Search

Potato crop has become integral part of our diet due to its wide use in variety of dishes, making it an important food crop. Its importance also stems from the fact that it is one of the cheapest vegetables available throughout the year. This makes it crucial to keep potato prices affordable for developing countries where the majority of the population falls under the middle-income bracket. Consequently, there is a need to develop a robust, effective, and portable technique to detect diseases in potato plant leaves. In this work, an attention-based disease detection technique is proposed. This technique selectively focuses on specific parts of an image which reveal the disease. This technique leverages transfer learning combined with two attention modules: the channel attention module and spatial attention module. By focusing on specific parts of the images, the proposed technique is able to achieve almost similar accuracy with significantly fewer parameters. The proposed technique has been validated using four pre-trained models: DenseNet169, XceptionNet, MobileNet, and VGG16. All of these models are able to achieve almost the same level of training and validation accuracy, around 90–97%, even after reducing the number of parameters by 40–50%. It shows that the proposed technique effectively reduces model complexity without compromising performance. [ABSTRACT FROM AUTHOR]

The study aimed to classify two classes of vehicles, Tuktuk and Motorcycle, using a modified RCNN model. The MAjN_IRAQ Dataset, created from a camera system in Baghdad city, was used for training, detection, and classification of some vehicles to allow them to enter some crowded streets of Baghdad and to prevent others from entering the same streets. New layers were added and the number and size of filters were changed, which led to improve the process of training, detection and classification of vehicles with high accuracy, which leads to improving the proposed model's performance. The results showed that the modified RCNN model performed better when trained for 80 epochs. It improved performance measures such as precision, recall, and F1 score measure. The model was compared to other transfer learning methods (Alex Net, VGG16, and VGG19) and showed superior results for the Tuktuk class. The training and testing time for the proposed RCNNmodified model was also lower compared to the other models. At 80 epochs, the precision for the Tuktuk class was approximately 0.94, while for the Motorcycle class, it was approximately 0.89. The TPR was higher for the Tuktuk class at approximately 0.93, while the lower value was approximately 0.84 for VGG16. When the VGG16 model was used, the F1 score was better in the Motorcycle category (about 0.95) but worse in the Tuktuk category (0.86%). Both the suggested RCNN-modified model and the Alex Net model worked well in a reasonable amount of time. [ABSTRACT FROM AUTHOR]

Intrusion Detection Model (IDM) is an essential device for network defence in current trend. Malicious users analyse the vulnerabilities of IDSs to capture unauthorized access. Furthermore, intrusion detection encompasses numerous numerical attributes and models, resulting in elevated detection errors and triggering false alarms. Hence, optimal computational intelligence shall be incorporated in IDM to achieve high detection rate and less number of false alarms. Considering the same, a new hybrid IDM framework is developed as the combination of Fuzzy Genetic Algorithm with Multi-Objective Particle Swarm Optimization that maximizes the detection accuracy, minimizes the false alarms and takes less computational complexity which will be explained first phase. The existing IDSs are constraint to the information trained incur into false positives based on user continuity for normal activity. The objective of this proposal is to extract optimal classification rules automatically from training data that helps to identify types of attacks correctly including the unknown attack types. For achieving this goal, Multi-Objective Particle Swarm Optimization (MOPSO) is used as classifier to enhance the identification of the rare attack classes within the IDM. The effectiveness of this method lies in its capacity to leverage information within an unfamiliar search space, guiding subsequent searches towards valuable subspaces. It provides better separability of various classes' i.e. normal behaviour and false alarms. In this FGA-MOPSO model, Principal Component Analysis (PCA) serves as the feature selection technique employed to identify pertinent features within the dataset, thereby enhancing the classifier's performance and Fuzzy Genetic Algorithm (FGA) is used to create new population for training the classifier with the help of three operations namely selection, crossover and mutation that helps to practice more patterns in training phase and to obtain better understanding of the proposed classifier. The simulation will illustrate that the system is competent to speed-up the training and testing process of intrusions detection is important for network applications.Please confirm if the author names are presented accurately and in the correct sequence (given name, middle name/initial, family name). Author 1 Given name: [Arun Kumar] Last name [Ramamoorthy]. Also, kindly confirm the details in the metadata are correct.Checked and Verified for Author 1. In Author 2 name, Given Name was [K.] and last name was[Karuppasamy], But its is just the opposite. Given Name is [Karuppasamy] and Last Name is [K.]. I have edited it. [ABSTRACT FROM AUTHOR]

Objectives: Natural language processing (NLP) represents one of the adjunct technologies within artificial intelligence and machine learning, creating structure out of unstructured data. This study aims to assess the performance of employing NLP to identify and categorize unstructured data within the emergency medicine (EM) setting. Methods: We systematically searched publications related to EM research and NLP across databases including MEDLINE, Embase, Scopus, CENTRAL, and ProQuest Dissertations & Theses Global. Independent reviewers screened, reviewed, and evaluated article quality and bias. NLP usage was categorized into syndromic surveillance, radiologic interpretation, and identification of specific diseases/events/syndromes, with respective sensitivity analysis reported. Performance metrics for NLP usage were calculated and the overall area under the summary of receiver operating characteristic curve (SROC) was determined. Results: A total of 27 studies underwent meta‐analysis. Findings indicated an overall mean sensitivity (recall) of 82%–87%, specificity of 95%, with the area under the SROC at 0.96 (95% CI 0.94–0.98). Optimal performance using NLP was observed in radiologic interpretation, demonstrating an overall mean sensitivity of 93% and specificity of 96%. Conclusions: Our analysis revealed a generally favorable performance accuracy in using NLP within EM research, particularly in the realm of radiologic interpretation. Consequently, we advocate for the adoption of NLP‐based research to augment EM health care management. [ABSTRACT FROM AUTHOR]

Background: Artificial intelligence (AI) offers a promising solution to expedite various phases of the systematic review process such as screening. Objective: We aimed to assess the accuracy of an AI tool in identifying eligible references for a systematic review compared to identification by human assessors. Methods: For the case study (a systematic review of knowledge translation interventions), we used a diagnostic accuracy design and independently assessed for eligibility a set of articles (n = 300) using human raters and the AI system DistillerAI (Evidence Partners, Ottawa, Canada). We analysed a series of 64 possible confidence levels for the AI's decisions and calculated several standard parameters of diagnostic accuracy for each. Results: When set to a lower AI confidence threshold of 0.1 or greater and an upper threshold of 0.9 or lower, DistillerAI made article selection decisions very similarly to human assessors. Within this range, DistillerAI made a decision on the majority of articles (93–100%), with a sensitivity of 1.0 and specificity ranging from 0.9 to 1.0. Conclusion: DistillerAI appears to be accurate in its assessment of articles in a case study of 300 articles. Further experimentation with DistillerAI will establish its performance among other subject areas. [ABSTRACT FROM AUTHOR]

