Extensive Expertise Research Articles

“Decoding Bird Species Diversity through Image Analysis

Bird species diversity plays an integral role in maintaining ecosystem equilibrium and serves as a significant indicator of environmental health. However, the meticulous monitoring and cataloging of bird species within specific regions pose considerable challenges, often requiring extensive time and expertise from ornithologists. In today's rapidly advancing technological landscape, the integration of image analysis and machine learning presents a promising avenue to streamline bird species identification and diversity assessment processes. Nonetheless, the increasing rarity of certain bird species presents a formidable obstacle, complicating their classification. Birds encountered across diverse environments present varying sizes, shapes, colors, and orientations, adding complexity to accurate identification via image analysis. Moreover, image- based classification exhibits more pronounced variations compared to audio classification, although human perception of birds through images remains intuitively comprehensible. Leveraging the deep convolutional neural network (DCNN) algorithm, images undergo conversion into grayscale format to generate autographs using TensorFlow, resulting in the creation of multiple comparison nodes. Subsequently, these nodes undergo comparison with the testing dataset, generating a score sheet for analysis. Interpretation of this score sheet facilitates the prediction of the target bird species based on the highest score achieved. Experimental analysis conducted on datasets such as Caltech-UCSD Birds demonstrates the algorithm's efficacy, with bird identification accuracy ranging between 80% and 90%.

QML Powered Interface for Diffusion Imaging

In the field of medical imaging, Diffusion Imaging (DI) has emerged as a powerful technique for investigating the microstructural properties of biological tissues. However, the complexity of DI analysis software often poses a significant barrier to its widespread adoption, as it typically requires proficiency in Python programming and command-line interactions. This technical barrier can limit the accessibility of DI technology to individuals without extensive technical expertise, hindering its potential impact in various medical and research applications To address this challenge, we propose a novel solution that leverages the capabilities of Query Markup Language (QML) to develop a user-friendly interface for Diffusion Imaging. By combining the power of Python technology, which forms the core of DI analysis, with the intuitive interface design capabilities of QML, our project aims to democratize DI analysis and make it accessible to a broader audience, including medical professionals, researchers, and students. Our research focuses on bridging the gap between the technical complexities of DI analysis and user accessibility. The proposed QML-powered interface will feature modern UI elements with fluid animations, ensuring a seamless and engaging user experience. Crucially, it will abstract away the intricacies of Python programming and command-line interactions, allowing users to concentrate on the analysis and interpretation of DI data without the burden of technical hurdles.

Development of Arabic Language Curriculum Focused on Diversity and Inclusion

This literature review explores the development of an Arabic language curriculum prioritizing diversity and inclusion in an interconnected global context. It aims to formulate a curriculum catering to learners from diverse cultural backgrounds, abilities, and learning preferences, ensuring fair access and meaningful engagement. The methodology involves an extensive literature review, expert consultations, and data collection through surveys, interviews, and focus group discussions. Thematic coding and triangulation facilitate data analysis, revealing the importance of integrating diverse perspectives and inclusive pedagogical approaches. The study emphasizes nurturing an inclusive learning environment that embraces differences and fosters mutual respect. It highlights implications for educators, curriculum developers, and policymakers, stressing deliberate efforts to address diversity and inclusion within Arabic language education. Inclusive practices can effectively address diverse learner needs, promote cross-cultural understanding, and cultivate belonging. This research advances inclusive language education and encourages further exploration in this critical field.

