External Features Research Articles

Perbandingan Metode Random Forest, Convolutional Neural Network, dan Support Vector Machine Untuk Klasifikasi Jenis Mangga

Mango is a fruit known as the "King of Fruit" due to its rich flavor, vast variability, and high nutritional value. Classifying mangoes based on their external appearance is the initial step in the process of identifying and categorizing mango types conventionally. The classification process can be performed by examining external features such as fruit color, shape, and size. Classifying different types of mango fruits accurately can assist researchers in developing superior varieties and also aid farmers for cultivation purposes, sales, distribution, and selecting the right varieties for local growth and weather conditions. This research conducts the classification of mango types based on color from mango images using machine learning. The study compares three methods, namely Random Forest, Support Vector Machine (SVM), and Convolutional Neural Network (CNN), to determine the best method for classifying mango types based on their images. The dataset underwent preprocessing, where image sizes were standardized to 300 x 300 pixels, and color was changed to grayscale. The dataset was then divided into training and testing data with a ratio of 70:30. Subsequently, the dataset was processed using three methods, and their accuracy results were compared. The findings indicate that the Random Forest method yielded the highest accuracy compared to the other methods, with an accuracy rate of 96%. The accuracy of the SVM method was 95%, and the accuracy of the CNN method was 33%. From these results, it can be concluded that the Random Forest method is highly effective for classifying mango types based on their image compared to SVM and CNN methods.

Enhancing geospatial prediction models with feature engineering from road networks: a graph-driven approach

Traditional geospatial predictive models for property valuation have naturally relied on coordinates as well as ‘hedonic’ (internal and external) features. In particular, location-centric methods such as Geographically Weighted Regression (GWR) and Kriging have focused on intrinsic target characteristics together with distances between individual targets. However, especially in the context of heavily urbanized areas, these approaches might overlook crucial aspects arising from the underlying topological structure that presents itself in such areas. Concretely, in this work, we focus on the structure arising from the road network connecting properties. We introduce a novel though straightforward technique for feature engineering based on graphs constructed on a road network. We then extract relevant features from these and utilize those as inputs for predictive models and assess their performance benefits when used together with a variety of both well-known geospatial models and state-of-art machine learning models. To this end, we present an exhaustive experiment using four different real-life data sets across various regions and exhibiting sizes outperforming many comparative works in the field. Our findings reveal that our feature engineering approach offers significant improvements in predictive performance. Finally, we apply Shapley values as an interpretability technique to confirm the reliability and effectiveness of our approach.

Comparative analysis of sipeimine content, metabolome and chloroplast genome in cultivated and wild varieties of Fritillaria taipaiensis.

The wild variety Fritillaria taipaiensis E.B (EB) is known for its superior therapeutic effects, but its limited production cannot meet demand. As a result, the cultivated variety F. taipaiensis P. Y. Li (PY) has been widely grown. In this study, we conducted a comprehensive analysis comparing EB and PY in terms of external features, sipeimine content, metabolome and chloroplast genome to differentiate these two varieties. Our research revealed that the petals and pods of EB are green, while those of PY have purple markings. The bulbs of EB contain significantly higher levels of sipeimine compared to those of PY. Metabolomic analysis identified 56 differentially expressed metabolites (DMs), with 23 upregulated and 33 downregulated in EB bulbs. Particularly, 3-hydroxycinnamic acid and secoxyloganin may serve as distinctive DMs. These DMs were associated with 17 KEGG pathways, including pyrimidine metabolism, alanine, aspartate and glutamate metabolism, and galactose metabolism. Differences in the length of the chloroplast genome were primarily observed in the large single-copy (LSC) region, with the largest variation in the trnH-GUC-psbA region. The placement of the trnH gene and the rps gene in proximity to the LSC/IRb boundary differs between EB and PY. The results of this study provide valuable insights for the introduction and comprehensive development of wild F. taipaiensis from a scientific perspective. © 2024 Society of Chemical Industry.

Fetal external features and morphology of the umbilical cord of wild boars.