This research investigates the utilization of machine learning methodologies for the purpose of forecasting the fluctuations in stock values inside the financial market. The application of a Random Forest classifier is utilized on a dataset including historical stock prices (namely, the KSE-100 Index) to generate predictions regarding the future movement of stocks, specifically whether they would experience an increase or decrease. The model is trained via a sliding window methodology and is assessed through the utilization of precision, recall, and F1-score criteria. The study furthermore incorporates the utilization of back testing and hyper-parameter tweaking techniques in order to enhance the performance of the model. The findings indicate that the model demonstrates a precision score of 58%, representing an enhancement compared to the previous score of 48%. Nevertheless, the model's total accuracy stands at a mere 58%, underscoring the need for future enhancements. The report additionally proposes potential avenues for future research, such as exploring alternate data sources, employing sentiment analysis techniques, and developing more advanced algorithms. The findings of this study hold significant significance for investors and financial institutions, as they highlight the potential of machine learning in facilitating informed investment decisions and improving financial forecasts and analysis. [ABSTRACT FROM AUTHOR]

Computed tomography (CT) films are used to construct cross-sectional pictures of a particular region of the body by using many x-ray readings that were obtained at various angles. There is a general agreement in the medical community at this time that chest CT is the most accurate approach for identifying COVID-19 disease. It was demonstrated that chest CT had a higher sensitivity than reverse transcription polymerase chain reaction (RTPCR) for the detection of COVID-19 illness. This article presents gray-level co-occurrence matrix (GLCM) texture feature extraction and convolutional neural network (CNN)-enabled optimized diagnostic model for COVID-19 detection. In this diagnostic model, CT scan images of patients are given as input. Firstly, GLCM algorithm is used to extract texture features from the CT scan images. This feature extraction helps in achieving higher classification accuracy. Classification is performed using CNN. It achieves higher accuracy than the k-nearest neighbors (KNN) algorithm and multilayer preceptor (MLP). The accuracy of GLCM based CNN is 99%, F1 score is 99% and the recall rate is also 98%. CNN has achieved better results than MLP and KNN algorithms for COVID-19 detection. [ABSTRACT FROM AUTHOR]

Models such as finite state automata are widely used to abstract the behavior of software systems by capturing the sequences of events observable during their execution. Nevertheless, models rarely exist in practice and, when they do, get easily outdated; moreover, manually building and maintaining models is costly and error-prone. As a result, a variety of model inference methods that automatically construct models from execution traces have been proposed to address these issues. However, performing a systematic and reliable accuracy assessment of inferred models remains an open problem. Even when a reference model is given, most existing model accuracy assessment methods may return misleading and biased results. This is mainly due to their reliance on statistical estimators over a finite number of randomly generated traces, introducing avoidable uncertainty about the estimation and being sensitive to the parameters of the random trace generative process. This article addresses this problem by developing a systematic approach based on analytic combinatorics that minimizes bias and uncertainty in model accuracy assessment by replacing statistical estimation with deterministic accuracy measures. We experimentally demonstrate the consistency and applicability of our approach by assessing the accuracy of models inferred by state-of-the-art inference tools against reference models from established specification mining benchmarks. [ABSTRACT FROM AUTHOR]

A neurological condition affecting both the brain and behavior is identified as autism spectrum disorder (ASD). Due to the absence of a reliable medical test for detecting autism, diagnoses rely on historical evidence. Essential in assessing the degree of autism are models like Convolutional Neural Networks (CNNs) and Random Forest (RF). In order to reduce the number of diagnostic tests required for autism diagnosis, this research work presents a new hybrid model that combines the strengths of RF and CNNs, providing healthcare solutions. It is noteworthy that this model properly predicted the severity of autism with an astounding accuracy rate of 99.15% when applied to historical data gathered from the Kaggle Repository. [ABSTRACT FROM AUTHOR]

The creation of frameworks for lowering natural hazards is a sustainable development goal specified by the United Nations. This study aims to predict drought occurrence in Tamil Nadu, India, using 26 years of data, with only 3 drought years. Since the drought-occurrence years are minimal, it is an imbalanced dataset, which gives a suboptimal classification performance. The accuracy metric has a tendency to produce misleadingly high results by focusing on the accuracy of forecasting the majority class while ignoring the minority class; hence, this work considers the metrics' precision and recall. A novel strategy uses attribute (or instance) weighting, which allots weights to attributes (or instances) based on their importance, to improve precision and recall. These weights are found using a bio-inspired optimization algorithm, by designing its fitness function to improve precision and recall of the minority (drought) class. Since increasing precision and recall is a tug-of-war, multi-objective optimization helps to identify optimal attribute (or instance) weight balancing precision and recall while maximizing both. The newly introduced Synergistic Optimization Algorithm (SOA) is utilized for multi-objective optimization in order to ascertain weights for attributes (or instances). In SOA, to solve multi-objective optimization, each objective's population was generated using three distinct algorithms, namely, the Genetic, Firefly, and Particle Swarm Optimization (PSO) algorithms. The experimental results demonstrated that the prediction performance for the minority drought class was superior when utilizing instance (or attribute) weighting compared to the approach not employing attribute/instance weighting. The Gradient Boosting classifier with an attribute-weighted dataset achieved precision and recall values of 0.92 and 0.79, whereas, with instance weighting, the values were 0.9 and 0.76 for the drought class. The attribute weighting shows that in addition to the default drought indices SPI and SPEI, pollution factors and mean sea level rise are valuable indicators in drought prediction. From instance weighting, it is inferred that the instances of the months of March, April, July, and August contribute most to drought prediction. [ABSTRACT FROM AUTHOR]