Retrofitting Battery Electric Machinery with Unchanged Hydraulic System and Enhanced Control Strategies

The push for environmental sustainability has accelerated the acceptance of electric vehicles, as well as the exploration of electrified Non-Road Mobile Machinery. This study emphasizes the challenges of electrifying off-highway machinery, which include the many machinery layouts and the presence of Small- and Medium-sized Enterprises in the market. Recognizing the barriers faced by these companies, this paper shows how modeling and simulation can be effective tools for system integration and control optimization, even when lacking extensive expertise in the topic. However, it emphasizes the need for user-friendly modeling tools and methods adaptable to the operational needs of Small- and Medium-sized Enterprises. This study presents a case study of a retrofitted battery-electric hydraulic material handler. The machinery is simulated using Simscape, and the accuracy of the model is confirmed through experimental validation. By simulating a rational duty cycle, this study proposes two solutions for performance enhancement while maintaining the integrity of the hydraulic system. These solutions offer a balanced compromise between energy consumption and productivity and a novel control algorithm to minimize energy consumption. Most importantly, the two proposed solutions can be easily switched by the operator, which can decide to favor productivity over energy saving based on driving needs.

AnVILWorkflow: A runnable workflow package for Cloud-implemented bioinformatics analysis pipelines.

Advancements in sequencing technologies and the development of new data collection methods produce large volumes of biological data. The Genomic Data Science Analysis, Visualization, and Informatics Lab-space (AnVIL) provides a cloud-based platform for democratizing access to large-scale genomics data and analysis tools. However, utilizing the full capabilities of AnVIL can be challenging for researchers without extensive bioinformatics expertise, especially for executing complex workflows. Here we present the AnVILWorkflow R package, which enables the convenient execution of bioinformatics workflows hosted on AnVIL directly from an R environment. AnVILWorkflowsimplifies the setup of the cloud computing environment, input data formatting, workflow submission, and retrieval of results through intuitive functions. We demonstrate the utility of AnVILWorkflowfor three use cases: bulk RNA-seq analysis with Salmon, metagenomics analysis with bioBakery, and digital pathology image processing with PathML. The key features of AnVILWorkflow include user-friendly browsing of available data and workflows, seamless integration of R and non-R tools within a reproducible analysis pipeline, and accessibility to scalable computing resources without direct management overhead. While some limitations exist around workflow customization, AnVILWorkflowlowers the barrier to taking advantage of AnVIL's resources, especially for exploratory analyses or bulk processing with established workflows. This empowers a broader community of researchers to leverage the latest genomics tools and datasets using familiar R syntax. This package is distributed through the Bioconductor project (https://bioconductor.org/packages/AnVILWorkflow), and the source code is available through GitHub (https://github.com/shbrief/AnVILWorkflow).

Lived experiences of caregivers with infants treated at home with continuous invasive or noninvasive ventilation.

Caring for children dependent upon continuous invasive ventilation in the home setting requires extensive expertise, coordination, and can result in impaired caregiver quality of life. Less is known regarding the experiences of caregivers with children requiring continuous noninvasive ventilation. To evaluate caregiver experiences with invasive and noninvasive home mechanical ventilation, and to compare parental quality of life based on the child's mode of ventilation. Caregivers of infants who were discharged home with continuous ventilatory support were recruited to complete semi-structured qualitative interviews. Interviews explored their decision-making process, the transition to home, and health related quality of life. Caregivers of 16 children were interviewed, of whom eight were treated with continuous invasive ventilation, and eight with continuous noninvasive ventilation. The decision to pursue home ventilation in both groups was greatly influenced by the desire to be discharged and reunite the family at home. Following the transition to home, caregivers from both groups described high rates of insomnia, emotional distress, work disruption and familial hardship. Despite this, parents were overwhelmingly pleased with the decision to proceed with home ventilation and perceived their children to be living enriched lives outside of the hospital. Factors associated with easing the transition to home were in-hospital training and the presence of a robust support system. Lives of families with children dependent on continuous mechanical ventilation are characterized by isolation, lifestyle disruption, adverse mental and physical health consequences, and impaired interpersonal relationships, irrespective of the mode of ventilation.

