Computer-aided Framework Research Articles

Multi-Period Operational Modelling and Optimization for Large-Scale Natural Gas Networks Considering Linepack Functions in Long-Distance Transmission Pipelines

As a promising energy resource, offshore natural gas is primarily used for power generation. The comprehensive offshore gas-to-power system, which includes extraction, treatment, compression, pipeline transmission, and power generation, is extensive and operates within various regulatory, operational, and financial constraints. This complexity offers opportunities to optimize one or more system operations to enhance profitability while fulfilling user demands and environmental considerations. In this research, we present a model-based, computer-aided framework that intuitively connects upstream natural gas operations with downstream power generation and distribution. We develop a multi-period Mixed-Integer Nonlinear Programming (MINLP) model that integrates gas treatment, compression, and long-distance transmission with power generation. The model combines first-principle mechanistic process models with a linepack model that calculates the gas volume storable in long-distance pipelines for transmission. The linepack model facilitates gas storage and withdrawal across different periods to accommodate demand scheduling. We apply this framework using the MINLP model in three scenarios: profit maximization, cost minimization, and supply-demand balancing using linepack. The results demonstrate improved economic performance for offshore natural gas-based power generation in China under varying periodic power demands.

Computer-aided framework for the design of entrainer for palm process residue recovery

Oleochemical industry produced substantial palm process residue during hydrogenation process of fatty acid/methyl ester, containing medium- to long-chain fatty alcohols and alkanes with overlapping boiling points. Recovering fatty alcohols for sale and utilizing alkanes for jet fuel, lubricants, and gasoline is beneficial. However, separating them through conventional distillation (CD) is challenging and expensive due to the difficulty in achieving the necessary temperature differentials for phase changes, especially with high reflux ratio required. To address this challenge, extractive distillation (ED) with an entrainer, designed through computer-aided molecular design (CAMD), was employed. However, implementing ED with a high boiling entrainer is challenging due to the high boiling point of the target components. Therefore, the design of the entrainer focused on the relative volatilities (α) of involved components and associated utility costs. Then, Aspen HYSYS was employed to evaluate the performance of the designed entrainer through product purity and economic analysis. For the separation of C10OH and n-C12, octane and dimethylcyclohexane were generated as entrainers. Dimethylcyclohexane entrainer demonstrated superior separation and generated higher profit than octane entrainer. For the separation of C12OH and n-C14, n-C15 was generated as entrainer to replace the infeasible CD. Therefore, the study concluded that ED with tailored entrainer can effectively replace CD for separating fatty alcohols from alkanes, demonstrating significant industrial feasibility.

Large-scale optimization of nonconvex MINLP refinery scheduling

Modeling and optimization of large-scale refinery scheduling problems is challenging because of their complexity and size. Herein, we propose a mathematical model to represent such problems more accurately and realistically, and a state-of-the-art optimization framework for its solution. The framework leverages the use of mathematical optimization and algorithmic methods by combining modeling approaches (process design, model decompositions), solving strategies (rescheduling, heuristics), and machine learning regression (surrogate models). An industrial-size refinery scheduling problem (2 blenders, 4 feed tanks, distillation network with 5 towers, processing network with FCC, hydrotreaters, debutanizers, superfractionator, catalytic reformer) is formulated as a hierarchical nonconvex mixed-integer nonlinear programming (MINLP) model and is successfully optimized, providing higher profitability and more efficient scheduling operations considering 12 feedstocks, 10 products and multiple scenarios for time horizon and step. Results highlight the importance of tuning scheduling parameters and employing an enhanced computer-aided framework to enable the solution of industrial refinery scheduling operations.

Reinforced Computer-Aided Framework for Diagnosing Thyroid Cancer.

