Identification Method Research Articles

Updated Multiple Sclerosis Incidence in France, 2011-2021.

Multiple sclerosis (MS) is a chronic neurologic disorder with significant implications for public health as being the first cause of nontraumatic neurologic disability in young adults. Although the global prevalence of MS has been increasing, recent temporal trends in incidence remain unclear. We aimed to evaluate current MS incidence trends in France over 11 years using the Système National des Données de Santé, a nationwide administrative database covering 99% of the French population. We used a published algorithm that incorporates multiple data sources, including benefits from long-term diseases, specific disease-modifying treatment prescriptions, and hospital discharge, to identify incident MS cases from January 1, 2011, to December 31, 2021. Sex-standardized and age-standardized incidence and prevalence were estimated using a "specific" and a "sensitive" definition providing bounds on the evolution of recent incidence. We used multivariable Poisson regression models to estimate temporal trends in incidence rates, calculating incidence rate ratios (IRRs) along with corresponding 95% CIs. In a sensitivity analysis, the time lag between past visits to neurologists and the database recording of MS was analyzed to ensure that the diagnosis extraction date was reliable. A total of 67,311 individuals with suspected MS were identified between 2011 and 2021, with 50,320 individuals classified as incident MS using the specific definition. The sensitive definition identified 56,918 individuals with incident cases. The median age at diagnosis was 40.6 years for the specific definition and 41.5 years for the sensitive definition. The study found stable incidence of MS over the 11-year period (adjusted IRR: 0.998 [95% CI 0.996-1.001] for the specific cohort). The female-to-male ratio of incident MS cases remained stable while sex-standardized and age-standardized prevalence of MS continued to rise. The median time lag between probable diagnosis and database recording was estimated to be less than 18 months, with variations depending on age and method of patient identification. This study provides a comprehensive analysis of MS epidemiology in France, demonstrating stable incidence and sex ratio. The increase in prevalence suggests improved management and survival and highlights the ongoing need for health care systems to support the growing population of individuals with MS.

Automatic construction of risk transmission network about subway construction based on deep learning models

Safety risks management is a critical part during the subway construction. However, conventional methods for risk identification heavily rely on experience from experts and fail to effectively identify the relationship between risk factors and events embedded in accident texts, which fail to provide substantial guidance for subway safety risks management. With a dataset comprising 562 occurrences of subway construction accidents, this study devised a domain-specific entity recognition model for identifying safety hazards during the subway construction. The model was constructed by a Bidirectional Long Short-Term Memory Network with Conditional Random Fields (BiLSTM-CRF). Additionally, a domain-specific entity causal relation extraction model employing Convolutional Neural Networks (CNN) was also developed in thsi model. The constructed models automatically extract safety risk factors, safety events, and their causal relationships from the texts about subway accidents. The precision, recall, and F1 scores of Metro Construction Safety Risk Named Entity Recognition Model (MCSR-NER-Model) all exceeded 77%. Its performance in the specialized domain named entity recognition (NER) with a limited volume of textual data is satisfactory. The Metro Construction Safety Risk Domain Entity Causal Relationship Extraction Model (MCSR-CE-Model) achieved an impressive accuracy, recall, and F1 score of 98.96%, exhibiting excellent performance. Moreover, the extracted entities were normalized and domain dictionary was developed. Based on the processed entities and relationships processed by the domain dictionary, 533 domain entity causal relation triplets were obtained, facilitating the establishment of the directed and unweighted complex network and case database about the risks of subway construction. This research successfully converted accident texts into a causal chain structure of “safety risk factors to risk events,” providing detailed categorization of safety risks and events. Concurrently, it revealed the interrelationships and historical statistical patterns among various safety risk factors and categories of risk events through the complex safety risks network. The construction of the database facilitated project managers in conducting management decisions about safety risks.

Algorithms and Methods for Individual Source Camera Identification: A Survey

Source camera identification (SCI) is a key issue in the field of digital forensics. This paper presents a comprehensive review of the existing methods and algorithms used for this purpose. It discusses approaches based on matrix noise analysis, including methods utilizing sensor pattern noise, photo response non-uniformity, statistical methods, aberrations analysis, as well as modern techniques based on deep neural networks and machine learning. Particular attention is paid to the effectiveness and robustness of the algorithms to different types of interference and their possible application in practical cases, such as law enforcement investigations. Moreover, we also discuss the issue of camera identification using videos and provide a brief description of popular image datasets that might be used for source camera identification method benchmarking.

