Search

Lead generation refers to the identification of potential topics (the 'leads') of importance for journalists to report on. In this article we present μ XL, a new lead generation tool based on a microservice architecture that includes a component of explainable AI. μ XL collects and stores historical and real-time data from web sources, like Google Trends, and generates current and future leads. Leads are produced by a novel engine for hypothetical reasoning based on temporal logical rules, which can identify propositions that may hold depending on the outcomes of future events. This engine also supports additional features that are relevant for lead generation, such as user-defined predicates (allowing useful custom atomic propositions to be defined as Java functions) and negation (needed to specify and reason about leads characterized by the absence of specific properties). Our microservice architecture is designed using state-of-the-art methods and tools for API design and implementation, namely API patterns and the Jolie programming language. Thus, our development provides an additional validation of their usefulness in a new application domain (journalism). We also carry out an empirical evaluation of our tool. [ABSTRACT FROM AUTHOR]

Counterfactual explanations are increasingly used as an Explainable Artificial Intelligence (XAI) technique to provide stakeholders of complex machine learning algorithms with explanations for data-driven decisions. The popularity of counterfactual explanations resulted in a boom in the algorithms generating them. However, not every algorithm creates uniform explanations for the same instance. Even though in some contexts multiple possible explanations are beneficial, there are circumstances where diversity amongst counterfactual explanations results in a potential disagreement problem among stakeholders. Ethical issues arise when for example, malicious agents use this diversity to fairwash an unfair machine learning model by hiding sensitive features. As legislators worldwide tend to start including the right to explanations for data-driven, high-stakes decisions in their policies, these ethical issues should be understood and addressed. Our literature review on the disagreement problem in XAI reveals that this problem has never been empirically assessed for counterfactual explanations. Therefore, in this work, we conduct a large-scale empirical analysis, on 40 data sets, using 12 explanation-generating methods, for two black-box models, yielding over 192,000 explanations. Our study finds alarmingly high disagreement levels between the methods tested. A malicious user is able to both exclude and include desired features when multiple counterfactual explanations are available. This disagreement seems to be driven mainly by the data set characteristics and the type of counterfactual algorithm. XAI centers on the transparency of algorithmic decision-making, but our analysis advocates for transparency about this self-proclaimed transparency. [ABSTRACT FROM AUTHOR]

The Bdi model of rational agency has been studied for over three decades. Many robust multiagent systems have been developed, and a number of Bdi logics have been studied. Following this intensive development phase, the importance of integrating Bdi models with inconsistency handling and revision theory have been emphasized. There is also a demand for a tighter connection between Bdi-based implementations and Bdi logics. In this paper, we address these postulates by introducing a novel, paraconsistent logical Bdi model close to implementation, with building blocks that can be represented as Sql/rule-based databases. Importantly, tractability is achieved by reasoning as querying. This stands in a sharp contrast to the high complexity of known Bdi logics. We also extend belief shadowing, a shallow and lightweight alternative to deep and computationally demanding belief revision, to encompass agents' motivational attitudes. [ABSTRACT FROM AUTHOR]

This paper summarises several contributions to the theory of belief change by the authors' dissertation thesis. First, a relational characterization of belief revision for Tarskian logics is considered, encompassing first-order predicate logic, description logic, modal logics and many monotonic logics with model-theoretic semantics. Those logics where total preorders are the standard semantics for revision are characterized. The second contribution considered is a theory of belief revision that builds upon the idea that agents are limited in what the outcome of a revision is. Furthermore, advancements in principles for iterated belief contraction given in the thesis are outlined. [ABSTRACT FROM AUTHOR]

This paper introduces and studies the sequential composition and decomposition of propositional logic programs. We show that acyclic programs can be decomposed into single-rule programs and provide a general decomposition result for arbitrary programs. We show that the immediate consequence operator of a program can be represented via composition which allows us to compute its least model without any explicit reference to operators. This bridges the conceptual gap between the syntax and semantics of a propositional logic program in a mathematically satisfactory way. [ABSTRACT FROM AUTHOR]

We illustrate how a variety of logical methods and techniques provide useful, though currently underappreciated, tools in the foundations and applications of reasoning under uncertainty. The field is vast spanning logic, artificial intelligence, statistics, and decision theory. Rather than (hopelessly) attempting a comprehensive survey, we focus on a handful of telling examples. While most of our attention will be devoted to frameworks in which uncertainty is quantified probabilistically, we will also touch upon generalisations of probability measures of uncertainty, which have attracted a significant interest in the past few decades.

