CRISPR-DIPOFF: an interpretable deep learning approach for CRISPR Cas-9 off-target prediction.

CRISPR Cas-9 is a groundbreaking genome-editing tool that harnesses bacterial defense systems to alter DNA sequences accurately. This innovative technology holds vast promise in multiple domains like biotechnology, agriculture and medicine. However, such power does not come without its own peril, and one such issue is the potential for unintended modifications (Off-Target), which highlights the need for accurate prediction and mitigation strategies. Though previous studies have demonstrated improvement in Off-Target prediction capability with the application of deep learning, they often struggle with the precision-recall trade-off, limiting their effectiveness and do not provide proper interpretation of the complex decision-making process of their models. To address these limitations, we have thoroughly explored deep learning networks, particularly the recurrent neural network based models, leveraging their established success in handling sequence data. Furthermore, we have employed genetic algorithm for hyperparameter tuning to optimize these models' performance. The results from our experiments demonstrate significant performance improvement compared with the current state-of-the-art in Off-Target prediction, highlighting the efficacy of our approach. Furthermore, leveraging the power of the integrated gradient method, we make an effort to interpret our models resulting in a detailed analysis and understanding of the underlying factors that contribute to Off-Target predictions, in particular the presence of two sub-regions in the seed region of single guide RNA which extends the established biological hypothesis of Off-Target effects. To the best of our knowledge, our model can be considered as the first model combining high efficacy, interpretability and a desirable balance between precision and recall.

GA-GBLUP: leveraging the genetic algorithm to improve the predictability of genomic selection.

Genomic selection (GS) has emerged as an effective technology to accelerate crop hybrid breeding by enabling early selection prior to phenotype collection. Genomic best linear unbiased prediction (GBLUP) is a robust method that has been routinely used in GS breeding programs. However, GBLUP assumes that markers contribute equally to the total genetic variance, which may not be the case. In this study, we developed a novel GS method called GA-GBLUP that leverages the genetic algorithm (GA) to select markers related to the target trait. We defined four fitness functions for optimization, including AIC, BIC, R2, and HAT, to improve the predictability and bin adjacent markers based on the principle of linkage disequilibrium to reduce model dimension. The results demonstrate that the GA-GBLUP model, equipped with R2 and HAT fitness function, produces much higher predictability than GBLUP for most traits in rice and maize datasets, particularly for traits with low heritability. Moreover, we have developed a user-friendly R package, GAGBLUP, for GS, and the package is freely available on CRAN (https://CRAN.R-project.org/package=GAGBLUP).

Biclustering analysis on tree-shaped time-series single cell gene expression data of Caenorhabditis elegans.

BACKGROUND: In recent years, gene clustering analysis has become a widely used tool for studying gene functions, efficiently categorizing genes with similar expression patterns to aid in identifying gene functions. Caenorhabditis elegans is commonly used in embryonic research due to its consistent cell lineage from fertilized egg to adulthood. Biologists use 4D confocal imaging to observe gene expression dynamics at the single-cell level. However, on one hand, the observed tree-shaped time-series datasets have characteristics such as non-pairwise data points between different individuals. On the other hand, the influence of cell type heterogeneity should also be considered during clustering, aiming to obtain more biologically significant clustering results. RESULTS: A biclustering model is proposed for tree-shaped single-cell gene expression data of Caenorhabditis elegans. Detailedly, a tree-shaped piecewise polynomial function is first employed to fit non-pairwise gene expression time series data. Then, four factors are considered in the objective function, including Pearson correlation coefficients capturing gene correlations, p-values from the Kolmogorov-Smirnov test measuring the similarity between cells, as well as gene expression size and bicluster overlapping size. After that, Genetic Algorithm is utilized to optimize the function. CONCLUSION: The results on the small-scale dataset analysis validate the feasibility and effectiveness of our model and are superior to existing classical biclustering models. Besides, gene enrichment analysis is employed to assess the results on the complete real dataset analysis, confirming that the discovered biclustering results hold significant biological relevance.

Optimization of an anatomically and electrically detailed rodent subthalamic nucleus neuron model.

Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is an effective treatment for Parkinson's disease, but its mechanisms of action remain unclear. Detailed multicompartment computational models of STN neurons are often used to study how DBS electric fields modulate the neurons. However, currently available STN neuron models have some limitations in their biophysical realism. In turn, the goal of this study was to update a detailed rodent STN neuron model originally developed by Gillies and Willshaw in 2006. Our design requirements consisted of explicitly representing an axon connected to the neuron and updating the ion channel distributions based on the experimental literature to match established electrophysiological features of rodent STN neurons. We found that adding an axon to the STN neuron model substantially altered its firing characteristics. We then used a genetic algorithm to optimize biophysical parameters of the model. The updated model exhibited spontaneous firing, action potential shape, hyperpolarization response, and frequency-current curve that aligned well with experimental recordings from STN neurons. Subsequently, we evaluated the general compatibility of the updated biophysics by applying them to 26 different STN neuron morphologies derived from three-dimensional anatomical reconstructions. The different morphologies affected the firing behavior of the model, but the updated biophysics were robustly capable of maintaining the desired electrophysiological features. The new STN neuron model developed in this work offers a valuable tool for studying STN neuron firing properties and may find application in simulating STN local field potentials and analyzing the effects of STN DBS.NEW & NOTEWORTHY This study presents an anatomically and biophysically realistic rodent STN neuron model. The work showcases the use of a genetic algorithm to optimize the model parameters. We noted a substantial influence of the axon on the electrophysiological characteristics of STN neurons. The updated model offers a valuable tool to investigate the firing of STN neurons and their modulation by intrinsic and/or extrinsic factors.