This study aimed to describe the gestational and morphological aspects of the fetuses and their respective umbilical cords from two pregnant wild boars (Sus scrofa). Morphological descriptions were provided for 23 fetuses and the gestational ages were estimated through fetal characteristics and formula application. The specimens were fixed in 10% formalin for subsequent macroscopic and microscopic examination. Histological characterization was performed using haematoxylin-eosin (H&E), Masson's trichrome (MT) and Verhöeff's staining techniques. The wild boar fetuses exhibited an estimated gestational age of 55 days (in the larger uterus) and 45 days (in the smaller uterus). They displayed well-developed features consistent with domestic pig fetuses, except for the presence of five pairs of mammae. Additionally, the umbilical cord consisted of two arteries, one vein, an allantoic duct, and a vitelline duct (the latter two identified only microscopically), located in the juxtafetal, intermediate and juxtaplacental portions. The arteries and veins were comprised of endothelium, smooth muscle and collagen fibres, with no elastic fibres observed in the vessel walls. The allantoic duct was lined with simple cuboidal epithelium, while the vitelline duct featured a simple squamous epithelium. In conclusion, the morphological characteristics observed in the examined structures align with the expected patterns for species of the Suidae family. Furthermore, these findings contribute substantially to the morphological characterization of the wild boar, yielding valuable insights into the fetal morphology and the structure of the umbilical cord.

Real-time prediction of transit origin–destination flows during underground incidents

Efficient transportation planning and management are critical for ensuring the smooth operation of rail transit systems, particularly in urban areas with high passenger demand. Real-time prediction of transit flow during underground incidents is vital for ensuring passenger safety, minimizing disruptions, and optimizing resource allocation. This study presents a comprehensive framework to address the considerable challenges associated with short-term origin–destination (OD) flow prediction, particularly during incidents. We propose integrating convolutional long short-term memory cells with self-attention cells to learn the long-range spatiotemporal information of historical OD flows. To overcome the absence of a real-time OD matrix, we introduce an improved graph convolution operation, considering the local connection of ridership, to capture vital spatiotemporal interaction patterns. Quantitative and qualitative analyses were conducted to evaluate the performance of the framework, providing insights into the role of each module. Experimental results suggest that incorporating incident matrix theory enhances the accuracy of capturing declining OD flows during incidents by up to approximately 25%. Furthermore, integrating external features like weather and time comprehensively assesses the impact of erratic change factors, especially during off-peak periods. Additionally, introducing more than one cycle of historical OD flow as an input may introduce noise, and increased attention is needed for OD flows with average daily flows exceeding 30 passengers. Designed with a high degree of modularity and adaptability, the proposed framework serves as a valid tool for transportation professionals and researchers to address evolving challenges in the management and operation of urban transportation systems.

Development of a Mango-Grading and -Sorting System Based on External Features, Using Machine Learning Algorithms

Development of a Mango-Grading and -Sorting System Based on External Features, Using Machine Learning Algorithms

Gross pathology of brain mass lesions by intraoperative ultrasonography: a comparative study