A two-step bridge damage identification method based on influence lines information fusion and Bayesian model updating

A two-step bridge damage identification method based on influence lines information fusion and Bayesian model updating

Urban Viaduct Structural Health Monitoring: A Review of Wireless Sensor Approaches

Urban viaducts have been extensively built in large cities due to traffic pressure on main roads. Although urban viaducts provide relief and reduce traffic, they also pose potential threats to citizens’ safety due to the possibility of collapse. However, most collapses do not happen instantly. Structural health monitoring (SHM) systems can effectively detect structural damage to prevent collapses; however, they are not widely deployed due to the high cost of sensor installation. With wireless sensor technology thriving due to its accuracy and cost-efficiency, the wireless monitoring of massive urban viaducts has become possible. In this paper, we review the full-chain methods of employing wireless sensor technology for urban viaduct structural health monitoring. By proposing a general wireless structural health monitoring approach as a framework, we first review the sensor types and wireless transmission technologies, then the data processing and modal identification methods, and finally the damage detection methods. This paper aims to provide a full-chain review of the mainstream methods in wireless sensor approaches for the SHM of urban viaducts.

Evaluating Validity and Test-retest Reliability on Indonesian Basketball Talent Scouting Model for Athletes Aged 10 to 14

Background. Identifying talent in young athletes is crucial for effective sports coaching. However, in Indonesia, early detection of basketball talent is often hindered by the limitations of current identification methods and tools. Objectives. This study aimed to enhance the current aptitude test for basketball players aged 10 to 14. To assess the effectiveness of the revised model, the study evaluated its validity and test-retest reliability using data from both male and female athletes. Materials and methods. To ensure validity, four doctoral-qualified experts and seven experienced basketball coaches with an average of 12.78±2.2 years coaching experience, with a type B license and bachelor’s degree in sports, evaluated the test. The test-retest reliability was assessed including 40 athletes aged 10 to 14 with an average age of 12.3±1.0 years, consisting of 20 males (height 160.2±1.3 cm, weight 47.5±7.2 kg, average training 3.5±4.6 years) and 20 females (height 157.2±3.7 cm, weight 44.5±6.3 kg, average training 3.2±6.6 years). All participants were regional champions. The test was administered twice, with a one-week interval between sessions. Results. The study produced three types of tests, namely anthropometry (height, weight, fat range, arm length), biomotor (endurance, strength, flexibility, speed, reaction, balance, general motion), basketball skills (dribbling, passing, shooting) with Aiken V >0.8 validity, test-retest with a product moment correlation of p<0.05 and r=0.786, and independent t-test on male athletes and female athletes sig. 0.134 or p<0.05. Conclusions. The findings indicate that the talent scouting model of Indonesian basketball athletes aged 10 to 14 has proven to be valid and reliable from the aspects of anthropometric tests, biomotor tests and basketball skills tests. The ease of implementation, clarity of instructions, and security of the test also add to the advantages of this model. In addition, this model can be applied to male and female athletes without significant differences. Further research is needed to facilitate ongoing development by adding psychological tests and expanding the number of samples.

A New Contact Force Estimation Method for Heavy Robots Without Force Sensors by Combining CNN-GRU and Force Transformation

In response to the safety control requirements of heavy robot operations, to address the problems of cumbersome, time-consuming, poor accuracy and low real-time performance in robot end contact force estimation without force sensors by using traditional manual modeling and identification methods, this paper proposes a new contact force estimation method for heavy robots without force sensors by combining CNN-GRU and force transformation. Firstly, the CNN-GRU machine learning method is utilized to construct the robot Joint Motor Current-Joint External Force Model; then, the Joint External Force-End Contact Force Model is constructed through the Kalman filter and Jacobian force transformation method, and the robot end contact force is estimated by finally uniting them. This method can achieve robot end contact force estimation without a force sensor, avoiding the cumbersome manual modeling and identification process. Compared with traditional manual modeling and identification methods, experiments show that the proposed method in this paper can approximately double the estimation accuracy of the contact force of heavy robots and reduce the time consumption by approximately half, with advantages such as convenience, efficiency, strong real-time performance, and high accuracy.

