Perfect Classification Accuracy Research Articles

Smart classification of organic and inorganic pineapple juice using dual NIR spectrometers combined with chemometric techniques

The global demand for organic foods, driven by health benefits and consumer preferences, necessitates reliable methods for distinguishing organic products from their inorganic counterparts. This study investigates the application of dual handheld near infrared (NIR) spectroscopy devices, SCiO and Tellspec, combined with chemometric techniques for the nondestructive differentiation of organic and inorganic pineapple juices. The objective was to establish a rapid and robust method to differentiate organic pineapple juice from inorganic juice using unique spectral data from the two devices. Eighty-four pineapple juice samples were analyzed with preprocessing techniques, including mean centering, multiplicative scatter correction, standard normal variate, first derivative, and second derivative applied to the spectral data. Partial least squares discriminant analysis (PLS-DA) was employed for classification, and variable importance in projection (VIP) was used for optimal wavelength selection. The results demonstrated that the Tellspec scanner, particularly with second derivative preprocessing, achieved high accuracy in differentiating organic from inorganic pineapple juice. The fusion of data from both SCiO (740–1070 nm) and Tellspec (900–1700 nm) scanners, without preprocessing, coupled with the PLS-DA model, achieved perfect classification accuracy, sensitivity, and specificity (100 %) in both training and testing sets. This study highlights the potential of integrating dual handheld NIR spectroscopy with chemometrics to effectively and accurately classify organic and inorganic pineapple juices. The findings support using these advanced techniques for quality assurance and authentication in the food industry.

Fault diagnosis of monoblock centrifugal pumps using pre-trained deep learning models and scalogram images

The monoblock centrifugal pump (MCP) is widely utilized in a diverse range of applications encompassing residential and industrial usage. Sectors such as agriculture, civil projects, mine dewatering, and numerous other industrial applications have employed centrifugal pumps. Despite their extensive usage, these pumps are susceptible to faults and failures due to the presence of critical components that are prone to issues such as bearing faults, sealing problems, cavitation and impeller faults. Therefore, conducting timely fault diagnosis becomes crucial to ensure uninterrupted operation. To address this, the technique of transfer learning, a form of deep learning, is employed. This method entails utilizing prior knowledge from previous operations to improve fault diagnostic performance in monoblock centrifugal pumps. Specifically, scalogram images derived from vibration signals collected during experimental setups were used in fault diagnosis. The study classified faults in monoblock centrifugal pumps using fifteen pre-trained networks including DenseNet-201, GoogLeNet, VGG-19, InceptionResNetV2, Xception, ShuffleNet, VGG-16, InceptionV3, ResNet101, ResNet-50, EfficientNetb0, NasNetmobile, ResNet-18, AlexNet and MobileNet-v2. The highest classification accuracy was obtained by carefully adjusting the hyperparameters which were subsequently employed in the fault classification process. AlexNet, one of the pre-trained network models, showcased remarkable capabilities by achieving a perfect classification accuracy of 100% within a relatively fast computation time of 18 s. This approach employs a reliable and effective process for discovering defects from the start, lowering the risk of possible damage and ensuring the seamless operation of the system.

Score-based denoising for atomic structure identification

We propose an effective method for removing thermal vibrations that complicate the task of analyzing complex dynamics in atomistic simulation of condensed matter. Our method iteratively subtracts thermal noises or perturbations in atomic positions using a denoising score function trained on synthetically noised but otherwise perfect crystal lattices. The resulting denoised structures clearly reveal underlying crystal order while retaining disorder associated with crystal defects. Purely geometric, agnostic to interatomic potentials, and trained without inputs from explicit simulations, our denoiser can be applied to simulation data generated from vastly different interatomic interactions. The denoiser is shown to improve existing classification methods, such as common neighbor analysis and polyhedral template matching, reaching perfect classification accuracy on a recent benchmark dataset of thermally perturbed structures up to the melting point. Demonstrated here in a wide variety of atomistic simulation contexts, the denoiser is general, robust, and readily extendable to delineate order from disorder in structurally and chemically complex materials.

