Traditional Rule-based Approaches Research Articles

Leveraging Artificial Intelligence for enhanced tax fraud detection in modern fiscal systems

The increasing sophistication of tax evasion schemes poses significant challenges to fiscal authorities worldwide, necessitating advanced technological solutions for fraud detection. This comprehensive review examines the integration of artificial intelligence (AI) technologies in modern tax administration systems, focusing on their application in detecting and preventing tax fraud. The paper analyzes various AI methodologies, including machine learning algorithms, deep learning networks, and natural language processing techniques, evaluating their effectiveness in identifying suspicious patterns and anomalies in tax-related data. Our review encompasses both theoretical frameworks and practical implementations across different jurisdictions, highlighting successful case studies and emerging challenges. The findings indicate that AI-powered systems demonstrate superior accuracy in detecting complex fraud patterns compared to traditional rule-based approaches, with some implementations showing up to 85% improvement in fraud detection rates. However, challenges persist regarding data quality, privacy concerns, and the need for continuous model adaptation to evolving fraud tactics. This review also addresses the regulatory implications and ethical considerations of implementing AI in tax administration, providing recommendations for policymakers and tax authorities to optimize their fraud detection capabilities while maintaining fairness and transparency in their operations.

Review of Language Structures and NLP Techniques for Chinese, Japanese, and English

The increasing demand for cross-lingual communication in a globally interconnected world has spurred significant advancements in Natural Language Processing (NLP), a branch of artificial intelligence aimed at enabling computers to comprehend, generate, and process human language. Over the past few years, NLP has transitioned from traditional rule-based and statistical approaches to deep learning-based methods, with pre-trained models like BERT and GPT demonstrating remarkable performance across a variety of tasks, including text classification and machine translation. However, the linguistic diversity of the world's languages presents ongoing challenges, as many NLP models are primarily developed for high-resource languages like English, leaving other languages underserved. This paper examines the linguistic features of three representative languagesChinese, Japanese, and Englishand explores NLP methodologies tailored to their distinct grammatical, lexical, and structural properties. Through comparative linguistic analysis, this study discusses the challenges of multilingual NLP and the potential for cross-lingual applications. The findings underscore the importance of adapting NLP models to different language characteristics to enhance the effectiveness and inclusivity of cross-lingual processing.

Scenario Identification and Classification to Support the Assessment of Advanced Driver Assistance Systems

In recent years, driver assistance systems in cars, buses, and trucks have become more common and powerful. In particular, the introduction of AI methods to sensors, signal fusion, and traffic recognition allows us to step forward from actual level-2 assistance to level-3 Advanced Driver Assistance Systems (ADAS), where driving becomes autonomous and responsibility shifts from the driver to the automobile manufacturers. This, however, requires a high-precision risk assessment of failure, which can only be achieved by extensive data acquisition and statistical analysis of real traffic scenarios (which is impossible to perform by humans). Therefore, critical driving situations have to be identified and classified automatically. This paper develops and compares two different strategies—a traditional rule-based approach derived from deterministic causal considerations, and an AI-based approach trained with idealized cut-in, cut-out, and cut-through maneuvers. Application to a 10-h measurement sequence on a German highway demonstrates that the latter has the higher performance, whereas the former misses some of the safety-relevant events to be identified.

A Machine Learning Application to Classify Patients at Differing Levels of Risk of Opioid Use Disorder: Clinician-Based Validation Study.

