Manual Solutions Research Articles

Classifying Tumor Reportability Status From Unstructured Electronic Pathology Reports Using Language Models in a Population-Based Cancer Registry Setting.

Population-based cancer registries (PBCRs) collect data on all new cancer diagnoses in a defined population. Data are sourced from pathology reports, and the PBCRs rely on manual and rule-based solutions. This study presents a state-of-the-art natural language processing (NLP) pipeline, built by fine-tuning pretrained language models (LMs). The pipeline is deployed at the British Columbia Cancer Registry (BCCR) to detect reportable tumors from a population-based feed of electronic pathology. We fine-tune two publicly available LMs, GatorTron and BlueBERT, which are pretrained on clinical text. Fine-tuning is done using BCCR's pathology reports. For the final decision making, we combine both models' output using an OR approach. The fine-tuning data set consisted of 40,000 reports from the diagnosis year of 2021, and the test data sets consisted of 10,000 reports from the diagnosis year 2021, 20,000 reports from diagnosis year 2022, and 400 reports from diagnosis year 2023. The retrospective evaluation of our proposed approach showed boosted reportable accuracy, maintaining the true reportable threshold of 98%. Disadvantages of rule-based NLP in cancer surveillance include manual effort in rule design and sensitivity to language change. Deep learning approaches demonstrate superior performance in classification. PBCRs distinguish reportability status of incoming electronic cancer pathology reports. Deep learning methods provide significant advantages over rule-based NLP.

Application of Ethephon Manually or via Drone Enforces Bud Dormancy and Enhances Flowering Response to Chilling in Litchi (Litchi chinensis Sonn.)

Ethephon (2-chloroethylphosphonic acid) is frequently used for flush management in order to maximize flowering in litchi. However, the optimal dosage of ethephon, which balances between flush control effect and the detrimental effect on leaves, is unknown. This study aimed to identify the optimal ethephon dosage and test more efficient ethephon application methods, using a drone for flush control and flowering promotion in litchi. The effects of a single manual full-tree spray of 250, 500 or 1000 mg/L of ethephon in early November on the bud break rate, leaf drop rate, net photosynthetic rate, LcFT1 expression and floral induction (panicle emergence rate and panicle number) in ‘Jingganghongnuo’ litchi were examined in the season of 2021–2022. In the season of 2022–2023, the effects of drone application of 1000 mg/L of ethephon in early November on bud growth and floral induction were observed. The results showed that the manual ethephon treatments were effective at enforcing bud dormancy and elongating the dormancy period and that the effects were positively dependent on dosage. One manual spray of 1000 mg/L of ethephon in late autumn enabled a dormancy period of 6 weeks. The treatments advanced seasonal abscission of old leaves in winter and caused short-term suppression on photosynthesis within 2 weeks after treatment. Ethephon treatments, especially at 1000 mg/L, enhanced the expression of LcFT1 in the mature leaves and promoted floral induction reflected by earlier panicle emergence and increased panicle emergence rate and number in the terminal shoot. The floral promotion effect was also positively dosage dependent. The cumulative chilling hours below 15 °C from the date of treatment to the occurrence of a 20% panicle emergence rate were lowered in ethephon treatments. A drone spray of 1000 mg/L of ethephon solution consumed a sixth of the manual spray solution volume and was two thirds less effective in suppressing bud break compared with manual spraying. However, it achieved a significant flowering promotion effect comparable to traditional manual spraying. The results suggest that ethephon application enhanced flowering responsiveness to chilling as well as enforced bud dormancy. The application of ethephon with a drone proved to be an efficient method for flush control and flower promotion.

