Tuning Technique Research Articles

Adaptable, wearable, and stretchable coils: A review.

Over the last four decades, there have been various evolutions in the design and development of coils, from volume coils to the recent introduction of wireless receive arrays. A recent aim has been to develop coils that can closely conform to the anatomy of interest to increase the acquired signal. This goal has given rise to designs ranging from adaptable transmit coils to on-body stretchable receive arrays made using fabric or elastomer substrates. This review covers the design, fabrication details, experimental setup, and MRI results of adaptable, wearable, and stretchable MRI coils. The active and passive automatic tuning and matching strategies are examined with respect to mitigating signal-to-noise ratio reduction when the coil form is altered. A brief discussion of wireless MRI coils, which provide a solution to overcome the cabling issues associated with MRI coil development, is also included. The adaptable, wearable, and stretchable coils and various coil tuning techniques represent innovative radiofrequency coil solutions that pave the way for next-generation MRI hardware development.

All-fiber chirp tuning of ultrashort pulses via long chirped fiber Bragg grating pair

Chirp tuning of ultrashort pulses is crucial for nonlinear fiber amplification and nonlinear dynamics investigations. Here we demonstrate all-fiber chirp tuning via a chirped fiber Bragg grating (CFBG) pair. Two identically long CFBGs were placed reversely to cancel out most of their huge dispersion (∼40 ps/nm or ∼22.4 ps2 @1030 nm), while the controllable temperature gradient along them could be used for precise chirp tuning with a tuning range of ∼ps2, verified by dispersion measurement and ultrashort pulse broadening. This relatively large chirp tuning could be used in prechirp management in nonlinear fiber amplifiers, exemplified by the optical spectrum tailoring therein. In addition, we also show this precise chirp tuning capability could be very helpful for pulse temporal quality diagnosis, which is indispensable for seed pulse optimization. We believe this all-fiber chirp tuning technique would find wide applications in nonlinear amplification and ultrafast nonlinear dynamics investigations.

Development and validation of an explainable machine learning model for mortality prediction among patients with infected pancreatic necrosis.

Infected pancreatic necrosis (IPN) represents a severe complication of acute pancreatitis, commonly linked with mortality rates ranging from 15% to 35%. However, the present mortality prediction tools for IPN are limited and lack sufficient sensitivity and specificity. This study aims to develop and validate an explainable machine learning (ML) model for death prediction among patients with IPN. We performed a prospective cohort study of 344 patients with IPN consecutively enrolled from a large Chinese tertiary hospital from January 2011 to January 2023. Ten ML models were developed to predict 90-day mortality in these patients. A benchmarking test, involving nested resampling, automatic hyperparameter tuning and random search techniques, was conducted to select the ML model. Sequential forward selection method was employed to select the optimal feature subset from 31 candidate subsets to simplify the model and maximize predictive performance. The final model was internally validated with the 1000 bootstrap method and externally validated using an independent cohort of 132 patients with IPN retrospectively collected from another Chinese tertiary hospital from January 2018 to January 2023. The SHapley Additive exPlanations (SHAP) method was employed to interpret the model in terms of features importance and features effect. The final model constructed with optimal feature subset was deployed as an interactive web-based Shiny app. Random survival forest (RSF) model showed the best predictive performance than other 9ML models (internal validation, C-index=0.863 [95% CI: 0.854-0.875]; external validation, C-index=0.857 [95% CI: 0.850-0.865]). Multiple organ failure, Acute Physiology and Chronic Health Examination II (APACHE II) score ≥20, duration of organ failure ≥21 days, bloodstream infection, time from onset to first intervention <30 days, Bedside Index of Severity in Acute Pancreatitis score ≥3, critical acute pancreatitis, age ≥ 50 years, and hemorrhage were 9 most important features associated with mortality. Furthermore, SHAP algorithm revealed insightful nonlinear interactive associations between important predictors and mortality, identifying 9 features pairs with high interaction SHAP value and clinical significance. Two interactive web-based Shiny apps were developed to enhance clinical practicability: https://rsfmodels.shinyapps.io/IPN_app/ for cases where the APACHE II score was available and https://rsfmodels.shinyapps.io/IPNeasy/ for cases where it was not. An explainable ML model for death prediction among IPN patients was feasible and effective, suggesting its superior potential in guiding clinical management and improving patient outcomes. Two publicly accessible web tools generated for the optimized model facilitated its utility in clinical settings. The Natural Science Foundation of Hunan Province (2023JJ30885), Postdoctoral Fellowship Program of CPSF (GZB20230872), The Youth Science Foundation of Xiangya Hospital (2023Q13), The Project Program of National Clinical Research Center for Geriatric Disorders of Xiangya Hospital (2021LNJJ19).