Despite restrictive opioid management guidelines, opioid use disorder (OUD) remains a major public health concern. Machine learning (ML) offers a promising avenue for identifying and alerting clinicians about OUD, thus supporting better clinical decision-making regarding treatment. This study aimed to assess the clinical validity of an ML application designed to identify and alert clinicians of different levels of OUD risk by comparing it to a structured review of medical records by clinicians. The ML application generated OUD risk alerts on outpatient data for 649,504 patients from 2 medical centers between 2010 and 2013. A random sample of 60 patients was selected from 3 OUD risk level categories (n=180). An OUD risk classification scheme and standardized data extraction tool were developed to evaluate the validity of the alerts. Clinicians independently conducted a systematic and structured review of medical records and reached a consensus on a patient's OUD risk level, which was then compared to the ML application's risk assignments. A total of 78,587 patients without cancer with at least 1 opioid prescription were identified as follows: not high risk (n=50,405, 64.1%), high risk (n=16,636, 21.2%), and suspected OUD or OUD (n=11,546, 14.7%). The sample of 180 patients was representative of the total population in terms of age, sex, and race. The interrater reliability between the ML application and clinicians had a weighted kappa coefficient of 0.62 (95% CI 0.53-0.71), indicating good agreement. Combining the high risk and suspected OUD or OUD categories and using the review of medical records as a gold standard, the ML application had a corrected sensitivity of 56.6% (95% CI 48.7%-64.5%) and a corrected specificity of 94.2% (95% CI 90.3%-98.1%). The positive and negative predictive values were 93.3% (95% CI 88.2%-96.3%) and 60.0% (95% CI 50.4%-68.9%), respectively. Key themes for disagreements between the ML application and clinician reviews were identified. A systematic comparison was conducted between an ML application and clinicians for identifying OUD risk. The ML application generated clinically valid and useful alerts about patients' different OUD risk levels. ML applications hold promise for identifying patients at differing levels of OUD risk and will likely complement traditional rule-based approaches to generating alerts about opioid safety issues.

Deep reinforcement learning for artificial upwelling energy management

The potential of artificial upwelling in stimulating seaweed growth, consequently enhancing ocean carbon sequestration has been gaining increasing attention in recent years. This has led to the development of the first solar-powered and air-lifted artificial upwelling system (AUS) in China. However, effective scheduling of the air injection system and energy storage system in dynamic marine environments remains a crucial challenge in the operation of the AUS, as it holds the potential to significantly improve system performance. To tackle this challenge, we propose a novel energy management approach that utilizes the deep reinforcement learning (DRL) algorithm to determine the optimal operational parameters of the AUS at each time interval. Specifically, we formulate the energy optimization problem as a Markov decision process and integrate the quantile network in distributional reinforcement learning with the deep dueling network to solve the problem. Through extensive simulations, we evaluate the performance of our algorithm and demonstrate its superior effectiveness over traditional rule-based approaches and other DRL algorithms in enhancing energy utilization while ensuring the secure and reliable operation of the AUS. Our findings suggest that a DRL-based approach offers a promising way to provide valuable guides for the operation of the AUS and enhance the sustainability of seaweed cultivation and carbon sequestration in the ocean.

MRC-VulLoc: Software source code vulnerability localization based on multi-choice reading comprehension

Recently, automatic vulnerability detection approaches based on machine learning (ML) have outperformed traditional rule-based approaches in terms of detection performance. Existing ML-based approaches typically concentrate on function or line granularity, which fail to realize accurate vulnerability localization and are insufficient to support effective root cause analysis of vulnerability. To address this issue, we propose a new approach that maps the multi-choice reading comprehension (MRC) task to the vulnerability localization task at the granularity of vulnerability triggering path named MRC-VulLoc. Initially, we design six large datasets (including C/C++ and Java languages) in the form of MRC. Subsequently, we introduce a novel pre-trained vulnerability localization model, combining the effective code semantic comprehension ability of pre-trained model with the advantages of Bidirectional Short-Term Memory Network (Bi-LSTM) and Convolutional Neural Network (CNN) models. Lastly, we conduct experiments to evaluate the vulnerability localization with several state-of-the-art MRC approaches and vulnerability detectors. Experimental results demonstrate the effectiveness of the proposed datasets in evaluating MRC approaches for vulnerability localization. Furthermore, MRC-VulLoc achieves higher precision on vulnerability localization compared to comparative vulnerability detectors.

