Linear Classifier Research Articles

Heart Disease Detection by Machine Learning System

Heart disease is a prevalent global health issue that impacts a substantial number of individuals worldwide. It is characterized by symptoms such as shortness of breath, muscle weakness, and swollen feet. However, the current diagnostic methods for heart disease have limitations in terms of accuracy and efficiency, making early detection challenging. Consequently, researchers are striving to develop an effective approach for early detection of heart disease. The lack of advanced medical equipment and qualified healthcare professionals further complicates the diagnosis and management of cardiac conditions., there have been approximately 26 million reported cases of heart disease, with an additional 3.6 million new cases identified annually. In the United States, a significant proportion of the population is affected by heart disease. Typically, doctors diagnose heart disease by considering the patient's medical history, conducting a physical examination, and assessing any concerning symptoms. However, this diagnostic method does not consistently provide accurate identification of individuals with heart disease. The importance of employing. There are numerous crucial elements in the process for developing a smart parking system in an IoT context. First, sensors are placed in parking places to gather up-to-the-minute occupancy information. Then, using wireless communication protocols, this data is sent to a central server or cloud computing platform. After that, a data processing and analysis module interprets the gathered data using algorithms and machine learning techniques and presents parking availability information to users via a mobile application or other user interfaces. For effective management and monitoring of parking spaces, the system also includes automated payment methods and interacts with existing infrastructure. “Patient 1,patient 2,patient 3 and patient 4.” Dyspnea can be described as a sensation of breathlessness and inadequate breathing, where one feels unable to take in enough air or breathe deeply. It involves the interplay of mechanoreceptors in the upper airways, lungs, and chest wall, along with peripheral receptors, chemoreceptors, and other sensory receptors. Edema refers to the accumulation of excessive fluid in the body tissues, leading to swelling. While edema can occur in any part of the body, it is more commonly observed in the lower extremities Ascites - The pathological buildup of fluid in the abdominal cavity is known as ascites. It is the most frequent cirrhosis consequence and happens in 50% of patients with decompensated cirrhosis within 10 years. Ascites formation marks the change from stressed to decompensated cirrhosis. Patent 1 is in rank 1 and patient 5 is ranked 5. In weighted table every value is equally split by 1,so that each value is equal. In the study, the researchers compared the sensitivity levels of two classifiers: the Relief FS method with a linear SVM classifier and the NB classifier with specific features from the LASSO FS algorithm. The findings revealed that the NB classifier, utilizing LASSO FS features, exhibited the highest performance in terms of sensitivity. Additionally, the Logistic Regression MCC classifier, employing the FCMIM FS method, achieved a classification accuracy of 91%.

An IoT based Tree Specific Soil Nutrient Management System Using Neural Network for Cashew Cultivation

Anacardium occidentale commonly known as Cashew was introduced into India by Portuguese in 16th century. Farmers of Cuddalore District, Tamil Nadu in India, are interested in Cashew Cultivation due to its export market values. To achieve better yield from cashew cultivation, farmers need to supply balanced nutrition to the soil and by following intercropping method. In literature, Recent Technologies like Artificial Intelligence and IOT are widely used to predict dosage of the fertilizer to be applied. By examining the numerous connected ascribe success locations of Cashew orchards, it was possible to determine how much macronutrients like Nitrogen (N), Phosphorus (P), and Potassium (K) were present in the soil and it will be helpful for the understanding of soil fertility level of the area. In our work, using IOT set up which includes Arduino UNO, NPK sensor and OLED display, we identified NPK values of soil for various cashew trees in a particular area. Along with NPK values of soil, inputs include the local soil type, PH and Tree age. Based on the input factors, DL trained model will provide suggestions of fertilizer dose to be applied for a specific tree for the Cashew cultivating farmers for better yield. In our proposed work, LSTM based Recurrent Neural Network (RNN) Algorithm is used to provide a better prediction of fertilizer. With the help of this research, we can be provided with what intercrop to plant and how much fertilizer to use, in what ratio to supply and fertilizer shop suggestion to enhance agricultural knowledge across the globe using the Internet of Things (IoT) and Artificial Intelligence. The result of RNN model was compared with Random Forest, Linear Regression, Linear Random Classifier, Decision Tree Classifier with proving accuracy of 98.7 %. Together with a decrease in the farmers' input efforts, these strategies will increase the productivity of the fields.