Integrative art therapy has achieved great results in improving neurosis, palliative care, mental development of special children, and mental health education of adolescents. Integrative art therapy is an applied technique that integrates artistic creation and psychotherapy. This topic studies the influence of integrated art therapy on adolescent mental health based on big data analysis, and establishes a big data analysis model of adolescent mental health. Through DM(data mining), the most valuable information is extracted, expressed in an easy-to-understand way, and analyzed and evaluated accordingly. In this process, the information should be filtered, hoping to get the information that meets the purpose of mining. Descriptive mining is used to describe the general properties of the mined data. If we want to make predictions by inferring the current data, we should use predictive mining. The results show that the scores of each item factor of SCL-90 self-rating scale in the experimental group have been improved obviously. It is mainly manifested in: somatization, obsessive-compulsive symptoms, interpersonal sensitivity, depression, hostility, terror and paranoia. The scores of these seven items have all dropped below 1.5. The median probability of using C4.5 model to predict the mental state as “abnormal” is 0.8135, and the lowest probability of using BPNN (BP neural network) model to predict the mental state as “abnormal” is 0.6082. This provides an idea for designing a psychological crisis prevention system based on the comprehensive C4.5 and BPNN technologies.

This article presents an innovative method for predicting transformer temperature and faults in distribution substations using a digital twin model combined with deep learning techniques. By constructing a digital model of the transformer, real-time monitoring and precise simulation of its operating status are achieved. In the prediction process, convolutional neural networks (CNN) and long short-term memory networks (LSTM) are fused to mine data features deeply and predict the future state of the transformer. The results show that this method demonstrates significant advantages in transformer temperature and fault prediction, with an accuracy rate as high as 96.55%. Moreover, the error rate of this method has been significantly reduced through comparative experimental verification. In addition to ensuring high accuracy, this method achieves a false alarm rate of less than 0.12% and an average detection time of only 1.35 seconds, further highlighting its effectiveness in practical applications. Therefore, the transformer temperature and fault prediction system developed in this article for distribution substations can effectively improve the stability and safety of the electrical power system (EPS) and provide new and powerful support for the intelligent management and maintenance of transformers.

With the rapid development of science and technology, computer-aided technology has been widely used in the field of education, but in the field of innovation and entrepreneurship education (Hereinafter referred to as IEE), there are still problems such as uneven distribution of resources and the disconnection between teaching content and actual needs. This paper puts forward a new model framework of computer-aided IEE, which is student-centered and practice-oriented. Through clear teaching objectives, rich course content, diverse teaching methods, and a scientific evaluation system, students’ innovative consciousness and entrepreneurial ability are comprehensively improved. The course covers innovative thinking, business models, market research, and other theoretical knowledge, and introduces virtual reality (VR) and augmented reality (AR) technologies to simulate the real entrepreneurial process and provide a practical platform. In the aspect of algorithm application, the research combines the content recommendation algorithm and collaborative filtering recommendation algorithm, constructs accurate user portraits by analyzing students’ learning behavior data, and matches them according to the characteristics of learning resources to recommend personalized learning resources for students. At the same time, the learning path optimization algorithm is developed, and the personalized and efficient learning path is planned by using the shortest path algorithm in graph theory to ensure that students can master the required knowledge in the shortest time. The experimental part designed a one-semester teaching experiment, and compared the differences between the experimental group and the control group in academic performance, learning participation, and satisfaction. The results show that the computer-aided IEE model significantly improves students’ academic performance, learning participation, and satisfaction, which verifies the effectiveness of the model. The research on the model and algorithm of computer-aided IEE proposed in this paper provides new ideas and methods for IEE, and helps to cultivate more high-quality talents with innovative thinking and entrepreneurial ability.

