment methods. The FMEA is a proactive technique consisting of the evaluation of failure modes associated with a studied process using three factors: occurrence, non-detection, and severity, in order to obtain the risk priority number using fuzzy logic approach and machine learning algorithms, namely the support vector machine and the k-nearest neighbours. The proposed model is applied in the case of the central sterilization unit of a tertiary national reference centre of dental treatment, where its efficiency is evaluated compared to the classical approach. These comparisons are based on expert advice and machine learning performance metrics. Our developed model proved high effectiveness throughout the results of the expert's vote (she agrees with 96% fuzzy-FMEA results against 6% with classical FMEA results). Furthermore, the machine learning metrics show a high level of accuracy in both training data (best rate is 96%) and testing data (90%). This study represents the first study that aims to perform artificial intelligence approach to risk management in the Moroccan healthcare sector. The perspective of this study is to promote the application of the artificial intelligence in Moroccan health management, especially in the field of quality and safety management.

Comparison study of a landslide-event hazard mapping using a multi-approach of fuzzy logic, TRIGRS model, and support vector machine in a data-scarce Andes Mountain region

Landslides are a significant global hazard, especially prevalent in regions with high rainfall, active tectonic processes, and rugged topography, such as the Colombian Andean region. Therefore, it is crucial to identify areas prone to landslides in order to protect human lives and mitigate the adverse impacts on national economies, especially in developing countries situated in tropical and mountainous regions. Assessing landslide hazard and susceptibility is a fundamental step in comprehending the fundamental characteristics of slopes susceptible to failure, particularly under extreme rainfall conditions. Various researchers have devised methods and techniques to assess and map landslides, employing heuristic, statistical, and deterministic approaches. This study carried out a geographic information system-based approach for shallow landslides, with the objective to compare different methods for a landslide-event hazard mapping using the landslide records on May 18, 2015, triggered by a rainstorm in the La Liboriana basin (Colombia). In the first place, a fuzzy logic gamma model was applied using landslide conditioning factors. Then, the deterministic model TRIGRS was applied to assess shallow landslides. Finally, a support vector machine (SVM) model was used to obtain an intermediate scale solution. All models consider the rainfall that triggered the aforementioned landslide event. The results indicated that the SVM (radial basis function) model permits to obtain a better performance (AUC = 0.95) in landslide hazard zonation rather than quantitative heuristic fuzzy gamma model (AUC = 0.86) and the deterministic TRIGRS model (AUC = 0.60), obtaining best accurate at predicting the landslide hazard in the study area.

Characterization of Synthetic Health Data Using Rule-Based Artificial Intelligence Models.

The aim of this study is to apply and characterize eXplainable AI (XAI) to assess the quality of synthetic health data generated using a data augmentation algorithm. In this exploratory study, several synthetic datasets are generated using various configurations of a conditional Generative Adversarial Network (GAN) from a set of 156 observations related to adult hearing screening. A rule-based native XAI algorithm, the Logic Learning Machine, is used in combination with conventional utility metrics. The classification performance in different conditions is assessed: models trained and tested on synthetic data, models trained on synthetic data and tested on real data, and models trained on real data and tested on synthetic data. The rules extracted from real and synthetic data are then compared using a rule similarity metric. The results indicate that XAI may be used to assess the quality of synthetic data by (i) the analysis of classification performance and (ii) the analysis of the rules extracted on real and synthetic data (number, covering, structure, cut-off values, and similarity). These results suggest that XAI can be used in an original way to assess synthetic health data and extract knowledge about the mechanisms underlying the generated data.

Hybrid fuzzy support vector machine approach for Coconut tree classification using image measurement

Classification of trees based on morphological parameters is important for identification, taxonomy, ecological research, conservation etc. The manual measurement of these parameters is tedious, laborious, and inconsistent. Even though there are many tree classification methods based on the morphological parameters available in the literature, there is hardly any research in classification of Coconut trees based on morphological parameters. This research proposes a novel hybrid fuzzy support vector machine approach for classification of Coconut trees based on three critical morphological parameters such as height, inclination, and orientation. A fuzzy logic-based parameter measurement from image is used to estimate critical morphological parameters the from the images. An original dataset of 17000 images of Indian west coast tall Coconut trees is created to train and test the proposed method. The classification for each of the three parameters is carried out separately using fuzzy logic and support vector machine and the best classification is chosen using confidence voting method. The final classification of the Coconut trees based on all the three parameters is obtained using weight-based indexing by combining the individual outcome of confidence voting method. The results showed that the proposed architecture gives better performance than state-of-the-art classifiers, with an accuracy of 88.86%. The statistical analysis showed that the proposed architecture is stable and robust than other methods, gives least confidence interval value of ±2.5, ±3.2, ±1.9 for three different datasets other than the original dataset.