The global dissemination of SARS-CoV-2 resulted in the emergence of several variants, including Alpha, Alpha + E484K, Beta, and Omicron. Our research integrated the study of eukaryotic translation factors and fundamental components in general protein synthesis with the analysis of SARS-CoV-2 variants and vaccination status. Utilizing statistical methods, we successfully differentiated between variants in infected individuals and, to a lesser extent, between vaccinated and non-vaccinated infected individuals, relying on the expression profiles of translation factors. Additionally, our investigation identified common causal relationships among the translation factors, shedding light on the interplay between SARS-CoV-2 variants and the host's translation machinery. [ABSTRACT FROM AUTHOR]

Thunderstorms are natural disasters that impact people, animals, and the economy. Thunderstorms' detrimental repercussions can be avoided by identifying their occurrence in advance. The current work, in this respect, uses soft computing techniques such as K-Nearest Neighbour (KNN), Decision Tree (DT), Logistic Regression (LR), and Support Vector Machine (SVM) with various kernel functions to categorize the occurrence of thunderstorms over Ranchi, India. These techniques were trained and tested using two data sets: daily average and hourly meteorological datasets. The primary purpose of this study is to find which dataset-classifier combination is optimal for categorizing thunderstorm occurrence in Ranchi. No classifier was found to adequately classify either the Day Average Dataset or the Modified Day Average Dataset. On the other hand, the Hourly Dataset was found to be more balanced in terms of the number of thunderstorms that occurred than the Day Average and Modified Average datasets. The F-Score value of the incidence of thunderstorm incidents after using different classifiers was used to compare the outcomes of these datasets. The results reveal that using SVM with radial basis function. The Hourly Dataset is the best for thunderstorm day classification. For the overall and only incidence of thunderstorms classes, SVM-RBF gets 0.81 and 0.74 F-Scores, respectively. Other approaches, like grid search and Bagging, have been used to increase SVM-RBF performance. Grid search and Bagging are used on SVM-RBF to produce a hybrid Grid-Bag-SVM-RBF classifier with 82.04% accuracy and F-scores of 0.83 and 0.78 for overall and just thunderstorm occurrence, respectively. [ABSTRACT FROM AUTHOR]

Deep Learning is becoming an emerging field in the Internet of Things (IoT) due to its ability to provide a comprehensive approach to automatic feature extraction and predictive modeling for analysis and decision-making. This paper introduces an IoT-based Dance Movement Recognition Model based on a Deep Learning Framework. The framework consists of a convolutional neural network (CNN) with a data-centric architecture to identify dance movements from the acquired data gathered by an IoT device. The IoT device collects 3D motion data captured by three accelerometers. Feature extraction is then done with the CNN architecture, resulting in a flattened matrix representing the movement. Subsequently, a Multi-Layer Perception (MLP) is used to classify the movements. The proposed system is experimentally evaluated on a standardized dataset of 16 dance steps with three-speed levels. The results show that our model outperforms state-of-the-art approaches in accuracy, evaluation time, and classification accuracy. The proposed model reached 90.74% accuracy, 87.12% precision, 83.78% recall and 84.39% F1-Score. The proposed model can serve as a basis for a reliable and intuitive system that can be used to monitor patient's dance movements with accuracy. [ABSTRACT FROM AUTHOR]

The "Daijiworld News" forum, a well-known news website in coastal Karnataka, was the source of the comments for this paper's sentiment analysis study, which was done on about 15,000 reader comments. The comments were scraped using Beautiful Soup, a popular web scraping library and labelled as positive, negative, and neutral. Pre-processing of comments was made using techniques such as stop word removal, tokenization, stemming, lemmatization, and lowercase conversion. Logistic regression, support vector machine (SVM), naive Bayes, random forest, K-nearest neighbors (KNN), AdaBoost, gradient boosting and neural networks was used for classification. Performance metrics including accuracy, precision, recall, and F1 score were evaluated. Logistic regression achieved the highest precision (0.75), recall (0.74), accuracy (0.74), and F1 score (0.74), followed closely by the neural network classifier with a precision of 0.670, recall of 0.670, accuracy of 0.670, and F1 score of 0.669. The study demonstrates the effectiveness of logistic regression and neural networks in sentiment analysis of news forum comments, giving insightful information to grasp public opinion and improving user engagement. The findings contribute to the field of sentiment analysis, emphasising the significance of web scraping and pre-processing techniques in enhancing sentiment classification accuracy. The results serve as a reference for researchers and practitioners, assisting in the selection of appropriate classifiers for sentiment analysis in similar contexts. The study encourages further exploration of advanced techniques to enhance sentiment classification accuracy in regional news forums, paving the way for future research in sentiment analysis. [ABSTRACT FROM AUTHOR]

Data mining is one of the emerging technologies used in many applications such as Market analysis and Machine learning. Temporal data mining is used to get a clear knowledge about current trend and to predict the upcoming future. The rudimentary challenge in introducing a data mining procedure is, processing time and memory consumption are highly increasing while trying to improve the accuracy, precision or recall. As well as, while trying to reduce the processing time or memory consumption, accuracy, precision and recall values are reducing significantly. So, for improving the performance of the system and to preserve the memory and processing time, Three-Dimensional Fuzzy FP-Tree (TDFFPT) is proposed for Temporal data mining. Three functional modules namely, Three-Dimensional Temporal data FP-Tree (TTDFPT), Fuzzy Logic based Temporal Data Tree Analyzer (FTDTA) and Temporal Data Frequent Itemset Miner (TDFIM) are integrated in the proposed method. This algorithm scans the database and generates frequent patterns as per the business need. Every time a client purchases a new item, it gets stored in the recent database layer instead of rescanning the entire records which are placed in the old layer. The results obtained shows that the performance of the proposed model is more efficient than that of the existing algorithm in terms of overall accuracy, processing time, reduction in the memory utilization, and the number of databases scans. In addition, the proposed model also provides improved decision making and accurate pattern prediction in the time series data. [ABSTRACT FROM AUTHOR]