A constrained optimisation framework for parameter identification of the SIRD model.

We consider a numerical framework tailored to identifying optimal parameters in the context of modelling disease propagation. Our focus is on understanding the behaviour of optimisation algorithms for such problems, where the dynamics are described by a system of ordinary differential equations associated with the epidemiological SIRD model. Applying an optimise-then-discretise approach, we examine properties of the solution operator and determine existence of optimal parameters for the problem considered. Further, first-order optimality conditions are derived, the solution of which provides a certificate of goodness of fit, which is not always guaranteed with parameter tuning techniques. We then propose strategies for the numerical solution of such problems, based on projected gradient descent, Fast Iterative Shrinkage-Thresholding Algorithm (FISTA), nonmonotone Accelerated Proximal Gradient (nmAPG), and limited memory BFGS trust region approaches. We carry out a thorough computational study for a range of problems of interest, determining the relative performance of these numerical methods. Our results provide insights into the effectiveness of these strategies, contributing to ongoing research into optimising parameters for accurate and reliable disease spread modelling. Moreover, our approach paves the way for calibration of more intricate compartmental models.

Classification of Brain Tumor based on Machine Learning Algorithms: A Review

Brain tumor classification using machine learning algorithms is pivotal for medical diagnostics, particularly in magnetic resonance imaging (MRI) analysis. This review provides a comprehensive overview of recent advancements in brain tumor classification methodologies, emphasizing preprocessing, feature extraction, and classification phases. Preprocessing steps involve noise reduction and intensity normalization, while feature extraction encompasses texture analysis and deep learning-based methods. Machine learning algorithms such as support vector machines (SVM) and convolutional neural networks (CNNs) are utilized for accurate classification based on extracted features. Recent literature highlights the significance of diverse datasets, hyperparameter tuning, and segmentation techniques in improving diagnostic accuracy. Noteworthy methodologies include deep learning models for glioma grading and novel optimization techniques for tumor segmentation. The review underscores interdisciplinary collaboration between medical professionals and computational scientists to refine existing methodologies and overcome challenges. A systematic search of academic databases, including PubMed, IEEE Xplore, ACM Digital Library, ScienceDirect, Springer and Google Scholar, was conducted. Continued evolution in brain tumor classification promises enhanced diagnostic accuracy and personalized treatment strategies, ultimately improving patient outcomes in neuro-oncology.

Interaction between Hydrogen and Magnesium Films: From Hydrogenochromism to Applications.

Hydrogen, as a promising clean energy carrier, underscores the critical need for reliable detection technologies to ensure its safe and efficient use. Magnesium (Mg) thin films, with their hydrogenochromic properties, are particularly well-suited for hydrogen sensing applications due to their dramatic optical transitions. However, practical implementation faces challenges in achieving both rapid response and durability under cyclic conditions. To overcome these limitations, advanced interfacial tuning techniques have been developed to optimize hydrogen diffusion pathways and reinforce structural resilience. This review focuses on the scientific mechanism governing the interaction between Mg-based thin films and hydrogen, highlighting their suitability as hydrogen sensors with superior hydrogenochromic characteristics. Controllable manufacturing methods allow precise control over the alloy composition and microstructure of Mg-based thin films, facilitating the construction of phases and interfaces conducive to support efficient hydride formation, ultimately improving hydrogen response performance. Recent advancements in microstructure engineering, refined in situ characterization techniques, and promising optical applications drive the rapid development of Mg-based thin films.

Enhancing structural damage detection: A comprehensive study on feature engineering and hyperparameters for pattern recognition algorithms