This study aims to explore the application of computer vision technology in smart home environments and its influence on space design optimization. Through the comprehensive application of image recognition and processing technology, the behavior patterns of family members, the placement status of household items, and the real-time changes in the indoor environment in smart home systems are deeply analyzed. The experimental results show that computer vision technology can effectively improve smart home systems’ perception and analysis ability, providing data support for automatically adjusting indoor environments and providing personalized service. At the same time, this study also focuses on the optimization strategy of space design based on computer vision technology and puts forward a series of humanized design schemes through reasonable arrangement of cameras and sensors, real-time analysis of user behavior data and environmental parameters, aiming at improving living comfort and achieving efficient use of energy. This study reveals the internal relationship between computer vision technology and space design, which complement each other and jointly promote the intelligent and humanized development of smart homes.

The full English name of VR (Virtual Reality) is a new technology in the computer field. This technology has been widely used and invested in most fields, which shows its reliability and strong computing power. This technology has also played a very important role in the courses taught in colleges and universities. Because of the addition of this technology in college teaching, both language and physical and chemical disciplines have achieved very good results in college teaching, which is why all walks of life also value VR. However, as far as the current situation is concerned, VR still has many problems and difficulties that need to be solved, which also reminds us that we need to look at each issue dialectically. This paper studies the construction of an online English teaching management system in colleges and universities based on VR to achieve scientific and systematic teaching methods and good teaching results. The test results show that the quality of online college English teaching using VR technology has reached 78.93, which is 24.36 higher than that of traditional teaching methods. Therefore, the use of VR technology in English teaching has its unique advantages. This paper can also carry out effective experiments for different experimental objects.

As smart grids increase, the scope of power dispatch systems has broadened, encompassing not just traditional dispatch services but also multifaceted information services, encompassing data fusion, heterogeneous system integration, and big data analytics. However, managing intricate information businesses like big data analysis poses numerous challenges for the current power dispatch system, hindering its ability to keep up with escalating business demands. We introduce a cloud computing and big data analytics-based design scheme for a power dispatch data processing and automation management system to address this. Leveraging the distributed computing prowess of cloud computing platforms, the system ensures swift processing and analysis of vast power dispatch data. Additionally, by harnessing big data analysis techniques, the system delves into historical data, uncovers potential operational patterns and risk areas, and offers insights for optimizing the Electric Power System’s (EPS) operations. Experimental outcomes demonstrate the system’s remarkable proficiency in enhancing data processing, real-time control, and automation management capabilities, thereby bolstering the growth of intelligent power dispatch systems with robust technical backing.

This study discusses the application value of behavior analysis based on deep learning in the evaluation of depression in art students. Because of the professional characteristics and creative pressure, art college students are at high risk of mental health, among which the incidence of depression is increasing year by year, which has a serious impact on their studies and quality of life. With the rapid development of AI technology, deep learning algorithms show significant advantages in processing complex data and pattern recognition. In this study, by collecting the daily behavior data of art college students and combining it with a deep learning algorithm, an efficient depression evaluation model was constructed. The model aims to realize the early identification and evaluation of depressive symptoms of art college students and provide new methods and means for mental health management. The study collected data using various methods such as questionnaire surveys, mobile application tracking, and social media data crawling, and went through detailed data preprocessing steps, including missing value processing, outlier detection, data standardization, and feature selection, to ensure data quality and model training effectiveness. Subsequently, this study designed a deep learning model (CNN-LSTM) based on the combination of Convolutional Neural Network (CNN) and Long Short Term Memory Network (LSTM), which can capture temporal dependencies and spatial relationships between features in the data, thereby improving the accuracy of depression assessment. The empirical findings demonstrate that the CNN-LSTM integrated model has attained remarkable accuracy in assessing the depressive tendencies of art students, underscoring the efficacy of deep learning techniques in behavioral analysis. This research further scrutinizes the impact of various attributes on the predictive outcomes, highlighting the significance of social interaction frequency, academic stress, and artistic engagement levels in depression assessment.

In recent years, the rapid development of artificial intelligence (AI) technology has brought new opportunities to the field of education. With its powerful data processing and analysis capabilities, AI technology has shown great potential in the integration of educational resources and personalized teaching. Specifically in the realm of design education, AI technology holds immense potential to enhance our comprehension of the cultural essence of urban public spaces, elevate the standards of design education, and thereby foster a generation of design talents equipped with both innovative thinking and practical proficiency. The objective of this study is to delve into the application and impact of AI technology in the educational setting, against the backdrop of cultural preservation and urban public space innovation. By conducting a comparative analysis between an experimental group and a control group, this research aims to thoroughly examine the role AI technology plays in augmenting students’ spatial design proficiency, cultural comprehension, and innovative thinking capabilities. The research results show that AI technology significantly improves students’ abilities in the above three aspects by providing personalized learning paths, rich learning resources, and real-time learning feedback. Specifically, students’ spatial design abilities such as spatial composition and color matching have been improved, their ability to understand and appreciate different cultures has also been enhanced, and their innovative thinking and imagination have also been effectively stimulated. This study provides the theoretical basis and practical guidance for educators to better integrate AI technology into teaching, which helps promote the inheritance and innovation of urban public space culture.