Applied for Higher Order Bezier Curve using MATLAB

A Bézier curve is a parametric curve used in computer graphics and related fields. A set of discrete "control points" defines a smooth, continuous curve by means of a formula. The piecewise nature of a Bezier curve means that its representative equation is a linear combination of Bezier of particular degrees. The aim of this study is to infer Bézier curve graphs from higher orders using MATLAB. Where the applied analytical method was used I have reached .Will be clarified, and the following results have been reached is used in the linear curve association to express the distance ( on the line between the points and , In a second-order Bezier curve, we can create intermediate points such as and . These points have a value located in the interval , To obtain a Bezier curve for higher degrees, note that the idea in arriving at drawing the curve is to divide each line by placing a point on it and then connect the new points to each other (note that we get rid of a point at each stage), and we repeat the process until we have only one line left. So, we put ( on it and then we draw the curve. By comparing the manual solution and the solution using MATLAB, we find that the solution using MATLAB is faster and more accurate, especially at higher levels. And the study recommends the following : It is noted that the curve lies completely within the convex closure of the points, so these points are used with ease to form the required curve, it is also possible to apply geometric transformations (such as rotation and sliding) to the curve by applying this transformation to the control points of this curve.

Employing Machine Learning for Seismic Intensity Estimation Using a Single Station for Earthquake Early Warning

An earthquake early-warning system (EEWS) is an indispensable tool for mitigating loss of life caused by earthquakes. The ability to rapidly assess the severity of an earthquake is crucial for effectively managing earthquake disasters and implementing successful risk-reduction strategies. In this regard, the utilization of an Internet of Things (IoT) network enables the real-time transmission of on-site intensity measurements. This paper introduces a novel approach based on machine-learning (ML) techniques to accurately and promptly determine earthquake intensity by analyzing the seismic activity 2 s after the onset of the p-wave. The proposed model, referred to as 2S1C1S, leverages data from a single station and a single component to evaluate earthquake intensity. The dataset employed in this study, named “INSTANCE,” comprises data from the Italian National Seismic Network (INSN) via hundreds of stations. The model has been trained on a substantial dataset of 50,000 instances, which corresponds to 150,000 seismic windows of 2 s each, encompassing 3C. By effectively capturing key features from the waveform traces, the proposed model provides a reliable estimation of earthquake intensity, achieving an impressive accuracy rate of 99.05% in forecasting based on any single component from the 3C. The 2S1C1S model can be seamlessly integrated into a centralized IoT system, enabling the swift transmission of alerts to the relevant authorities for prompt response and action. Additionally, a comprehensive comparison is conducted between the results obtained from the 2S1C1S method and those derived from the conventional manual solution method, which is considered the benchmark. The experimental results demonstrate that the proposed 2S1C1S model, employing extreme gradient boosting (XGB), surpasses several ML benchmarks in accurately determining earthquake intensity, thus highlighting the effectiveness of this methodology for earthquake early-warning systems (EEWSs).

Accurate non-linear bending analytical solutions setting new benchmarks for rectangular thin plates with four simply supported edges

In the field of nonlinear structural analysis, the ability to provide accurate and reliable analytical solutions is of paramount importance. This paper presents more accurate nonlinear analytical solutions for rectangular plates with four simply supported edges, establishing a new benchmark that replaces and complements Lévy’s manual analytical solutions. These accurate solutions can serve as a reference for validating various nonlinear numerical and approximate analytical solutions, thereby providing a robust basis for engineering design. Notably, the central deflection error in this study is less than 0.005%, while the central stress error remains below 0.4%. The accuracy of the present solutions provided significantly exceeds that found in the existing literature.

An exact algorithm for unpaired pickup and delivery vehicle routing problem with multiple commodities and multiple visits

This paper addresses a new multi-commodity unpaired pickup and delivery vehicle routing problem in which each vehicle is allowed to visit each customer more than once for both pickup and delivery of each commodity. It is a complex variant of the classical capacitated vehicle routing problem and comes from resource transfer among different plants in a distributed manufacturing environment. Notably, the pairing decisions of pickup and delivery for each commodity and the routing decisions among customers are interdependent, and they need to be made simultaneously and collaboratively. Firstly, a mixed integer programming model is developed, and then new valid inequalities are derived to improve the linear programming relaxation. Afterwards, a branch-and-cut algorithm is proposed by exploring different branching strategies and tailored separation algorithms. Computational results based on real-case instances from an automobile manufacturing company demonstrate that the costs are considerably reduced by considering the multiple visits compared to the single visit of each customer. In addition, our proposed branch-and-cut algorithm outperforms a manual solution method adopted by the company in practice and two solution methods in the literature. Furthermore, two adaptations of our branch-and-cut algorithm also perform better than two state-of-the-art algorithms in solving two closely-related problems in terms of solution quality and computation time. Sensitivity analyses with respect to vehicle capacity, vehicle duration, and vehicle speed are conducted to derive several valuable managerial insights.