One of the appealing alternatives, especially for detect, localize, and quantify the multiple simultaneously damages in structures, is using dataset-based damage detection (DBDD) technics. While machine learning (ML) algorithms have been applied to pattern recognition in DBDD studies, comprehensive research and sensitivity analysis on the effects of various parameters, such as ML algorithm choice, hyperparameter (HP) tuning, and feature engineering techniques, remain limited. This can hinder the selection of optimal parameter values, especially for large structures, without incurring significant computational costs. This study addresses this gap by employing extensive single-objective sensitivity analyses to evaluate the impact of these parameters on DBDD damage detection in a 3D sample structure, whose numerical model has been verified by comparing its Frequency Response Functions (FRFs) with experimental data. By comparing grid search outcomes, it was shown that leveraging insights from single-objective optimization can significantly reduce computational costs by limiting the parameter search space. Additionally, an innovative hybrid feature engineering method is proposed to enhance feature quality, reduce dataset size, and enable the feasibility of conducting extensive sensitivity analyses. Furthermore, the study investigates the impact of ensemble techniques with tuned algorithms and excitation point configuration on DBDD prediction accuracy. By using proposed feature engineering, optimal excitation configuration, optimized ML algorithms and HPs, in addition to shrinking the dataset to 5% of its original size, the accuracy of DBDD damage prediction can be improved by up to 60%. These results can be leveraged to pre-select optimal parameters for DBDD damage detection in similar structures, significantly reducing computational costs and improving accuracy.

Utilizing Raspberry-Pi 3 to Implement Fuzzy Logic Controller Optimized by Genetic Algorithm

The development of Fuzzy Logic Controllers (FLC) with low error rates and cost effectiveness has been the subject of numerous studies. This paper study goals to the investigation and then implementation an FLC using the readily accessible and reasonably priced Raspberry Pi technology. The FLC used in this work has two inputs, one output, and five Membership Functions (MFs) for each input and output. The FLC goes through two processes, tweaking the MF parameters and tuning input/ output Scaling Factors. The tuning technique makes use of the Genetic Algorithm (GA). The whole set of the FLC probabilities is taken into account as the tuned FLC controller, and then transformed into a lookup table. The Center of Gravity (COG) approach is used to determine the output for the tuned FLC controller. The resulting table is converted into values of digital binary using a specific type of encoder, and then extraction of the set of Boolean functions to apply this tuned circuit. Finally, the Python 3 programming language is used to define the resultant Boolean functions on the Raspberry Pi platform, and then a decoder extracted the appropriate control action from the output. The Benefit of this method is the use of a digital numbering system to define the FLC, which is implemented on Raspberry Pi technology and allows for fuzzified high processing speed output per second. The controller speed has not been unaffected by the quantity for these fuzzy rules.

A Review of Miniature Radio Transmitters for Wildlife Tracking.

This article surveys the literature on miniature radio transmitters designed to track free-ranging wild animals using emitter-localization techniques. The articles covers the topics of power sources used in such transmitters, including miniature batteries and energy harvesting, techniques for generating the transmitted radio-frequency carrier, techniques for creating short radio pulses and more general on-off schedules, modulation in modern wildlife-tracking transmitters, construction, manufacturing, and tuning techniques, and recent trends in this area. The article also describes the recreation of the first successful wildlife-tracking transmitter, a nontrivial invention that had a profound impact on wildlife ecology, and explores its behavior.

Evaluating and Enhancing Japanese Large Language Models for Genetic Counseling Support: Comparative Study of Domain Adaptation and the Development of an Expert-Evaluated Dataset.

Advances in genetics have underscored a strong association between genetic factors and health outcomes, leading to an increased demand for genetic counseling services. However, a shortage of qualified genetic counselors poses a significant challenge. Large language models (LLMs) have emerged as a potential solution for augmenting support in genetic counseling tasks. Despite the potential, Japanese genetic counseling LLMs (JGCLLMs) are underexplored. To advance a JGCLLM-based dialogue system for genetic counseling, effective domain adaptation methods require investigation. This study aims to evaluate the current capabilities and identify challenges in developing a JGCLLM-based dialogue system for genetic counseling. The primary focus is to assess the effectiveness of prompt engineering, retrieval-augmented generation (RAG), and instruction tuning within the context of genetic counseling. Furthermore, we will establish an experts-evaluated dataset of responses generated by LLMs adapted to Japanese genetic counseling for the future development of JGCLLMs. Two primary datasets were used in this study: (1) a question-answer (QA) dataset for LLM adaptation and (2) a genetic counseling question dataset for evaluation. The QA dataset included 899 QA pairs covering medical and genetic counseling topics, while the evaluation dataset contained 120 curated questions across 6 genetic counseling categories. Three enhancement techniques of LLMs-instruction tuning, RAG, and prompt engineering-were applied to a lightweight Japanese LLM to enhance its ability for genetic counseling. The performance of the adapted LLM was evaluated on the 120-question dataset by 2 certified genetic counselors and 1 ophthalmologist (SK, YU, and AY). Evaluation focused on four metrics: (1) inappropriateness of information, (2) sufficiency of information, (3) severity of harm, and (4) alignment with medical consensus. The evaluation by certified genetic counselors and an ophthalmologist revealed varied outcomes across different methods. RAG showed potential, particularly in enhancing critical aspects of genetic counseling. In contrast, instruction tuning and prompt engineering produced less favorable outcomes. This evaluation process facilitated the creation an expert-evaluated dataset of responses generated by LLMs adapted with different combinations of these methods. Error analysis identified key ethical concerns, including inappropriate promotion of prenatal testing, criticism of relatives, and inaccurate probability statements. RAG demonstrated notable improvements across all evaluation metrics, suggesting potential for further enhancement through the expansion of RAG data. The expert-evaluated dataset developed in this study provides valuable insights for future optimization efforts. However, the ethical issues observed in JGCLLM responses underscore the critical need for ongoing refinement and thorough ethical evaluation before these systems can be implemented in health care settings.