Machine Learning Techniques for Fraud Detection in Financial Services

Fraudulent activities remain a critical challenge for financial institutions, prompting a continual quest for robust detection mechanisms. While effective to a certain extent, traditional rule-based approaches often fall short of capturing fraudsters' evolving tactics. In response, the integration of machine learning (ML) techniques has emerged as a promising avenue to bolster fraud detection capabilities. This paper presents a comprehensive review of recent advancements in ML algorithms specifically tailored for fraud detection within the realm of financial services. Leveraging a plethora of methodologies, including supervised, unsupervised, and semi-supervised learning, researchers and practitioners have endeavored to devise innovative strategies to combat fraudulent transactions effectively. Supervised learning techniques, such as logistic regression, decision trees, random forests, and gradient-boosting machines, have garnered significant attention due to their ability to learn from labeled data and discern patterns indicative of fraudulent behavior. Conversely, unsupervised learning methods, including clustering and anomaly detection algorithms, strive to identify transactional data irregularities without needing labeled examples. Semi-supervised learning techniques bridge the gap between supervised and unsupervised approaches by leveraging a small set of labeled data in conjunction with a larger pool of unlabeled data to enhance detection accuracy. A pivotal aspect in the efficacy of ML models for fraud detection lies in feature engineering. Given the unique characteristics of financial data, feature selection and transformation play a vital role in capturing meaningful signals while mitigating noise. Techniques such as PCA (Principal Component Analysis), LDA (Linear Discriminant Analysis), and feature scaling are commonly employed to preprocess data and extract relevant features that encapsulate the underlying patterns of fraudulent behavior. Despite the strides made in ML based fraud detection, several challenges persist. Imbalanced datasets, wherein fraudulent transactions constitute a minority class, pose a significant hurdle, potentially leading to biased models favoring the majority class. Addressing this imbalance requires careful consideration of sampling techniques, cost-sensitive learning, and performance metrics tailored to asymmetric distributions. Furthermore, the interpretability of ML models remains a pressing concern, particularly in highly regulated industries like finance. Explainable AI (XAI) methodologies, such as SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations), seek to elucidate the decision-making process of complex models, fostering trust and transparency in their deployment. Looking ahead, the convergence of emerging technologies, including deep learning and blockchain, holds promise for enhancing fraud detection capabilities. Deep learning architectures, with their ability to automatically extract hierarchical features from raw data, offer potential avenues for improving detection accuracy, albeit at the cost of interpretability. Similarly, the immutable nature of blockchain technology presents opportunities for enhancing data integrity and transaction transparency, thereby fortifying fraud prevention measures.

Application of fuzzy reinforcement learning in IoT-based robotics for autonomous navigation and collision avoidance

In this study, we investigate the viability of applying fuzzy reinforcement learning (FRL) to Internet of Things-based robots for purposes of autonomous navigation and collision avoidance. The proposed approach utilises FRL, IoT, and a sensor network to give the robot the ability to learn from its environment and act in accordance with those policies. The authors used FRL to train a mobile robot with wheels to move around and avoid obstacles, and then they put the robot through its paces in a virtual world. Results showed that the FRL-based technique improved the robot’s navigation and collision avoidance performance compared to traditional rule-based approaches. The results of this study indicate that FRL may be a viable technique for enabling autonomous navigation and obstacle avoidance in IoT-based robotics.

Using machine learning to develop smart reflex testing protocols.

Reflex testing protocols allow clinical laboratories to perform second line diagnostic tests on existing specimens based on the results of initially ordered tests. Reflex testing can support optimal clinical laboratory test ordering and diagnosis. In current clinical practice, reflex testing typically relies on simple "if-then" rules; however, this limits the opportunities for reflex testing since most test ordering decisions involve more complexity than traditional rule-based approaches would allow. Here, using the analyte ferritin as an example, we propose an alternative machine learning-based approach to "smart" reflex testing. Using deidentified patient data, we developed a machine learning model to predict whether a patient getting CBC testing will also have ferritin testing ordered. We evaluate applications of this model to reflex testing by assessing its performance in comparison to possible rule-based approaches. Our underlying machine learning models performed moderately well in predicting ferritin test ordering (AUC=0.731 in reference to actual ordering) and demonstrated promising potential to underlie key clinical applications. In contrast, none of the many traditionally framed, rule-based, hypothetical reflex protocols we evaluated offered sufficient agreement with actual ordering to be clinically feasible. Using chart review, we further demonstrated that the strategic deployment of our model could avoid important ferritin test ordering errors. Machine learning may provide a foundation for new types of reflex testing with enhanced benefits for clinical diagnosis.