Thyroid cancer is the most pervasive disease in the endocrine system and is getting extensive attention. The most prevalent method for an early check is ultrasound examination. Traditional research mainly concentrates on promoting the performance of processing a single ultrasound image using deep learning. However, the complex situation of patients and nodules often makes the model dissatisfactory in terms of accuracy and generalization. Imitating the diagnosis process in reality, a practical diagnosis-oriented computer-aided diagnosis (CAD) framework towards thyroid nodules is proposed, using collaborative deep learning and reinforcement learning. Under the framework, the deep learning model is trained collaboratively with multiparty data; afterward classification results are fused by a reinforcement learning agent to decide the final diagnosis result. Within the architecture, multiparty collaborative learning with privacy-preserving on large-scale medical data brings robustness and generalization, and diagnostic information is modeled as a Markov decision process (MDP) to get final precise diagnosis results. Moreover, the framework is scalable and capable of containing more diagnostic information and multiple sources to pursue a precise diagnosis. A practical dataset of two thousand thyroid ultrasound images is collected and labeled for collaborative training on classification tasks. The simulated experiments have shown the advancement of the framework in promising performance.

Platform for Learning and Virtual Reality in Animal Husbandry

Nowadays, digital technologies are extensively used in the field of education. Virtual and augmented reality and 3D technologies are entering the field of education at all educational levels. They are a prerequisite for the application of new approaches in the presentation of the educational content and its easier perception and assimilation by the learners. The paper presents an integrated platform for open science and educational resource sharing, as well as an environment for distance learning and data analysis in animal husbandry derived from the learning resources of a given course in the system. The research is aimed at developing a computer-aided framework in the field of digitized education and creating new educational resources for distance learning in animal husbandry.

Projector-based augmented stacking framework for irregularly shaped objects

Augmented reality in additive fabrication is predominantly applied to the manufacturing of structures from regularly shaped materials. Our work however embraces natural heterogeneity, by focusing on the assembly of irregularly shaped elements such as mineral scraps. We introduce a computer-aided framework with a 3D stacking engine and an augmented reality interface capable of guiding users through the balanced positioning of discrete and highly nonuniform objects according to an on-the-fly computed model and without prior trimming of the building unit. The pipeline is tested by the construction of two dry-stone structures (i.e., lacking any adhesives), and its accuracy is validated with a comparative study between the point cloud of the as-built digitized artifacts and the generated execution model, which shows an average 2.9 ± 1.8 cm error between the stones of the two models. We finally show how the proposed framework could be improved both in terms of software and hardware. In the interests of reproducibility, all the methods are shared as open source with the community.Graphical abstract

Point cloud-based optimization of roadside LiDAR placement at constructed highways

Current approaches for optimizing the placement of roadside LiDAR (RSL) at constructed highways work on handcrafted scenes which fail to precisely map real-world situations. This study proposes a computer-aided framework to address the issue. First, high-accuracy point cloud data are introduced to model the as-built highway infrastructures, based on which an unsupervised clustering approach is applied to segment the target monitoring area (TMA). Then, candidate RSL locations are generated in a semi-automated manner combining manual delineation and spline resampling. Next, new deterministic and a U-net-based LiDAR models are separately developed to virtually estimate candidate RSL's joint coverage. Finally, based on the proposed sensor models, a detection matrix is created to facilitate the application of binary integer programming that minimizes the number of RSL while ensuring complete coverage of TMA. The tests on point cloud data of the three different sites demonstrate the effectiveness of the proposed workflow.

Development of a Fully Automated Graf Standard Plane and Angle Evaluation Method for Infant Hip Ultrasound Scans.

Background: Graf’s method is currently the most commonly used ultrasound-based technique for the diagnosis of developmental dysplasia of the hip (DDH). However, the efficiency and accuracy of diagnosis are highly affected by the sonographers’ qualification and the time and effort expended, which has a significant intra- and inter-observer variability. Methods: Aiming to minimize the manual intervention in the diagnosis process, we developed a deep learning-based computer-aided framework for the DDH diagnosis, which can perform fully automated standard plane detection and angle measurement for Graf type I and type II hips. The proposed framework is composed of three modules: an anatomical structure detection module, a standard plane scoring module, and an angle measurement module. This framework can be applied to two common clinical scenarios. The first is the static mode, measurement and classification are performed directly based on the given standard plane. The second is the dynamic mode, where a standard plane from ultrasound video is first determined, and measurement and classification are then completed. To the best of our knowledge, our proposed framework is the first CAD method that can automatically perform the entire measurement process of Graf’s method. Results: In our experiments, 1051 US images and 289 US videos of Graf type I and type II hips were used to evaluate the performance of the proposed framework. In static mode, the mean absolute error of α, β angles are 1.71° and 2.40°, and the classification accuracy is 94.71%. In dynamic mode, the mean absolute error of α, β angles are 1.97° and 2.53°, the classification accuracy is 89.51%, and the running speed is 31 fps. Conclusions: Experimental results demonstrate that our fully automated framework can accurately perform standard plane detection and angle measurement of an infant’s hip at a fast speed, showing great potential for clinical application.