Amidst the swift advancement of smart grid technology, traditional power dispatching methods have become inadequate in addressing escalating power needs and intricate system management prerequisites. By incorporating a deep learning model, we have refined these methods, facilitating data-driven dispatching decisions and optimizing power resource allocation and dispatching efficiency. Our experimental outcomes reveal that the Long Short-Term Memory network (LSTM) excels in handling intricate time series data, boasting superior accuracy and convergence rates compared to the Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN). Detailed performance evaluations confirm LSTM’s proficiency in capturing long-term dependencies and processing time series traits inherent in power dispatching data. Furthermore, a 10-fold cross-validation underscores the LSTM model’s stability and generalizability. In essence, this study concludes that in the realm of power dispatching automation, the LSTM deep learning model demonstrates remarkable effectiveness and holds vast potential, anticipating crucial support for the reliable operation and optimal dispatching of the electrical power system (EPS).

With the rapid development of urbanization and the continuous growth of population, the design and planning of high-rise residential buildings have become increasingly important. The purpose of this study is to explore the space optimization design method of high-rise residential buildings based on genetic algorithm(GA), focusing on the comparative analysis between traditional GA and Adaptive genetic algorithm(AGA). In this paper, AGA is used to establish the spatial optimization model of high-rise residential buildings. By dynamically adjusting the parameters of the algorithm, AGA makes the algorithm better adapt to the characteristics of the problem and improves the search efficiency. The results show that AGA is superior to traditional GA in global convergence probability, especially when the population size is large. AGA improves the adaptability and robustness of the algorithm by dynamically adjusting the crossover and mutation probability. AGA has better flexibility and adaptability in the design of high-rise residential buildings and is expected to provide more optimized solutions for solving complex design problems. The findings of this study provide a useful reference for innovation and sustainable development in the field of high-rise building design and also provide practical methods and tools for the application of GA.

Nowadays, with the swift advancement of Artificial Intelligence (AI) technology, its applications have become widespread across diverse fields. AI is no longer a mere abstract idea but has seamlessly integrated into our daily lives, bringing numerous conveniences through its myriad benefits. One such domain where AI has made significant inroads in college physical education and training. The integration of Intelligent Computer-Aided Instruction (ICAI) with computer-assisted teaching systems, AI-powered wearable devices, motion capture systems in sports training, and virtual demonstration technology for simulating athletic movements has greatly enhanced both the precision of physical education and the efficacy of physical training. AI continues to evolve rapidly, indicating vast potential for further development in its integration with physical education and training. This paper highlights the widespread adoption of AI in sports and delves into its specific applications within this domain. The findings reveal that the algorithm employed in this context excels in identifying sports movement features, outperforming the comparison algorithm by 27.65%. Moreover, it precisely pinpoints the edge contours of human movement. In comparison to traditional Support Vector Machines (SVM), Convolutional Neural Networks (CNN) exhibit clear advantages during the later stages of operation, reducing errors by 36.69%. The experimental results underscore the importance of comprehensive human body detection in ensuring stable and accurate sports action tracking.

At present, most graphic design methods of 3D animation scenes only get a small part of 3D animation scenes, and all of them are in a 3D coordinate system, with observers as the core, so it is difficult to express the depth information of 3D animation scenes. This project intends to study a plane design method for 3D animation scenes based on deep learning. CNN (Convolutional Neural Network) is used to build a multi-view 3D animation scene generation network, and 3D geometry and structure of objects are reconstructed through multiple or a group of images. On this basis, the feature extraction method of 3D animation scenes is studied, and the collaborative learning model of multiple networks is established to improve the modeling accuracy of 3D animation scenes. The experimental results show that the network model is superior to the method based on multi-view and 0-1 voxel in detecting retrieval performance, and the accuracy rate can reach 91.725%. The multi-view 3D animation scene generation method in this paper has achieved better results than the current advanced methods, which proves that the multi-view feature fusion network proposed in this paper is a more reasonable method to fuse multi-view image features.