Generalization of linear and non-linear support vector machine in multiple fields: a review

Support vector machines (SVMs) are a set of related supervised learning methods used for classification and regression. They belong to a family of generalized linear classifiers. In other terms, SVM is a classification and regression prediction tool that uses machine learning theory to maximize predictive accuracy. In this article, the discussion about linear and non-linear SVM classifiers with their functions and parameters is investigated. Due to the equality type of constraints in the formulation, the solution follows from solving a set of linear equations. Besides this, if the under-consideration problem is in the form of a non-linear case, then the problem must convert into linear separable form with the help of kernel trick and solve it according to the methods. Some important algorithms related to sentimental work are also presented in this paper. Generalization of the formulation of linear and non-linear SVMs is also open in this article. In the final section of this paper, the different modified sections of SVM are discussed which are modified by different research for different purposes.

Generalization of linear and non-linear support vector machine in multiple fields: a review

Support vector machines (SVMs) are a set of related supervised learning methods used for classification and regression. They belong to a family of generalized linear classifiers. In other terms, SVM is a classification and regression prediction tool that uses machine learning theory to maximize predictive accuracy. In this article, the discussion about linear and non-linear SVM classifiers with their functions and parameters is investigated. Due to the equality type of constraints in the formulation, the solution follows from solving a set of linear equations. Besides this, if the under-consideration problem is in the form of a non-linear case, then the problem must convert into linear separable form with the help of kernel trick and solve it according to the methods. Some important algorithms related to sentimental work are also presented in this paper. Generalization of the formulation of linear and non-linear SVMs is also open in this article. In the final section of this paper, the different modified sections of SVM are discussed which are modified by different research for different purposes.

Health monitoring of historic buildings using machine learning in real-time internet of things

<span>In this paper, structural health monitoring (SHM) is used to detect the damage level for the historic building. The damaged level is defined based on the support vector machine (SVM) algorithm to extract the damage feature. Physical checks allow us to detect any damage or structural degeneration. Supervised training machine learning (ML) is used as a tool to examine accelerometer data to ascertain the condition of structures following an occurrence. The three training models, the SVM, the random forest linear classification, and the k-nearest neighbor (KNN) model are tested and compared to classify data. The data obtained from structural health monitoring, teams of responders, and investigators can be used to manage the most vulnerable structures. The accuracy of the SVM algorithm was found up to 94% accurate and precise, at a high level. The internet of things (IoT) architecture is also introduced with SVM learning algorithms for early warning. The proposed system makes use of an SHM system to identify seismic events or accelerations. The IoT system SHM uses real data from the structure, allowing for online damage identification and ongoing monitoring. A dashboard is used to represent the monitoring data and the damage level.</span>