In today's world multiple type of datasets are available, they are mainly divided into two type namely classification and regression; based on the dataset type machine learning models are applied. There is a technique called bagging in which multiple models are trained simultaneously and produce results on testing dataset. These results are then clubbed to vote in the majority of the same outputs produced. This output is then considered as final output. The bagging technique used in this study is Random Forest (RF) algorithm, where the multiple models are replaced with decision trees. The RF algorithm requires multiple parameters to produce optimum output. These parameters are n_estimators, max_ samples, max_features etc. Though RF algorithm produces favourable results with default values of parameters, but to improve the efficiency of RF algorithm tuning of parameters is preferred. In this study, parameter n_estimators is tuned, on basis of the length of dataset to produce improved results as compared to the default parameters value. Further the proposed tuning method has been applied to RF algorithm and improvement of class prediction efficiency on different datasets is measured in terms of accuracy, precision, recall, F1-score. Also, implementation of ROC curves and auc is performed to depict the improvement of RF algorithm for datasets under consideration, for instance increase in auc values from 0.915 to 0.932 for Spine (2 Classes) dataset and 0.705 to 0.720 for Haberman's survival dataset. [ABSTRACT FROM AUTHOR]

This research investigates the utilization of machine learning methodologies for the purpose of forecasting the fluctuations in stock values inside the financial market. The application of a Random Forest classifier is utilized on a dataset including historical stock prices (namely, the KSE-100 Index) to generate predictions regarding the future movement of stocks, specifically whether they would experience an increase or decrease. The model is trained via a sliding window methodology and is assessed through the utilization of precision, recall, and F1-score criteria. The study furthermore incorporates the utilization of back testing and hyper-parameter tweaking techniques in order to enhance the performance of the model. The findings indicate that the model demonstrates a precision score of 58%, representing an enhancement compared to the previous score of 48%. Nevertheless, the model's total accuracy stands at a mere 58%, underscoring the need for future enhancements. The report additionally proposes potential avenues for future research, such as exploring alternate data sources, employing sentiment analysis techniques, and developing more advanced algorithms. The findings of this study hold significant significance for investors and financial institutions, as they highlight the potential of machine learning in facilitating informed investment decisions and improving financial forecasts and analysis.

The Legal Division of PT. ABC has implemented EDMS using the Integrated Legal Document Management Application, Centralized Legal Administration System (CLAS), to make the management of documents more accessible. The urgency is the system's accuracy in retrieving data or document input. The study employed a quantitative method with an experimental approach. Data collection techniques were observation, application search tests, documentation, and literature. Data analysis regarding the recall, precision, and F-measure calculation formulas will be compared with the standard information retrieval system effectiveness. The calculation results show that the average recall value for the search equals 1 or 100%. For the precision value that uses quotation marks, it is equal to 0.9713, while for searching without quotation marks, it is equal to 0.3920. From these results, the precision value is lower than the recall value. The precision value of 0.9713 is in the range of 0.68–1.00, which is placed as high precision, meaning that information retrieval is effective. The F-measure value is 0.98, close to 1, so the tracing system is sound. CLAS is quite effective in retrieving information according to user needs.

In recent years, the widespread adaptation of Unmanned Aerial Vehicles (UAVs), commonly known as drones, among the public has led to significant security concerns, prompting intense research into drones’ classification methodologies. The swift and accurate classification of drones poses a considerable challenge due to their diminutive size and rapid movements. To address this challenge, this paper introduces (i) a novel drone classification approach utilizing deep convolution and deep transfer learning techniques. The model incorporates bypass connections and Leaky ReLU activation functions to mitigate the ‘vanishing gradient problem’ and the ‘dying ReLU problem’, respectively, associated with deep networks and is trained on a diverse dataset. This study employs (ii) a custom dataset comprising both audio and visual data of drones as well as analogous objects like an airplane, birds, a helicopter, etc., to enhance classification accuracy. The integration of audio–visual information facilitates more precise drone classification. Furthermore, (iii) a new Finite Impulse Response (FIR) low-pass filter is proposed to convert audio signals into spectrogram images, reducing susceptibility to noise and interference. The proposed model signifies a transformative advancement in convolutional neural networks’ design, illustrating the compatibility of efficacy and efficiency without compromising on complexity and learnable properties. A notable performance was demonstrated by the proposed model, with an accuracy of 100% achieved on the test images using only four million learnable parameters. In contrast, the Resnet50 and Inception-V3 models exhibit 90% accuracy each on the same test set, despite the employment of 23.50 million and 21.80 million learnable parameters, respectively.

In recent years, deep convolutional networks (DCNN) have gained popularity for different classification (or recognition) tasks. In this paper, three well known DCNN structures were used, i.e., AlexNet, SqueezeNet and GoogLeNet, and their classification performances in recognizing handwritten Bangla isolated characters were compared. These networks have simpler structures compared to the recent DCNNs. Experiments on a standard Bangla database revealed that the overall performance of GoogLeNet is slightly better than the other two networks. Further analysis using saliency maps of the test samples revealed the important features that are learned by the networks for classifying characters. This information led us to understand why classification of some samples fail and how to rectify these. [ABSTRACT FROM AUTHOR]

Prompt diagnostics and appropriate cancer therapy necessitate the use of gene expression databases. The integration of analytical methods can enhance detection precision by capturing intricate patterns and subtle connections in the data. This study proposes a diagnostic-integrated approach combining Empirical Bayes Harmonization (EBS), Jensen–Shannon Divergence (JSD), deep learning, and contour mathematics for cancer detection using gene expression data. EBS preprocesses the gene expression data, while JSD measures the distributional differences between cancerous and non-cancerous samples, providing invaluable insights into gene expression patterns. Deep learning (DL) models are employed for automatic deep feature extraction and to discern complex patterns from the data. Contour mathematics is applied to visualize decision boundaries and regions in the high-dimensional feature space. JSD imparts significant information to the deep learning model, directing it to concentrate on pertinent features associated with cancerous samples. Contour visualization elucidates the model's decision-making process, bolstering interpretability. The amalgamation of JSD, deep learning, and contour mathematics in gene expression dataset analysis diagnostics presents a promising pathway for precise cancer detection. This method taps into the prowess of deep learning for feature extraction while employing JSD to pinpoint distributional differences and contour mathematics for visual elucidation. The outcomes underscore its potential as a formidable instrument for cancer detection, furnishing crucial insights for timely diagnostics and tailor-made treatment strategies. [ABSTRACT FROM AUTHOR]