Automated Extension-Based Penetration Testing for Web Vulnerabilities

Depending on manual solutions for finding security vulnerabilities in web applications is time-consuming, error-prone, and requires high levels of expertise. This paper proposes a model for an automated extension-based penetration testing for web vulnerabilities that is compatible with any web application. It consists of three stages that start with information gathering, followed by a vulnerability assessment process to test for exploit. The results are then automatically generated as a report at the conclusion. To examine the model, a tool is developed based on the suggested model. Results demonstrate that the proposed technique has effectively and promptly identified application’s vulnerabilities.

A Simplified One-Parallel-Element Automatic Impedance-Matching Network Applied to Electromagnetic Acoustic Transducers Driving

Ultrasonic waves generated and received by electromagnetic acoustic transducers (EMATs) are advantageous in non-destructive testing, mainly due to the ability to operate without physical contact with the medium under test. Nevertheless, they present a main drawback of less efficiency, which leads to a lower signal-to-noise ratio. To overcome this, the L-network impedance-matching network is often used in order to ensure maximum power transfer to the EMAT from the excitation electronics. There is a wide range of factors that affect an EMAT’s impedance, apart from the transducer itself; namely, the properties of the specimen material, temperature, and frequency. Therefore, to ensure optimal power transfer, the matching network’s configuration needs to be fine-tuned often. Therefore, the automation of the laborious process of manually adjusting the network is of great benefit to the use of EMAT transducers. In this work, a simplified one-parallel-element automatic matching network is proposed and its theoretical optimal value is derived. Next, an automatic matching network was designed and fabricated. Experiments were performed with two different EMATs at several frequencies obtaining good agreement with theoretical predictions. The automatic system was able to determine the best configuration for the one-element matching network and provided up to 5.6 dB gain, similar to a standard manual solution and considerably faster.

Automated Fixing Cost Estimation of Photovoltaic System Failures for the Creation of a Decision Support System

The increasing focus on sustainability connected to extended lifetimes with guaranteed high energy yields in the photovoltaic (PV) sector brings new challenges in operating and maintaining PV systems. Additionally, as the PV Terawatt Age has been reached in 2022 and a sustained exponential PV deployment growth is expected, operation and maintenance (O&M) companies have an ever‐increasing portfolio of PV plants to operate while maintaining cost competitive. Therefore, a shift from manual fault detection and solution toward smart and automated alternatives is required to keep downtime due to faults at a minimum while ensuring that PV systems can operate safely and efficiently. This work extends past developments of an automated O&M decision support system (DSS) by focusing on the automation of selecting and prioritizing solutions in case of PV system event/failure appearance. Thereby, the TRUST‐PV Solution Matrix is added to the published TRUST‐PV Risk Matrix, providing a standardized list of solutions for all events and failures which can appear in a PV system. Furthermore, the Cost Priority Number, a prioritization methodology to assess technical failures and their economic impact in energy systems, is improved by integrating automated fixing cost calculations into the DSS.