Computer-Aided Classification Framework of Parkinsonian Disorders Using 11C-CFT PET Imaging.

PurposeTo investigate the usefulness of a novel computer-aided classification framework for the differential diagnosis of parkinsonian disorders (PDs) based on 11C-methyl-N-2β-carbomethoxy-3β-(4-fluorophenyl)-tropanel (11C-CFT) positron emission tomography (PET) imaging.MethodsPatients with different forms of PDs—including Parkinson's disease (PD), multiple system atrophy (MSA) and progressive supranuclear palsy (PSP)—underwent dopamine transporter (DAT) imaging with 11C-CFT PET. A novel multistep computer-aided classification framework—consisting of magnetic resonance imaging (MRI)-assisted PET segmentation, feature extraction and prediction, and automatic subject classification—was developed. A random forest method was used to assess the diagnostic relevance of different regions to the classification process. Finally, the performance of the computer-aided classification system was tested using various training strategies involving patients with early and advanced disease stages.ResultsAccuracy values for identifying PD, MSA, and PSP were 85.0, 82.2, and 89.7%, respectively—with an overall accuracy of 80.4%. The caudate and putamen provided the highest diagnostic relevance to the proposed classification framework, whereas the contribution of midbrain was negligible. With the exception of sensitivity for diagnosing PSP, the strategy comprising both early and advanced disease stages performed better in terms of sensitivity, specificity, positive predictive value, and negative predictive value within each PDs subtype.ConclusionsThe proposed computer-aided classification framework based on 11C-CFT PET imaging holds promise for improving the differential diagnosis of PDs.

A Lightweight Approach for Skin Lesion Detection Through Optimal Features Fusion

Skin diseases effectively influence all parts of life. Early and accurate detection of skin cancer is necessary to avoid significant loss. The manual detection of skin diseases by dermatologists leads to misclassification due to the same intensity and color levels. Therefore, an automated system to identify these skin diseases is required. Few studies on skin disease classification using different techniques have been found. However, previous techniques failed to identify multi-class skin disease images due to their similar appearance. In the proposed study, a computer-aided framework for automatic skin disease detection is presented. In the proposed research, we collected and normalized the datasets from two databases (ISIC archive, Mendeley) based on six Basal Cell Carcinoma (BCC), Actinic Keratosis (AK), Seborrheic Keratosis (SK), Nevus (N), Squamous Cell Carcinoma (SCC), and Melanoma (M) common skin diseases. Besides, segmentation is performed using deep Convolutional Neural Networks (CNN). Furthermore, three types of features are extracted from segmented skin lesions: ABCD rule, GLCM, and in-depth features. AlexNet transfer learning is used for deep feature extraction, while a support vector machine (SVM) is used for classification. Experimental results show that SVM outperformed other studies in terms of accuracy, as AK disease achieved 100% accuracy, BCC 92.7%, M 95.1%, N 97.8%, SK 93.1%, SCC 91.4% with a global accuracy of 95.4%.

Computer-Aided Framework for the Design of Optimal Bio-Oil/Solvent Blend with Economic Considerations

A major obstacle in utilising pyrolysis bio-oil as biofuel is its relatively low heating value, high viscosity, and non-homogeneity. Solvent addition is a simple yet practical approach in upgrading pyrolysis bio-oil. However, most solvents are often manufactured as specialty chemicals, and thus, this leads to a high production cost of solvents. It is crucial for the designed solvent-oil blend to achieve both fuel functionality and economic targets to be competitive with the conventional diesel fuel. Hence, the objective of this work is to generate feasible solvent candidates by solving this multi-objective optimisation (MOO) problem via a computer-aided molecular design (CAMD) approach. Initially, an optimisation model was developed to identify potential solvents that satisfied the predefined targeted properties. Next, a MOO model was developed via a fuzzy optimisation approach to identify the trade-off between profitability and heating value of the solvent-oil blend. A pricing model was employed to estimate the profitability of the solvent-oil blend. The production of bio-oil in a pyrolysis plant was used to illustrate the applicability of the pricing model. Lastly, phase stability analysis was conducted to ensure the stability and miscibility of the solvent-oil blend. With the developed framework, a promising and cost-effective solvent-oil blend can be generated while displaying optimal biofuel properties.