Root zone microbial communities of Artemisia ordosica Krasch. at different successional stages in Mu US Sandy Land: a metagenomic perspective with culturomics insights

Phytoremediation offers a promising strategy for addressing the global challenge of land desertification. In the Mu Us Sandy Land of China, Artemisia ordosica Krasch. has emerged as a key species for desertification control. Its root-associated microbial communities may enhance the plant’s adaptability to sandy, nutrient-poor environments. Despite their ecological significance, comprehensive investigations of these microbial communities remain limited. In this study, microbial communities in the root zone (i.e., rhizosphere soil, non-rhizosphere soil, and root endosphere) of A. ordosica were analyzed via high-throughput sequencing and different isolation approaches across successional stages (moving dunes, semi-fixed dunes, and fixed dunes) in the Mu Us Sandy Land of northern China. Metagenomic analysis revealed that microbial diversity was significantly higher in the rhizosphere and non-rhizosphere soils than in the root endosphere; moving dunes exhibited lower diversity than semi-fixed and fixed dunes. Meanwhile, distinct microbial community structures across successional stages were revealed by principal coordinates analysis (PCoA), demonstrating substantial differences between the root endosphere and other zones. Environmental factors, including nitrate nitrogen (NO3−-N), organic matter (OM), available potassium (AK), and total potassium (TK), significantly influenced microbial community composition. Moreover, dominant genera such as Arthrobacter and Paraphoma were identified, potentially contributing to A. ordosica growth. From a culturomics perspective, 93 bacterial isolates were obtained using conventional streak plate and colony pick methods, with Firmicutes (37.63%) and Bacillus (23.66%) identified as the dominant taxa. In parallel, 14 fungal strains were isolated, primarily belonging to Penicillium (35.71%) and Aspergillus (21.43%), both of which are well-documented for their stress tolerance in arid ecosystems. A high-throughput cultivation and identification method, tailored to recover rare and slow-growing bacteria, was employed and successfully broadened the cultured diversity to include Proteobacteria (46.43%) and representatives of the rarely cultivated Deinococcus-Thermus phylum. This study provides metagenomic with culturomics insights into the microbial communities associated with A. ordosica, enhancing the understanding of plant–microbe interactions in sandy land ecosystems.

