User-defined Rules Research Articles

Fully Automated Paper Document Sorting Robot Design

A fully automated paper document sorting robot was developed in this project. This robot classifies documents efficiently and accurately. The objective of this project was to improve the efficiency of classifying or sorting paper documents, reduce costs, and save time. The robot can classify documents according to user-defined rules, such as keywords, dates, serial numbers, bar codes, and the meaning of paragraphs. Since it can classify or sort documents intelligently, it can complete large-scale document classification quickly. The robot is constructed using an aluminum profile to create a box-type truss gantry structure frame. It was built on the LubanCat 4 motherboard and controlled through Python language programming. Driven by a stepper motor to move the manipulator. The camera module is combined with an artificial intelligence algorithm to recognize paper in real time, and the text is recognized after taking pictures of the paper. The sorting function is performed by several sensors. In addition, a web-based human-computer interaction platform was developed using the Flask web framework in Python. Users could access this platform in a variety of ways, allowing them to easily and swiftly configure parameters and send operational instructions to perform various functions.

An approach for proactive mobile recommendations based on user-defined rules

In the Big Data era, context-aware mobile recommender systems are crucial in assisting citizens and tourists in making informed decisions, providing a suitable way for users to find the relevant data. These systems should be proactive, able to detect the ideal time and location to provide recommendations for a specific item or activity. To accomplish this, push-based recommender systems can be employed, utilizing context rules to determine when a recommendation should be initiated. However, there is very limited reported experience in defining and implementing such systems and a complete generic solution that adapts flexibly to the preferences of users and protects their privacy is still missing.In this paper, we present a novel approach where appropriate types of recommendations are provided automatically, without the need for user input. Our proposal allows users to easily activate, deactivate, customize, and create rules for improved personalization. Additionally, the module that, based on the context, decides the types of recommendations required is executed on the user’s mobile device, reducing wireless communication and safeguarding the user’s privacy, as context data are evaluated locally. To illustrate the approach, we have developed R-Rules, a prototype for Android devices focused on the triggering of recommendation rules, which provides a friendly user interface that facilitates user personalization. We have evaluated various technological options and demonstrated the feasibility, performance, and scalability of the proposal, as well as its suitability to users’ needs.

A Highly Configurable Packet Sniffer Based on Field-Programmable Gate Arrays for Network Security Applications

Web applications and online business transactions have grown tremendously in recent years. As a result, cyberattacks have become a major threat to the digital services that are essential for our society. To minimize the risks of cyberattacks, many countermeasures are deployed on computing nodes and network devices. One such countermeasure is the firewall, which is designed with two main architectural approaches: software running on standard or embedded computers, or hardware specially designed for the purpose, such as (Application Specific Integrated Circuits) ASICs. Software-based firewalls offer high flexibility and can be easily ported to upgradable hardware, but they cannot handle high data rates. On the other hand, hardware-based firewalls can process data at very high speeds, but are expensive and difficult to update, resulting in a short lifespan. To address these issues, we explored the use of an (Field-Programmable Gate Array) FPGA architecture, which offers low latency and high-throughput characteristics along with easy upgradability, making it a more balanced alternative to other programmable systems, like (Graphics Processor Unit) GPUs or microcontrollers. In this paper, we presented a packet sniffer designed on the FPGA development board KC705 produced by Xilinx, which can analyze Ethernet frames, check the frame fields against a set of user-defined rules, and calculate statistics of the received Ethernet frames over time. The system has a data transfer rate of 1 Gbit/s (with preliminary results of increased data rates to 10 Gbit/s) and has been successfully tested with both ad hoc-generated Ethernet frames and real web traffic by connecting the packet sniffer to the internet.

Physiowise: A Physics-aware Approach to Dicrotic Notch Identification.

Dicrotic Notch (DN), one of the most significant and indicative features of the arterial blood pressure (ABP) waveform, becomes less pronounced and thus harder to identify as a matter of aging and pathological vascular stiffness. Generalizable and automatic DN identification for such edge cases is even more challenging in the presence of unexpected ABP waveform deformations that happen due to internal and external noise sources or pathological conditions that cause hemodynamic instability. We propose a physics-aware approach, named Physiowise (PW), that first employs a cardiovascular model to augment the original ABP waveform and reduce unexpected deformations, then apply a set of predefined rules on the augmented signal to find DN locations. We have tested the proposed method on in-vivo data gathered from 14 pigs under hemorrhage and sepsis study. Our result indicates 52% overall mean error improvement with 16% higher detection accuracy within the lowest permitted error range of 30ms. An additional hybrid methodology is also proposed to allow combining augmentation with any application-specific user-defined rule set.