In modern medicine, medical tests are used for various purposes including diagnosis, disease screening, prognosis, and risk prediction. To quantify the performance of the binary medical test, we often use sensitivity, specificity, and negative and positive predictive values as measures. Additionally, the F1$$ {F}_1 $$‐score, which is defined as the harmonic mean of precision (positive predictive value) and recall (sensitivity), has come to be used in the medical field due to its favorable characteristics. The F1$$ {F}_1 $$‐score has been extended for multi‐class classification, and two types of F1$$ {F}_1 $$‐scores have been proposed for multi‐class classification: a micro‐averaged F1$$ {F}_1 $$‐score and a macro‐averaged F1$$ {F}_1 $$‐score. The micro‐averaged F1$$ {F}_1 $$‐score pools per‐sample classifications across classes and then calculates the overall F1$$ {F}_1 $$‐score, whereas the macro‐averaged F1$$ {F}_1 $$‐score computes an arithmetic mean of the F1$$ {F}_1 $$‐scores for each class. Additionally, Sokolova and Lapalme1$$ {}^1 $$ gave an alternative definition of the macro‐averaged F1$$ {F}_1 $$‐score as the harmonic mean of the arithmetic means of the precision and recall over classes. Although some statistical methods of inference for binary and multi‐class F1$$ {F}_1 $$‐scores have been proposed, the methodology development of hypothesis testing procedure for them has not been fully progressing yet. Therefore, we aim to develop hypothesis testing procedure for comparing two F1$$ {F}_1 $$‐scores in paired study design based on the large sample multivariate central limit theorem. [ABSTRACT FROM AUTHOR]

The glm R package is commonly used for generalized linear modeling. In this paper, we evaluate the ability of the glm package to predict binomial outcomes using logistic regression. We use single-cell RNA-sequencing datasets, after a series of normalization, to fit data into glm models repeatedly using 10-fold cross-validation over 100 iterations. Our evaluation criteria are glm's Precision, Recall, F1-Score, Area Under the Curve (AUC), and Runtime. Scores for each evaluation category are collected, and their medians are calculated. Our findings show that glm has fluctuating Precision and F1-Scores. In terms of Recall, glm has shown more stable performance, while in the AUC category, glm shows remarkable performance. Also, the Runtime of glm is consistent. Our findings also show that there are no correlations between the size of fitted data and glm's Precision, Recall, F1-Score, and AUC, except for Runtime. [ABSTRACT FROM AUTHOR]

Credit card Fraud detection is a critical task in various industries, including finance and e-commerce, where identifying fraudulent activities can help prevent financial losses and protect users. It begins by combining two datasets containing fraudulent and non-fraudulent transactions to create a comprehensive dataset for analysis. Data is preprocessed by removing unnecessary features, calculating distance metrics, and generating new variables to capture temporal patterns and transaction history. Multicollinearity issues are addressed through feature selection. Improved Random Forest (RF) algorithm is used to improve fraud detection. The experimental results indicate that the improved Random Forest algorithm achieves commendable accuracy in fraud detection. The proposed model achieves 99.87% training accuracy and 99.41% testing accuracy. The Model's performance is evaluated by measuring precision, recall, F1-score and support. Our research emphasizes the importance of considering improved algorithms to achieve better results. The findings provide valuable insights for organizations aiming to enhance their fraud detection capabilities and make informed decisions to protect their systems and users. [ABSTRACT FROM AUTHOR]

Copyright of Journal of the College Of Basic Education is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper examines the use of deep recurrent neural networks to classify traffic patterns in smart cities. We propose a novel approach to traffic pattern classification based on deep recurrent neural networks, which can effectively capture traffic patterns' dynamic and sequential features. The proposed model combines convolutional and recurrent layers to extract features from traffic pattern data and a SoftMax layer to classify traffic patterns. Experimental results show that the proposed model outperforms existing methods regarding accuracy, precision, recall, and F1 score. Furthermore, we provide an in-depth analysis of the results and discuss the implications of the proposed model for smart cities. The results show that the proposed model can accurately classify traffic patterns in smart cities with a precision of as high as 95%. The proposed model is evaluated on a real-world traffic pattern dataset and compared with existing classification methods. [ABSTRACT FROM AUTHOR]

Many social media (SM) platforms have emerged as a result of the online social network's (OSN) rapid expansion. SM has become important in day-to-day life, and spammers have turned their attention to SM. Spam detection (SD) is done in two different ways, such as machine learning (ML) and expert-based detection. The expert-based detection technique's accuracy depends on expert knowledge, and it takes huge time to detect the spams. Thus, ML-based spam detection is preferred in OSN. Spam identification on social networks is a difficult operation involving a variety of factors, and spam and ham have resulted in an imbalanced data distribution, which gives flexibility to spammers for corrupting our devices. SD based on ML algorithms like logistic regression (LR), K-nearest neighbor (KNN), decision trees (DT), random forest (RF), support vector machine (SVM) and eXtreme gradient boosting (XGB), voting classifier (VC) and extra tree classifier (ETC) are used to design the address balance and to attain high assessment accuracy in an imbalanced datasets. ETC method minimizes the bias through the original sampling process. For reducing processing complexity, the ETC method uses a smaller size constant factor instead of a larger one. Thus, the ETC technique produces better data splitting than DT and RF techniques. Text is vectorized by vectorizers, and all the relative results are stored in it. The VC is an ensemble method that integrates predictions form several methods to forecast an output class depending on which predictions have the highest probability. The multi-class results are aggregated and forecast for the majority voted class. The experimental result shows that, as compared to KN, NB, ETC, RF, SVC, LR, XGB and DT, the proposed VC provides a higher classification accuracy rate of 97.96%, 97.56% of precision, 89.95% of recall and 91.96% of F1-measures. Similarly, ETC provides 97.77% accuracy, 98.31% of precision, 84.78% of recall and 91.05% of F1-measures. Compared to conventional ML algorithms, VC and ETC provide higher accuracy, precision, recall and F1-measures. Thus, ETC and VC are preferable for spam detection. The website has been designed to detect messages as spam or not. [ABSTRACT FROM AUTHOR]

Fingerprints are widely used as effective personal authentication systems, because they constitute unique, robust, and risk-free evidence. Fingerprinting techniques refer to biometric procedures used for identifying individuals based on their physical characteristics. A fingerprint image contains ridges and valleys forming a directionally-oriented pattern. The robustness of the fingerprint authentication technique determines the quality of the fingerprint image. This study proposed an intelligent 12-layered Convolutional Neural Network (CNN) model using Deep learning (DL) for gender determination based on fingerprints. Further, the study compared the performance of this model to existing state-of-the-art methods. The primary goal of this study was to reduce the number of comparisons within a large database obtained from automatic fingerprint recognition systems. The classification process was found to be swifter and more accurate when analysis of the DL algorithm was performed. With reference to the criteria of precision, recall, and accuracy evaluation during classification, this proposed 12-layered CNN model outperformed the Residual Neural Network with 50 Layers (ResNet-50) and Dense Convolutional Network with 201 Layers (DenseNet-201) models. The accuracies obtained were 97.0%, 95.8%, 98.0%, and 96.8% for female-left, female-right, male-left, and male-right classes respectively, while achieving an overall accuracy of 94.0%. [ABSTRACT FROM AUTHOR]