Dog Breed Prediction Using Deep Learning

Abstract The increasing popularity of pet ownership has led to a growing interest in methods for accurately identifying dog breeds. This interest is not only driven by the desire of pet owners to understand their pets better but also by the implications for veterinary care, breeding practices, and animal welfare. Traditional methods of breed identification often rely on expert knowledge, which can be inconsistent and subjective. In contrast, advancements in deep learning, particularly through Convolutional Neural Networks (CNNs), offer a promising solution to automate and enhance the accuracy of breed classification. Deep learning is a subset of machine learning that utilizes neural networks with multiple layers to analyze complex data. CNNs, specifically designed for processing grid-like data such as images, have shown exceptional performance in various image classification tasks. Their architecture allows them to learn spatial hierarchies of features, making them particularly adept at recognizing patterns in visual data. The ability of CNNs to automatically extract relevant features from images eliminates the need for manual feature engineering, significantly streamlining the classification process. The Kaggle Dog Breed Dataset serves as an ideal resource for training deep learning models aimed at dog breed classification. This dataset comprises thousands of labeled images of dogs belonging to various breeds, providing a rich foundation for model training and evaluation. For this study, we focus on a subset of four dog breeds to simplify the classification task while still allowing for meaningful analysis. The selected breeds include Labrador Retriever, German Shepherd, Golden Retriever, and French Bulldog—each with distinct physical characteristics that can be visually identified. Data preprocessing is a critical step in preparing the dataset for training. This involves resizing images, normalizing pixel values, and applying data augmentation techniques to enhance the diversity of the training set. Data augmentation methods, such as rotation, flipping, and scaling, help to artificially increase the dataset size and improve the model’s ability to generalize to unseen images. By creating variations of existing images, the model learns to recognize the core features of each breed, regardless of changes in orientation, lighting, or background. The architecture of the CNN employed in this study is designed to maximize classification accu- racy. It consists of multiple convolutional layers, each followed by activation functions and pooling layers to reduce dimensionality and retain important features. Dropout layers are also incorporated to prevent overfitting by randomly setting a fraction of input units to zero during training, thus promoting the model’s ability to generalize. The final layers of the network include fully connected layers that output the probabilities of each breed classification, allowing for effective decision-making based on learned features. Training the model involves feeding it the preprocessed images and their corresponding labels. The model’s performance is monitored using metrics such as accuracy, precision, recall, and F1-score. These metrics provide a comprehensive understanding of the model’s classification capabilities, par- ticularly in distinguishing between the selected dog breeds. Cross-validation techniques are employed to ensure that the model is not only effective on the training set but also capable of performing well on unseen data. The results of the study demonstrate the efficacy of deep learning methods in accurately pre- dicting dog breeds. The CNN model achieves a high classification accuracy, showcasing its ability to learn and generalize from the training data. Furthermore, the model’s performance is compared against existing traditional methods, highlighting the advantages of using deep learning for image classification tasks. The findings indicate that the deep learning approach significantly outperforms conventional techniques, providing a reliable solution for dog breed identification. Interpretability is a crucial aspect of AI applications, especially in domains such as veterinary sci- ence where understanding the decision-making process is vital. To enhance the interpretability of the model’s predictions, techniques such as Grad-CAM (Gradient-weighted Class Activation Mapping) are utilized. Grad-CAM generates heatmaps that highlight the regions of an image most influential in the model’s decision-making process. This provides valuable insights into which features the model considers important for classifying specific breeds, thereby fostering trust and transparency in AI systems. The implications of this research extend beyond academic interest; they hold practical signifi- cance for pet owners, breeders, and veterinary professionals. An accurate dog breed classification system can assist veterinarians in diagnosing breed-specific health issues, guide breeders in making informed decisions, and help pet owners understand their dogs’ behavior and care needs. Addition- ally, the automated nature of the deep learning model can facilitate quicker and more consistent breed identification, enhancing user experience and satisfaction.

Expanding biobank pharmacogenomics through machine learning calls of structural variation.

Biobanks linking genetic data with clinical health records provide exciting opportunities for pharmacogenomic (PGx) research on genetic variation and drug response. Designed as central and multi-use resources, biobanks can facilitate diverse PGx research efforts, including the study of drug efficacy and adverse effects. Specialized PGx alleles and phenotypes are critical for such studies and can be conveniently called from existing array-based genotypes routinely collected in most biobanks. We describe a central callset of PGx alleles and phenotypes in over 80,000 participants of the Michigan Genomics Initiative (MGI) biobank, created using the PyPGx software on TOPMed imputed genotypes. The array-based PGx allele calls demonstrate concordance (>92%) with a set of PCR-validated alleles collected during clinical care, but do not identify PGx alleles dependent on structural variation, including the clinically important CYP2D6*5 deletion. To address this, we developed a support vector machine trained on genotype array SNV probe intensities to classify CYP2D6*5 carriers. This method had >99% accuracy and reclassified ∼7% of African American and ∼4% of White MGI participants to lower activity metabolizer phenotypes, predicting higher risks of adverse drug reactions. We demonstrate that central PGx callsets created with existing tools and genetic data can be augmented by customized calls for challenging alleles based on structural variants to broaden the research potential and clinical utility of biobanks. These PGx callsets can be created in biobanks with existing array-based genotype data and highlight the utility of advanced computational methods in PGx allele identification.

Unknown IoT Device Identification Models and Algorithms Based on CSCL-Siamese Networks and Weighted-Voting Clustering Ensemble