Transliterating Latin to Amharic scripts using user-defined rules and character mappings

Transliterating Latin to Amharic scripts using user-defined rules and character mappings

CusProSe: a customizable protein annotation software with an application to the prediction of fungal secondary metabolism genes

We report here a new application, CustomProteinSearch (CusProSe), whose purpose is to help users to search for proteins of interest based on their domain composition. The application is customizable. It consists of two independent tools, IterHMMBuild and ProSeCDA. IterHMMBuild allows the iterative construction of Hidden Markov Model (HMM) profiles for conserved domains of selected protein sequences, while ProSeCDA scans a proteome of interest against an HMM profile database, and annotates identified proteins using user-defined rules. CusProSe was successfully used to identify, in fungal genomes, genes encoding key enzyme families involved in secondary metabolism, such as polyketide synthases (PKS), non-ribosomal peptide synthetases (NRPS), hybrid PKS-NRPS and dimethylallyl tryptophan synthases (DMATS), as well as to characterize distinct terpene synthases (TS) sub-families. The highly configurable characteristics of this application makes it a generic tool, which allows the user to refine the function of predicted proteins, to extend detection to new enzymes families, and may also be applied to biological systems other than fungi and to other proteins than those involved in secondary metabolism.

MODULAR ARCHITECTURE OF THE TRANSDISCIPLINARY VIRTUAL STEMCENTER

This article presents a detailed analysis of a sophisticated software system for a transdisciplinary STEM (Science, Technology, Engineering, and Mathematics) center. The system integrates modules to consolidate ontological and network knowledge bases, create methodological developments, and generate user preference-based recommendations. A notable feature is its capability to rank and filter information based on user-defined rules and present it in an ontological transdisciplinary format. l transdisciplinary format. detailed analysis of a sophisticated software system for a transdisciplinary STEM (Science, Technology, Engineering, and Mathematics) center is presented. The system integrates a series of modules aimed at consolidating ontological and network knowledge bases, creating methodological developments, and generating user preference-based recommendations. A notable feature is its capability to rank and filter information based on userdefined rules, and present it in ontological transdisciplinary format.The system's architecture is characterized by two principal models: the Information Model and the Functional-Component Model. The Information Model ensures interoperability between popular content management systems like WordPress and the advanced KIT "Polyhedron" system, highlighting the system's applicability and versatility. The Functional-Component Model, on the other hand, offers insights into the interactions and dependencies between various software modules, delineating the system's comprehensive structure and operational dynamics.A key aspect of the T-STEM center's architecture is its ability to process structured and unstructured data, covering various formats from JSON, XML, OWL, and CSV to PDF, TXT, DOC, and HTML. This flexibility makes the system adaptable to multiple data types and user needs. Structuring of unstructured data is achieved through modules like the "stemua.science Environment," "Recursive Reducer Module," and "Indexer," along with a user interface for structuring educational materials, enhancing its educational functionality.m JSON, XML, OWL, CSV to PDF, TXT, DOC, and HTML. This flexibility makes the system adaptable to various data types and user needs. Structuring of unstructured data is achieved through modules like the "stemua.science Environment," "Recursive Reducer Module," and "Indexer," along with a user interface for structuring educational materials, enhancing its educational functionality.The system also features specialized subsystems for processing ontologies, such as the "Audit Subsystem," "Alternative Subsystem," and "Analytical System," facilitating user interaction with structured materials through components like "Taxonomic Representation," "Object Representation," and the "Transdisciplinary Cube." This innovative architecture positions the T-STEM center at the forefront of educational technology, offering a robust and user-friendly platform for transdisciplinary studies.

A method to produce a flexible and customized fuel models dataset

Simulation of vegetation fires very often resorts to fire-behavior models that need fuel models as input. The lack of fuel models is a common problem for researchers and fire managers because its quality depends on the quality/availability of data. In this study we present a method that combines expert- and research-based knowledge with several sources of data (e.g. satellite and fieldwork) to produce customized fuel models maps. Fuel model classes are assigned to land cover types to produce a basemap, which is then updated using empirical and user-defined rules. This method produces a map of surface fuel models as detailed as possible. It is reproducible, and its flexibility relies on juxtaposing independent spatial datasets, depending on their quality or availability. This method is developed in a ModelBuilder/ArcGis toolbox named FUMOD that integrates ten sub-models. FUMOD has been used to map the Portuguese annual fuel models grids since 2019, supporting regional fire risk assessments and suppression decisions. Datasets, models and supplementary files are available in a repository (https://github.com/anasa30/PT_FuelModels).•FUMOD is a flexible toolbox with ten sub-models included that maps updated Portuguese fuel models.