LIFESPAN OF DAIRY CATTLE DEPENDING ON THE LEVEL OF EVALUATION OF UDDER LINEAR TRAITS

The dependence of cows lifespan of Ukrainian Black-and-White dairy (UBWD) and Holstein (H) breeds on the level of evaluation of linear type traits that characterize udder morphological qualities in the general system of linear classification was studied. Descriptive traits of the evaluated conformation type were: front udder parts attachment, height of rear udder parts attachment, central ligament, udder depth, front teats placement and length. A certain correlative variability was established between level of evaluation of linear type traits and lifespan of animals. The highly reliable difference between evaluated cows for linear type trait of front udder parts attachment with 1 and 9 scores is significant and was 841 (UBWD; P<0.001) and 810 (H; P<0.001) days. An interbreed comparison of cows lifespan, depending on the evaluation, testified in favor cows of Holstein breed with variability within 43-159 days by an unreliable difference. Difference between the lowest and highest scores for type trait of height rear udder attachment in cows of experimental breeds was 740 (UBWD; Р<0.001) and 810 (H; Р<0.001) days. Animals with an assessment for trait development of central udder ligament lower than 1-3 scores live, according to evaluated breeds, from 2089 to 2401 (UBWD) and from 2154 to 2468 (H) days. Cows with 9 scores for both breeds had the highest lifespan – 2663 days (UBWD), inferior to cows with the lowest score by 754 (Р<0.001) and 2803 days (H) with significant increase on 649 days (Р<0.001). Difference between the average lifespan in cows of Ukrainian Black-and-White dairy breed with 9 and 1 scores for linear type trait of udder depth was 739 (Р<0.001) and 832 days (Р<0.001) in Holstein cows. Lifespan of cows both breeds in the herd was characterized by slight curvilinear variability, depending on the assessment of linear type trait of front teats placement. Consequently, cows of both breeds with an average score of 7 were used in the herd for the longest period. Evaluation of correlative variability of the front teats length with lifespan of cows in controlled breeds indicated that animals with an average score of 5, which was equal to their teats length at 5 cm, had longer functional life. Research results showed that each of evaluated descriptive traits in cows of both breeds has an impact on lifespan with different variability within individual body part, so better expression of linear type trait can be a breeding trait as an indirect predictor of longevity.

The influence of food values on snacks and beverage choices: an experimental study in Mexico

This study examines whether Mexican consumers consider the value associated with the attributes of manufactured snacks when deciding what to eat between meals. A choice experiment involving the selection of healthy versus unhealthy snacks and beverages was performed using Qualtrics. A set of four options, each one corresponding to a combination of mid-day snack and beverage, was presented to 256 Mexican consumers, who, after making a choice, specified the importance they assigned to food choice values. Linear discriminant analysis and classification trees were used to identify what food choice values and psychographic and demographic traits explain the choices. The analytical results indicate weight control, healthiness and sustainability, and the emotional value of healthy snacks mainly drives the choices of health-conscious consumers.

Leveraging linear mapping for model-agnostic adversarial defense

In the ever-evolving landscape of deep learning, novel designs of neural network architectures have been thought to drive progress by enhancing embedded representations. However, recent findings reveal that the embedded representations of various state-of-the-art models are mappable to one another via a simple linear map, thus challenging the notion that architectural variations are meaningfully distinctive. While these linear maps have been established for traditional non-adversarial datasets, e.g., ImageNet, to our knowledge no work has explored the linear relation between adversarial image representations of these datasets generated by different CNNs. Accurately mapping adversarial images signals the feasibility of generalizing an adversarial defense optimized for a specific network. In this work, we demonstrate the existence of a linear mapping of adversarial inputs between different models that can be exploited to develop such model-agnostic, generalized adversarial defense. We further propose an experimental setup designed to underscore the concept of this model-agnostic defense. We train a linear classifier using both adversarial and non-adversarial embeddings within the defended space. Subsequently, we assess its performance using adversarial embeddings from other models that are mapped to this space. Our approach achieves an AUROC of up to 0.99 for both CIFAR-10 and ImageNet datasets.

The Performance of a Lip-Sync Imagery Model, New Combinations of Signals, a Supplemental Bond Graph Classifier, and Deep Formula Detection as an Extraction and Root Classifier for Electroencephalograms and Brain–Computer Interfaces