Psychological health education is the main battlefield for promoting the mental health of college students. This article studies the impact of ideological and political education in universities on the mental health of college students. Research on Student Mental Health Based on DL. A student emotion recognition model based on DL (deep learning) has been established. The separable CNN (Convolutional neural network) is used to detect the face in the image, and the face is located and tracked through the tracker. After normalizing the facial image, it is input into a deep separable CNN for classification. The results indicate that the regression equation can explain 74.106% of the total variation. The political characteristics of Demographics characteristics have a significant impact on college students’ political entity identity, while gender, grade, and major have no significant impact on college students’ Party identification. Social practice and campus culture have a significant positive impact on the political entity identity of college students. Compared with traditional machine learning-based emotion recognition methods, the classification accuracy of the proposed method in this paper has been improved by 8.036%, and research based on DL technology has significant advantages in accuracy.

This study focuses on innovative practices in sustainable urban planning, demonstrating significant advancements in key areas such as solar panel efficiency, rainwater harvesting capacity, community garden space, and bike-sharing station accessibility through in-depth experimentation and analysis. The research results show that the energy conversion rate of solar panels reached 25%, surpassing the market standard of 24%, which is crucial for enhancing self-sufficiency in energy in urban areas. The rainwater harvesting system performed well, achieving a capacity of 600 liters per square meter, slightly below the market rate of 650 liters, but still demonstrating significant potential in dense urban environments. Additionally, our project provided 3 square meters of community garden space per resident, exceeding the market average, effectively promoting urban greening and improving residents’ quality of life. In terms of transportation, our experimental model featured 1.5 bike-sharing stations per 1000 residents, better than the market data of 1.2 stations, contributing to the development of sustainable urban transportation. These outcomes not only showcase the potential of sustainable urban planning but also provide practical references and guidance for future urban development.

In the multimedia context, it is important to enrich the teaching forms, challenge the traditional teaching concepts and realize the innovation of education mode. In this paper, a detailed review of translation strategies for college students in the multimedia context is presented, and the traditional GLR translation teaching analysis algorithm is analyzed. To compensate for the shortcomings of low translation teaching efficiency caused by over-fitting in the traditional GLR translation teaching analysis algorithm, a Bayesian model is constructed, and an adversarial neural network is built on its basis. Generate a translation teaching innovation model applicable to the translation teaching of university students. The translation teaching method is evaluated using the BLEU evaluation method. Experimental results: Both the correct translation rate of utterances based on the statistical computing method and dynamic memory algorithm reached 90%-95%. The traditional GLR translation teaching analysis algorithm achieved 95% correctness in recognizing declarative sentences, while the correctness rate for question and exclamation sentences was less than 95%. The correct translation rate of all the statements of the innovative model of translation teaching reached more than 97%. It can be seen that: The innovative model of translation teaching for college students with multimedia backgrounds is simpler and faster in calculation and more practical than other translation teaching algorithms, which is suitable for English translation work of college students and meets the proofreading needs of college students for translation teaching.

In today’s highly developed technology, computer and Internet technology has seen a climax of innovation and its application areas are becoming more and more extensive. Computer simulation technology is the direction of computer development proposed in recent years, which can change our way of life to a greater extent. In order to explore the role of finite element analysis in structural analysis and computer simulation, this paper uses ANSYS finite element analysis combined with structural analysis methods and verified by computer simulation examples of welding thermal cycles. The results show that the computer simulation of the simulated temperature curve trend and the experimentally measured temperature curve is basically the same. Absolute error curve increases first and then decreases, basically at 11 s when the maximum, followed by a rapid decline, and then gradually slow down the rate of decline, and eventually converge on 200 °C or 180 °C or so. Such a computer simulation in a certain range to be able to more accurately simulate the welding temperature field, the study of welding problems is very valuable reference. For the simulation speed of computer simulation, combined with the structural analysis of finite element analysis, the running time was reduced by an average of 3.58 min, and the overall efficiency was improved by 21.81%. It shows that the FEA method can effectively reduce the running time and significantly improve the running efficiency. In summary, finite element analysis can optimize common problems in structural analysis, strengthen the analysis effect, and expand the application of computer simulation technology.