Virtual analysis of urban road visibility using mobile laser scanning data and deep learning

This study proposes a new computer-aided framework for virtually analyzing urban road visibility using mobile laser scanning (MLS) data. The proposed framework compromises three main parts: 1) based on the data reorganization procedure, the 3D U-net is successfully introduced to tackle the issue of non-stationary noises that significantly hinders accurate detections of stationary sight obstructions, 2) a multi-step procedure is developed to extract the road areas to be estimated and fill data gaps caused by occlusions, and 3) a virtual scanning method (VSM) is proposed to achieve a fast and accurate visibility assessment of the extracted road areas. The proposed VSM also facilitates the application of deep neural networks in the automated driving domain to classify sight obstacles. By enabling multiple outputs, the proposed virtual framework provides a comprehensive understanding of urban road visibility, which can help road administrators detect and understand poor-visibility locations on urban streets.

Computer-aided engineering of a branching sucrase for the glucodiversification of a tetrasaccharide precursor of S. flexneri antigenic oligosaccharides

Enzyme engineering approaches have allowed to extend the collection of enzymatic tools available for synthetic purposes. However, controlling the regioselectivity of the reaction remains challenging, in particular when dealing with carbohydrates bearing numerous reactive hydroxyl groups as substrates. Here, we used a computer-aided design framework to engineer the active site of a sucrose-active mathrm{alpha }-transglucosylase for the 1,2-cis-glucosylation of a lightly protected chemically synthesized tetrasaccharide, a common precursor for the synthesis of serotype-specific S. flexneri O-antigen fragments. By targeting 27 amino acid positions of the acceptor binding subsites of a GH70 branching sucrase, we used a RosettaDesign-based approach to propose 49 mutants containing up to 15 mutations scattered over the active site. Upon experimental evaluation, these mutants were found to produce up to six distinct pentasaccharides, whereas only two were synthesized by the parental enzyme. Interestingly, we showed that by introducing specific mutations in the active site of a same enzyme scaffold, it is possible to control the regiospecificity of the 1,2-cis glucosylation of the tetrasaccharide acceptor and produce a unique diversity of pentasaccharide bricks. This work offers novel opportunities for the development of highly convergent chemo-enzymatic routes toward S. flexneri haptens.

Deep learning methods for predicting brain abnormalities and compute human cognitive power using fMRI

In modern times, digital medical images play a significant progression in clinical diagnosis to treat the populace earlier to hoard their lives. Magnetic Resonance Imaging (MRI) is one of the most advanced medical imaging modalities that facilitate scanning various parts of the human body like the head, chest, abdomen, and pelvis and identify the diseases. Numerous studies on the same discipline have proposed different algorithms, techniques, and methods for analyzing medical digital images, especially MRI. Most of them have mainly focused on identifying and classifying the images as either normal or abnormal. Computing brainpower is essential to understand and handle various brain diseases efficiently in critical situations. This paper knuckles down to design and implement a computer-aided framework, enhancing the identification of humans’ cognitive power from their MRI. Images. The proposed framework converts the 3D DICOM images into 2D medical images, preprocessing, enhancement, learning, and extracting various image information to classify it as normal or abnormal and provide the brain’s cognitive power. This study widens the efficient use of machine learning methods, Voxel Residual Network (VRN), with multimodality fusion architecture to learn and analyze the image to classify and predict cognitive power. The experimental results denote that the proposed framework demonstrates better performance than the existing approaches.