BackgroundThe purpose of this study was to evaluate the ability of intraoperative ultrasound (IOUS) to differentiate the gross pathological features of brain mass lesions in comparison with preoperative imaging and confirmable histopathological results.ResultsA total of 365 patients were operated on for brain mass lesions removal from May 2017 to May 2022 under the guidance of intraoperative ultrasound with transducers 2.5–8 megahertz (MHZ). Ultrasound gross pathological findings were compared to the preoperative imaging and the confirmable histopathological results. Intraoperative ultrasound defined either internal or external gross pathological features of all brain mass lesions. The IOUS showed spontaneous enhancements of the brain abscess walls, which were equivalent to contrasted CT and MRI. Significantly large diameters were noted in the IOUS measurement of abscesses in comparison with CT and MRI (P = 0.001). The walls of the brain abscesses were significantly well defined in IOUS imaging in comparison with CT (P = 0.001) and equivalent to MRI. IOUS showed equivalent significance to CT and MRI in characterizing intra-parenchymal hematomas. Significantly large diameters were noted in the IOUS measurement of hematomas in comparison with CT and MRI (P = 0.001). IOUS showed significant definition of brain tumors in comparison with CT and MRI regarding tumor edge definition, tumor contours, necrosis, and cystic components (cystic definition, cystic multiplicity, cystic trabeculations, and cystic wall thickness) (P = 0.001). IOUS was equivalent to CT and MRI regarding intra-tumoral hematomas and brain edema. IOUS was equivalent to CT regarding calcification detection. The significant criteria for high-grade brain tumors versus low grade by IOUS were: P = 0.001 (necrosis, brain edema, rare calcifications, presence of cystic components, thick cystic walls, large diameter, hypo-echogenicity, and heterogeneity); P = 0.002 (cystic trabeculations); P = 0.005 (multiple cysts); and P = 0.03 (irregular contour). IOUS can characterize brain tumors and suspect specific and significant criteria for many types with great overlap.ConclusionsIntraoperative ultrasound has the ability to differentiate the gross pathological features of brain mass lesions in comparison with preoperative imaging and confirmable histopathological results.

A review on importance of forensic photography in investigation of drowning deaths

Forensic photography plays an important role in solving the cases related with drowning, a proper photography of crime scene or victim/deceased helps in proper investigation, ruling out doubts and also in court room presentation. A recent report of the World Health Organization (WHO) labels drowning as one of the world's leading causes of death As police investigation continues, parallel public investigations also start which can spread rumours, misinformation and speculation. The onlookers on crime scene (including Local Media) may misinterpret the visible post mortem changes of the body of drowned victims as antemortem injuries. A clear photography using correct lighting, accurate angling, and different viewpoints of the characteristic external features like (Bluish Skin, Froth and foam, Washerwomen’s Hand, Cutis anserina, Cyanosis, Keratin loss, Cadaveric spasm) of drowned body and evidences around the crime scene will help in avoiding possible misinterpretation and public pressure on officials and also helps the medical officer in autopsy findings and in preparation of report. This article discusses the importance of Photography of drowning cases.

The southern geographic range of Micronycteris sanborni (Chiroptera, Phyllostomidae)

Abstract The southern distribution of Micronycteris sanborni became controversial after the description of Micronycteris yatesi based on specimens formerly reported as M. sanborni in Bolivia. It raised doubts on the identity of the southernmost specimen of M. sanborni reported from Serra da Bodoquena, Brazil. We rechecked the identification of this specimen and report four new records of M. sanborni from Serra da Bodoquena. External and craniodental features of all five examined specimens fit the current M. sanborni diagnosis, supporting this region as the southern boundary of its geographic range in South America.

New species of the genus <i>Calycomyza</i> Hendel (Diptera, Agromyzidae) in the South Caucasus fauna

To study the diversity of agromizids (leaf miners) in the South Caucasus, the species external morphological features, their host plants, the development of larvae and pupae and to assess the degree of crop infestation by leaf‐miners.The study was carried out within the framework of the scs 21‐002 scientific program “Leaf miners as pests of agricultural plants (Diptera: Agromyzidae): the latest control measures”. Type samples were fixed in 75 % ethyl alcohol and deposited in the Agrarian Scientific Research Laboratory of the Scientific Centre of Zoology and Hydroecology. Species were identified by examining the male genitalia. The degree of damage of the host–plant was determined based on intensity indicators.As a result of this research, a new species of the Calycomyza genus was discovered in the South Caucasus fauna. Larvae of C. jucunda (Wulp, 1867) were found on the leaves of Beta vulgaris, a host plant mentioned for the first time here. As a Nearctic species, it was also first discovered in the southern Caucasus.The study of the male genitalia indicates expansion of the biogeographical distribution of Calycomyza species, as most of them are found in the Nearctic and Neotropical regions. In terms of intensity, C. jucunda is classified as a less dangerous species for agricultural crops.