A Novel Knowledge Graph Reasoning Approach in Real-Time Based on Ontology and User-Defined Rules Via Low-Code Editor

A Novel Knowledge Graph Reasoning Approach in Real-Time Based on Ontology and User-Defined Rules Via Low-Code Editor

АВТОМАТИЗАЦІЯ БІЗНЕС-ПРОЦЕСІВ ЯК НЕОБХІДНА УМОВА ЕФЕКТИВНОСТІ ОРГАНІЗАЦІЙ

The use of advanced technologies to complete business processes with minimal human intervention is known as "business process automation". The purpose of automation is to replace manual human labor with machine labor and optimize the entire production process. With the help of modern technologies of machine interaction, automated parameter control systems are implemented at factories, the data of which is transferred to the server and processed. Taking into account the analysis of this data, the machine itself decides on any action. Automation speeds up work by redirecting information to the right person at the right time with user-defined rules and actions, helping managers move to a new, higher level of management. It gives an opportunity to focus on the company's strategic goals. Automation is currently a very relevant and important direction in the field of theory and practice of business process management. Its main goal is to increase the socio-economic efficiency of the enterprise through the purposeful implementation of software and hardware systems that increase the speed and accuracy of the implementation of business processes, while minimizing erroneous actions and decisions arising under the influence of the so-called "human factor". The automation system helps to turn monotonous manual work into automatic, making such work more technological and advanced. Enterprises work in a highly competitive environment, therefore, they need constant development, use of best practices and new technologies. With the increase in the number of management tasks in large systems, the volume of processed information increases significantly and the complexity of management algorithms increases. As a result, there is a mismatch between the complexity of the managed object and the ability of any governing body to receive and process information. Therefore, the automation of business processes is a necessary condition for the company's survival in the modern world. Automation of business processes is one of the fastest growing technologies today. Businesses need to do less with more and ensure their processes are as efficient and effective as possible. To do this, they turn to business process automation software to scale processes, solve unique workflow challenges, and maximize productivity.

Sample size formula for general win ratio analysis.

Originally proposed for the analysis of prioritized composite endpoints, the win ratio has now expanded into a broad class of methodology based on general pairwise comparisons. Complicated by the non-i.i.d. structure of the test statistic, however, sample size estimation for the win ratio has lagged behind. In this article, we develop general and easy-to-use formulas to calculate sample size for win ratio analysis of different outcome types. In a nonparametric setting, the null variance of the test statistic is derived using U-statistic theory in terms of a dispersion parameter called the standard rank deviation, an intrinsic characteristic of the null outcome distribution and the user-defined rule of comparison. The effect size can be hypothesized either on the original scale of the population win ratio, or on the scale of a "usual" effect size suited to the outcome type. The latter approach allows one to measure the effect size by, for example, odds/continuation ratio for totally/partially ordered outcomes and hazard ratios for composite time-to-event outcomes. Simulation studies show that the derived formulas provide accurate estimates for the required sample size across different settings. As illustration, real data from two clinical studies of hepatic and cardiovascular diseases are used as pilot data to calculate sample sizes for future trials.

TabReformer: Unsupervised Representation Learning for Erroneous Data Detection

Error detection is a crucial preliminary phase in any data analytics pipeline. Existing error detection techniques typically target specific types of errors. Moreover, most of these detection models either require user-defined rules or ample hand-labeled training examples. Therefore, in this article, we present TabReformer, a model that learns bidirectional encoder representations for tabular data. The proposed model consists of two main phases. In the first phase, TabReformer follows encoder architecture with multiple self-attention layers to model the dependencies between cells and capture tuple-level representations. Also, the model utilizes a Gaussian Error Linear Unit activation function with the Masked Data Model objective to achieve deeper probabilistic understanding. In the second phase, the model parameters are fine-tuned for the task of erroneous data detection. The model applies a data augmentation module to generate more erroneous examples to represent the minority class. The experimental evaluation considers a wide range of databases with different types of errors and distributions. The empirical results show that our solution can enhance the recall values by 32.95% on average compared with state-of-the-art techniques while reducing the manual effort by up to 48.86%.

Multi-Camera Collaborative Network Experimental Study Design of Video Surveillance System for Violated Vehicles Identification

In this paper, we propose an experimental study of multi-camera collaborative network for surveillance the highway traffic turn in real life scenario, the target of surveillance based offline video processing is capturing the violated vehicles that driving violated paths in many cases specified by user-defined rules. Best topology of the experiment zone is considered and covered by four pillars; each has two (fixed and motorized) cameras that casing the entire specific effective field of view. As to author knowledge, there is no such available experiment, and hence, it could serve researchers that interested in. However, the experiment is done for around 180 recorded hours for 8 videos during 9 days, each video for one camera. It is designed based on the collaborative cameras principle for intelligent video surveillance systems and the outcomes show that the surveillance and the tracking of violated vehicles have been successes in most user-defined rules cases for more than 90 % cases.