Machine Learning and XAI approaches for Allergy Diagnosis

This work presents a computer-aided framework for allergy diagnosis which is capable of handling comorbidities. The system was developed using datasets collected from allergy testing centers in South India. Intradermal skin test results of 878 patients were recorded and it was observed that the data contained very few samples for comorbid conditions. Modified data sampling techniques were applied to handle this data imbalance for improving the efficiency of the learning algorithms. The algorithms were cross-validated to choose the optimal trained model for multi-label classification. The transparency of the machine learning models was ensured using post-hoc explainable artificial intelligence approaches. The system was tested by verifying the performance of a trained random forest model on the test data. The training and validation accuracy rate of the decision tree, support vector machine and random forest are 81.62, 81.04 and 83.07 respectively. During evaluation, random forest achieved a rate of 86.39 accuracy overall, and 75% sensitivity for the comorbid Rhinitis-Urticaria class. The framework along with all the functionalities were deployed on mobile devices. The average performance of the clinicians before and after using the decision support system were 77.21% and 81.80% respectively. The diagnosis system integrated with mobile applications serves as a source of information whereby junior clinicians can use it to confirm their diagnostic predictions.

Computer-aided identification of degenerative neuromuscular diseases based on gait dynamics and ensemble decision tree classifiers.

This study proposes a reliable computer-aided framework to identify gait fluctuations associated with a wide range of degenerative neuromuscular disease (DNDs) and health conditions. Investigated DNDs included amyotrophic lateral sclerosis (ALS), Parkinson's disease (PD), and Huntington's disease (HD). We further performed a statistical and classification comparison elucidating the discriminative capability of different gait signals, including vertical ground reaction force (VGRF), stride duration, stance duration, and swing duration. Feature representation of these gait signals was based on statistical amplitude quantification using the root mean square (RMS), variance, kurtosis, and skewness metrics. We investigated various decision tree (DT) based ensemble methods such as bagging, adaptive boosting (AdaBoost), random under-sampling boosting (RUSBoost), and random subspace to tackle the challenge of multi-class classification. Experimental results showed that AdaBoost ensembling provided a 6.49%, 0.78%, 2.31%, and 2.72% prediction rate improvement for the VGRF, stride, stance, and swing signals, respectively. The proposed approach achieved the highest classification accuracy of 99.17%, sensitivity of 98.23%, and specificity of 99.43%, using the VGRF-based features and the adaptive boosting classification model. This work demonstrates the effective capability of using simple gait fluctuation analysis and machine learning approaches to detect DNDs. Computer-aided analysis of gait fluctuations provides a promising advent to enhance clinical diagnosis of DNDs.

A framework for the development of Pedagogical Process Simulators (P2Si) using explanatory models and gamification

Process simulators are powerful supporting tools employed at all educational levels of engineering education. Meanwhile, digitalization is obliging the educational systems to adapt. In this new era marked by the Industry 4.0 movement, the formulation and implementation of models are fundamental for process digitalization; therefore, students and new trainees must be familiar with process models, simulators and programming. In this work, a computer-aided framework for the development of process simulators is proposed (P2Si). This framework integrates the following aspects: (i) the use, reuse, and explanation of process models; (ii) a tailored learning design; (iii) game elements; and, (iv) the use of students as co-designers through participatory design to improve the human-computer interaction. Through the application of a series of hierarchical steps, the framework’s workflow aims to arrive at a promising candidate to facilitate the teaching of processes. Furthermore, a proof of concept is developed for the teaching and training of undergraduate students, where the case of an aerobic microbial conversion process at industrial scale is explored. By applying this framework, we obtained the conceptual design of a pedagogical process simulator, which was then implemented as a prototype software platform, BioVL (www.biovl.com), for further development and testing. The main output of this work is the conceptual design of pedagogical process simulators integrating gamification and the use of process models as educational tools. In conclusion, the proposed framework has shown its merit when designing a computer-aided tool suited to support the transition towards the increased industrial digitalization as well as to address current educational challenges.

Computer-aided diagnosis and regional segmentation of nasopharyngeal carcinoma based on multi-modality medical images.