Knowledge Authoring for Rules and Actions

AbstractKnowledge representation and reasoning (KRR) systems describe and reason with complex concepts and relations in the form of facts and rules. Unfortunately, wide deployment of KRR systems runs into the problem that domain experts have great difficulty constructing correct logical representations of their domain knowledge. Knowledge engineers can help with this construction process, but there is a deficit of such specialists. The earlier Knowledge Authoring Logic Machine (KALM) based on Controlled Natural Language (CNL) was shown to have very high accuracy for authoring facts and questions. More recently, KALMFL, a successor of KALM, replaced CNL with factual English, which is much less restrictive and requires very little training from users. However, KALMFL has limitations in representing certain types of knowledge, such as authoring rules for multi-step reasoning or understanding actions with timestamps. To address these limitations, we propose KALMRA to enable authoring of rules and actions. Our evaluation using the UTI guidelines benchmark shows that KALMRA achieves a high level of correctness (100%) on rule authoring. When used for authoring and reasoning with actions, KALMRA achieves more than 99.3% correctness on the bAbI benchmark, demonstrating its effectiveness in more sophisticated KRR jobs. Finally, we illustrate the logical reasoning capabilities of KALMRA by drawing attention to the problems faced by the recently made famous AI, ChatGPT.

Uncovering Predictors of Lipid Goal Attainment in Type 2 Diabetes Outpatients Using Logic Learning Machine: Insights from the AMD Annals and AMD Artificial Intelligence Study Group.

Identifying and treating lipid abnormalities is crucial for preventing cardiovascular disease in diabetic patients, yet only two-thirds of patients reach recommended cholesterol levels. Elucidating the factors associated with lipid goal attainment represents an unmet clinical need. To address this knowledge gap, we conducted a real-world analysis of the lipid profiles of 11.252 patients from the Annals of the Italian Association of Medical Diabetologists (AMD) database from 2005 to 2019. We used a Logic Learning Machine (LLM) to extract and classify the most relevant variables predicting the achievement of a low-density lipoprotein cholesterol (LDL-C) value lower than 100 mg/dL (2.60 mmol/L) within two years of the start of lipid-lowering therapy. Our analysis showed that 61.4% of the patients achieved the treatment goal. The LLM model demonstrated good predictive performance, with a precision of 0.78, accuracy of 0.69, recall of 0.70, F1 Score of 0.74, and ROC-AUC of 0.79. The most significant predictors of achieving the treatment goal were LDL-C values at the start of lipid-lowering therapy and their reduction after six months. Other predictors of a greater likelihood of reaching the target included high-density lipoprotein cholesterol, albuminuria, and body mass index at baseline, as well as younger age, male sex, more follow-up visits, no therapy discontinuation, higher Q-score, lower blood glucose and HbA1c levels, and the use of anti-hypertensive medication. At baseline, for each LDL-C range analysed, the LLM model also provided the minimum reduction that needs to be achieved by the next six-month visit to increase the likelihood of reaching the therapeutic goal within two years. These findings could serve as a useful tool to inform therapeutic decisions and to encourage further in-depth analysis and testing.

Smart proxy models art and future directions in the oil and gas industry: A review