The Application of Machine Learning in Diagnosing the Financial Health and Performance of Companies in the Construction Industry

Diagnosing the financial health of companies and their performance is currently one of the basic questions that attracts the attention of researchers and experts in the field of finance and management. In this study, we focused on the proposal of models for measuring the financial health and performance of businesses. These models were built for companies doing business within the Slovak construction industry. Construction companies are identified by their higher liquidity and different capital structure compared to other industries. Therefore, simple classifiers are not able to effectively predict their financial health. In this paper, we investigated whether boosting ensembles are a suitable alternative for performance analysis. The result of the research is the finding that deep learning is a suitable approach aimed at measuring the financial health and performance of the analyzed sample of companies. The developed models achieved perfect classification accuracy when using the AdaBoost and Gradient-boosting algorithms. The application of a decision tree as a base learner also proved to be very appropriate. The result is a decision tree with adequate depth and very good interpretability.

Effective acoustic parameters for automatic classification of performed and synthesized Guzheng music

This study focuses on exploring the acoustic differences between synthesized Guzheng pieces and real Guzheng performances, with the aim of improving the quality of synthesized Guzheng music. A dataset with consideration of generalizability with multiple sources and genres is constructed as the basis of analysis. Classification accuracy up to 93.30% with a single feature put forward the fact that although the synthesized Guzheng pieces in subjective perception evaluation are recognized by human listeners, there is a very significant difference to the performed Guzheng music. With features compensating to each other, a combination of only three features can achieve a nearly perfect classification accuracy of 99.73%, with the essential two features related to spectral flux and an auxiliary feature related to MFCC. The conclusion of this work points out a potential future improvement direction in Guzheng synthesized algorithms with spectral flux properties.

Integrated Machine Learning Model for Predicting Asphaltene Damage Risk and the Asphaltene Onset Pressure

Asphaltene precipitation can promote a drastic reduction in oil production because of asphaltene precipitation and deposition damage. Therefore, screening models to predict the risk of asphaltene damage and equations of state (EoS) to predict the asphaltene onset pressure (AOP) are useful to prevent production drops and optimize the management of oil resources. Most asphaltene screening models have been focused on the oil compositions (SARA analysis); however, these screening models do not consider key variables for asphaltene stability such as the temperature, pressure, well depth, gas–oil ratio, and so on. As the EoS are typically based on experimental data, to fit parameters needed to reproduce the experimental AOP, expensive laboratory analyses are required for this objective. In this study, a classification machine learning (CML) model based on support vector machines was proposed to predict the asphaltene damage risk from the asphaltene stability class index data and the in situ live crude oil densities. In addition, a model based on linear regression (MLR) to predict AOP from the reservoir pressure, saturation pressure, temperature, and some in situ live crude oil compositions was proposed. In total, 24 crude oils were evaluated experimentally to propose the classification model, and a perfect classification accuracy (100%) was obtained in both cases. The CML results were compared to compositional screenings, where classification accuracy was between 29 and 88%, the best accuracy being obtained from the well-known de Boer plot. The MLR model was obtained from data from 53 live crude oils, using hypothesis tests to select the statistically representative characteristics regarding AOP, and a determination coefficient of 0.77 was obtained. The proposed integrated ensemble model contributes to predicting the potential risk of damage due to asphaltene precipitation and estimating a pressure range where these asphaltenes precipitate, allowing the necessary preventive measures to be taken to avoid an oil production decline.

A Robust Feature-Based Approach for Recognition of Line Coding Schemes

Decoding communication signals in a non-cooperative environment has always been a challenging task. Even after the estimation of various transmission-related parameters, the unknown received signal still cannot be decoded without the correct classification of the incorporated line coding scheme. In this paper, a robust short-sample feature-based approach is presented which recognizes line coding schemes in a sequential manner by an in-depth examination of linked characteristic features. The proposed approach provides an overall correct classification accuracy higher than 90 percent with an input of just 13 bit-waveforms whereas perfect classification accuracy (100 percent) is achieved with just 30 bit-waveforms of the unknown received signal. A detailed comparison considering noiseless as well as noisy channel environment is also carried out vis-à-vis existing approach based on extensive simulation results. Additionally, the paper bridges the gap between theory and simulations to justify the obtained accuracy results for conventional line codes under consideration. The substantial increase in classification accuracy for a smaller number of input bit-waveforms shall aid effective decoding of the unknown received signal even at the initial stages of reception. In general, it can benefit many practical spectrum surveillance applications, where proactiveness is paramount.