A Machine Learning-Based Interest Flooding Attack Detection System in Vehicular Named Data Networking

A vehicular ad hoc network (VANET) has significantly improved transportation efficiency with efficient traffic management, driving safety, and delivering emergency messages. However, existing IP-based VANETs encounter numerous challenges, like security, mobility, caching, and routing. To cope with these limitations, named data networking (NDN) has gained significant attention as an alternative solution to TCP/IP in VANET. NDN offers promising features, like intermittent connectivity support, named-based routing, and in-network content caching. Nevertheless, NDN in VANET is vulnerable to a variety of attacks. On top of attacks, an interest flooding attack (IFA) is one of the most critical attacks. The IFA targets intermediate nodes with a storm of unsatisfying interest requests and saturates network resources such as the Pending Interest Table (PIT). Unlike traditional rule-based statistical approaches, this study detects and prevents attacker vehicles by exploiting a machine learning (ML) binary classification system at roadside units (RSUs). In this connection, we employed and compared the accuracy of five (5) ML classifiers: logistic regression (LR), decision tree (DT), K-nearest neighbor (KNN), random forest (RF), and Gaussian naïve Bayes (GNB) on a publicly available dataset implemented on the ndnSIM simulator. The experimental results demonstrate that the RF classifier achieved the highest accuracy (94%) in detecting IFA vehicles. On the other hand, we evaluated an attack prevention system on Python that enables intermediate vehicles to accept or reject interest requests based on the legitimacy of vehicles. Thus, our proposed IFA detection technique contributes to detecting and preventing attacker vehicles from compromising the network resources.

Comparative Review of Credit Card Fraud Detection using Machine Learning and Concept Drift Techniques

Credit card fraud is a significant concern for financial institutions and cardholders alike. As fraudulent activities become more sophisticated, traditional rule-based approaches struggle to keep up. This has led to the adoption of machine learning techniques for fraud detection, which have shown promising results. However, the dynamic nature of credit card fraud poses a challenge due to the concept drift phenomenon. Concept drift refers to the changes in the underlying data distribution over time, requiring models to adapt and evolve to maintain their effectiveness. This research paper aims to provide a comprehensive comparative review of credit card fraud detection methods using machine learning and concept drift techniques. This literature review provides an overview of relevant studies comparing credit card fraud detection using machine learning techniques and concept drift handling methods. The paper evaluates the performance, strengths, and limitations of various approaches in addressing credit card fraud detection under concept drift scenarios.

Fraudulent Banking Transaction Classification Using Deep Learning Algorithm.

Financial fraud is a significant problem in the banking industry, and detecting fraudulent transactions is a critical task for banks to protect their customers and maintain trust in the financial system. Traditional rule-based approaches for detecting fraud often rely on pre-defined thresholds and heuristics, which can be circumvented by sophisticated fraudsters. As a result, machine learning techniques have gained increasing attention in recent years for their ability to automatically learn from data and adapt to changing fraud patterns .In this project, we propose a novel approach for classifying fraudulent banking transactions using a deep learning algorithm. Our approach leverages the power of deep neural networks to automatically extract meaningful features from transaction data, and then use these features to accurately classify transactions as either fraudulent or legitimate

Model predictive control for a university heat prosumer with data centre waste heat and thermal energy storage

Data centres (DCs) are energy-intensive facilities that convert most of their energy use into waste heat. Given the rapidly increasing energy and environmental impacts of DCs, and the need to optimize regional energy structures, there is an increasing effort to recover DC waste heat for district heating (DH) systems. However, previous research mainly focused on exploring the possibilities and proposing technical solutions for capturing DC waste heat for DH systems. They rarely investigated solutions on optimal control of the DH system after recovering DC waste heat, particularly for a DC waste heat-based heat prosumer with thermal energy storage (TES). Therefore, this study applied a model predictive control (MPC) scheme for a university heat prosumer with DC waste heat and water tank TES by simulation. In the framework, the objective function minimized the overall energy cost considering the dynamic heating and electricity prices simultaneously, and the incorporated model described system dynamics including DC waste heat recovery units, TES, and campus DH system. The MPC framework was demonstrated to be more effective than a traditional rule-based control approach in terms of 1) providing more stable chilled water for the DC cooling system and 2) cutting monthly energy costs by up to 3.2%.