Architecting the metabolic reprogramming survival risk framework in LUAD through single-cell landscape analysis: three-stage ensemble learning with genetic algorithm optimization.

Recent studies have increasingly revealed the connection between metabolic reprogramming and tumor progression. However, the specific impact of metabolic reprogramming on inter-patient heterogeneity and prognosis in lung adenocarcinoma (LUAD) still requires further exploration. Here, we introduced a cellular hierarchy framework according to a malignant and metabolic gene set, named malignant & metabolism reprogramming (MMR), to reanalyze 178,739 single-cell reference profiles. Furthermore, we proposed a three-stage ensemble learning pipeline, aided by genetic algorithm (GA), for survival prediction across 9 LUAD cohorts (n = 2066). Throughout the pipeline of developing the three stage-MMR (3 S-MMR) score, double training sets were implemented to avoid over-fitting; the gene-pairing method was utilized to remove batch effect; GA was harnessed to pinpoint the optimal basic learner combination. The novel 3 S-MMR score reflects various aspects of LUAD biology, provides new insights into precision medicine for patients, and may serve as a generalizable predictor of prognosis and immunotherapy response. To facilitate the clinical adoption of the 3 S-MMR score, we developed an easy-to-use web tool for risk scoring as well as therapy stratification in LUAD patients. In summary, we have proposed and validated an ensemble learning model pipeline within the framework of metabolic reprogramming, offering potential insights for LUAD treatment and an effective approach for developing prognostic models for other diseases.

Genetic algorithm-based semisupervised convolutional neural network for real-time monitoring of Escherichia coli fermentation of recombinant protein production using a Raman sensor.

As a non-destructive sensing technique, Raman spectroscopy is often combined with regression models for real-time detection of key components in microbial cultivation processes. However, achieving accurate model predictions often requires a large amount of offline measurement data for training, which is both time-consuming and labor-intensive. In order to overcome the limitations of traditional models that rely on large datasets and complex spectral preprocessing, in addition to the difficulty of training models with limited samples, we have explored a genetic algorithm-based semi-supervised convolutional neural network (GA-SCNN). GA-SCNN integrates unsupervised process spectral labeling, feature extraction, regression prediction, and transfer learning. Using only an extremely small number of offline samples of the target protein, this framework can accurately predict protein concentration, which represents a significant challenge for other models. The effectiveness of the framework has been validated in a system of Escherichia coli expressing recombinant ProA5M protein. By utilizing the labeling technique of this framework, the available dataset for glucose, lactate, ammonium ions, and optical density at 600 nm (OD600) has been expanded from 52 samples to 1302 samples. Furthermore, by introducing a small component of offline detection data for recombinant proteins into the OD600 model through transfer learning, a model for target protein detection has been retrained, providing a new direction for the development of associated models. Comparative analysis with traditional algorithms demonstrates that the GA-SCNN framework exhibits good adaptability when there is no complex spectral preprocessing. Cross-validation results confirm the robustness and high accuracy of the framework, with the predicted values of the model highly consistent with the offline measurement results.

GADNN: a revolutionary hybrid deep learning neural network for age and sex determination utilizing cone beam computed tomography images of maxillary and frontal sinuses.

INTRODUCTION: The determination of identity factors such as age and sex has gained significance in both criminal and civil cases. Paranasal sinuses like frontal and maxillary sinuses, are resistant to trauma and can aid profiling. We developed a deep learning (DL) model optimized by an evolutionary algorithm (genetic algorithm/GA) to determine sex and age using paranasal sinus parameters based on cone-beam computed tomography (CBCT). METHODS: Two hundred and forty CBCT images (including 129 females and 111 males, aged 18-52) were included in this study. CBCT images were captured using the Newtom3G device with specific exposure parameters. These images were then analyzed in ITK-SNAP 3.6.0 beta software to extract four paranasal sinus parameters: height, width, length, and volume for both the frontal and maxillary sinuses. A hybrid model, Genetic Algorithm-Deep Neural Network (GADNN), was proposed for feature selection and classification. Traditional statistical methods and machine learning models, including logistic regression (LR), random forest (RF), multilayer perceptron neural network (MLP), and deep learning (DL) were evaluated for their performance. The synthetic minority oversampling technique was used to deal with the unbalanced data. RESULTS: GADNN showed superior accuracy in both sex determination (accuracy of 86%) and age determination (accuracy of 68%), outperforming other models. Also, DL and RF were the second and third superior methods in sex determination (accuracy of 78% and 71% respectively) and age determination (accuracy of 92% and 57%). CONCLUSIONS: The study introduces a novel approach combining DL and GA to enhance sex determination and age determination accuracy. The potential of DL in forensic dentistry is highlighted, demonstrating its efficiency in improving accuracy for sex determination and age determination. The study contributes to the burgeoning field of DL in dentistry and forensic sciences.