Industrial control system device classification using network traffic features and neural network embeddings

Characterization of modern cyber–physical Industrial Control System (ICS) devices is critical to the evaluation of their security posture and an understanding of the underlying industrial processes with which they interact. In this work, we address two related ICS device identification tasks: (1) separating ICS from non-ICS devices and (2) identifying specific ICS device types. We propose two distinct methods (one based on the existing IP2Vec method, and a novel traffic-features-based method) for achieving the first task. For transferability of the first task between two datasets, the traffic-features-based method performs significantly better (75% overall accuracy) compared to IP2Vec (22.5% overall accuracy). We further propose a novel method called DNP2Vec to address the second task. DNP2Vec is evaluated on two different datasets and achieves perfect multi-class classification accuracy (100%) for both datasets.

Validity and reliability of Raman spectroscopy for carotenoid assessment in cattle skin

Carotenoids are powerful antioxidants capable of helping to protect the skin from the damaging effects of exposure to sun by reducing the free radicals in skin produced by exposure to ultraviolet radiation, and they may also have a physical protective effect in human skin. Since carotenoids are lipophilic molecules which can be ingested with the diet, they can accumulate in significant quantities in the skin. Several studies on humans have been conducted to evaluate the protective function of carotenoids against various diseases, but there is very limited published information available to understand the mechanism of carotenoid bioavailability in animals. The current study was conducted to investigate the skin carotenoid level (SCL) in two cattle skin sets – weaners with an unknown feeding regime and New Generation Beef (NGB) cattle with monitored feed at three different ages. Rapid analytical and sensitive Raman spectroscopy has been shown to be of interest as a powerful technique for the detection of carotenoids in cattle skin due to the strong resonance enhancement with 532 nm laser excitation. The spectral difference of both types of skin were measured and quantified using univariate and linear discriminant analysis. SCL was higher in NGB cattle than weaners and there is a perfect classification accuracy between weaners and NGB cattle skin using carotenoid markers as a basis. Further work carried out on carotenoid rich NGB cattle skin of 8, 12 and 24 months of age identified an increasing trend in SCL with age. The present work validated the ability of Raman spectroscopy to determine the skin carotenoid level in cattle by comparing it with established HPLC methods. There is an excellent correlation of R2 = 0.96 between the two methods that could serve as a model for future application for larger population studies.

Hyperspectral Image Classification across Different Datasets: A Generalization to Unseen Categories

With the rapid developments of hyperspectral imaging, the cost of collecting hyperspectral data has been lower, while the demand for reliable and detailed hyperspectral annotations has been much more substantial. However, limited by the difficulties of labelling annotations, most existing hyperspectral image (HSI) classification methods are trained and evaluated on a single hyperspectral data cube. It brings two significant challenges. On the one hand, many algorithms have reached a nearly perfect classification accuracy, but their trained models are hard to generalize to other datasets. On the other hand, since different hyperspectral datasets are usually not collected in the same scene, different datasets will contain different classes. To address these issues, in this paper, we propose a new paradigm for HSI classification, which is training and evaluating separately across different hyperspectral datasets. It is of great help to labelling hyperspectral data. However, it has rarely been studied in the hyperspectral community. In this work, we utilize a three-phase scheme, including feature embedding, feature mapping, and label reasoning. More specifically, we select a pair of datasets acquired by the same hyperspectral sensor, and the classifier learns from one dataset and then evaluated it on the other. Inspired by the latest advances in zero-shot learning, we introduce label semantic representation to establish associations between seen categories in the training set and unseen categories in the testing set. Extensive experiments on two pairs of datasets with different comparative methods have shown the effectiveness and potential of zero-shot learning in HSI classification.

Speech Metrics and Samples That Differentiate Between Nonfluent/Agrammatic and Logopenic Variants of Primary Progressive Aphasia.