Feature generation and contribution comparison for electronic fraud detection

Modern money transfer services are convenient, attracting fraudulent actors to run scams in which victims are deceived into transferring funds to fraudulent accounts. Machine learning models are broadly applied due to the poor fraud detection performance of traditional rule-based approaches. Learning directly from raw transaction data is impractical due to its high-dimensional nature; most studies construct features instead by extracting patterns from raw transaction data. Past literature categorizes these features into recency, frequency, monetary, and anomaly detection features. We use various machine learning algorithms to examine the performance of features in these four categories with real transaction data; we compare them with the performance of our feature generation guideline based on the statistical perspectives and characteristics of (non)-fraudulent accounts. The results show that except for the monetary category, other feature categories used in the literature perform poorly regardless of which machine learning algorithm is used; anomaly detection features perform the worst. We find that even statistical features generated based on financial knowledge yield limited performance on a real transaction dataset. Our atypical detection characteristic of normal accounts improves the ability to distinguish them from fraudulent accounts and hence improves the overall detection results, outperforming other existent methods.

Machining feature recognition based on a novel multi-task deep learning network

• Propose a novel learning-based machining feature recognition method that can effectively determine the faces that constitute machining features. • Construct a novel multi-task deep learning network based on point cloud data that can realize machining feature segmentation, machining feature identification, and bottom face identification simultaneously. • Propose a novel loss function that can be applied to the tasks of multi-label classification in deep learning. • Promote the application of deep learning in the manufacturing industry. Machining feature recognition is an essential task to realize the integration of computer-aided design (CAD), process planning (CAPP), and manufacturing (CAM) systems. In general, traditional rule-based machining feature recognition approaches are inflexible and computationally expensive. Moreover, it's not easy to design rules for intersecting machining features. To this end, various learning-based approaches were proposed in recent years. However, some of the existing learning-based approaches are complicated, time-consuming, and hard to deal with intersecting machining features, while some only approximately locate the position of the machining features rather than accurately segmenting them from the parts, which is not conducive to subsequent process planning. To address the above issues, a novel multi-task network named Associatively Segmenting and Identifying Network (ASIN) based on point cloud data is proposed for machining feature recognition. The proposed network performs three tasks: clusters the part faces with high similarities into machining features whose type are unidentified, predicts the semantic class (e.g. hole, pocket) for each face to identify the type of each machining feature, and identifies the bottom faces of the machining features. Through the three tasks, ASIN can realize machining feature segmentation, machining feature identification, and bottom face identification simultaneously. The final machining feature recognition results are obtained by combining the results of the above three tasks. After being trained with a large labeled point cloud dataset of 3D CAD models and a novel loss function, ASIN can be used to recognize machining features. Experimental results demonstrate that the proposed approach can effectively segment the machining features by determining the faces that compose them, and performs well in recognizing intersecting machining features.

MICER: a pre-trained encoder-decoder architecture for molecular image captioning.

Automatic recognition of chemical structures from molecular images provides an important avenue for the rediscovery of chemicals. Traditional rule-based approaches that rely on expert knowledge and fail to consider all the stylistic variations of molecular images usually suffer from cumbersome recognition processes and low generalization ability. Deep learning-based methods that integrate different image styles and automatically learn valuable features are flexible, but currently under-researched and have limitations, and are therefore not fully exploited. MICER, an encoder-decoder-based, reconstructed architecture for molecular image captioning, combines transfer learning, attention mechanisms and several strategies to strengthen effectiveness and plasticity in different datasets. The effects of stereochemical information, molecular complexity, data volume and pre-trained encoders on MICER performance were evaluated. Experimental results show that the intrinsic features of the molecular images and the sub-model match have a significant impact on the performance of this task. These findings inspire us to design the training dataset and the encoder for the final validation model, and the experimental results suggest that the MICER model consistently outperforms the state-of-the-art methods on four datasets. MICER was more reliable and scalable due to its interpretability and transfer capacity and provides a practical framework for developing comprehensive and accurate automated molecular structure identification tools to explore unknown chemical space. https://github.com/Jiacai-Yi/MICER. Supplementary data are available at Bioinformatics online.