Machine learning (ML) is a logical investigation of various algorithms and factual models that PCs utilize to carry out particular operations that are not clearly programmed. This paper aims to statistically analyze different machine learning algorithms, and compare and contrast their performance for credit card fraud detection. Algorithms used are Artificial Neural Networks(ANN), Sample Vector Machine (SVM), and Kth Nearest Neighbour (KNN), Decision Tree, Logistic Regression and Random Forest. All these above mentioned algorithms are compared on basis of performance measures. It is deduced that the random forest algorithm is the best algorithm. [ABSTRACT FROM AUTHOR]

Recently, Panama wilt disease that attacks banana leaves has caused enormous economic losses to farmers. Early detection of this disease and necessary preventive measures can avoid economic damage. This paper proposes an improved method to predict Panama wilt disease based on symptoms using an agro deep learning algorithm. The proposed deep learning model for detecting Panama wilts disease is essential because it can help accurately identify infected plants in a timely manner. It can be instrumental in large-scale agricultural operations where Panama wilts disease could spread quickly and cause significant crop loss. Additionally, deep learning models can be used to monitor the effectiveness of treatments and help farmers make informed decisions about how to manage the disease best. This method is designed to predict the severity of the disease and its consequences based on the arrangement of color and shape changes in banana leaves. The present proposed method is compared with its previous methods, and it achieved 91.56% accuracy, 91.61% precision, 88.56% recall and 81.56% F1-score.

Human health issues require estimation of heart rhythm anomalies, brain wave pattern abnormalities, blood parameter outliers, social media analysis, and more. Researchers propose many deep learning models to estimate these issues, and each uses neural optimizations to classify input parameters into disease types. But most of the existing models are either highly complex, or are not capable of capturing multiple body parameters, in order to perform comprehensive disease diagnosis. To overcome the challenges of feature representation and classification, this text proposes design of a high-density feature representation model for multidomain analysis of human health issues. The proposed model collects patient-specific datasets from multidomain sources like blood reports, electrocardiograms (ECGs), electroencephalograms (EEGs), social media posts, and physiological parameters to generate comprehensive health feature vectors. Fourier, Wavelet, Convolutional, and Gabor components transform vectors into multimodal feature sets. Representing the input vector into these components improves feature density, which helps identify multiple disease types. Bee Colony Optimization Models estimate high-variance feature sets using these features. A 1D CNN Model classifies these sets to help identify disease classes. The model performed well in accuracy, precision, recall, and AUC (area under the curve) tests for heart, brain, and psychological issues, making it suitable for clinical use. Compared to standard disease classification models, it improved accuracy, precision, recall, and fMeasure by 3.2%, 3.5%, 2.9%, and 2.5%, making it useful for real-time deployments. [ABSTRACT FROM AUTHOR]

There are multiple distinct sources through which numerous news contents that occur in digital medium tend to converge. Web contents constitute massive number of features. Complete coverage of all kinds of news is absolutely vital to retain customer confidence and to have a competitive edge over other news agencies. Aggregating such massive news content from different heterogeneous sources requires an integration of convergent computing. Classification of these online news is a challenging task in the age of Internet where news keeps flowing from several heterogeneous sources. Due to constant rise in manipulation of web contents, accurate classification of digital news is the need of the hour. Precise detection of specific news into their respective class is a major challenge in recent times. In this scenario, the need of an automated predictive-based approach can be of great use in effective organization and classification of news in a pool of web portals. This research study comprises the application of Bernoulli model to determine the effectiveness of multi-class digital news categorization that arrive in real time. The system model presented in this analysis was evaluated using python, and the result was demonstrated using six distinct classes of news with a 6000 feature size dataset from TagMyNews dataset. The classification accuracy using the Bernoulli model was computed to be 98.4%, while the evaluated precision metric was 92.7%, and recall value was 90.6%. The F-Score metric generated an optimum value of 91.4%. The execution time for Bernoulli model was only 12 s. The computed result using Bernoulli model was compared with some other related renowned existing works and the results generated by Bernoulli model gave optimum performance and the news classification efficiency is highly enhanced. [ABSTRACT FROM AUTHOR]

Recently, Panama wilt disease that attacks banana leaves has caused enormous economic losses to farmers. Early detection of this disease and necessary preventive measures can avoid economic damage. This paper proposes an improved method to predict Panama wilt disease based on symptoms using an agro deep learning algorithm. The proposed deep learning model for detecting Panama wilts disease is essential because it can help accurately identify infected plants in a timely manner. It can be instrumental in large-scale agricultural operations where Panama wilts disease could spread quickly and cause significant crop loss. Additionally, deep learning models can be used to monitor the effectiveness of treatments and help farmers make informed decisions about how to manage the disease best. This method is designed to predict the severity of the disease and its consequences based on the arrangement of color and shape changes in banana leaves. The present proposed method is compared with its previous methods, and it achieved 91.56% accuracy, 91.61% precision, 88.56% recall and 81.56% F1-score. [ABSTRACT FROM AUTHOR]

This research explores neural network models' performance and adaptability in the context of the colorectal histology dataset as it pertains to the categorization of textures. Inception, VGG19, and MobileNet, together with their federated variations, are among the models being examined. The study includes a detailed evaluation, parameter analysis, and training information. VGG19 stands out as a particularly noteworthy high performance, with remarkable accuracy, precision, and recall. Due to its lightweight design, MobileNet performs less well, but its potential is enhanced by the addition of federated learning. The accuracy and precision of federated versions of Inception, VGG19, MobileNet, and a Lightweight MobileNet model are competitive, with FL-Lightweight MobileNet achieving outstanding results. The work has important ramifications for the field of medical image analysis since it shows how federated learning may balance the need for data confidentiality and privacy with model performance. This study marks a turning point in the development of medical imaging by opening the door to in-depth investigation into the complex interactions across federated paradigms. Furthermore, these results provide a compelling story in the wider discussion of how cutting-edge technologies and the pressing needs of contemporary healthcare might work together. [ABSTRACT FROM AUTHOR]