Purpose Of the three currently recognized variants of primary progressive aphasia, behavioral differentiation between the nonfluent/agrammatic (nfvPPA) and logopenic (lvPPA) variants is particularly difficult. The challenge includes uncertainty regarding diagnosis of apraxia of speech, which is subsumed within criteria for variant classification. The purpose of this study was to determine the extent to which a variety of speech articulation and prosody metrics for apraxia of speech differentiate between nfvPPA and lvPPA across diverse speech samples. Method The study involved 25 participants with progressive aphasia (10 with nfvPPA, 10 with lvPPA, and five with the semantic variant). Speech samples included a word repetition task, a picture description task, and a story narrative task. We completed acoustic analyses of temporal prosody and quantitative perceptual analyses based on narrow phonetic transcription and then evaluated the degree of differentiation between nfvPPA and lvPPA participants (with the semantic variant serving as a reference point for minimal speech production impairment). Results Most, but not all, articulatory and prosodic metrics differentiated statistically between the nfvPPA and lvPPA groups. Measures of distortion frequency, syllable duration, syllable scanning, and-to a limited extent-syllable stress and phonemic accuracy showed greater impairment in the nfvPPA group. Contrary to expectations, classification was most accurate in connected speech samples. A customized connected speech metric-the narrative syllable duration-yielded excellent to perfect classification accuracy. Discussion Measures of average syllable duration in multisyllabic utterances are useful diagnostic tools for differentiating between nfvPPA and lvPPA, particularly when based on connected speech samples. As such, they are suitable candidates for automatization, large-scale study, and application to clinical practice. The observation that both speech rate and distortion frequency differentiated more effectively in connected speech than on a motor speech examination suggests that it will be important to evaluate interactions between speech and discourse production in future research.

ISOM-GSN: an integrative approach for transforming multi-omic data into gene similarity networks via self-organizing maps.

One of the main challenges in applying graph convolutional neural networks (CNNs) on gene-interaction data is the lack of understanding of the vector space to which they belong, and also the inherent difficulties involved in representing those interactions on a significantly lower dimension, viz Euclidean spaces. The challenge becomes more prevalent when dealing with various types of heterogeneous data. We introduce a systematic, generalized method, called iSOM-GSN, used to transform 'multi-omic' data with higher dimensions onto a 2D grid. Afterwards, we apply a CNN to predict disease states of various types. Based on the idea of Kohonen's self-organizing map, we generate a 2D grid for each sample for a given set of genes that represent a gene similarity network. We have tested the model to predict breast and prostate cancer using gene expression, DNA methylation and copy number alteration. Prediction accuracies in the 94-98% range were obtained for tumor stages of breast cancer and calculated Gleason scores of prostate cancer with just 14 input genes for both cases. The scheme not only outputs nearly perfect classification accuracy, but also provides an enhanced scheme for representation learning, visualization, dimensionality reduction and interpretation of multi-omic data. The source code and sample data are available via a Github project at https://github.com/NaziaFatima/iSOM_GSN. Supplementary data are available at Bioinformatics online.

Comparison of Deep Transfer Learning Techniques in Human Skin Burns Discrimination

While visual assessment is the standard technique for burn evaluation, computer-aided diagnosis is increasingly sought due to high number of incidences globally. Patients are increasingly facing challenges which are not limited to shortage of experienced clinicians, lack of accessibility to healthcare facilities and high diagnostic cost. Certain number of studies were proposed in discriminating burn and healthy skin using machine learning leaving a huge and important gap unaddressed; whether burns and related skin injuries can be effectively discriminated using machine learning techniques. Therefore, we specifically use transfer learning by leveraging pre-trained deep learning models due to deficient dataset in this paper, to discriminate two classes of skin injuries—burnt skin and injured skin. Experiments were extensively conducted using three state-of-the-art pre-trained deep learning models that includes ResNet50, ResNet101 and ResNet152 for image patterns extraction via two transfer learning strategies—fine-tuning approach where dense and classification layers were modified and trained with features extracted by base layers and in the second approach support vector machine (SVM) was used to replace top-layers of the pre-trained models, trained using off-the-shelf features from the base layers. Our proposed approach records near perfect classification accuracy in categorizing burnt skin ad injured skin of approximately 99.9%.