To promote the development and application of “blockchain+supply chain finance” in the agricultural logistics industry, this paper uses the ECC algorithm in the blockchain model as the basis and implements an asymmetric encryption algorithm based on elliptic curve mathematical theory to optimize the ECC algorithm. Based on the ECC algorithm in the blockchain model, this paper implements an asymmetric encryption algorithm based on elliptic curve mathematical theory to optimize the ECC algorithm. Combining the dynamic variational particle swarm optimization algorithm and the AdaBoost integration algorithm, the DPSO-SVM algorithm is weighted and combined into a strong classifier, and an evaluation model based on AdaBoost-DPSO-SVM is established, and the model is compared with other models. The experimental results show that the data platform based on “blockchain + supply chain finance” can well solve the problem of loss of confidentiality in the process of identifying agricultural products in the agricultural logistics industry. This also shows that through the way of “blockchain + supply chain finance”, it can provide a better development path for the agricultural logistics industry and can truly achieve low-cost commercial communication, i.e. multi-functional integration development.

Logistic regression and neural networks have developed rapidly in recent years, and the poor diet of people in modern society has led to the emergence of various diseases in which drug-resistant bacterial infections occur during treatment, so this paper proposes logistic regression to analyze risk factors and preventive control of multi-drug-resistant bacterial infections. A logistic regression model was established to determine the magnitude of the effect of each factor on the dependent variable based on the standardized values, and the prevalence was recoded in the prediction stage, with the screened indicators serving as factors and covariates. The number of neurons in the input and output layers is determined, and the weights are continuously adjusted in iterations to calculate the average error rate between the actual number of morbidities and the predicted values. The gradient explosion and dispersion problems of in-depth analysis are solved by selecting the maximum probability for classification. The error values were calculated by using the cost function, adjusting the model parameters, comparing the errors between predicted and observed values, and updating the weights with the hidden layer error values, thus improving the accuracy of the model for analyzing risk factors of multi-drug resistant bacterial infections and preventing and controlling the deterioration of the disease. The analysis of the results showed that the logistic regression analysis method, using the area of the ROC curve as a discriminant, yielded an AUC of 0.831 in this study, which combined with the neural network model to predict multi-drug resistant bacteria infections with a higher accuracy of 85.6%, identify the potential risk of multi-drug resistant bacteria occurrence, and prevent the aggravation of the infection.

The expansion of local legislative authority has prompted the introduction of various local regulations, which have promoted local governance in various places. However, the formulation of local legislation suffers from problems such as singularity and fragmentation, and its informatization has not kept pace with the development of artificial intelligence. In order to study the application of artificial intelligence in local legislation, this paper applies artificial intelligence to the intelligent screening of legislative solicitations and the intelligent review of draft regulations through the study of generative adversarial networks and their optimization models. Facing legislative opinions with large amounts of data and complex text, the text recognition rate of AI reaches 98.24%, the success rate of similar opinion de-duplication is 84.69%, and the success rate of classifying opinions applying to different fields and different legal articles is 79.09%. Artificial intelligence can also filter out 71.13% of invalid opinions. In reviewing draft regulations, the success rate of artificial intelligence in judging whether it conflicts with the higher law is 83.01%, and the success rate of judging whether it conflicts with the same law is 80.64%. Artificial intelligence has a natural advantage in assisting local legislators to deal with a large amount of repetitive paperwork, which can effectively improve the efficiency of local legislation. Using artificial intelligence to assist local legislation can help local legislation make great progress and development to maintain local stability better and promote local development.

We present a GDPR-compliant data privacy and access use case of a distributed data wallet and we explore its modeling using two options, AspectOWL and Prova. This use case requires a representation capable of expressing the dynamicity and interaction between parties. While both approaches provide the expressiveness of non-monotonic states and fluent state transitions, their scope and semantics are vastly different. AspectOWL is a monotonic contextualized ontology language, able to represent dynamic state transitions and knowledge retention by wrapping parts of the ontology in isolated contexts, called aspects, while Prova can handle state transitions at runtime using non-monotonic state transition semantics. We present the two implementations and we discuss the similarities, advantages, and differences of the two approaches. [ABSTRACT FROM AUTHOR]