This paper presents a review of the state of the art of proxy models application in the oil and gas industry from upstream, midstream, and downstream. The focus on proxy models is because they are the pillar of the digital twins. They compensate for the slow response of the numerical simulation models. Proxy models can get updated very quickly with new data compared to numerical models. The proxy models apply to cross-disciplines such as fluid mechanics, thermodynamics, and electronics. Proxy models are tools for the swift response to the process events when the cost of decision time is high. The history of the proxy model is discussed first followed by a review of the literature. First, a literature review and the history of the proxy model are covered. The objectives and uses of proxy models are then thoroughly described while the evolution and development process of proxy models are detailed. A few proxy model examples are provided to emphasize the significance of the proxy model and technical advancement. Regression, artificial neural networks, fuzzy logic, and support vector machines are the major approaches for delivering proxy models. Each method's strengths and drawbacks are addressed. These case studies show the need for data cleansing, data transformation to the appropriate domain, and a precise model verification and validation strategy for creating a trustworthy proxy model. Industry-wide, the gaps, and difficulties are addressed, including data accessibility, workflow, model health check, operability, and model uncertainty. A review of proxy models revealed that both technical solution acceptance and workflow robustness have greatly increased at the maturity level in proxy model applications in the oil and gas industry. However, the typical workflow is not being used, and many case studies show that crucial steps like verification and validation are not being taken. The key issue identified in the review was that proxy models are derived from analytical and numerical models, which is in contrast to proxy models, which by their nature rely on the data at hand to inform predictions and optimizations. The astounding potential of proxy models in prediction and optimization is still untapped, and more research is needed to improve model quality, incorporate data into the core of the proxy models, increase their robustness, and develop robust performance metrics to address and evaluate the performance, dependability, and timeliness of the proxy models. Currently, proxy models are secondary tools for optimization of the processes and decision making, while in the future outlook is to be the main tool not only in daily surveillance and monitoring but for the optimization process. In this paper, a best practice workflow for the proxy model is proposed for the oil and gas industry. The evolution of proxy models and their level of complexity is reviewed. Most published work on proxy models is built based on the synthetic data and simulation model output. In the applied workflow, most model validation and verification are missed or ignored. Except for a few published works on the real-time usage, the models are barely connected to real-time and they are used for static decision-making process other than real-time usage.

Development of flapping wing robot and vision-based obstacle avoidance strategy.

Due to the flight characteristics such as small size, low noise, and high efficiency, studies on flapping wing robots are being actively conducted. In particular, the flapping wing robot is in the spotlight in the field of search and reconnaissance. Most of the research focuses on the development of flapping wing robots rather than autonomous flight. However, because of the unique characteristics of flapping wings, it is essential to consider the development of flapping wing robots and autonomous flight simultaneously. In this article, we describe the development of the flapping wing robot and computationally efficient vision-based obstacle avoidance algorithm suitable for the lightweight robot. We developed a 27 cm and 45 g flapping wing robot named CNUX Mini that features an X-type wing and tailed configuration to attenuate oscillation caused by flapping motion. The flight experiment showed that the robot is capable of stable flight for 1.5 min and changing its direction with a small turn radius in a slow forward flight condition. For the obstacle detection algorithm, the appearance variation cue is used with the optical flow-based algorithm to cope robustly with the motion-blurred and feature-less images obtained during flight. If the obstacle is detected during straight flight, the avoidance maneuver is conducted for a certain period, depending on the state machine logic. The proposed obstacle avoidance algorithm was validated in ground tests using a testbed. The experiment shows that the CNUX Mini performs a suitable evasive maneuver with 90.2% success rate in 50 incoming obstacle situations.

The Digital Mind: How Computers (Re)Structure Human Consciousness

Technologies of communication condition human sense-making. They do so by creating the social environment we inhabit and extending their structural biases and logics through human use. As such, this essay inquires into the prevailing habits of mind in the digital era. Employing a media ecology of communication, I argue that digital computers and microprocessors are defined by three structural properties and, hence, underlying logics: digitization (binary code), algorithmic execution (input/output), and efficiency (machine logic). Repeated exposure to these logics cultivates a digital mind, a model of thinking, communicating, and sense-making characterized by intransigence, impertinence, and impulsivity. I conclude the essay by exploring the broader implications of a digital mind, paying particular attention to the challenges it poses to democratic politics.

When Machine Logic is Unobvious: The Problem of Artificial Intelligence Transparency from a Legal Perspective

When Machine Logic is Unobvious: The Problem of Artificial Intelligence Transparency from a Legal Perspective

Quantum technology to expand soft computing

Soft computing was founded to unify and advance computing methods beyond the limits of binary variables, Boolean logic and Turing machines. David Deutsch invented a way to use massive quantum parallelism to massively improve the power of Turing machines in some applications. Here we give a roadmap to use quantum parallelism to massively improve the power of soft computing, focusing on tasks in optimization ranging from function optimization, finding a needle in a haystack, optimal control, energy technology and reinforcement learning (Quantum artificial general intelligence, AGI) in a path leading up to optimization of physical plants themselves put into quantum superpositions. The path begins with design and test of prototypes built on platforms such as Nuclear Magnetic Resonance, sparse quantum optics, superconductors (sQuID), quantum dots and new high speed electronics.