An efficient novel approach for iris recognition based on stylometric features and machine learning techniques

This paper presents a novel iris recognition system based on machine learning methods. The motivation behind this research resides in the interrelatedness of biometric systems and stylometry, as shown in our previous research. The main goal of the proposed model is to reach virtually perfect classification accuracy, eliminate false acceptance rates, and cancel the possibility of recreating an iris image from a generated template. To achieve this, we omit Gabor wavelets and other filter banks typically employed in iris recognition systems based on the pioneering work of John Daugman. Instead, we employ machine learning methods that classify biometric templates as numeric features. The biometric templates are generated by converting a normalized iris image into a one-dimensional set of fixed-length codes, which then undergoes stylometric feature extraction. The extracted features are further used for classification. A new recognition method is developed using the CASIA iris database, and its generalizability is demonstrated on the MMU and IITD iris databases separately, and also on their unification with the CASIA database, by applying oversampling before and during the cross-validation procedure. The experimental evaluation shows that the system performs as intended. In addition, the computational costs are significantly decreased with respect to traditional systems, which in turn reduces the overall complexity of the recognition system, making it suitable for use in practical applications.

A machine learning approach to online fault classification in HPC systems

As High-Performance Computing (HPC) systems strive towards the exascale goal, failure rates both at the hardware and software levels will increase significantly. Thus, detecting and classifying faults in HPC systems as they occur and initiating corrective actions before they can transform into failures becomes essential for continued operation. Central to this objective is fault injection, which is the deliberate triggering of faults in a system so as to observe their behavior in a controlled environment. In this paper, we propose a fault classification method for HPC systems based on machine learning. The novelty of our approach rests with the fact that it can be operated on streamed data in an online manner, thus opening the possibility to devise and enact control actions on the target system in real-time. We introduce a high-level, easy-to-use fault injection tool called FINJ, with a focus on the management of complex experiments. In order to train and evaluate our machine learning classifiers, we inject faults to an in-house experimental HPC system using FINJ, and generate a fault dataset which we describe extensively. Both FINJ and the dataset are publicly available to facilitate resiliency research in the HPC systems field. Experimental results demonstrate that our approach allows almost perfect classification accuracy to be reached for different fault types with low computational overhead and minimal delay.

A High-Accuracy Model Average Ensemble of Convolutional Neural Networks for Classification of Cloud Image Patches on Small Datasets

Research on clouds has an enormous influence on sky sciences and related applications, and cloud classification plays an essential role in it. Much research has been conducted which includes both traditional machine learning approaches and deep learning approaches. Compared with traditional machine learning approaches, deep learning approaches achieved better results. However, most deep learning models need large data to train due to the large number of parameters. Therefore, they cannot get high accuracy in case of small datasets. In this paper, we propose a complete solution for high accuracy of classification of cloud image patches on small datasets. Firstly, we designed a suitable convolutional neural network (CNN) model for small datasets. Secondly, we applied regularization techniques to increase generalization and avoid overfitting of the model. Finally, we introduce a model average ensemble to reduce the variance of prediction and increase the classification accuracy. We experiment the proposed solution on the Singapore whole-sky imaging categories (SWIMCAT) dataset, which demonstrates perfect classification accuracy for most classes and confirms the robustness of the proposed model.

Machine learning approach yields epigenetic biomarkers of food allergy: A novel 13-gene signature to diagnose clinical reactivity.

BackgroundCurrent laboratory tests are less than 50% accurate in distinguishing between people who have food allergies (FA) and those who are merely sensitized to foods, resulting in the use of expensive and potentially dangerous Oral Food Challenges. This study presents a purely-computational machine learning approach, conducted using DNA Methylation (DNAm) data, to accurately diagnose food allergies and potentially find epigenetic targets for the disease.Methods and resultsAn unbiased feature-selection pipeline was created that narrowed down 405,000+ potential CpG biomarkers to 18. Machine-learning models that utilized subsets of this 18-feature aggregate achieved perfect classification accuracy on completely hidden test cohorts (on an 8-fold hidden dataset). Ensemble classification was also shown to be effective for this High Dimension Low Sample Size (HDLSS) DNA methylation dataset. The efficacy of these machine learning classifiers and the 18 CpGs was further validated by their high accuracy on a large number of hidden data permutations, where the samples in the training, cross-validation, and hidden sets were repeatedly randomly allocated. The 18-CpG signature mapped to 13 genes, on which biological insights were collected. Notably, many of the FA-discriminating genes found in this study were strongly associated with the immune system, and seven of the 13 genes were previously associated with FA.ConclusionsPrevious studies have also created highly-accurate classifiers for this dataset, using both data-driven and a priori biological insights to construct a 96-CpG signature. This research builds on previous work because it uses a completely computational approach to obtain a perfect classification accuracy while using only 18 highly discriminating CpGs (0.005% of the total available features). In machine learning, simpler models, as used in this study, are generally preferred over more complex ones (other things being equal). Lastly, the completely data-driven methodology presented in this research eliminates the need for a priori biological information and allows for generalizability to other DNAm classification problems.