In a 2003-article, Sven Ove Hansson discusses the justificatory structure of a belief base, by highlighting that some beliefs of the belief base are held only because they are (deductively) justified by some other beliefs. He concludes that the relation between the justificatory structure of a belief base and the vulnerability of its beliefs (which in turn reflects their resistance to change) remains an open issue, both on a conceptual and on a technical level. Motivated by Hanssons' remarks, we introduce in this article a new interesting type of change-operation, called deductive belief change (contraction and revision), and abbreviated as DBC. DBC associates in a natural manner the deductive justification that the logical sentences of the language have, in the context of a belief base B, with their vulnerability relative to B. According to DBC, the more explicit B-beliefs imply a sentence φ, the more resistant to change φ is, with respect to B. We characterize DBC both axiomatically, in terms of natural postulates, and constructively, in terms of kernel belief change, illustrating its simple and intuitive structure. Interestingly enough, as we prove, kernel belief change (and its central specialization partial-meet belief change) already encodes a strong coupling between justificatory structure and vulnerability, as it implements DBC. Furthermore, we show that deductive belief revision, properly adapted to the belief-sets realm, is indistinguishable from Parikh's relevance-sensitive revision, a fundamental type of revision which, due to its favourable properties, constitutes a promising candidate for a variety of real-world applications. As a last contribution, we study relevance in the context of belief bases, and prove that kernel belief change respects Parikh's notion of relevance. [ABSTRACT FROM AUTHOR]

Agriculture is the economic backbone and the main means of livelihood in numerous developing countries. Numerous challenges related to farming and agriculturists exist. Cultivators face crop loss due to inappropriate selection of crops, inappropriate use of fertilizers, alterations in soil, ambiguous conditions in climate, and so on. The type of soil forms a crucial element in agriculture.The class of soil plays an important role in identifying what kind of crop should be planted along with the manure type to be applied. Classification of soil is essential to make effective use of the resources of soil. The texture of the soil has a major impact on crop growth. The role played by soil texture in determining the type of crop to be grown is significant. It is also employed in soil labs for determining the categories of soil. Soil texture plays a major role in determining the suitability of crops and handling famines. Soil chemical properties include "Electrical Conductivity" ( E C ), "Organic Carbon" ( O C ), "Phosphorous" (P), "Potassium" (K), "Power of Hydrogen" ( P H ), "Zinc" ( Z n ), "Boron" (B), and "Sulphur" (S). The crop growth is heavily influenced by the soil's chemical composition. Keeping these considerations in mind, this work develops a customised decision tree ( C DT ) that serves as a soil classifier (SC). A predictive framework is then devised that utilises the C DT to perform the soil classification based on the texture of the soil and its chemical properties. Extensive experiments on several real-world soil datasets from Karnataka, India; and benchmark agricultural datasets such as seeds, Urban Land Cover (ULC), Satellite Image of Land Data (LS), and Forest Cover Type (FCT) were conducted. The results demonstrated that the designed C DT classifier outperformed existing classifiers such as k-Nearest Neighbor ( K NN ), Logistic Regression ( L R ), Artificial Neural Network ( A NN ), Classification and Regression Trees ( C ART ), C 4.5 ), traditional SVM ( S VM ), and Random Forest ( R F ) in terms of Accuracy ( A cc ), Sensitivity ( S ens ), Specificity ( S pec ), Precision ( P rec ), and F-Score ( F S ) on these datasets. The devised SC was deployed on the Heroku (Hk) cloud for effective access. Effective access in terms of end-user availability at all times was provided. An expert system for soil classification was built to provide information about soil classification round the clock using an internet-enabled device to the stakeholders of agriculture, such as cultivators and agricultural organizations. The agricultural raw data was stored in the form of blob objects on Amazon S3 (AS3). [ABSTRACT FROM AUTHOR]

In this paper, a formal transition system model is presented called Linear Temporal Public Announcement Logic (LTPAL) to extract knowledge in a classification process. The model combines Public Announcement Logic (PAL) and Linear Temporal Logic (LTL). For this purpose, first, an epistemic logic model is created to capture information gathered by classifiers in single-framed data input. Next, using LTL, classifiers are considered for data stream inputs. Then, a verification method is proposed for such data streams. Finally, we formalize natural language properties in LTPAL with a video-stream object detection sample. [ABSTRACT FROM AUTHOR]