Analysis on the Recent Trends in Machine Translation

Machine translation is to translate one language into another language, which has undergone a great evolution. The model of machine translation has been continuously improved, aiming to make the translation effect closer to the artificial translation. This article briefly summarizes the development history of machine translation, and introduces the main models of each stage of development. The initial machine translation mode is the Rule Based Machine Translation (RBMT) and Statistical Machine Translation (SMT). Recent mainstream translation approach enables Neural Machine Translation (NMT). It includes the input and the output, attention mechanism, and BLEU evaluation method. On this basis, there are also many expansion and innovation models, such as GPKD and other models to improve the evaluation effect. In general, machine translation can replace a part of human translation. However, it cannot completely replace human beings, because of the different human thinking and machine logic. People and machines have to cooperate with each other to improve the common efficiency.

Correlation between transverse cerebellar diameter and gestational age in second and third trimester of singleton pregnancies

BACKGROUND & OBJECTIVE: Trans cerebellar diameter stands out as an important fetal parameter for estimating gestational age in second and third trimester when all the other parameters start showing margin of error of 3 to 4weeks. The study was designed with intent to gather more evidence on TCD measurements validity. This will help us in using TCD on routine basis in advance pregnancies. Our objective is to determine the correlation between mean transverse cerebellar diameter and mean gestational age in 20 to 40 weeks of gestation.
 METHODOLOGY: This research is being conducted at radiology department of Social Security Hospital Islamabad from 1-02-2022 till 01-06-2022. Non-probability convenient sampling was done and a total of sixty (n=60) healthy women with a singleton pregnancy between 18 to 40 years of age with gestational age of 20 to 40 weeks as confirmed by ultrasound were enrolled in the study. An expert radiologist used Logic P6 ultrasonography machine during the study. TCD, HC, BPD and FL was measured in each patient and correlated with gestational age. Pearson correlation coefficient was computed using SPSS-17.0.
 RESULTS: Significant and strong positive correlation (r=0.98) and p<0.001 was found between TCD measured by ultrasonography and gestational age at a 0.05 significance level.
 CONCLUSION: Significant and strong positive correlation was found between TCD measured by ultrasonography and gestational age.

A quick review of ethics, design thinking, gender, and AI development

ABSTRACT Ethics, artificial intelligence (AI), and design thinking are current buzz words. The threat of bias-riddled machine learning algorithms is represented media-wide. Research and development initiatives are endeavoring to ‘translate’ ethics into processes and machine logic and design thinking as a method is adopted to gauge the interests and values of a vast range of stakeholders. Gender, its framing, reflection, and critical evaluation in relation to design thinking as a means for developing ethical AI appear to be less represented in scholarly discourse. Against a background of critical theory and gender studies that describe and problematize gender, its construction and norms in socio-technological discourse, the authors of this article aim to generate insight into the current state of gender in design thinking research focused on ethics and AI. A review of scholarly articles revealed trends in popularity of concepts and prominence in the application of design thinking in specific fields (i.e., educational research). Repetition characterizes the more challenging topics or wicked problems. Provocation and investigation of gender from the perspectives of practitioners, creativity, and its influence in design thinking seem all but visible.

Sensitivity of Logic Learning Machine for Reliability in Safety-Critical Systems

Nowadays, artificial intelligence (AI) is bursting in many fields, including critical ones, giving rise to reliable AI that means ensuring safety of autonomous decisions. As the false negatives may have a safety impact (e.g., in a mobility scenario, prediction of no collision, but collision in reality), the aim is to push them as close to zero as possible, thus designing “safety regions” in the feature space with statistical zero error. We show here how sensitivity analysis of an explainable AI model drives such statistical assurance. We test and compare the proposed algorithms on two different datasets (physical fatigue and vehicle platooning) and achieve quite different conclusions in terms of achievable performance that strongly depend on the level of noise in the dataset rather than on the algorithms at hand.

A Sentence Prediction Approach Incorporating Trial Logic Based on Abductive Learning

Sentencing prediction is an important direction of artificial intelligence applied to the judicial field. The purpose is to predict the trial sentence for the case based on the description of the case in the adjudication documents. Traditional methods mainly use neural networks exclusively, which are trained on a large amount of data to encode textual information and then directly regress or classify out the sentence. This shows that machine learning methods are effective, but are extremely dependent on the amount of data. We found that there is still external knowledge such as laws and regulations that are not used. Moreover, the prediction of sentences in these methods does not fit well with the trial process. Thus, we propose a sentence prediction method that incorporates trial logic based on abductive learning, called SPITL. The logic of the trial is reflected in two aspects: one is that the process of sentence prediction is more in line with the logic of the trial, and the other is that external knowledge, such as legal texts, is utilized in the process of sentence prediction. Specifically, we establish a legal knowledge base for the characteristics of theft cases, translating relevant laws and legal interpretations into first-order logic. At the same time, we designed the process of sentence prediction according to the trial process by dividing it into key circumstance element identification and sentence calculation. We fused the legal knowledge base as weakly supervised information into a neural network through the combination of logical inference and machine learning. Furthermore, a sentencing calculation method that is more consistent with the sentencing rules is proposed with reference to the Sentencing Guidelines. Under the condition of the same training data, the effect of this model in the experiment of responding to the legal documents of theft cases was improved compared with state-of-the-art models without domain knowledge. The results are not only more accurate as a sentencing aid in the judicial trial process, but also more explanatory.