Evaluation of Three-Dimensional Reconstruction Technology in Precision Hepatectomy for Primary Liver Cancer

Abstract Background Primary Liver Cancer has become a potent threat to the world due to its high morbidity and mortality rate. Up till now, Liver transplantation is the most suggested treatment but it is not feasible owing to the unavailability of donors and high cost. Hepatectomy provides an alternative treatment to this deadliest disease. Precision hepatectomy is performed with the aid of traditional 2 dimensional technology and image processing such as CT scan and Magnetic Resonance Imaging. However, it requires extensive expertise and pose challenges to the young doctors in decision making. Modern imaging and computer technology has opened the new avenues in medical field with the advent of 3 dimensional Reconstruction and visualization methods. Material and Methods We conducted a cohort retrospective study. In this study, we tried to evaluate the efficacy an impacts of 3 dimensional reconstruction on the preoperative planning of hepatectomy, intraoperative conditions and postoperative complications. We took 95 patients and divided them in two groups A and B. Group A has 67 patients who underwent hepatectomy before the application of 3 dimensional reconstruction and 28 patients on whom hepatectomy was performed according to the planning and methods of 3dimensional reconstruction and results were evaluated. Results Our study found that 3 dimensional reconstruction can help in better diagnosis, resection planning and reduce the postoperative complication. Results were not significant difference p > 0.05 on the incidence of postoperative complication between group A and B. Results were significant p < 0.05 for the intraoperative blood loss, optimal surgery time and postoperative hospitalization. Conclusion Hence, 3 dimensional reconstruction is a landmark discovery in medical sciences for the accurate evaluation and resection of complex liver cancers.

PROMPT: A Fast and Extensible Memory Profiling Framework

Memory profiling captures programs’ dynamic memory behavior, assisting programmers in debugging, tuning, and enabling advanced compiler optimizations like speculation-based automatic parallelization. As each use case demands its unique program trace summary, various memory profiler types have been developed. Yet, designing practical memory profilers often requires extensive compiler expertise, adeptness in program optimization, and significant implementation effort. This often results in a void where aspirations for fast and robust profilers remain unfulfilled. To bridge this gap, this paper presents PROMPT, a framework for streamlined development of fast memory profilers. With PROMPT, developers need only specify profiling events and define the core profiling logic, bypassing the complexities of custom instrumentation and intricate memory profiling components and optimizations. Two state-of-the-art memory profilers were ported with PROMPT where all features preserved. By focusing on the core profiling logic, the code was reduced by more than 65% and the profiling overhead was improved by 5.3× and 7.1× respectively. To further underscore PROMPT’s impact, a tailored memory profiling workflow was constructed for a sophisticated compiler optimization client. In 570 lines of code, this redesigned workflow satisfies the client’s memory profiling needs while achieving more than 90% reduction in profiling overhead and improved robustness compared to the original profilers.

Strategic Machine Learning Optimization for Cardiovascular Disease Prediction and High-Risk Patient Identification

Despite medical advancements in recent years, cardiovascular diseases (CVDs) remain a major factor in rising mortality rates, challenging predictions despite extensive expertise. The healthcare sector is poised to benefit significantly from harnessing massive data and the insights we can derive from it, underscoring the importance of integrating machine learning (ML) to improve CVD prevention strategies. In this study, we addressed the major issue of class imbalance in the Behavioral Risk Factor Surveillance System (BRFSS) 2021 heart disease dataset, including personal lifestyle factors, by exploring several resampling techniques, such as the Synthetic Minority Oversampling Technique (SMOTE), Adaptive Synthetic Sampling (ADASYN), SMOTE-Tomek, and SMOTE-Edited Nearest Neighbor (SMOTE-ENN). Subsequently, we trained, tested, and evaluated multiple classifiers, including logistic regression (LR), decision trees (DTs), random forest (RF), gradient boosting (GB), XGBoost (XGB), CatBoost, and artificial neural networks (ANNs), comparing their performance with a primary focus on maximizing sensitivity for CVD risk prediction. Based on our findings, the hybrid resampling techniques outperformed the alternative sampling techniques, and our proposed implementation includes SMOTE-ENN coupled with CatBoost optimized through Optuna, achieving a remarkable 88% rate for recall and 82% for the area under the receiver operating characteristic (ROC) curve (AUC) metric.