This paper uses Deep Learning to classify if a display panel with defects in the manufacturing line can be repaired. Both tabular data and images are fused together to make predictions, with separate feature extraction undertaken for each of the modalities. The model's predictions achieve high Average Precision as well as robust Precision values in the high Recall regions, which makes it practical for deployment. We also demonstrate superior results with multi‐modal data compared to only tabular data. [ABSTRACT FROM AUTHOR]

An information retrieval system (IRS) is used to retrieve documents based on an information need. The IRS makes relevance judgements by attempting to match a query to a document. As IRS capabilities are indexing design dependent, the hybrid indexing method (IRS-H) is introduced. The objectives of this article are to examine IRS-H (as an alternative indexing method that performs exact phrase matching) and IRS-I, regarding retrieval usefulness, identification of relevant documents, and the quality of rejecting irrelevant documents by conducting three experiments and by analysing the related data. Three experiments took place where a collection of 100 research documents and 75 queries were presented to: (1) five participants answering a questionnaire, (2) IRS-I to generate data and (3) IRS-H to generate data. The data generated during the experiments were statistically analysed using the performance measurements of Precision, Recall and Specificity, and one-tailed Student's t -tests. The results reveal that IRS-H (1) increased the retrieval of relevant documents, (2) reduced incorrect identification of relevant documents and (3) increased the quality of rejecting irrelevant documents. The research found that the hybrid indexing method, using a small closed document collection of a hundred documents, produced the required outputs and that it may be used as an alternative IRS indexing method. [ABSTRACT FROM AUTHOR]

An Artificial Neuron Network (ANN) is a computational model that mimics the way neurons in the human brain work. In agriculture, ANN can be used for various tasks, such as disease and insect detection, crop yield forecasting, soil fertility management, seed categorization, and quality evaluation. Marketing and development of sustainable agricultural systems rely on accurate seed classification. One major goal of this research is to create an ANN model that can reliably classify different types of dried bean seeds based on their shared characteristics. Data from the UC Irvine machine learning repository was used for this study. With the use of principal component analysis (PCA), the most informative characteristics of a dataset are isolated. Using the proposed approach, we intend to categorise seven distinct types of dry bean seeds. The suggested ANN model is then trained using the optimally tuned hyperparameters. The ANN model's effectiveness is measured by its confusion matrix, accuracy, precision, Recall, and F1-Score. After extensive testing, it was determined that the ANN with PCA model had the highest classification accuracy for dried bean seeds (94%) and the highest F1-score (95%). [ABSTRACT FROM AUTHOR]

Citizen science data are increasingly used for biodiversity monitoring. However, concerns are often raised over the accuracy of species identifications in citizen science databases, as data are collected mostly by non‐professionals. Misidentifications can simultaneously generate two error types: false positives (erroneous reports of a species) and false negatives (lack of reports of the misidentified species). Large‐scale assessments of identification errors should provide insights into the strengths and weaknesses of citizen science data. Here we show that citizen science photographic data for birds are trustworthy overall, although problems arise in hard‐to‐identify bird groups. We reviewed over 104 000 images of 377 passerine species from the southern Neotropics (Argentina) stored in eBird – a large citizen science platform – and quantified erroneous reports to calculate precision and recall metrics as measures for data accuracy. Precision increases with fewer false positives and recall increases with fewer false negatives; hence, high values of precision and recall will mirror a higher data accuracy. We found that 97% of the photos of all species were correctly identified. Most species (77%; n = 291) showed high accuracy in their identifications (precision and recall > 95%), with 122 species showing no errors. A few hard‐to‐identify species (10%; n = 40) showed low levels of data quality (63–90% precision or recall). Similarly, few species (12%; n = 46) exhibited intermediate precision or recall scores (90–95%). Further, we uncovered the existence of a complex network of cross‐identifications composed of 272 species, with a predominance of tyrant flycatchers and ovenbirds, reflecting the strong traffic of errors that occurs within these families. To our knowledge, our study provides the first large‐scale quantification of identification errors in photos submitted by citizen science contributors. We underscore the relevance of performing such assessments to understand how identification errors are distributed across a database before analysing data, and provide tools for citizen science stakeholders to direct more specific efforts toward species that need an improvement in data quality. [ABSTRACT FROM AUTHOR]

• Soft variants of precision and recall introduced. • Set notation with soft cardinality is applied. • Application 1: evaluation of keyword extraction. • Application 2: evaluation of segmentation result. Precision and recall are classical measures used in machine learning. However, they are based on exact matching. This results in binary classification where the predicted item is either a true or false positive despite inexact matching is often preferred in pattern recognition. To address this problem, we introduce soft variants of precision and recall based on application-specific similarity measure. 2022 Elsevier Ltd. All rights reserved. [Display omitted] [ABSTRACT FROM AUTHOR]

Hate speech specially racism, gender and religion discrimination, defaming comments are becoming one of the biggest problems in Twitter these days, that are making people to switch to other social media. Its effect is long-standing and unpreventable. To stop hateful activities from happening, Machine Learning approaches are needed to be applied. This research article focuses on the performance analysis and effectiveness of Logistic Regression, Gaussian Naive Bayes, K-Nearest Neighbor, Decision Tree, Random Forest and Support Vector Machine on detection of hate speech from Twitter. SVM, Decision Tree and Random Forest outperformed all the other models, achieving state-of-art 95.5%, 96.2% and 98.2% accuracy respectively on comments gather over a stretch. [ABSTRACT FROM AUTHOR]

The Artificial Intelligence Recommender System has emerged as a significant research interest. It aims at helping users find things online by offering recommendations that closely fit their interests. Recommenders for research papers have appeared over the last decade to make it easier to find publications associated with the field of researchers' interests. However, due to several issues, such as copyright constraints, these methodologies assume that the recommended articles' contents are entirely openly accessible, which is not necessarily the case. This work demonstrates an efficient model, known as RPRSCA: Research Paper Recommendation System Using Effective Collaborative Approach, to address these uncertain systems for the recommendation of quality research papers. We make use of contextual metadata that are publicly available to gather hidden relationships between research papers in order to personalize recommendations by exploiting the advantages of collaborative filtering. The proposed system, RPRSCA, is unique and gives personalized recommendations irrespective of the research subject. Thus, a novel collaborative approach is proposed that provides better performance. Using a publicly available dataset, we found that our proposed method outperformed previous uncertain methods in terms of overall performance and the capacity to return relevant, valuable, and quality publications at the top of the recommendation list. Furthermore, our proposed strategy includes personalized suggestions and customer expertise, in addition to addressing multi-disciplinary concerns. [ABSTRACT FROM AUTHOR]