Many current brain–computer interface (BCI) applications depend on the quick processing of brain signals. Most researchers strive to create new methods for future implementation and enhance existing models to discover an optimal feature set that can operate independently. This study focuses on four key concepts that will be used to complete future works. The first concept is related to potential future communication models, whereas the others aim to enhance previous models or methodologies. The four concepts are as follows. First, we suggest a new communication imagery model as a substitute for a speech imager that relies on a mental task approach. As speech imagery is intricate, one cannot imagine the sounds of every character in every language. Our study proposes a new mental task model for lip-sync imagery that can be employed in all languages. Any character in any language can be used with this mental task model. In this study, we utilized two lip-sync movements to indicate two sounds, characters, or letters. Second, we considered innovative hybrid signals. Choosing an unsuitable frequency range can lead to ineffective feature extractions. Therefore, the selection of an appropriate frequency range is crucial for processing. The ultimate goal of this method is to accurately discover distinct frequencies of brain imagery activities. The restricted frequency range combination presents an initial proposal for generating fragmented, continuous frequencies. The first model assesses two 4 Hz intervals as filter banks. The primary objective is to discover new combinations of signals at 8 Hz by selecting filter banks with a 4 Hz scale from the frequency range of 4 Hz to 40 Hz. This approach facilitates the acquisition of efficient and clearly defined features by reducing similar patterns and enhancing distinctive patterns of brain activity. Third, we introduce a new linear bond graph classifier as a supplement to a linear support vector machine (SVM) when handling noisy data. The performance of the linear support vector machine (SVM) significantly declines under high-noise conditions. To complement the linear support vector machine (SVM) in noisy-data situations, we introduce a new linear bond graph classifier. Fourth, this paper presents a deep-learning model for formula recognition that converts the first-layer data into a formula extraction model. The primary goal is to decrease the noise in the formula coefficients of the subsequent layers. The output of the final layer comprises coefficients chosen by different functions at various levels. The classifier then extracts the root interval for each formula, and a diagnosis is established based on these intervals. The final goal of the last idea is to explain the main brain imagery activity formula using a combination formula for similar and distinctive brain imagery activities. The results of implementing all of the proposed methods are reported. The results range between 55% and 98%. The lowest result is 55% for the deep detection formula, and the highest result is 98% for new combinations of signals.

TCF4 and RBFOX1 as peripheral biomarkers for the differential diagnosis and treatment of major depressive disorder

BackgroundRecent genome-wide association studies on major depressive disorder (MDD) have indicated the involvement of LRFN5 and OLFM4; however, the expression levels and roles of these molecules in MDD remain unclear. The present study aimed to determine the serum levels of TCF4 and RBFOX1 in patients with MDD and to investigate whether these molecules could be used as biomarkers for MDD diagnosis. MethodsThe study included 99 drug-naïve MDD patients, 90 drug-treated MDD patients, and 81 healthy controls (HCs). Serum TCF4 and RBFOX1 levels were measured by ELISA. Pearson's correlation analysis was conducted to determine the association between TCF4/RBFOX1 and clinical variables. Linear support vector machine classifier was used to evaluate the diagnostic capabilities of TCF4 and RBFOX1. ResultsSerum TCF4 and RBFOX1 levels were substantially higher in MDD patients than in HCs and significantly lower in drug-treated MDD patients than in drug-naïve MDD patients. Moreover, serum TCF4 and RBFOX1 levels were associated with the Hamilton Depression Scale score, duration of illness, serum lipids levels, and hepatic function. Thus, both these molecules showed potential as biomarkers for MDD. TCF4 and RBFOX1 combination exhibited a higher diagnostic performance, with the mean area under the curve values of 0.9861 and 0.9936 in the training and testing sets, respectively. LimitationsSmall sample size and investigation of only the peripheral nervous system. ConclusionsTCF4 and RBFOX1 may be involved in the pathogenesis of MDD, and their combination may serve as a diagnostic biomarker panel for MDD.