Fishing resources of the traditional gastronomy of Macaronesia: A navigation through the intangible food heritage in the Azores, Madeira, Canary Islands and Cabo Verde

Artisanal fishing is a vital activity in the Macaronesia archipelagos (Azores, Madeira, Canaries, and Cabo Verde) within the Northeast Atlantic (15°–39°N). It has historically played a pivotal role in poverty alleviation, employment generation, and the fortification of food security and sovereignty. This sector faces chronic threats from resource overexploitation, poaching, and the rising trend of recreational fishing. Recent decades have witnessed the growth of mass tourism, primarily reliant on processed fish from distant sources, exacerbating the situation alongside the impact of warming seas. Traditional fishing resources and their connection to regional gastronomy form a crucial part of the intangible cultural heritage of these archipelagos. Therefore, promoting local production and fostering education around smarter, healthier, and more sustainable consumption are imperative. Data on traditional fishery resources in Macaronesian gastronomy have been collated from diverse sources, including literature, specialised websites, interviews, and the extensive expertise of the authors. This information has been categorised by environmental resource groups for each archipelago. The biodiversity exploited by Macaronesia's artisanal fleets, integral to classic regional cuisine, encompasses over 220 marine species, with around 330 culinary dishes and seafood preparation methods catalogued. While there exists substantial similarity in the fishery resources utilised in the traditional cuisines of these four archipelagos, the Canaries have historically incorporated additional species from the Northwest African coasts. Meanwhile, Cabo Verde has integrated more tropical elements and has had limited developed in its deep-water fisheries. Macaronesia's gastronomic heritage, rooted in Portuguese and Spanish traditions, reflects a Mediterranean Diet characterised by lifestyle and the utilization of traditional recipes.

Recognition and Management of Delirium in the Neonatal Intensive Care Unit: Case Series From a Single-Center Level IV Intensive Care Unit.

Delirium often goes unrecognized in neonates and children because of lack of experience in evaluating behavior and cognition, insufficient awareness of the prevalence, and nondistinctive symptoms in this population. Although there are increasing reports of the presence of delirium in neonates, there are little data to guide the pharmacologic treatment in this population. In this retrospective single-center case series, we present our experience using quetiapine to treat delirium in 9 medically complex neonates. Based on an extensive literature review, expert opinion, and institutional experience, we propose an approach for monitoring and treating delirium in neonates and infants.

Transorbital approach to the cavernous sinus: an anatomical study of the related cranial nerves.

The cavernous sinus (CS) is a demanding surgical territory, given its deep location and the involvement of multiple neurovascular structures. Subjected to recurrent discussion on the optimal surgical access, the endoscopic transorbital approach has been recently proposed as a feasible route for selected lesions in the lateral CS. Still, for this technique to safely evolve and consolidate, a comprehensive anatomical description of involved cranial nerves, dural ligaments, and arterial relations is needed. Detailed anatomical description of the CS, the course of III, IV, VI, and V cranial nerves, and C3-C7 segments of the carotid artery, all described from the ventrolateral endoscopic transorbital perspective. Five embalmed human cadaveric heads (10 sides) were dissected. An endoscopic transorbital approach with lateral orbital rim removal, anterior clinoidectomy, and petrosectomy was performed. The course of the upper cranial nerves was followed from their apparent origin in the brainstem, through the middle fossa or cavernous sinus, and up to their entrance to the orbit. Neuronavigation was used to follow the course of the nerves and to measure their length of surgical exposure. The transorbital approach allowed us to visualize the lateral wall of the CS, with cranial nerves III, IV, V1-3, and VI. Anterior clinoidectomy and opening of the frontal dura and the oculomotor triangle revealed the complete course of the III nerve, an average of 37 (±2) mm in length. Opening the trigeminal pore and cutting the tentorium permitted to follow the IV nerve from its course around the cerebral peduncle up to the orbit, an average of 54 (±4) mm. Opening the infratrochlear triangle revealed the VI nerve intracavernously and under Gruber's ligament, and the extended petrosectomy allowed us to see its cisternal portion (27 ± 6 mm). The trigeminal root was completely visible and so were its three branches (46 ± 2, 34 ± 3, and 31 ± 1 mm, respectively). Comprehensive anatomic knowledge and extensive surgical expertise are required when addressing the CS. The transorbital corridor exposes most of the cisternal and the complete cavernous course of involved cranial nerves. This anatomical article helps understanding relations of neural, vascular, and dural structures involved in the CS approach, essential to culminating the learning process of transorbital surgery.