Computational Analysis of Bifurcation of Raghuganga Hydropower Project

Computational analysis is the modern design optimization tool used widely for determining the effect of different loading parameters where operating conditions and geometry are complex for manual solutions to execute. This study has great significance in the design and optimization of penstock branches as the ancient technology used for the design has least chance of having minimum head loss and good structural strength at the same time. Bifurcation of Raghuganga Hydropower Project of 40 MW installed capacity is chosen for this study in which, head loss, velocity and pressure distribution and stress distribution around the branching regions have been observed by varying the angle of cone of bifurcation. Upon varying the cone angles gradually starting from 3 degrees up to 15 degrees, the values of head loss have been reduced from 0.972 m to 0.086 m till 13-degree angle of cone and upon further increasing the angle to 15 degrees, the head loss increased sharply to 2.201 m. Also, for the structural analysis on the optimized cone angle profile, pipe thickness was varied from 25 mm till the values of stress was in the acceptable range. Upon simulations, it was found that optimum pipe thickness is 40 mm and sickle reinforcement of 75 mm with the value of maximum stress (Von-Mises) at the branching to be 167 MPa and minimum factor of safety of 1.49 for the material chosen i.e. E 250 corresponding to I S 2062.

An object‐oriented approach toward two‐dimensional engineering mechanics

AbstractThe present work proposes an object‐oriented approach for the solution of problems in two‐dimensional engineering mechanics. New classes (in the terminology of object‐oriented programming) are proposed and implemented in the popular programming language ‘Python.’ These classes, along with the symbolic computation module of Python ‘sympy,’ enable one to reduce the solution of a large class of problems in undergraduate engineering mechanics to a set of Python statements. These statements are definitions of objects as instances of the proposed classes and calling of their relevant methods. If the thought process in the manual solution is represented by a flowchart, the present work can be viewed as a flowchart translator. As all the calculations are automatically performed, the present work relieves the student from the burden and fear of lengthy calculations. Different diagrammatic representations of velocity, acceleration, shear force, and bending moments are included for better physical understanding. It is believed that the proposed simple implementation would make problem‐solving and the learning process more enjoyable. Apart from a standard PC, the proposed work runs on a single‐board computer (tested in raspberry pi 4) and on an Android mobile device. A student feedback study ascertains the acceptability of the proposed method.

An automated optimization pipeline for clinical-grade computer-assisted planning of high tibial osteotomies under consideration of weight-bearing

3D preoperative planning for high tibial osteotomies (HTO) has increasingly replaced 2D planning but is complex, time-consuming and therefore expensive. Several interdependent clinical objectives and constraints have to be considered, which often requires multiple rounds of revisions between surgeons and biomedical engineers. We therefore developed an automated preoperative planning pipeline, which takes imaging data as an input to generate a ready-to-use, patient-specific planning solution. Deep-learning based segmentation and landmark localization was used to enable the fully automated 3D lower limb deformity assessment. A 2D-3D registration algorithm allowed the transformation of the 3D bone models into the weight-bearing state. Finally, an optimization framework was implemented to generate ready-to use preoperative plannings in a fully automated fashion, using a genetic algorithm to solve the multi-objective optimization (MOO) problem based on several clinical requirements and constraints. The entire pipeline was evaluated on a large clinical dataset of 53 patient cases who previously underwent a medial opening-wedge HTO. The pipeline was used to automatically generate preoperative solutions for these patients. Five experts blindly compared the automatically generated solutions to the previously generated manual plannings. The overall mean rating for the algorithm-generated solutions was better than for the manual solutions. In 90% of all comparisons, they were considered to be equally good or better than the manual solution. The combined use of deep learning approaches, registration methods and MOO can reliably produce ready-to-use preoperative solutions that significantly reduce human workload and related health costs.

Semi-automatic meteoroid fragmentation modeling using genetic algorithms

Context. Meteoroids are pieces of asteroids and comets. They serve as unique probes to the physical and chemical properties of their parent bodies. We can derive some of these properties when meteoroids collide with the atmosphere of Earth and become a meteor or a bolide. Even more information can be obtained when meteoroids are mechanically strong and slow enough to drop meteorites. Aims. Through physical modeling of bright meteors, we describe their fragmentation in the atmosphere. We also derive their mechanical strength and the mass distribution of the fragments, some of which may hit the ground as meteorites. Methods. We developed a semi-automatic program for meteoroid fragmentation modeling using parallel genetic algorithms. This allowed us to determine the most probable fragmentation cascade of the meteoroid, and also to specify its initial mass and velocity. These parameters can be used in turn to derive the heliocentric orbit of the meteoroid and to place constraints on its likely age as a separate object. Results. The program offers plausible solutions for the majority of fireballs we tested, and the quality of the solutions is comparable to that of manual solutions. The two solutions are not the same in detail, but the derived quantities, such as the fragment masses of the larger fragments and the proxy for their mechanical strength, are very similar. With this method, we would like to describe the mechanical properties and structure of both meteoroids belonging to major meteor showers and those that cause exceptional fireballs.