Current methods for identifying unknown Internet of Things (IoT) devices are relatively limited. Most approaches can identify only one type of the unknown IoT devices at a time and with a relatively low accuracy. Herein, we propose a method for unknown IoT device identification (UDI) based on cost-sensitive contrastive loss (CSCL)-Siamese networks and a weighted-voting clustering ensemble (WVE). First, we integrate data visualization techniques with a permutation sample-pairing strategy to generate a complete and nonredundant set of positive–negative sample pairs. Then, we present an algorithm to generate permutation positive–negative sample pairs to provide a rich set of contrastive training data. To overcome the bias in the decision boundary caused by an insufficient number of positive sample pairs, we developed a Siamese network based on CSCL. The CSCL-Siamese network is used to identify known IoT devices and establish an embedded vector database for known IoT devices. Next, we extract the embedding vectors of unknown IoT devices using the trained CSCL-Siamese network and the embedded vector database. Finally, combining weighting factors with a voting ensemble strategy, we develop a UDI algorithm based on a WVE. This presented algorithm integrates the clustering capabilities of multiple unsupervised clustering algorithms to perform clustering on the extracted embedding vectors of unknown IoT devices, thereby enhancing the identification capability of the CSCL-WVE-UDI method. Experimental results demonstrate that the CSCL-WVE-UDI method can effectively identify multiple types of unknown IoT devices at the same time.

Classification of energy consumption profiles with a locality-sensitive hashing-based classifier

Abstract This paper explores the application of a fingerprinting algorithm to the problem of load profile classification in manufacturing environments. Inspired by the Shazam algorithm, which is used for music recognition, we adapt the concept to classify energy consumption patterns in time series data by creating unique fingerprints for each product variant using locality-sensitive hashing (LSH). Our LSH-based classifier (LSHC) demonstrates its potential for efficient and accurate load profile classification, uniquely representing each product variant’s energy consumption pattern. One significant advantage of our method is that indexing just one time series sample per product variant is sufficient for recognizing the same product variant in future queries, similar to one-shot learning in machine learning. Experimental results show that LSHC performs exceptionally well in noise-free or slightly noisy environments, demonstrating robustness to deviations. LSHC is also highly flexible, allowing adjustments in window size, step size, and features based on the data type. However, we identify a potential limitation in the form of index blowup with large training sets, which can significantly increase querying time. While the LSHC meets key requirements such as speed, robustness, and flexibility, challenges with scalability remain. Future work will focus on addressing these scalability issues, extending the algorithm for clustering tasks, and developing methods for real-time identification of load profiles from continuous large time series.

Forensic odontology: a comprehensive review of advances and applications in dental forensic medicine.

Forensic odontology is essential in medico-legal investigations, aiding in the identification of individuals, particularly in cases involving decomposed or severely damaged remains. Teeth, due to their durability and uniqueness, serve as critical forensic markers. This field also plays a role in age estimation, bite mark analysis, and legal disputes related to dental malpractice. Key forensic dental techniques include comparative dental analysis, radiographic imaging, and DNA extraction from teeth, which offer resistance to environmental degradation. Advanced methods such as aspartic acid racemization, radiocarbon dating, and histological analysis further enhance age estimation accuracy. Bite mark impressions, though controversial, remain relevant in forensic investigations. Additionally, forensic odontology collaborates with anthropology, botany, and entomology to strengthen identification processes. Technological advancements, including digital forensic tools, 3D imaging, and improved DNA analysis, have enhanced the precision of forensic dental identification. Bite mark analysis, while debated, benefits from computer-assisted comparisons. Forensic dentists are increasingly involved in legal cases, particularly in dental malpractice disputes, requiring specialized knowledge to assess liability and damages. Forensic odontology continues to evolve, integrating innovative technologies to improve accuracy and efficiency. Future research will focus on refining identification methods, utilizing AI-driven forensic analysis, and addressing ethical concerns related to DNA usage. Expanding forensic dental expertise in both clinical and legal contexts will be crucial for maintaining the discipline's role in forensic science.

Integrating HiTOP and RDoC frameworks part II: shared and distinct biological mechanisms of externalizing and internalizing psychopathology.