Metabolomic profiling of preterm birth in pregnant women living with HIV

BackgroundPreterm birth is a leading cause of death in children under the age of five. The risk of preterm birth is increased by maternal HIV infection as well as by certain antiretroviral regimens, leading to a disproportionate burden on low- and medium-income settings where HIV is most prevalent. Despite decades of research, the mechanisms underlying spontaneous preterm birth, particularly in resource limited areas with high HIV infection rates, are still poorly understood and accurate prediction and therapeutic intervention remain elusive.ObjectivesMetabolomics was utilized to identify profiles of preterm birth among pregnant women living with HIV on two different antiretroviral therapy (ART) regimens.MethodsThis pilot study comprised 100 mother-infant dyads prior to antiretroviral initiation, on zidovudine monotherapy or on protease inhibitor-based antiretroviral therapy. Pregnancies that resulted in preterm births were matched 1:1 with controls by gestational age at time of sample collection. Maternal plasma and blood spots at 23–35 weeks gestation and infant dried blood spots at birth, were assayed using an untargeted metabolomics method. Linear regression and random forests classification models were used to identify shared and treatment-specific markers of preterm birth.ResultsClassification models for preterm birth achieved accuracies of 95.5%, 95.7%, and 80.7% in the untreated, zidovudine monotherapy, and protease inhibitor-based treatment groups, respectively. Urate, methionine sulfone, cortisone, and 17α-hydroxypregnanolone glucuronide were identified as shared markers of preterm birth. Other compounds including hippurate and N-acetyl-1-methylhistidine were found to be significantly altered in a treatment-specific context.ConclusionThis study identified previously known as well as novel metabolomic features of preterm birth in pregnant women living with HIV. Validation of these models in a larger, independent cohort is necessary to ascertain whether they can be utilized to predict preterm birth during a stage of gestation that allows for therapeutic intervention or more effective resource allocation.

Research on the diagnosis of corona virus disease 2019(COVID-19) based on machine-learning

In recent years, the Corona Virus Disease 2019(COVID-19) has brought a huge impact on people's daily life and the normal operation of society, and as machine learning research deepens, this technology could help detect viruses such as the novel coronavirus. According to this, how to accurately, quickly and effectively analyze and classify laboratory results with multiple indicators through the method of machine learning is the object of this paper. In order to explore the classification performance of various machine learning classification algorithms on laboratory results, linear and non-linear methods were used respectively to analyze and classify the laboratory results. In linear analysis, distance discriminant and fisher discriminant were used to explore the classification effect of linear classification on laboratory results. The non-linear analysis mainly used Adaptive Boosting(AdaBoost) and Random Forest algorithm which are widely used to test the classification effect under the influence of multiple indexes. In this paper, python and other tools were used to classify samples of different combinations by using the idea of cross validation. By comparing the running time and detection accuracy, it was found that Adaboost algorithm is applicable in most cases and was a relatively fast and accurate classification method. In addition, Random Forest algorithm had similar accuracy, but it might have better performance on a large data set.

Enhancement of Classifier Performance Using Swarm Intelligence in Detection of Diabetes from Pancreatic Microarray Gene Data.

In this study, we focused on using microarray gene data from pancreatic sources to detect diabetes mellitus. Dimensionality reduction (DR) techniques were used to reduce the dimensionally high microarray gene data. DR methods like the Bessel function, Discrete Cosine Transform (DCT), Least Squares Linear Regression (LSLR), and Artificial Algae Algorithm (AAA) are used. Subsequently, we applied meta-heuristic algorithms like the Dragonfly Optimization Algorithm (DOA) and Elephant Herding Optimization Algorithm (EHO) for feature selection. Classifiers such as Nonlinear Regression (NLR), Linear Regression (LR), Gaussian Mixture Model (GMM), Expectation Maximum (EM), Bayesian Linear Discriminant Classifier (BLDC), Logistic Regression (LoR), Softmax Discriminant Classifier (SDC), and Support Vector Machine (SVM) with three types of kernels, Linear, Polynomial, and Radial Basis Function (RBF), were utilized to detect diabetes. The classifier's performance was analyzed based on parameters like accuracy, F1 score, MCC, error rate, FM metric, and Kappa. Without feature selection, the SVM (RBF) classifier achieved a high accuracy of 90% using the AAA DR methods. The SVM (RBF) classifier using the AAA DR method for EHO feature selection outperformed the other classifiers with an accuracy of 95.714%. This improvement in the accuracy of the classifier's performance emphasizes the role of feature selection methods.

Decision Tree Versus Linear Support Vector Machine Classifier in the Screening of Medial Speech Sounds: A Quest for a Sound Rationale.