Advancing understanding of the linkages between local land policy interventions and the responsiveness of housing supply: Intervention mechanisms in the Finnish context

Land policy interventions are important ways for municipalities to implement their spatial development objectives. Such interventions may, however, generate both intended and unintended effects to housing supply and its responsiveness. It is therefore essential to better understand how and through what kind of mechanisms local land policy interventions can influence the quantity of housing supply. This paper addresses these questions. First, we develop a conceptual classification of so-called intervention mechanisms that describes the linkages between local land policy interventions and the quantity and responsiveness of housing supply. The intervention mechanisms build on a review of the urban economics literature and are further developed empirically using extensive expert interview data on local land policy interventions and practices in 30 Finnish municipalities. Based on the understanding that such intervention primarily influences housing supply through either direct or indirect costs on development, we conceptualize seven intervention mechanisms in the Finnish land policy context. Second, we demonstrate the variation in the application of land policy interventions that contribute to the (in)responsiveness of housing supply at the municipal level. Our findings highlight significant variation in the application of such interventions, potentially leading to different outcomes in housing supply restrictiveness. The findings contribute to a deeper understanding of the mechanisms by which land policy interventions operate to affect the (in)responsiveness of housing supply.

Green Construction Supply Chain Barriers Assessment: Evidence from Indian Construction Industry

This study aims to identify the key barriers influencing green supply chain management (GSCM) practices for the construction industry. The study is based on a survey of 20 manager-level employees from the Indian construction industry. Considering the extensive literature review and expert opinion, 15 key barriers influencing GSCM practices were identified and the interrelationship among them was established using multi-criteria-based Interpretative Structure Modelling methodology. Furthermore, by using Matrix Cross-Reference Multiplication Applied for Classification analysis, the barriers were classified as autonomous, dependent, linkage, and independent barriers to understand their relative importance. The barriers were grouped into a three-group hierarchy and it was found that the lower group of barriers, that is, green design, suppliers and green materials, certifications, and financial constraints were highly influencing GSCM practices implementation. The study can help construction practitioners develop a supply chain strategy focusing on critical barriers hindering the adoption of GSCM practices.

The Activity Management Inventory for Pain (AMI-P): Initial Development and Validation of a Questionnaire Based on Operant Learning and Energy Conservation Models of Activity Management.

Activity management is an important treatment component in chronic pain programs. However, there are shortcomings in measures of this construct, leading to inconsistencies in research findings. Here, we describe the development of the Activity Management Inventory for Pain (AMI-P). The AMI-P was developed by a group of international researchers with extensive expertise in both chronic pain and activity management. The initial evaluation of the AMI-P items included 2 studies that were both conducted in Canadian tertiary pain care centers. The resulting 20-item measure has 3 behavior scales (Rest, Alternating Activity, and Planned Activity), and 4 goal scales (Feel Less Pain, Get More Done, Complete the Task, and Save Energy). The behavior scales evidenced marginal to good internal consistency and test-retest reliability, and a moderate positive association with an existing pacing measure. The Rest and Alternating Activity scales were associated with greater pain interference, the Alternating Activity and Planned Activity scales were associated with less satisfaction with social roles, and the Planned Activity scale was associated with fewer depressive symptoms. The Alternating Activity scale increased significantly from pretreatment to posttreatment. All goal scales were positively associated with all behavior scales. The Feel Less Pain goal scale was positively associated with measures of avoidance and pain interference, while the Get More Done goal scale was negatively associated with measures of depressive symptoms and overdoing. The findings support the reliability and validity of the AMI-P scales, while also highlighting the complexity and multidimensional aspects of activity management.