The Hierarchical Taxonomy of Psychopathology (HiTOP) and Research Domain Criteria (RDoC) frameworks emphasize transdiagnostic and mechanistic aspects of psychopathology. We used a multi-omics approach to examine how HiTOP's psychopathology spectra (externalizing [EXT], internalizing [INT], and shared EXT+INT) map onto RDoC's units of analysis. We conducted analyses across five RDoC units of analysis: genes, molecules, cells, circuits, and physiology. Using genome-wide association studies from the companion Part I article, we identified genes and tissue-specific expression patterns. We used drug repurposing analyses that integrate gene annotations to identify potential therapeutic targets and single-cell RNA sequencing data to implicate brain cell types. We then used magnetic resonance imaging data to examine brain regions and circuits associated with psychopathology. Finally, we tested causal relationships between each spectrum and physical health conditions. Using five gene identification methods, EXT was associated with 1,759 genes, INT with 454 genes, and EXT+INT with 1,138 genes. Drug repurposing analyses identified potential therapeutic targets, including those that affect dopamine and serotonin pathways. Expression of EXT genes was enriched in GABAergic, cortical, and hippocampal neurons, while INT genes were more narrowly linked to GABAergic neurons. EXT+INT liability was associated with reduced gray matter volume in the amygdala and subcallosal cortex. INT genetic liability showed stronger causal effects on physical health - including chronic pain and cardiovascular diseases - than EXT. Our findings revealed shared and distinct pathways underlying psychopathology. Integrating genomic insights with the RDoC and HiTOP frameworks advanced our understanding of mechanisms that underlie EXT and INT psychopathology.

Selected Legal Aspects of Biometric Identification in the Banking Sector

One of the most promising areas for providing remote banking and other services is the development of remote identification. Traditional passwords, codes, and messages, the use of which has been seriously compromised in recent years (confirmed by fraud statistics), are being replaced by biometric identification, which helps to remotely identify citizens with a higher degree of accuracy.Currently, various methods of biometric identification are employed in world practice, but the image of a face and voice are most widespread both in foreign countries and in Russia. At the same time, the development of artificial intelligence makes it possible to forge citizens’ data and calls into question their proper security. Biometric data loss can lead to fraudsters using them and causing harm to an individual.The legislator has formed the basic requirements for the protection of citizens’ biometric data. However, the risks that arise from remote identification and storage of biometric personal data remain, which is the reason for the low rates of citizens transferring their biometric data in Russia. The solution to this problem is seen in the application of a combination of technological and legal means. An important technical solution seems to be the use of a distributed registry (blockchain), the individual properties of which could ensure the safety of personal data of bank customers. In addition, it is necessary to enforce civil, administrative and criminal liability against persons who collect, process and store biometric personal data of citizens, including bank managers.

Differences in cause of death and age at death between people with and without diabetes over 10 years (2010-2020): A cross-sectional study in Japan.

Investigating the causes of death in individuals with diabetes compared with those without is essential for understanding diabetes care. However, methods for identifying individuals with diabetes within populations vary. We conducted a comparison of these groups under identical conditions, analyzing differences in causes and age at death, and assessing how different identification methods influence these outcomes. This study used the clinical records of inpatients who died at the National Center for Global Health and Medicine from September 1, 2010, to December 31, 2020. Individuals with or without diabetes were defined using prescriptions and laboratory data. The cause of death was determined by the name of the primary illness provided by the attending physician at the time of death. Individuals with diabetes were stratified by different definitions, and their age at death was compared. In Individuals with diabetes, males accounted for 67.6%, and in those without diabetes, 57.0%. The mean age at death was 75.0 ± 11.8 and 73.8 ± 16.0 years, respectively. Malignant neoplasia was the most common cause of death in both groups, with a higher frequency in individuals with diabetes (36.9% vs 31.0%). Age at death of individuals with diabetes differed by up to 1.5 years, depending on the definitions. Direct comparisons suggested that malignant neoplasia was the leading cause of death, and individuals with diabetes had a higher mean age at death. The method used to identify diabetes influenced these outcomes, emphasizing the importance of careful consideration in mortality studies.

Avoiding vehicle collisions in intersections using anomaly detection for the identification of chromatic index value in cubic graphs