Diagnosis of Malignant Endometrial Lesions from Ultrasound Radiomics Features and Clinical Variables Using Machine Learning Methods

Background: The prognosis of patients with early diagnosis of malignant endometrial lesions is good. We aimed to identify benign and malignant lesions in endometrial tissue, explore effective methods for assisting diagnosis, and improve the accuracy and precision of identifying endometrial lesions. Methods: 1142 ultrasound radiomics and 18 clinical features from 1254 patients were analyzed, from which 36 features were selected for machine learning. We sketched the region of interest (ROI) of the abnormalities on the ultrasound images. Then, the radiomics features were extracted. Six common machine learning algorithms, including Support Vector Machine (SVM), Logistic Regression, Decision Tree, Random Forest, Gradient Boosting Tree, and k-Nearest Neighbors, were employed to identify benign and malignant changes in endometrial tissue. Cross-validation and grid search techniques for hyperparameter tuning were utilized to obtain the best model performance. Accuracy, precision, sensitivity, F1-scores, area under the curve (AUC), cross-validation average score and bootstrap average accuracy were also used to evaluate algorithm performance, classification accuracy, and generalization capability. Results: We combined 21 ultrasound characteristics and 15 clinical characteristics to develop and validate six common machine learning algorithms. After internal validation, the best models were the Random Forest models, with accuracy of 89%, precision of 93%, sensitivity of 97%, F1-score of 95%, and AUC of 95%, as well as a 10-fold cross-validation average score of 95% and bootstrap average accuracy of 94%, implying flawless classification in the test set. Conclusions: We identified the clinical and ultrasound features in the early diagnosis of benign or malignant lesions in endometrial tissue. And Random Forest model algorithms have demonstrated excellent performance in identifying benign and malignant changes in endometrial tissue. This is significant for enhancing early diagnostic accuracy and improving treatment outcomes and long-term management.

Bi‐LORA: A Vision‐Language Approach for Synthetic Image Detection

ABSTRACTAdvancements in deep image synthesis techniques, such as generative adversarial networks (GANs) and diffusion models (DMs), have ushered in an era of generating highly realistic images. While this technological progress has captured significant interest, it has also raised concerns about the high challenge in distinguishing real images from their synthetic counterparts. This paper takes inspiration from the potent convergence capabilities between vision and language, coupled with the zero‐shot nature of vision‐language models (VLMs). We introduce an innovative method called Bi‐LORA that leverages VLMs, combined with low‐rank adaptation (LORA) tuning techniques, to enhance the precision of synthetic image detection for unseen model‐generated images. The pivotal conceptual shift in our methodology revolves around reframing binary classification as an image captioning task, leveraging the distinctive capabilities of cutting‐edge VLM, notably bootstrapping language image pre‐training (BLIP)2. Rigorous and comprehensive experiments are conducted to validate the effectiveness of our proposed approach, particularly in detecting unseen diffusion‐generated images from unknown diffusion‐based generative models during training, showcasing robustness to noise, and demonstrating generalisation capabilities to GANs. The experiments show that Bi‐LORA outperforms state of the art models in cross‐generator tasks because it leverages multi‐modal learning, open‐world visual knowledge, and benefits from robust, high‐level semantic understanding. By combining visual and textual knowledge, it can handle variations in the data distribution (such as those caused by different generators) and maintain strong performance across different domains. Its ability to transfer knowledge, robustly extract features and perform zero‐shot learning also contributes to its generalisation capabilities, making it more adaptable to new generators. The experimental results showcase an impressive average accuracy of 93.41% in synthetic image detection on unseen generation models. The code and models associated with this research can be publicly accessed at https://github.com/Mamadou‐Keita/VLM‐DETECT.