This paper describes the latest development in the classification stage of our Speech Sound Disorder (SSD) Screening algorithm and presents the results achieved by using two classifier models: the Classification and Regression Tree (CART)-based model versus the Single Decision Hyperplane-based Linear Support Vector Machine (SVM) model. For every single speech sound in medial position, 10 features extracted from the audio samples along with an 11th feature representing the validation of the (mis)pronunciation by the Speech Language Pathologist (SLP) were fed into the 2 classifiers to compare and discuss their performance. The accuracy achieved by the two classifiers on a data test size of 30% of the analyzed samples was 98.2% for the Linear SVM classifier, and 100% for the Decision Tree classifier, which are optimal results that encourage our quest for a sound rationale.

Hand-Breathe: Noncontact Monitoring of Breathing Abnormalities From Hand Palm

In post-covid19 world, radio frequency (RF)-based non-contact methods, e.g., software-defined radios (SDR)-based methods have emerged as promising candidates for intelligent remote sensing of human vitals, and could help in containment of contagious viruses like covid19. To this end, this work utilizes the universal software radio peripherals (USRP)-based SDRs along with classical machine learning (ML) methods to design a non-contact method to monitor different breathing abnormalities. Under our proposed method, a subject rests his/her hand on a table in between the transmit and receive antennas, while an orthogonal frequency division multiplexing (OFDM) signal passes through the hand. Subsequently, the receiver extracts the channel frequency response (basically, fine-grained wireless channel state information), and feeds it to various ML algorithms which eventually classify between different breathing abnormalities. Among all classifiers, linear SVM classifier resulted in a maximum accuracy of 88.1%. To train the ML classifiers in a supervised manner, data was collected by doing real-time experiments on 4 subjects in a lab environment. For label generation purpose, the breathing of the subjects was classified into three classes: normal, fast, and slow breathing. Furthermore, in addition to our proposed method (where only a hand is exposed to RF signals), we also implemented and tested the state-of-the-art method (where full chest is exposed to RF radiation). The performance comparison of the two methods reveals a trade-off, i.e., the accuracy of our proposed method is slightly inferior but our method results in minimal body exposure to RF radiation, compared to the benchmark method.

Application of machine learning algorithm in electronic book database management system

Intelligent algorithms have excellent performance in managing large databases and mining effective knowledge, and many researchers have introduced these algorithms into research to improve the performance of book management systems. This article introduced the application of machine learning algorithms in electronic book database management systems. A linear classifier (linear regression algorithm is one of machine learning algorithms) was used to analyze the empirical loss value. This paper studied the application of machine learning algorithm in the database management of library special collection resources, aiming to optimize the management of library special collection resources database through machine learning algorithm, and provided students with better experience of using special collection resources. This paper verified the effectiveness of the machine learning algorithm from three aspects: the retrieval time before and after the special resource database, the number of crashes in a month and the number of library staff. The average time of the five sets using the machine learning algorithm was about 150% faster than the average search time of the five sets of special resource databases. The number of crashes after using machine learning algorithm was 2, 1, 1, 2, 1, which was much lower than that of special resource database. After using the machine learning algorithm, the five groups of workers were 7, 5, 9, 6, and 4, respectively, far fewer than the five groups of special collectors. Finally, by comparing the linear regression model, Support vector machine model, and random forest model, it was found that the accuracy of the linear regression model reached 98.2%, an increase of 8.2% compared to the random forest model, the precision rate reached 96.7%, and the recall rate reached 98.2%. 97.8%, F1 value reached 97.5%.It can be seen from the experimental data that the machine learning algorithm plays a good role in the database management of the library special collection resources.