Inverse attitude solution of manipulator based on improved quaternion

Typically, quaternions or rotational matrices are used to establish kinematic equations and produce inverse kinematic solutions for the attitude of 6R decoupled manipulators. These approaches have certain drawbacks, such as duplicate equations and manual solution processes that cannot be eliminated automatically. In this study, we introduce the Ju-Gibbs quaternion to establish the kinematic equations, which are isomorphic to the Euler quaternion and share the same mathematical characteristics. Using this modeling method, one can create non-redundant kinematic equations wherein the number of equations equals the number of unknowns. A novel Dixon elimination method is then used to resolve the multilinear problem. Since no division operations are involved in the solution process, the solution has the advantage of being free of computation singularity issues. The experiment verifies that the proposed method can accomplish the autonomous modeling and elimination solution process of 6R manipulators with low computation complexity and high precision.

GAIL-PT: An intelligent penetration testing framework with generative adversarial imitation learning

Penetration testing (PT) is an efficient tool for network testing and vulnerability mining by simulating the hackers’ attacks to obtain valuable information applied in operating and database systems. Most of the traditional manual solutions are strongly relying on the domain knowledge of human experts with high penetration costs. Therefore, solutions based on the artificial intelligent algorithm such as reinforcement learning (RL) and deep reinforcement learning (DRL), with less time-consuming and lower labor costs, become a great solution to address the challenge. However, there are still a few challenges for RL/DRL-based PT in real penetration scenarios, such as the large dimension size of the agent’s discrete action space usually causing difficulties in convergence. To address the above issue, this paper proposes a novel framework named Generative Adversarial Imitation Learning based intelligent Penetration Testing (GAIL-PT), which utilizes expert knowledge base and GAIL network to guide the policy generation of RL/DRL agents with lower costs. Specifically, we first construct the expert knowledge bases by collecting state-action pairs from the successful exploitations of pre-trained RL/DRL models. Secondly, we feed the expert knowledge bases generated by different RL/DRL models online into the discriminator of GAIL-PT to guide its training process. Besides, we integrate the losses of the generator and the discriminator in GAIL-PT to optimize the overall objective and use the discriminator’s discounted rewards for policy generation. The extensive experiments conducted on the practical target hosts and simulated network scenarios demonstrate that GAIL-PT achieves outstanding performance, and outperforms the state-of-art method DeepExploit in exploiting Metasploitable2 and Q-learning in different scale networks. It also verified that GAIL-PT is a general leading framework suitable for RL/DRL-based methods. The code of GAIL-PT is open-sourced at https://github.com/Shulong98/GAIL-PT//.

Analysis of Implementation Project-Based Learning Model of Teaching Integrated with Computer Programming in Improving Computational Thinking Skills in a Classical Mechanics Course

This research aims to explore student computational thinking skills in implementing a project-based learning model of teaching integrated with computer programming in classical mechanics course in projectile motion topic. The research design uses one group pretest and post-test design. The computational thinking skills have five indicators: abstraction, generalization, decomposition, algorithm, and debugging. The computational thinking indicator was analyzed from the result of Pretest and post-test scores and a comparison between manual solution and numerical solution from computer programming. The instruments used in this study were tasks, rubrics, and questionnaires. The result shows the average score of the Pretest is 53.05, and the post-test score is 80.22. The student computational thinking skills in algorithm and debugging in Pretest are 29.70% and 24.30% and 59.00%, and 54.00% in the post-test stage. This result indicates the implementation of PBL model of Teaching integrated with computer programming has a significant impact on student computational thinking skills

Delineation of Mrutu Spring Protection Zone: An Attempt to Maintain the Sustainability of Groundwater Resources