Superior supercapacitor performance with tuneable 2D/3D morphological microporous carbons of zeolitic imidazolate frameworks synthesized by recycling mother liquors

Carbonized metal–organic frameworks (MOFs)-based nanoporous carbon materials (NPCs) offer attractive activities in electrochemical energy conversion and storage (EECS) applications; however, there is the need for scalable MOFs production under reduced energy/environmental impact. This study reports a green synthesis route for model zeolitic imidazolate framework (ZIF-8) materials via recycling methanol-based mother liquors (ZIF-RMLx) under room temperature stirring and their carbonized materials (CZC-RMLx) for high-performance supercapacitors. Series of ZIF-RMLx samples produced in four recycles offer rod-/sheet-/polyhedral-like 2D/3D microstructures with tuneable internal and external framework and morphological features. Accordingly, CZC-RMLx, obtained by direct pyrolysis, with high microporosity and surface area of 1500 m2/g deliver excellent capacitance values of 200–340F/g, compared to typical MOFs-derived or chemically activated/templated NPCs, produced via extended chemical processing. Structure-relevant and comparative performance analysis reveal insights for improved charge storage and carbonization-dependent graphitization, nitrogen-doping and microporosity-controlled capacitance characteristics in the CZC-RMLx over typical NPCs in literature. The device-level performance with a long-term durability over 21,000 cycles is demonstrated. The practical potential of CZC-RMLx is further evaluated by fabricating solid-state cells and their parallel and series circuit combinations result in overall capacitance and voltage boost to 450F/g and 2.4 V, respectively.

Droplet evaporation on curved surfaces: transients of internal and external transport phenomena

We explore the transient evolution of thermo-fluid-dynamics of evaporating sessile droplets over curved substrates in the liquid and gaseous domains. A computational model using the Arbitrary Lagrangian-Eulerian framework is adopted. The governing equations in both liquid and gaseous domains are solved in a fully coupled manner, considering coupled effects of evaporative cooling and heat advection due to bulk fluid motion. This bulk motion in the liquid domain is caused by natural advection due to thermal actuations such as thermal Marangoni flow and buoyancy-driven convection. For the gaseous domain, the additional effects of solutal convection (due to vapour-concentration variation), Stefan flow and interfacial viscous stresses are also considered. To depict a generalized role of substrate curvature, both concave and convex surfaces with curvatures over a wide range are studied. The surface wettability effects are also explored by varying the true contact angle of the droplets. Computational predictions on evaporation rate and internal flow field are validated against experimental results from literature. The interplay of wetting state and substrate curvature is noted to substantially affect the evaporation process and its thermo-fluidics. The convex curvature significantly augments internal advection while the same is weakened over concave substrates due to altered mass loss rate. Consequently, the duration of multi-vortex Marangoni flows in the development stages of evaporation and the advection in the external gaseous domain is markedly different for different curvatures. Further, on superhydrophobic curved surfaces, the effects of re-distributed evaporative fluxes play a major role. In such cases, the reduced mass flux over a large interfacial area near the periphery expedites the stable state Marangoni and external flow features.

A novel scenario generation method of renewable energy using improved VAEGAN with controllable interpretable features

With the high penetration of renewable generation systems in the power grid, the accurate simulation of the uncertainty in renewable energy generation is vital to the safe operation of the power system This paper proposes a novel controllable method for renewable scenario generation based on the improved VAEGAN model. The standard VAEGAN model is first improved using spectral normalization technique and the generator of GAN is trained using VAE. Then, the external and internal interpretable features in the latent space are learned as the controllable vector utilizing the principle of mutual information maximization. Finally, the renewable energy scenarios with overall features are generated using the external universal meteorological features, and renewable energy scenarios with specific features are generated by tuning along the internal interpretable feature of the controllable vector in the latent space. The proposed approach is used to produce real-time series data for renewable energy including wind and solar power. Experiments demonstrate that our method has a better performance in terms of controllable generation and enables the generation of preference patterns covering various statistical features.