End-to-end digitization of image format piping and instrumentation diagrams at an industrially applicable level

Abstract This study proposes an end-to-end digitization method for converting piping and instrumentation diagrams (P&IDs) in the image format to digital P&IDs. Automating this process is an important concern in the process plant industry because presently image P&IDs are manually converted into digital P&IDs. The proposed method comprises object recognition within the P&ID images, topology reconstruction of recognized objects, and digital P&ID generation. A data set comprising 75 031 symbol, 10 073 text, and 90 054 line data was constructed to train the deep neural networks used for recognizing symbols, text, and lines. Topology reconstruction and digital P&ID generation were developed based on traditional rule-based approaches. Five test P&IDs were digitalized in the experiments. The experimental results for recognizing symbols, text, and lines showed good precision and recall performance, with averages of 96.65%/96.40%, 90.65%/92.16%, and 95.25%/87.91%, respectively. The topology reconstruction results showed an average precision of 99.56% and recall of 96.07%. The digitization was completed in <3.5 hours (8488.2 s on average) for five test P&IDs.

Avoiding the Hook: Influential Factors of Phishing Awareness Training on Click-Rates and a Data-Driven Approach to Predict Email Difficulty Perception

Phishing attacks are still seen as a significant threat to cyber security, and large parts of the industry rely on anti-phishing simulations to minimize the risk imposed by such attacks. This study conducted a large-scale anti-phishing training with more than 31000 participants and 144 different simulated phishing attacks to develop a data-driven model to classify how users would perceive a phishing simulation. Furthermore, we analyze the results of our large-scale anti-phishing training and give novel insights into users’ click behavior. Analyzing our anti-phishing training data, we find out that 66% of users do not fall victim to credential-based phishing attacks even after being exposed to twelve weeks of phishing simulations. To further enhance the phishing awareness-training effectiveness, we developed a novel manifold learning-powered machine learning model that can predict how many people would fall for a phishing simulation using the several structural and state-of-the-art NLP features extracted from the emails. In this way, we present a systematic approach for the training implementers to estimate the average "convincing power" of the emails prior to rolling out. Moreover, we revealed the top-most vital factors in the classification. In addition, our model presents significant benefits over traditional rule-based approaches in classifying the difficulty of phishing simulations. Our results clearly show that anti-phishing training should focus on the training of individual users rather than on large user groups. Additionally, we present a promising generic machine learning model for predicting phishing susceptibility.

Model predictive control for a data centre waste heat-based heat prosumer in Norway

Waste heat from a data centre (DC) is a promising heat source because of the evenly distributed load profile and intensive waste heat generation. Many studies have proven the substantial financial benefits for the district heating (DH) operators by integrating DC waste heat with DH systems. However, there is a scarcity of research focusing on the optimal control of the DH system after integrating DC waste heat to further improve the system’s economic performance. Therefore, this study aimed to further improve the economic performance of a DH system with DC waste heat by utilizing a model predictive control (MPC) scheme. This MPC scheme employed an economic-related objective function and formulated technical operational constraints. The proposed MPC scheme was tested on a campus DH system in Norway by simulation. Compared to a traditional rule-based control approach, the MPC scheme reduced the monthly energy cost by 1.8% while providing more stable chilled water for the DC cooling system.

Modeling HMM Map Matching Using Multi-label Classification

Map matching deals with matching GPS coordinates to corresponding points or segments on a road network map. The work has various applications in both vehicle navigating and tracking domains. Traditional rule-based approach for solving the Map matching problem yielded great matching results. However, its performance depends on the underlying algorithm and Mathematical/Statistical models employed in the approach. For example, HMM Map Matching yielded O(N2) time complexity, where N is the number of states in the underlying Hidden Markov Model. Map matching techniques with large order of time complexity are impractical for providing services, especially within time-sensitive applications. This is due to their slow responsiveness and the critical amount of computing power required to obtain the results. This paper proposed a novel data-driven approach for projecting GPS trajectory onto a road network. We constructed a supervised-learning classifier using the Multi-Label Classification (MLC) technique and HMM Map Matching results. Analytically, our approach yields O(N) time complexity, suggesting that the approach has a better running performance when applied to the Map matching-based applications in which the response time is the major concern. In addition, our experimental results indicated that we could achieve Jaccard Similarity index of 0.30 and Overlap Coefficient of 0.70.