Lumajang Regency government plans to optimize water resources using Mrutu Spring groundwater as a water source for the Drinking Water Supply System (SPAM). The maintenance of the groundwater quality and quantity sustainability is necessary to delineate the protection zone of Mrutu Spring. Geological, hydrogeological, and land use parameters assessed the spring protection zone. The Mrutu Spring protection zone determination was conducted using manual and analytical solutions and combination hydrogeological methods. This study finds that the protection zone of Mrutu Spring is around Mrutu Spring up to Mrutu Spring groundwater recharge in the northwest. Mrutu Spring protection zone is divided into protection zone I, II, III, and groundwater recharge for the spring protection zone. The geometry of protection zone I is a circle with a radius of 1.64 km and 314 m2. Protection zone II is in the fifth circle with a 1.64 km and 2.87 km2. Protection zone II has an ellipsoidal shape with a radius of 16.74 km and 67.28 km2. The groundwater recharge for the spring protection zone is oval, with a radius of ± 12 km and 57,85 km2.

World robot challenge 2020 – partner robot: a data-driven approach for room tidying with mobile manipulator

Tidying up a household environment using a mobile manipulator poses various challenges in robotics, such as adaptation to large real-world environmental variations, and safe and robust deployment in the presence of humans. The Partner Robot Challenge in World Robot Challenge (WRC) 2020, a global competition held in September 2021, benchmarked tidying tasks in real home environments, and, importantly, tested for full system performances. For this challenge, we developed an entire household service robot system, which leverages a data-driven approach to adapt to numerous edge cases that occur during the execution, instead of classical manual pre-programmed solutions. In this paper, we describe the core ingredients of the proposed robot system, including visual recognition, object manipulation, and motion planning. Our robot system won the second prize, verifying the effectiveness and potential of data-driven robot systems for mobile manipulation in home environments.

Automated Process Planning for Embossing and Functionally Grading Materials via Site-Specific Control in Large-Format Metal-Based Additive Manufacturing.

The potential for site-specific, process-parameter control is an attribute of additive manufacturing (AM) that makes it highly attractive as a manufacturing process. The research interest in the functionally grading material properties of numerous AM processes has been high for years. However, one of the issues that slows developmental progress in this area is process planning. It is not uncommon for manual programming methods and bespoke solutions to be utilized for site-specific control efforts. This article presents the development of slicing software that contains a fully automated process planning approach for enabling through-thickness, process-parameter control for a range of AM processes. The technique includes the use of parent and child geometries for controlling the locations of site-specific parameters, which are overlayed onto unmodified toolpaths, i.e., a vector-based planning approach is used in which additional information, such as melt pool size for large-scale metal AM processes, is assigned to the vectors. This technique has the potential for macro- and micro-structural modifications to printed objects. A proof-of-principle experiment is highlighted in which this technique was used to generate dynamic bead geometries that were deposited to induce a novel surface embossing effect, and additional software examples are presented that highlight software support for more complex objects.

An IoT-based intelligent irrigation system with data fusion and a self-powered wide-area network

Water resources have a great influence on human society, but saving water in irrigation still remains a challenge. This article proposes an intelligent irrigation system that integrates a data fusion model and a long-rang (LoRa) network for optimizing the watering schedule. A data fusion model is proposed, which first adopts the long short-term memory (LSTM) network to simulate and predict the proper watering demands by integrating multi-source heterogeneous data, that is, historical weather data, user irrigation logs, weather forecasts, and online monitoring sensor data. A self-powered wide-area network is implemented and deployed by using LoRa to facilitate multiple Internet of Things (IoT) application scenarios. It includes a gateway and two types of nodes: a valve node and a sensing node. The node is capable of energy autonomy through the scheme of waterflow-based power generation, thus realizing maintenance-free throughout the life cycle. A cloud platform is designed to provide network management, intelligent irrigation control, and the interface of the mobile application. The proposed system is evaluated through a case study of landscape watering. On average, the proposed system achieves a water-saving efficiency of 94.74% compared with the conventional manual setting solutions.