Nasopharyngeal carcinoma (NPC) is a category of tumors with high incidence in head-and-neck (H&N) body region, and the diagnosis and treatment planning are usually conducted by radiologists manually, which is tedious, time-consuming and unrepeatable. In this paper, we integrated different stages of this process and proposed a computer-aided framework to realize automatic detection, tumor region and sub-region segmentation, and visualization of NPC, which are usually investigated separately in literatures. Multi-modality images are utilized in the framework. Firstly, NPC is detected by a convolutional neural network (CNN) on computed tomography (CT) scans. Then, NPC area is segmented from magnetic resonance imaging (MRI) images by using a multi-modality MRI fusion network. Thirdly, NPC sub-regions with different metabolic activities are divided on CT images of the same patient via an adaptive threshold algorithm. Finally, 3D surface model of NPC is generated for observing its shape, size, and location in the head region. The proposed method is compared with other algorithms by evaluation on the volumes and shapes of detected NPCs. Experiments are conducted on CT images of 130 NPC patients and 102 subjects without NPC and MRI images of 149 NPC patients, among which 52 subjects are overlapped with both CT and MRI images. The reference for evaluation is generated by three experienced radiologists. The results demonstrated that our utilized models outperform other strategies with detection accuracy 0.882 and Dice similarity coefficient 0.719 for NPC segmentation. Sub-region division and the 3D visualized models show great acceptability in clinical usage. The remarkable performance indicated the potential of our framework in alleviating workload of radiologist. Furthermore, the combined usage of multi-modality images is able to generate reliable segmentations of NPC area and sub-regions, which provide evidence to judge the heterogeneity among patients and guide the dose painting for radiation therapy.

An Analysis of Medical Informatics and Application of Computer-Aided Decision Support Framework

Due to the advent of technology in the medical sector, the future of the Computer-Aided Decision (CAD) is promising as a support system for the processing of images. Since there is significant results reported due to the application of diagnostic radiology in the healthcare facility, radiologists are looking forward to enhancing medical and bioinformatics using CAD. Medical evaluations and trials have been done over the past few decades to aid in the optimization of accurate programs and evaluate the real contributions of CAD in the medical informatics interpretation procedures. Health experts and radiologists utilizing patient outputs from fundamental application of CAD are placed in the best position to focus on the final decisions concerning the performance of patients and diagnosis. However, researches have shown that the computer outputs require not projecting significant general accuracy compared to a certain radiologist to enhance patients’ performance. The volume and measure of the present patient data including their complexity to enhance the process of making proper healthcare decisions while making it problematic for healthcare practitioners and physicians to facilitate the management of patients. This condition calls for the usage of biomedical informatics methodologies to effectively process information, create biomedical implementations and informatics frameworks for CAD support systems. With that regard, this paper evaluates the medical and bioinformatics based on the application of CAD systems. It further projects on the applications of the systems, their application guidelines and techniques. The paper ends with the analysis of the future problems and directions of the CAD support framework.

On building a smarter ecosystem using the internet of intelligent things: progress and future challenges

With a growing interest in the Internet of Things (IoT), the businesses are undergoing a revolution in the way they monitor and control. In the recent past, many applications were developed using the IoT system architectures in various business verticals such as industrial, healthcare, farming, transportation, etc. However, with the development of low-complex artificial intelligence frameworks which are capable of operating on the edge devices, the IoT architectures have taken a major leap leading to the Internet of Intelligent Things (IoIT). In this paper, we discuss our focused research and applications of IoIT across the following verticals: (1) healthcare, (2) smart buildings, (3) farming, along with the recent state of the art methodologies and future challenges. Under the healthcare, we laid our main focus on the development of AI enabled computer-aided diagnosis framework, which acquires the scanning information from a wireless ultrasound transducer and automatically identifies the abnormalities present. Also, we developed a low-complex brain-controlled IoT environments framework which automatically classifies the motor imagery task performed by the user using 22 channel electroencephalography. Using IoIT, we developed a novel non-invasive technology capable of monitoring various electrical parameters without any need for cutting the wires. This developed non-invasive power monitor is capable of generating real-time alerts in the case of system malfunctions and will be a key enabler for smart buildings. Also, we developed mathematical, simulation, and experimental models for analyzing the performance of channel access mechanisms of dense traffic IoT networks.