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 Machine vision faces significant challenges when applied to text recognition on cardboard packaging particularly due to multiple printing methods, irregular character shapes, and curved packaging surfaces. Methods This research introduces a novel deep learning application for recognizing binarized expiration date and batch code characters printed using multiple printing methods. The method, based on Region-based Convolutional Neural Networks (R-CNN), enables character recognition directly from in the images without the need for extracting handcrafted features. In detail, this approach performs character recognition by using the whole image as input, extracting and learning salient character features directly from the packaging surface images. Results The R-CNN model, with a precision of 91.1% and an F1 score of 80.9%, effectively recognizes manufacturing markings on pharmaceutical packages, with inconsistencies in the characters’ shapes. In a comparative experiment using the same dataset of images, the R-CNN model significantly outperformed Tesseract OCR, achieving much higher precision, recall, and F1 scores. Conclusions The results of this study reveal that the deep learning method outperforms the well-established optical character recognition method in recognizing text characters printed with different printing methods. Presented in this study, the deep learning method recognizes text characters with high precision. It is also suitable for recognizing text printed on curved surfaces, provided proper preprocessing is applied. The problem investigated in the study differs from previous research in the field, focusing on the recognition of texts printed with different printing methods. The research thus fills a gap in text recognition that existed in the research of the field. Furthermore, the study presents new ideas that will be utilized in our future research.

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]

Detection of heart diseases (HD) at an early stage diminishes the mortality rate. However, handling huge data is cumbersome for physicians. Hence, there is a need for a tool regarding the automation and processing of large data to help in making precise decisions. The proposed methodology aims to predict cases of HD or cardiovascular diseases (CD) well in advance based on the features of the patient. In the proposed methodology, the Cleveland Dataset of HD collected from University of California, Irvine (UCI) repository is evaluated. The various phases in the proposed methodology include, insight about the data, analyzing the data, feature engineering and finally building the model. The K-nearest neighbor (KNN), support vector machine (SVM), artificial neural network (ANN), classifier and convolutional neural network (CNN) are used to predict the HD and are evaluated on the dataset. The metrics considered are classification accuracy (CA), recall (r) and precision (p). The resulted CA, ‘r’ and ‘p’ for KNN-based approach are 66.7%, 91.7% and 88.8%, respectively. The SVM-based approach with ‘linear’ kernel achieved CA, ‘r’ and ‘p’ are 74.2%, 85.0% and 74.0%, respectively. The ANN-based approach resulted in 70.08%, 77.0% and 84.2% of CA, ‘p’ and ‘r’, respectively. Finally, the CNN-based prediction achieved CA, ‘p’ and ‘r’ are 83.61%, 76.0% and 97.0%, respectively. The experimental study concludes that the CNN-based prediction model outperformed the KNN, SVM and ANN-based prediction approaches regarding the prediction accuracy. An optimization algorithm can be incorporated into the model in future.

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]