Knowledge Authoring with Factual English

Knowledge representation and reasoning (KRR) systems represent knowledge as collections of facts and rules. Like databases, KRR systems contain information about domains of human activities like industrial enterprises, science, and business. KRRs can represent complex concepts and relations, and they can query and manipulate information in sophisticated ways. Unfortunately, the KRR technology has been hindered by the fact that specifying the requisite knowledge requires skills that most domain experts do not have, and professional knowledge engineers are hard to find. One solution could be to extract knowledge from English text, and a number of works have attempted to do so (OpenSesame, Google's Sling, etc.). Unfortunately, at present, extraction of logical facts from unrestricted natural language is still too inaccurate to be used for reasoning, while restricting the grammar of the language (so-called controlled natural language, or CNL) is hard for the users to learn and use. Nevertheless, some recent CNL-based approaches, such as the Knowledge Authoring Logic Machine (KALM), have shown to have very high accuracy compared to others, and a natural question is to what extent the CNL restrictions can be lifted. In this paper, we address this issue by transplanting the KALM framework to a neural natural language parser, mStanza. Here we limit our attention to authoring facts and queries and therefore our focus is what we call factual English statements. Authoring other types of knowledge, such as rules, will be considered in our followup work. As it turns out, neural network based parsers have problems of their own and the mistakes they make range from part-of-speech tagging to lemmatization to dependency errors. We present a number of techniques for combating these problems and test the new system, KALMFL (i.e., KALM for factual language), on a number of benchmarks, which show KALMFL achieves correctness in excess of 95%.

Big graphs

Big data is typically characterized with 4V's: Volume, Velocity, Variety and Veracity. When it comes to big graphs, these challenges become even more staggering. Each and every of the 4V's raises new questions, from theory to systems and practice. Is it possible to parallelize sequential graph algorithms and guarantee the correctness of the parallelized computations? Given a computational problem, does there exist a parallel algorithm for it that guarantees to reduce parallel runtime when more machines are used? Is there a systematic method for developing incremental algorithms with effectiveness guarantees in response to frequent updates? Is it possible to write queries across relational databases and semistructured graphs in SQL? Can we unify logic rules and machine learning, to improve the quality of graph-structured data, and deduce associations between entities? This paper aims to incite interest and curiosity in these topics. It raises as many questions as it answers.

Prediction of factors for Controlling of Green House Farming with Fuzzy based multiclass Support Vector Machine

A smart greenhouse is a scheme with the aim of allowing the plant growth optimally due to the control in temperature, soil moisture, and humidity. It is necessary to go for best possible smart greenhouse controlling system to maneuver the parameters in accordance with the climatic and seasonal changes plant. In this proposed work, the appropriate setting, monitoring of the model parameters like optimal temperature, humidity, and soil moisture in the greenhouse farm available at Modakkurichi near Erode is carried out using fuzzy logic and multiclass Support Vector Machine (SVM) techniques. It is efficiently implemented as the fuzzy trapezoidal membership function for each sample within the hyper-sphere as a linear function of the selected sample’s distance in the non-linear SVM hyperplane. Based on the simulation and experimental results, the fuzzy logic with Multi-class Support Vector Machine method is effective in selection of the rules to make decision. Simulation of the work was carried out in Python using the open source tool COLAB. Statistical parameters are evaluated for the proposed Fuzzy based SVM method. Root Mean Square Error of the proposed controller has the minimum value as 0.962E-02 when compared to other controllers which vary from 1.04 E-02 to 8.27 E-02.

Methods of Ordering in Computer Sciences and Information Technologies

The purpose of the article is to analyze the known methods of ordering in computer science. The research methodology consists of methods of ordered pairs, relations, Gödel numbering, and Glushkov’s system of algorithmic algebras. The scientific novelty is to create a method of both description and transformation of orders. Conclusions. In the methods of ordered pairs, relations, Gödel numbering, mathematical logic, Post and Turing machines, and the modified system of Glushkov’s algorithmic algebras there is no possibility of equivalent transformations of orders which are available in algorithms.