The search strategy of a literature review is of utmost importance as it impacts the validity of its findings. In order to build the best query to guide the literature search on clinical decision support systems applied to nursing clinical practice, we developed an iterative process capitalizing on previous systematic reviews published on similar topics. Three reviews were analyzed relatively to their detection performance. Errors in the choice of keywords and terms used in title and abstract (missing MeSH terms, failure to use common terms), may make relevant articles invisible. [ABSTRACT FROM AUTHOR]

This paper discusses the methods the course teacher used to teach the Information Processing and Retrieval course [Course Code: 19LISC302]. A few aspects, including Chain Indexing, KWIC, Boolean operators, queries, logical relations, and recall & precision, have been highlighted here for illustration. The course teacher was able to improve the students' knowledge of the mentioned areas by using teaching methods based on the Revised Bloom's Taxonomy. The methods also made it possible to follow the students' progress. Boolean operators, queries, logical relations, and recall & precision exercises are taken into consideration for the discussions here, but chain indexing and KWIC related classroom practice formats are only supplied at Annexure-i. The course teacher created the application that is connected to logical relations (Truth Table), and the students have used it in class to practice. Various multifaceted key phrases, a few queries, the Boolean operators AND, OR, and NOT, and the Truth Table are all included in the aforementioned programme. For students to successfully obtain pertinent data from any database, they must have a solid understanding of logical ideas. Meaningful results won't be produced by executing the queries and operators automatically or blindly. Additionally, it could need extra time from information seekers. Boolean operators are used in information retrieval systems to evaluate queries. The Boolean operators are typically linked to the classes in the queries. The evaluation for each class is either True or False. To effectively use the operators in search queries and extract the necessary data, learners need be familiar with the Truth Table-related concepts. In addition, for the aforementioned subjects other than Chain Indexing and KWIC, the Revised Bloom's Taxonomy based teaching and the students' evaluation techniques have also been presented here. Wherever needed, enough screenshots of the aforementioned programme are produced. Students used a learning approach based on Revised Bloom's Taxonomy to study the concepts linked to the aforementioned themes, and they have been duly documented below. With the use of the methodologies utilised in this study, the teacher was able to glean the essential information necessary for determining the pupils' degrees of learning ability and applying that information to the necessary charts. The charts show the students' competence levels according to themes, making it simple to see the students' skill status. Realizing their ability levels is aided by each level wise clearance and their overall clearance status. Chain indexing, KWIC, logical relations, queries with Boolean operators, database sample records format, RBT levels-based evaluation format, recall, and precision are the examples of exercise forms shown in Annexure-i. Further, overall progress charts, each level wise progress charts and Student performance evaluation report are given at Annexure-ii, Annexure-iii and Annexure-iv respectively. [ABSTRACT FROM AUTHOR]

Aim/Purpose The amount of information published has increased dramatically due to the information explosion. The issue of managing information as it expands at this rate lies in the development of information extraction technology that can turn unstructured data into organized data that is understandable and controllable by computers Background The primary goal of named entity recognition (NER) is to extract named entities from amorphous materials and place them in pre-defined semantic classes. Methodology In our work, we analyze various machine learning algorithms and implement KNN which has been widely used in machine learning and remains one of the most popular methods to classify data. Contribution To the researchers' best knowledge, no published study has presented Named entity recognition for the Kikuyu language using a machine learning algorithm. This research will fill this gap by recognizing entities in the Kikuyu language. Findings An evaluation was done by testing precision, recall, and F-measure. The experiment results demonstrate that using K-NN is effective in classification performance. Recommendations for Researchers With enough training data, researchers could perform an experiment and check the learning curve with accuracy that compares to state of art NER. Impact on Society NER helps recognize important textual components including names of individuals, places, and monetary value among others. When dealing with enormous datasets, it is critical to sort unstructured data and to find vital information by identifying the major entities in a text. Future Research Future studies may be done using unsupervised and semi-supervised learning algorithms for other resource-scarce languages. [ABSTRACT FROM AUTHOR]

Clay, earthen elements, powders, and water mixtures are typically manipulated into desired shapes to create ceramics. The ceramic is then dispersed in a blast furnace, which is a high-temperature oven, after it has been molded. Varnishes are paint-like materials that are used to decorate ceramics and are resistant to water. Manually identifying ceramic samples can lead to the discovery of flaws. The chemical composition of the finished ceramic tiles is not visible. Exact identification of ceramic samples is still a difficult task for the user, as it necessitates more hands-on experience. With this overview, this paper focus on designing an effective workflow for classifying the ceramic samples based on chemical composition. The ceramic chemical sample dataset from KAGGLE with the dataset size of 88 with 19 features having 5 classes of ceramic as 0-"FLQ Ceramic", 1- "DYBS Ceramic", 2-"DYNS Ceramic", 3- "DYY Ceramic", 4- "DYMQC Ceramic". The data is preprocessed and normalized for splitting the training and testing dataset. The normalized dataset is fitted to Anova test analysis to extract the significant features. The insignificant features from Anova test is deleted from the original database dataset and anova normalized dataset is fitted to Exhaustive feature selection using KNN, Naive Bayes, Logistic regression, Decision Tree and Random Forest classifier. The exhaustive feature selected dataset is applied to the above-mentioned classifier algorithms to examine the efficiency with the presence and absence of feature scaling. The exhaustive feature selected dataset is again applied to random oversampling in order to improve the classifier performance. The random oversampled exhaustive feature selected dataset is applied to the above mentioned classifier algorithms to compare the performance metrics like precision, accuracy, fscore, recall and run time. Experimental results shows that the decision tree exhibits 49% accuracy with exhaustive feature selected dataset. The same decision tree classifier shows 100% accuracy after applying random oversampling with exhaustive feature selected dataset. [ABSTRACT FROM AUTHOR]