Protocol for the development and validation of machine-learning models for predicting the risk of hypertriglyceridemia in critically ill patients receiving propofol sedation using retrospective data.

Propofol is a widely used sedative-hypnotic agent for critically-ill patients requiring invasive mechanical ventilation (IMV). Despite its clinical benefits, propofol is associated with increased risks of hypertriglyceridemia. Early identification of patients at risk for propofol-associated hypertriglyceridemia is crucial for optimizing sedation strategies and preventing adverse outcomes. Machine learning (ML) models offer a promising approach for predicting individualized patient risks of propofol-associated hypertriglyceridemia. We propose the development of a ML model aimed at predicting the risk of propofol-associated hypertriglyceridemia in ICU patients receiving IMV. The study will utilize retrospective data from four Mayo Clinic sites. Nested cross-validation (CV) will be employed, with a 10-fold inner CV loop for model tuning and selection as well as an outer loop using leave-one-site-out CV for external validation. Feature selection will be conducted using Boruta and LASSO-penalized logistic regression. Data preprocessing steps include missing data imputation, feature scaling, and dimensionality reduction techniques. Six ML algorithms will be tuned and evaluated. Bayesian optimization will be used for hyperparameter selection. Global model explainability will be assessed using permutation importance, and local model explainability will be assessed using SHapley Additive exPlanations (SHAP). The proposed ML model aims to provide a reliable and interpretable tool for clinicians to predict the risk of propofol-associated hypertriglyceridemia in ICU patients. The final model will be deployed in a web-based clinical risk calculator. The model development process and performance measures obtained during nested cross-validation will be described in a study publication to be disseminated in a peer-reviewed journal. The proposed study has received ethics approval from the Mayo Clinic Institutional Review Board (IRB #23-007416). Robust external validation using a nested cross-validation (CV) framework will help assess the generalizability of models produced from the modeling pipeline across different hospital settings.A diverse set of machine learning (ML) algorithms and advanced hyperparameter tuning techniques will be employed to identify the most optimal model configuration.Integration of feature explainability will enhance the clinical applicability of the ML models by providing transparency in predictions, which can improve clinician trust and encourage adoption.Reliance on retrospective data may introduce biases due to inconsistent or erroneous data collection, and the computational intensity of the validation approach may limit replication and future model expansion in resource-constrained settings.

Intelligence analysis of drug nanoparticles delivery efficiency to cancer tumor sites using machine learning models

This study focuses on the use of machine learning (ML) models to predict the biodistribution of nanoparticles in various organs, using a dataset derived from research on nanoparticle behavior for cancer treatment. The dataset includes both categorical and numerical variables related to nanoparticle properties, with a focus on their distribution across organs such as the tumor, heart, liver, spleen, lung, and kidney tissues. In order to address the complex and non-linear nature of the data, three machine learning models were utilized: Bayesian Ridge Regression (BRR), Kernel Ridge Regression (KRR), and K-Nearest Neighbors (KNN). The selection of these models was based on their wide range of capabilities in dealing with non-linear relationships and data complexity. To further model performance and strength, the study also applied cutting-edge methods including the Firefly Algorithm for hyperparameter tuning and Recursive Feature Elimination (RFE) for feature selection. Based on higher R² and lower RMSE values for most output parameters, the study concluded that Kernel Ridge Regression (KRR) did better compared to other models in predicting biodistribution outcomes. The study revealed that machine learning models, particularly KRR, exhibit a high level of efficiency in accurately representing the non-linear characteristics of nanoparticle biodistribution. The results obtained provide valuable insights into the optimization of predictive models for the behavior of nanoparticles. These models can be further enhanced by the use of advanced feature selection and hyperparameter tuning techniques.