A classification tool to foster self-regulated learning with generative artificial intelligence by applying self-determination theory: a case of ChatGPT

Generative AI such as ChatGPT provides an instant and individualized learning environment, and may have the potential to motivate student self-regulated learning (SRL), more effectively than other non-AI technologies. However, the impact of ChatGPT on student motivation, SRL, and needs satisfaction is unclear. Motivation and the SRL process can be explained using self-determination theory (SDT) and the three phases of forethought, performance, and self-reflection, respectively. Accordingly, a Delphi design was employed in this study to determine how ChatGPT-based learning activities satisfy students’ each SDT need, and foster each SRL phase from a teacher perspective. We involved 36 SDT school teachers with extensive expertise in technology enhanced learning to develop a classification tool for learning activities that affect student needs satisfaction and SRL phases using ChatGPT. We collaborated with the teachers in three rounds to investigate and identify the activities, and we revised labels, descriptions, and explanations. The major finding is that a classification tool for 20 learning activities using ChatGPT was developed. The tool suggests how ChatGPT better satisfy SDT-based needs, and fosters the three SRL phrases. This classification tool can assist researchers in replicating, implementing, and integrating successful ChatGPT in education research and development projects. The tool can inspire teachers to modify the activities using generative AI for their own teaching, and inform policymakers on how to develop guidelines for AI in education.

New approaches in the neuropsychological evaluation of aADHD

IntroductionIn Hungary, the understanding and diagnosis of adult attention-deficit/hyperactivity disorder (aADHD) are influenced by a blend of international epidemiological data and the standardized criteria established in DSM-5. The diagnostic protocols at our aADHD Outpatient Clinic at Semmelweis University have been carefully adjusted and validated to align with the practical application of empirical evidence and the extensive clinical expertise of professionals. The current diagnostic protocol encompasses the use of diagnostic interviews (symptoms identification based on DSM criteria; SCID-5-PD; M.I.N.I.-PLUS-5.0), the Conners’ Adult ADHD Rating Scales–Self Report questionnaire (CAARS), heteroanamnesis with parents, a comprehensive neuropsychological instruments battery (including the Rey Auditory Verbal Learning Test, Stroop Test, Conners-CPT3, Trail Making Test) and WAIS-IV Intelligence Scale.ObjectivesA valid and appropriate diagnosis plays a crucial social role by legitimizing individuals’ attention/health issues, confirming their concerns, and addressing cultural and moral expectations. The primary objective of this work is to refine the diagnostic methodology by extensive review of the international literature and the analysis of our own data.MethodsWith the aim of aggregating and analyzing the collected data based on examinations of the Hungarian adult population, our assessment methods are employed to acquire detailed information regarding ADHD prevalence, symptoms, and the related neuropsychological profiles.ResultsWhile various diagnostic approaches generally demonstrated good alignment, in some cases, significant discrepancies between neuropsychological assessment and the rest of our tools were observed, indicating a number of instances of false positives or false negatives. Especially the relevance of Rey Auditory Verbal Learning Test and Trail Making Test are questionable.ConclusionsThe results highlight the necessity for more refined diagnostic criteria and a meticulous selection of neuropsychological techniques to enhance consistency between various approaches, ultimately enabling a more robust diagnostic accuracy.Disclosure of InterestNone Declared