Extending the learning and communicating shout-ahead architecture with user-defined exception rules -- a case study for traffic light controls

We present an extension of the shout-ahead agent architecture that allows for adding human user-defined exception rules to the rules created by the hybrid learning approach for this architecture. The user-defined rules can be added after learning as reaction to weaknesses of the learned rules or learning can be performed with the user-defined rules already in place. We applied the extended shout-ahead architecture and the associated learning to a new application area, cooperating controllers for the traffic lights of intersections. In our experimental evaluations, adding user-defined exception rules to the learned rules for several traffic flow instances increased the efficiency of the resulting controllers substantially compared to just using the learned rules. Performing learning with user-defined exception rules already in place decreased the learning time substantially for all flows, but had mixed results with respect to efficiency. We also evaluated user-defined exception rules for a variant of the architecture that is not using communication and saw similar effects as for the variant with communication. For the communicating version, both variants of adding user-defined exception rules create controllers that are much more flexible than what using the original shout-ahead architecture with its learning is able to create as indicated by experiments with variations of flows.

MolAICal: a soft tool for 3D drug design of protein targets by artificial intelligence and classical algorithm.

Deep learning is an important branch of artificial intelligence that has been successfully applied into medicine and two-dimensional ligand design. The three-dimensional (3D) ligand generation in the 3D pocket of protein target is an interesting and challenging issue for drug design by deep learning. Here, the MolAICal software is introduced to supply a way for generating 3D drugs in the 3D pocket of protein targets by combining with merits of deep learning model and classical algorithm. The MolAICal software mainly contains two modules for 3D drug design. In the first module of MolAICal, it employs the genetic algorithm, deep learning model trained by FDA-approved drug fragments and Vinardo score fitting on the basis of PDBbind database for drug design. In the second module, it uses deep learning generative model trained by drug-like molecules of ZINC database and molecular docking invoked by Autodock Vina automatically. Besides, the Lipinski’s rule of five, Pan-assay interference compounds (PAINS), synthetic accessibility (SA) and other user-defined rules are introduced for filtering out unwanted ligands in MolAICal. To show the drug design modules of MolAICal, the membrane protein glucagon receptor and non-membrane protein SARS-CoV-2 main protease are chosen as the investigative drug targets. The results show MolAICal can generate the various and novel ligands with good binding scores and appropriate XLOGP values. We believe that MolAICal can use the advantages of deep learning model and classical programming for designing 3D drugs in protein pocket. MolAICal is freely for any nonprofit purpose and accessible at https://molaical.github.io.

Design and Implementation of System Generator Based on Rule Engine

Abstract At present, most small and medium-sized enterprises still adopt the “hard coding” method to develop system, in this way, it lack of flexibility and reusability, and disable to respond users’ need with continuous updating quickly. To address this problem, we design a rule engine-based system generator that uses the improved Rete algorithm to match data objects with user-defined rules (production) and then implement specific functions through the system generator. Compared with the traditional development mode, this method is more concise and fast, has better reusability, and can effectively solve some problems of the traditional development methods. The user only need to configure the fact data according to the existing rules, and the system autonomously processes according to the configuration instance to generate various functions. The paper mainly introduces the implementation of the rule engine and the system generator.

TZVis: visual analysis of bicycle data for traffic zone division

Traffic zone is a geographical unit which is proposed to reduce the complexity of traffic control and management systems in modern urban road networks. Traffic zone could be generated by different division approaches (e.g., rule-based approaches, data-driven approaches), which may lead to different diverse division results and characteristics. The traditional division approaches usually rely on human experience or static constraints (e.g., political boundaries or natural environment) while neglecting the traveling pattern among different regions. Data-driven approaches are also utilized in recent years; however, domain knowledge and rules are not well integrated and represented in such systems. This paper proposes a new approach that both combines patterns that is hidden in the data and user-defined rules. It not only fully employs the traffic hot spots and traveling patterns among different regions, but also considers the realistic constraints such as road network. We also design TZVis, a visual analysis system that fully integrates with the division approach. The system allows users to generate multiple traffic zone division schemes under different requirements, analyze the schemes in multiple views and select an optimal traffic zone scheme. It provides a map overview to show the traffic zone division result, a matrix view to show the traffic relationship of zones, a parallel coordinates plot for displaying the specific traffic records, a LineUp view to display all the division results and a radar chart to show the features of each zones. We further test our division approach and demonstrate the usefulness of our system based on the shared bicycle dataset.