Clinical assessment of a non-invasive wearable MEMS pressure sensor array for monitoring of arterial pulse waveform, heart rate and detection of atrial fibrillation

There is an unmet clinical need for a low cost and easy to use wearable devices for continuous cardiovascular health monitoring. A flexible and wearable wristband, based on microelectromechanical sensor (MEMS) elements array was developed to support this need. The performance of the device in cardiovascular monitoring was investigated by (i) comparing the arterial pressure waveform recordings to the gold standard, invasive catheter recording (n = 18), (ii) analyzing the ability to detect irregularities of the rhythm (n = 7), and (iii) measuring the heartrate monitoring accuracy (n = 31). Arterial waveforms carry important physiological information and the comparison study revealed that the recordings made with the wearable device and with the gold standard device resulted in almost identical (r = 0.9–0.99) pulse waveforms. The device can measure the heart rhythm and possible irregularities in it. A clustering analysis demonstrates a perfect classification accuracy between atrial fibrillation (AF) and sinus rhythm. The heartrate monitoring study showed near perfect beat-to-beat accuracy (sensitivity = 99.1%, precision = 100%) on healthy subjects. In contrast, beat-to-beat detection from coronary artery disease patients was challenging, but the averaged heartrate was extracted successfully (95% CI: −1.2 to 1.1 bpm). In conclusion, the results indicate that the device could be useful in remote monitoring of cardiovascular diseases and personalized medicine.

Deep neural networks for bot detection

The problem of detecting bots, automated social media accounts governed by software but disguising as human users, has strong implications. For example, bots have been used to sway political elections by distorting online discourse, to manipulate the stock market, or to push anti-vaccine conspiracy theories that may have caused health epidemics. Most techniques proposed to date detect bots at the account level, by processing large amounts of social media posts, and leveraging information from network structure, temporal dynamics, sentiment analysis, etc. In this paper, we propose a deep neural network based on contextual long short-term memory (LSTM) architecture that exploits both content and metadata to detect bots at the tweet level: contextual features are extracted from user metadata and fed as auxiliary input to LSTM deep nets processing the tweet text. Another contribution that we make is proposing a technique based on synthetic minority oversampling to generate a large labeled dataset, suitable for deep nets training, from a minimal amount of labeled data (roughly 3000 examples of sophisticated Twitter bots). We demonstrate that, from just one single tweet, our architecture can achieve high classification accuracy (AUC > 96%) in separating bots from humans. We apply the same architecture to account-level bot detection, achieving nearly perfect classification accuracy (AUC > 99%). Our system outperforms previous state of the art while leveraging a small and interpretable set of features, yet requiring minimal training data.

A Comparison between Theoretical and Experimental Measures of Consciousness as Integrated Information in an Anatomically Based Network of Coupled Oscillators

The rise of mathematical developments in the theories of consciousness has led to new measures to detect consciousness in a system. The Integrated Information Theory (IIT) is one of the best mathematical rooted attempts to quantify the level of consciousness in a system with Φ as the effective information generated in a system above its parts. Recently, the IIT has inspired the Perturbational Complexity Index (PCI) to detect conscious states in patients with disorders of consciousness, and it has shown to have almost perfect classification accuracy. In this study, we explore the statistical correspondence between the theoretical Φ and the experimental PCI through a neurocomputational model of coupled oscillators that can be artificially perturbed, which mainly focuses on the dynamics of collective synchronization between subsets of brain areas. Our results reveal that both measures are statistically related but, in principle, this relationship is far to be perfect. These results are discussed in the context of the model of coupled oscillators, which mainly focuses on the dynamics of collective synchronization between subsets of brain areas.