UNRAVELING THE COMPLEXITIES OF CARDIOVASCULAR MEDICINE: A CONVERSATION WITH DR. PETER MCCULLOUGH (PT-BR VERSION)

Background: This interview covers Dr. Peter McCullough's medical career, experience as an editor of medical journals, and his expertise in areas such as cardiomyopathy, myocarditis, and pericarditis. Aims: The primary aim is to understand Dr. McCullough's perspectives on various medical topics, including his journey as a cardiologist, the importance of peer review, the phenomenon of Pheidippides cardiomyopathy, the differences between myocarditis and pericarditis, and the significance of ethical principles like the Nuremberg Code and the Declaration of Helsinki. Additionally, the interview aims to explore his concerns about censorship during the COVID-19 pandemic. Methods: The interview follows a question-and-answer format, with the interviewer posing questions to Dr. McCullough on various topics related to his medical career, research interests, and ethical considerations. Results: Dr. McCullough shares his insights on topics such as cardiomyopathy, myocarditis, and pericarditis, emphasizing the importance of peer review, identifying potential biases, and balancing scientific rigor with timely dissemination of findings. He also highlights the significance of the Nuremberg Code and the Declaration of Helsinki in ensuring informed consent and preventing coercion in medical research and treatment. Discussion: Dr. McCullough expresses concerns about censorship during the COVID-19 pandemic, which he believes impacted the ability of medical professionals to freely discuss and disseminate health-related information. He also discusses the potential role of COVID-19 vaccines in causing myocarditis and the need for transparent communication about treatment options and potential complications. Conclusion: The interview provides valuable insights from Dr. McCullough's extensive medical experience and expertise, covering a range of topics from cardiovascular conditions to ethical principles and the challenges posed by censorship during the COVID-19 pandemic.

Computerized constructed wetlands allocation model (based on ecosystem services demand)

Egypt’s urban communities face many threats, including, pluvial floods, heat waves, and lack of publicly accessible urban green spaces. Nature-based solutions such as constructed wetlands (CWs) present a promising solution that could offer a wide range of ecosystem services (ES). However, the adoption of CWs is challenged by the lack of local planning guides and uncertainty about potential benefits. There are various models and tools available for quantifying and valuing ES, however, many of them are either highly complex or require extensive data and expertise. The aim of this paper is to develop a GIS-based multi-criteria decision model to select CW sites based on the supply and demand of ES. The model is to operate on three main stages: (i) demand: based on the need for risk reduction or benefit provisioning, (ii) potential sites (PSs): identify and score suitable sites for establishing a CW, and (iii) supply: define the service benefiting areas (SBA). An experimental approach is used, where the model is tested on New Damietta, an Egyptian Mediterranean city, proving the model is a reliable decision-making tool during preliminary urban planning stages due to its practicality, flexibility, and reasonable data requirements.

Learning Multimodal Volumetric Features for Large-Scale Neuron Tracing

The current neuron reconstruction pipeline for electron microscopy (EM) data usually includes automatic image segmentation followed by extensive human expert proofreading. In this work, we aim to reduce human workload by predicting connectivity between over-segmented neuron pieces, taking both microscopy image and 3D morphology features into account, similar to human proofreading workflow. To this end, we first construct a dataset, named FlyTracing, that contains millions of pairwise connections of segments expanding the whole fly brain, which is three orders of magnitude larger than existing datasets for neuron segment connection. To learn sophisticated biological imaging features from the connectivity annotations, we propose a novel connectivity-aware contrastive learning method to generate dense volumetric EM image embedding. The learned embeddings can be easily incorporated with any point or voxel-based morphological representations for automatic neuron tracing. Extensive comparisons of different combination schemes of image and morphological representation in identifying split errors across the whole fly brain demonstrate the superiority of the proposed approach, especially for the locations that contain severe imaging artifacts, such as section missing and misalignment. The dataset and code are available at https://github.com/Levishery/Flywire-Neuron-Tracing.