Cantharis zapatai nom. nov., an overlooked species of Cantharis Linnaeus, 1758 from Central Spain (Coleoptera: Cantharidae)

Cantharis zapatai nom. nov. is proposed for Cantharis schrammi Pic, 1918, which is a primary homonym of Cantharis paulinoi var. schrammi Pic, 1907. The male of the species is redescribed, and the female is described here. The aedeagus and several external features are illustrated, and the species is compared with the closest relatives. Cantharis zapatai nom. nov. differs from its congeners by the characteristic spot in the vertex, yellowish pronotum and elytra, and black scutellum and appendages. The species is known from three localities of west central and central Spain (Iberian Peninsula), Guadalupe (Cáceres) (type locality), Puerto del Milagro (Toledo) and Fuencaliente (Ciudad Real). A key to the Iberian species of the genus Cantharis is provided.

BatSight: A Navigation Game to Map Environmental Information into Audio Cues

By using sound to visualize the real-world environment, audio games can offer a completely new game experience. In this paper, we study how audio cues can be visualized in computer games to enhance the navigation skills of players. To this end, we propose an audio game in which blindfolded players move through a physical maze with the help of audio cues. To realize this game, a sonar headset is designed and built based on ultrasonic sensors, which maps the external environment features into musical sounds.
 The game is played in a real-world environment and uses an augmented reality approach as it adds virtual sounds to the real world.
 The gaming environment of this game is a physical maze, where the blindfolded players enter the maze while wearing the sonar headset. A user study was conducted to evaluate the effect of using different sound mapping techniques on navigation performance and playing experience in the game proposed in this paper. The results show that producing musical sound can lead to better navigation performance, game experience, and immersion in players.

Musculoskeletal and tendinous details of selected anomalies in the locomotor system of anurans.

Previous studies on anuran anomalies predominantly examine isolated cases or focus on external and skeletal features. Our study analyzes a comprehensive sample collected from 1991 to 2017, examining the muscle-tendon system in 24 anuran species across adult, juvenile, and metamorphic stages. This extensive sample size allows us to investigate consistent anomaly patterns across different developmental stages and anuran families, exploring potential common developmental or genetic factors. Our detailed anatomical examination, encompassing musculature, tendons, and skeletal structures, revealed that 21% of the specimens displayed anomalies, a noteworthy finding considering the extensive sample size and duration of the studied sample. Of these anomalies, 17% affected the locomotor system, predominantly in the upper limbs. Key anomalies included, forelimbs and hindlimbs brachydactyly, rotation in forelimbs, partial kyphotic lordosis, and scoliosis. Notably, the digit 4 in the forelimbs and digits 4 and 5 in the hindlimbs were particularly susceptible to teratogenic effects, indicating possible prolonged exposure during development. Our study also uncovered combinations of anomalies and identified a phenotype similar to Poland syndrome. The findings validate the "Logic of Monsters" (LoMo theory) by Alberch, although the name itself may not be deemed appropriate, showing that developmental disruptions in tetrapods are not random but follow distinct sequences and patterns. The name, while unfortunate, accurately reflects the unusual nature of these developmental anomalies. This contributes to the evolving "Evo-Devo-Path" framework, highlighting the study's importance in understanding developmental disruptions in tetrapods.

BioDeepfuse: a hybrid deep learning approach with integrated feature extraction techniques for enhanced non-coding RNA classification

ABSTRACT The accurate classification of non-coding RNA (ncRNA) sequences is pivotal for advanced non-coding genome annotation and analysis, a fundamental aspect of genomics that facilitates understanding of ncRNA functions and regulatory mechanisms in various biological processes. While traditional machine learning approaches have been employed for distinguishing ncRNA, these often necessitate extensive feature engineering. Recently, deep learning algorithms have provided advancements in ncRNA classification. This study presents BioDeepFuse, a hybrid deep learning framework integrating convolutional neural networks (CNN) or bidirectional long short-term memory (BiLSTM) networks with handcrafted features for enhanced accuracy. This framework employs a combination of k-mer one-hot, k-mer dictionary, and feature extraction techniques for input representation. Extracted features, when embedded into the deep network, enable optimal utilization of spatial and sequential nuances of ncRNA sequences. Using benchmark datasets and real-world RNA samples from bacterial organisms, we evaluated the performance of BioDeepFuse. Results exhibited high accuracy in ncRNA classification, underscoring the robustness of our tool in addressing complex ncRNA sequence data challenges. The effective melding of CNN or BiLSTM with external features heralds promising directions for future research, particularly in refining ncRNA classifiers and deepening insights into ncRNAs in cellular processes and disease manifestations. In addition to its original application in the context of bacterial organisms, the methodologies and techniques integrated into our framework can potentially render BioDeepFuse effective in various and broader domains.