In traffic management and urban planning, it is necessary to allocate time slots for the free flow of traffic on intersected roads so that no traffic is allowed to course on any two adjacent roads simultaneously, therefore avoiding collisions of vehicles on said intersections. This NP-complete problem can be modelled and solved via edge coloring of a graph representing a selected intersection system, where the number of needed time slots is equal to the number of colors required for conflict-free edge coloring of such a graph − a property called chromatic index of a graph. The work presented in the scope of this study focuses on the design and implementation of an anomaly detection process for the identification of the chromatic index of a selected subset of intersections represented by a cubic graph, where conventionally three colors suffice for proper coloring, but in rare (anomalous) cases four are needed. The main objective of the study is achieving lower computational requirements when compared to standard graph edge coloring. Eight approaches to the anomaly detection − isolation forest, one-class random forest, multilayer perceptron network, support vector machine, encoder, and three types of ensemble models − were applied to the selected problem and evaluated from the point of view of decision-making quality and the duration of computation. Based on the reached results, the simple model of a one class random forest and the ensemble model consisting of one class random forest, multilayer perceptron network, and support vector machine applying AND voting system, are the most fitting of the considered approaches with 97% and 99% respective recall values in anomaly identification. Both approaches also reach better time complexity of training and testing than standard edge-coloring methods of chromatic index identification.

Mapping the Edges of Mass Spectral Prediction: Evaluation of Machine Learning EIMS Prediction for Xeno Amino Acids.

Mass spectrometry is one of the most effective analytical methods for unknown compound identification. By comparing observed m/z spectra with a database of experimentally determined spectra, this process identifies compound(s) in any given sample. Unknown sample identification is thus limited to whatever has been experimentally determined. To address the reliance on experimentally determined signatures, multiple state-of-the-art MS spectra prediction algorithms have been developed within the past half decade. Here we evaluate the accuracy of the NEIMS spectral prediction algorithm. We focus our analyses on monosubstituted α-amino acids given their significance as important targets for astrobiology, synthetic biology, and diverse biomedical applications. Our general intent is to inform those using generated spectra for detection of unknown biomolecules. We find predicted spectra are inaccurate for amino acids beyond the algorithms training data. Interestingly, these inaccuracies are not explained by physicochemical differences or the derivatization state of the amino acids measured. We thus highlight the need to improve both current machine learning based approaches and further optimization of ab initio spectral prediction algorithms so as to expand databases for structures beyond what is currently experimentally possible, even including theoretical molecules.

Duplex PCR assay to determine sex and mating status of Ixodes scapularis (Acari: Ixodidae), vector of the Lyme disease pathogen.

Ticks are a major health threat to humans and other animals, through direct damage, toxicoses, and transmission of pathogens. An estimated half a million people are treated annually in the United States for Lyme disease, a disease caused by the bite of a black-legged tick (Ixodes scapularis Say, 1821) infected with the bacterial pathogen Borrelia burgdorferi. This tick species also transmits another 6 human-disease causing pathogens, for which vaccines are currently unavailable. While I. scapularis are sexually dimorphic at the adult life stage, DNA sequence differences between male and female I. scapularis that could be used as a sex-specific marker have not yet been established. Here we identify sex-specific DNA sequences for I. scapularis (male heterogametic system with XY), using whole-genome resequencing and restriction site-associated DNA sequencing. Then we identify a male-specific marker that we use as the foundation of a molecular sex identification method (duplex PCR) to differentiate the sex of an I. scapularis tick. In addition, we provide evidence that this molecular sexing method can establish the mating status of adult females that have been mated and inseminated with male-determining sperm. Our molecular tool allows the characterization of mating and sex-specific biology for I. scapularis, a major pathogen vector, which is crucial for a better understanding of their biology and controlling tick populations.

Graph and Frequency Leverage: A Novel Coal Gangue Identification Method

Abstract Coal holds a significant position in the energy structure of China. Top-coal caving mining is one of the classical methods in coal mining technology. However considering the hazard environment of actual working faces, the identification accuracy can be greatly reduced. In this paper, with the aim of improving the identification accuracy, a graph conversion model based on the impact and vibration signals of coal gangue in the tail beam of hydraulic support was proposed. Fast Fourier transform was utilized for extracting frequency domain features firstly. After that, the features were extracted in the frequency domain and converted into graph data structure. The extracted features are then utilized for constructing graph representations based on their similarities utilizing proposed graph generation model. The identification of coal and gangue was conducted on the constructed graph representations by graph convolution networks. Finally, several comprehensive experiments were conducted to prove the effectiveness of the proposed method, with the results shown that the proposed method achieves higher accuracy comparing with baseline methods, it also have relatively less parameters. By the proposed of baseline methods, this paper provided a potential direction for the accurate coal gangue identification.