Self-Adaptive Body Bias Tuning Technique for Enhancing Baliga’s Figure-of-Merit (BFOM) in Thin Bulk Silicon LDMOS

Self-Adaptive Body Bias Tuning Technique for Enhancing Baliga’s Figure-of-Merit (BFOM) in Thin Bulk Silicon LDMOS

Random Forest Hyperparameter Tuning in Machine Learning for Improved Performance in Intrusion Detection Systems

In recent times, researchers have been proposing different Intrusion Detection methods to deal with the increasing number and complexity of threats as technology keeps emerging. In this context, Random Forest models have been providing a notable performance on her predictive capacity to applications in the realm of behavioural-based Intrusion Detection Systems and other related fields of specialization which includes medicines, Banking, commerce, etc in terms high magnitude forecasting and optimal predictions . In this work, in-depth evaluation analysis of the Random Forest tuning were carried out with respect to classification, feature selection, and proximity metrics. This empirical research will provide an inclusive review of the general basic concepts related to Intrusion Detection Systems, which includes taxonomies, data collection, modeling and evaluation metrics. Furthermore, the manual hyperparameter tuning technique was used for this research work and a desirable experimental output was achieved as showed in this work.

The Use of Hyperparameter Tuning in Model Classification: A Scientific Work Area Identification

This research aims to investigate the effectiveness of hyperparameter tuning, particularly using Optuna, in enhancing the classification performance of machine learning models on scientific work reviews. The study focuses on automating the classification of academic papers into eight distinct fields: decision support systems, information technology, data science, technology education, artificial intelligence, expert systems, image processing, and information systems. The research dataset comprises reviews of scientific papers ranging from 150 to 500 words, collected from the repository of Universitas Putra Indonesia YPTK Padang. The classification process involved the application of the TF-IDF method for feature extraction, followed using various machine learning algorithms including SVM, MNB, KNN, and RF, with and without the integration of SMOTE for data balancing and Optuna for hyperparameter optimization. The results show that combining SMOTE with Optuna significantly improves the accuracy, precision, recall, and F1-score of the models, with the SVM algorithm achieving the highest accuracy at 90%. Additionally, the research explored the effectiveness of ensemble methods, revealing that hard voting combined with SMOTE and Optuna provided substantial improvements in classification performance. These findings underscore the importance of hyperparameter tuning and data balancing in optimizing machine learning models for text classification tasks. The implications of this research are broad, suggesting that the methodologies developed can be applied to various text classification tasks in different domains. Future research should consider exploring other hyperparameter tuning techniques and ensemble methods to further enhance model performance across diverse datasets.

Application of Faster R-CNN Deep Learning Method for Rice Plant Disease Detection

Plant diseases, particularly in staple crops like rice, significantly affect the stability of rice production in Indonesia. Crop failure caused by rice plant diseases present a critical challenge for farmers. Early diagnosis is crucial for preventing and managing rice diseases, as it facilitates more effective preventive measures, reduces yield losses, and boosts overall agricultural production. This study aims to apply the Faster Region Convolutional Neural Network (Faster R-CNN), a deep learning approach, to detect rice plant diseases. The Grid Search method was employed as a hyperparameter tuning technique to identify the optimal parameter combination for enhancing algorithm performance. Experimental results demonstrate the model's performance, achieving an accuracy rate of 88%, recall and precision of 100%, and an F1 Score of 93%. These findings indicate that the Faster R-CNN method effectively recognizes and classifies rice plant diseases with a high degree of accuracy.

Performance Evaluation of Various Deep Learning Models in Gait Recognition Using the CASIA-B Dataset

Human gait recognition (HGR) has been employed as a biometric technique for security purposes over the last decade. Various factors, including clothing, carrying items, and walking surfaces, can influence the performance of gait recognition. Additionally, identifying individuals from different viewpoints presents a significant challenge in HGR. Numerous conventional and deep learning techniques have been introduced in the literature for HGR, but traditional methods are not well suited to handling large datasets. This research explores the effectiveness of four deep learning models for gait identification in the CASIA B dataset: the convolutional neural network (CNN), multi-layer perceptron (MLP), self-organizing map (SOMs), and transfer learning with EfficientNet. The selected deep learning techniques offer robust feature extraction and the efficient handling of large datasets, making them ideal in enhancing the accuracy of gait recognition. The collection includes gait sequences from 10 individuals, with a total of 92,596 images that have been reduced to 64 × 64 pixels for uniformity. A modified model was developed by integrating sequential convolutional layers for detailed spatial feature extraction, followed by dense layers for classification, optimized through rigorous hyperparameter tuning and regularization techniques, resulting in an accuracy of 97.12% for the test set. This work enhances our understanding of deep learning methods in gait analysis, offering significant insights for choosing optimal models in security and surveillance applications.

A mixed-mode on-chip automatic frequency tuning technique for biopotential amplifiers

A mixed-mode on-chip automatic frequency tuning technique for biopotential amplifiers