DeepBranchTracer: A Generally-Applicable Approach to Curvilinear Structure Reconstruction Using Multi-Feature Learning

Curvilinear structures, which include line-like continuous objects, are fundamental geometrical elements in image-based applications. Reconstructing these structures from images constitutes a pivotal research area in computer vision. However, the complex topology and ambiguous image evidence render this process a challenging task. In this paper, we introduce DeepBranchTracer, a novel method that learns both external image features and internal geometric characteristics to reconstruct curvilinear structures. Firstly, we formulate the curvilinear structures extraction as a geometric attribute estimation problem. Then, a curvilinear structure feature learning network is designed to extract essential branch attributes, including the image features of centerline and boundary, and the geometric features of direction and radius. Finally, utilizing a multi-feature fusion tracing strategy, our model iteratively traces the entire branch by integrating the extracted image and geometric features. We extensively evaluated our model on both 2D and 3D datasets, demonstrating its superior performance over existing segmentation and reconstruction methods in terms of accuracy and continuity.

Exceptional preservation of a marine tapeworm tentacle in Cretaceous amber

Parasites are ubiquitous in extant ecosystems but rarely preserved in the geological record, especially parasitic worms (helminths). One such group is Cestoda (tapeworms), a specialized endoparasitic group of platyhelminths (flatworms). They have a complex lifecycle with at least two hosts, infecting all major groups of vertebrates. However, their fossil record is extremely sparse due to their soft tissue and concealed habitats, with the only widely accepted example before the Quaternary being eggs discovered in a shark coprolite from the Permian. The lack of body fossils greatly hampers our understanding of their early evolution. We report a slender, armed fossil from mid-Cretaceous Kachin (Myanmar) amber (ca. 99 Ma). This fossil displays unique external (armature pattern) and internal (partially invaginated tentacle and rootless hooks) features that are most consistent with the tentacles of extant trypanorhynch tapeworms that parasitize marine elasmobranchs (mainly sharks and rays). Our study thus probably provides not only the first partial body fossil of a tapeworm, but also arguably the most convincing body fossil of a flatworm. In addition, the exquisite invaginated tentacle inside the fossil highlights that amber can preserve the internal structure of helminths. Remarkably, nearly all extant trypanorhynchs are endoparasites of marine elasmobranchs, thus our study provides an exceptional example of a marine endoparasite trapped in terrestrial amber.

Advancing electric demand forecasting through the temporal fusion transformer model

This research paper introduces a cutting-edge approach to electric demand forecasting by incorporating the Temporal Fusion Transformer (TFT). As the landscape of demand forecasting becomes increasingly intricate, precise predictions are vital for effective energy management. To tackle this challenge, we leverage the sequential and temporal patterns in an extensive electric demand dataset spanning from 2003 to 2014. Our proposed Temporal Fusion Transformer model combines attention mechanisms with the transformer architecture, enabling it to adeptly capture intricate temporal dependencies. Thorough data preprocessing, including temporal embedding and external features, enhances prediction accuracy. Through rigorous evaluation, the TFT model surpasses existing forecasting techniques, showcasing its capacity for accurate, resilient, and adaptive predictions. This research contributes to the advancement of electric demand forecasting, harnessing the TFT’s capabilities to excel in capturing diverse temporal patterns. The findings hold the potential to enhance energy management and support decision-making in the energy sector, bridging the gap between innovation and practical utility.