Supporting Programmable Autoscaling Rules for Containers and Virtual Machines on Clouds

With the increasing utilization of cloud computing and container technologies, orchestration is becoming an important area on both cloud and container levels. Beyond resource allocation, deployment and configuration, scaling is a key functionality in orchestration in terms of policy, description and flexibility. This paper presents an approach where the aim is to provide a high degree of flexibility in terms of available monitoring metrics and in terms of the definition of elasticity rules to implement practically any possible business logic for a given application. The aim is to provide a general interface for supporting programmable scaling policies utilizing monitoring metrics originating from infrastructure, application or any external components. The paper introduces a component, called Policy Keeper performing the auto-scaling based on user-defined rules, details how this component is operating in the auto-scaling framework, called MiCADO and demonstrates a deadline-based scaling use case.

Error-Free Data Visualization and Processing through imzML and mzML Validation.

Open data formats are key to facilitating data processing, sharing, and integration. The imzML format ( http://imzml.org/ ) has drastically improved these aspects of mass spectrometry imaging data. Efficient processing of data depends on data sets which are consistent and adhere to the specifications; however, this is not always the case. Here we present a validation tool for data stored in both imzML and the HUPO-PSI mass spectrometery counterpart, mzML, to identify any deviations from the published (i)mzML standard which could cause issues for the user when visualizing or processing data. The tool is released in two forms, a graphical user interface (GUI) for ease of use, and a command line version to fit into existing workflows and pipelines. When certain known issues are encountered, such as the presence of negative values for the location of the binary data, the validator resolves the issue automatically upon saving. The GUI version of the validator also allows editing of the metadata included within the (i)mzML files in order to resolve inconsistencies. We also present a means of performing conditional validation on the metadata within (i)mzML files, where user-defined rules are validated against depending on whether specific metadata are present (or not). For example, if the MALDI term is present, then additional rules related to MALDI (such as the requirement of inclusion of laser parameters) can be validated against this. This enables a flexible and more thorough automated validation of (i)mzML data. Such a system is necessary for validating data against more comprehensive sets of metadata such as minimum reporting guidelines or metadata requirements prior to submission and acceptance of data to data repositories. We demonstrate how this tool can be used to validate against the proposed minimum reporting guidelines in MSI as well as institute specific metadata criteria. The validator tool is endorsed for validation of imzML ( http://imzml.org/ ) and mzML ( http://www.psidev.info/mzml ) and is made available through the respective Web sites. The validator is also released as open source under Mozilla Public License 2.0 at https://gitlab.com/imzML/imzMLValidator .

FES-UPP: A Flexible Functional Electrical Stimulation System to Support Upper Limb Functional Activity Practice.

There is good evidence supporting highly intensive, repetitive, activity-focused, voluntary-initiated practice as a key to driving recovery of upper limb function following stroke. Functional electrical stimulation (FES) offers a potential mechanism to efficiently deliver this type of therapy, but current commercial devices are too inflexible and/or insufficiently automated, in some cases requiring engineering support. In this paper, we report a new, flexible upper limb FES system, FES-UPP, which addresses the issues above. The FES-UPP system consists of a 5-channel stimulator running a flexible FES finite state machine (FSM) controller, the associated setup software that guides therapists through the setup of FSM controllers via five setup stages, and finally the Session Manager used to guide the patient in repeated attempts at the activities(s) and provide feedback on their performance. The FSM controller represents a functional activity as a sequence of movement phases. The output for each phase implements the stimulations to one or more muscles. Progression between movement phases is governed by user-defined rules. As part of a clinical investigation of the system, nine therapists used the FES-UPP system to set up FES-supported activities with twenty two patient participants with impaired upper-limbs. Therapists with little or no FES experience and without any programming skills could use the system in their usual clinical settings, without engineering support. Different functional activities, tailored to suit the upper limb impairment levels of each participant were used, in up to 8 sessions of FES-supported therapy per participant. The efficiency of delivery of the therapy using FES-UPP was promising when compared with published data on traditional face-face therapy. The FES-UPP system described in this paper has been shown to allow therapists with little or no FES experience and without any programming skills to set up state-machine FES controllers bespoke to the patient’s impairment patterns and activity requirements, without engineering support. The clinical results demonstrated that the system can be used to efficiently deliver high intensity, activity-focused therapy. Nevertheless, further work to reduce setup time is still required.