High-Dimensional Feature Space for Diabetes Diagnosis and Identification of Diabetic-Sensitive Features in Ayurvedic Nadi Signals

Nadi-based disease diagnosis is a traditional art in Ayurvedic medicine that is an inquisitive yet not widely comprehended subject. A collection of higher dimensional features from a preprocessed Nadi dataset was extracted and analyzed to diagnose diabetes. The t-distributed Stochastic Neighbor Embedding was used to visualize the higher dimensional feature space in 2-D. The linear dimensionality reduction method of Principal Component Analysis and several linear and nonlinear classifiers were tested on the reduced feature space in identifying diabetes. The key outcomes of this paper are the ability to reduce the feature space by 73.33% while retaining a classification accuracy of 95.4%, identifying age as a compounding factor in diagnosis, and extracting the diabetes-sensitive features with eigenvalue loading.

Computational assessment of visual coding across mouse brain areas and behavioural states.

Our brain is bombarded by a diverse range of visual stimuli, which are converted into corresponding neuronal responses and processed throughout the visual system. The neural activity patterns that result from these external stimuli vary depending on the object or scene being observed, but they also change as a result of internal or behavioural states. This raises the question of to what extent it is possible to predict the presented visual stimuli from neural activity across behavioural states, and how this varies in different brain regions. To address this question, we assessed the computational capacity of decoders to extract visual information in awake behaving mice, by analysing publicly available standardised datasets from the Allen Brain Institute. We evaluated how natural movie frames can be distinguished based on the activity of units recorded in distinct brain regions and under different behavioural states. This analysis revealed the spectrum of visual information present in different brain regions in response to binary and multiclass classification tasks. Visual cortical areas showed highest classification accuracies, followed by thalamic and midbrain regions, with hippocampal regions showing close to chance accuracy. In addition, we found that behavioural variability led to a decrease in decoding accuracy, whereby large behavioural changes between train and test sessions reduced the classification performance of the decoders. A generalised linear model analysis suggested that this deterioration in classification might be due to an independent modulation of neural activity by stimulus and behaviour. Finally, we reconstructed the natural movie frames from optimal linear classifiers, and observed a strong similarity between reconstructed and actual movie frames. However, the similarity was significantly higher when the decoders were trained and tested on sessions with similar behavioural states. Our analysis provides a systematic assessment of visual coding in the mouse brain, and sheds light on the spectrum of visual information present across brain areas and behavioural states.

A novel method for detecting URLs phishing using hybrid machine learning algorithm

Abstract— The phishing attack is the type of cyberattack that targets people’s trust by masking the malicious intent of the attack as communications from reputable sources. The goal is to steal sensitive data from the victim(s) (banking information, social identification, credentials, etc.) for various purposes (selling for monetary gain, performing identity thief, using as a lever for escalation attack). In 2022, the number of reported phishing attacks will reach a whopping 255 million cases, an increment of 61% compared to 2021. Existing methods of phishing URL detection have limitations. The article proposes a method to increase the accuracy of detecting malicious URL by using machine learning methods Linear Support Vector Classification and multinomial Naive Bayes with voting mechanisms.

T-shaped partial least squares for high-dosed new active pharmaceutical ingredients in continuous twin-screw wet granulation: Granule size prediction with limited material information

This work presents a granule size prediction approach applicable to diverse formulations containing new active pharmaceutical ingredients (APIs) in continuous twin-screw wet granulation. The approach consists of a surrogate selection method to identify similar materials with new APIs and a T-shaped partial least squares (T-PLS) model for granule size prediction across varying formulations and process conditions. We devised a surrogate material selection method, employing a combination of linear pre-processing and nonlinear classification algorithms, which effectively identified suitable surrogates for new materials. Using only material properties obtained through four characterization methods, our approach demonstrated its predictive prowess. The selected surrogate methods were seamlessly integrated with our developed T-PLS model, which was meticulously validated for high-dose formulations involving three new APIs. When surrogating new APIs based on Gaussian process classification, we achieved the lowest prediction errors, signifying the method’s robustness. The predicted d-values were within the range of uncertainty bounds for all cases, except for d90 of API C. Notably, the approach offers a direct and efficient solution for early-phase formulation and process development, considerably reducing the need for extensive experimental work. By relying on just four material characterization methods, it streamlines the research process while maintaining a high degree of accuracy.