Recent Advances in Automated Structure-Based De Novo Drug Design.

As the number of determined and predicted protein structures and the size of druglike 'make-on-demand' libraries soar, the time-consuming nature of structure-based computer-aided drug design calls for innovative computational algorithms. De novo drug design introduces in silico heuristics to accelerate searching in the vast chemical space. This review focuses on recent advances in structure-based de novo drug design, ranging from conventional fragment-based methods, evolutionary algorithms, and Metropolis Monte Carlo methods to deep generative models. Due to the historical limitation of de novo drug design generating readily available drug-like molecules, we highlight the synthetic accessibility efforts in each category and the benchmarking strategies taken to validate the proposed framework.

Enhancing vehicular emissions monitoring: A GA-GRU-based soft sensors approach for HDDVs.

Vehicle emissions have a serious impact on urban air quality and public health, so environmental authorities around the world have introduced increasingly stringent emission regulations to reduce vehicle exhaust emissions. Nowadays, PEMS (Portable Emission Measurement System) is the most widely used method to measure on-road NOx (Nitrogen Oxides) and PN (Particle Number) emissions from HDDVs (Heavy-Duty Diesel Vehicles). However, the use of PEMS requires a lot of workforce and resources, making it both costly and time-consuming. This study proposes a neural network based on a combination of GA (Genetic Algorithm) and GRU (Gated Recurrent Unit), which uses CC (Pearson Correlation Coefficient) to determine and simplify OBD (On-board Diagnosis) data. The GA-GRU model is trained under three real driving conditions of HDDVs, divided by vehicle driving parameters, and then embedded as a soft sensor in the OBD system to monitor real-time emissions of NOx and PN within the OBD system. This research addresses the existing research gap in the development of soft sensors specifically designed for NOx and PN emission monitoring. In this study, it is demonstrated that the described soft sensor has excellent R2 values and outperforms other conventional models. This research highlights the ability of the proposed soft sensor to eliminate outliers accurately and promptly while consistently tracking predictions throughout the vehicle's lifetime. This method is a groundbreaking update to the vehicle's OBD system, permanently adding monitoring data to the vehicle's OBD, thus fundamentally improving the vehicle's self-monitoring capabilities.

A robust genetic algorithm-based optimal feature predictor model for brain tumour classification from MRI data.

Brain tumour can be cured if it is initially screened and given timely treatment to the patients. This proposed idea suggests a transform- and windowing-based optimization strategy for exposing and segmenting the tumour region in brain pictures. The processes of image processing that are included in the proposed idea include preprocessing, transformation, feature extraction, feature optimization, classification, and segmentation. In order to convert the pixels connected to the spatial domain into a multi-resolution domain, the Gabor transform is first applied to the brain test image. The Gabor converted brain image is then used to extract the parameters of the multi-level features. After that, the Genetic Algorithm (GA) is used to optimize the extracted features, and Neuro Fuzzy System (NFS) is used to classify the optimistic prominent section. Finally, the tumour region in brain images is found and segmented using the normalized segmentation algorithm. The effective detection and classification of brain tumours by the characteristics of sensitivity, specificity, and accuracy are described by the suggested GA-based NFS classification approach. The trial findings are displayed with an average of 99.37% sensitivity, 98.9% specificity, 99.21% accuracy, 97.8% PPV, 91.8% NPV, 96.8% FPR, and 90.4% FNR.

Evaluating the efficacy of recyclable nanostructured adsorbents for rapid removal of methylparaben from aqueous solutions.

In this study, we evaluate the efficiency of two novel nanostructured adsorbents - chitosan-graphitic carbon nitride@magnetite (CS-g-CN@Fe3O4) and graphitic carbon nitride@copper/zinc nanocomposite (g-CN@Cu/Zn NC) - for the rapid removal of methylparaben (MPB) from water. Our characterization methods, aimed at understanding the adsorbents' structures and surface areas, informed our systematic examination of influential parameters including sonication time, adsorbent dosage, initial MPB concentration, and temperature. We applied advanced modeling techniques, such as response surface methodology (RSM), generalized regression neural network (GRNN), and radial basis function neural network (RBFNN), to evaluate the adsorption process. The adsorbents proved highly effective, achieving maximum adsorption capacities of 255 mg g-1 for CS-g-CN@Fe3O4 and 218 mg g-1 for g-CN@Cu/Zn NC. Through genetic algorithm (GA) optimization, we identified the optimal conditions for the highest MPB removal efficiency: a sonication period of 12.00 min and an adsorbent dose of 0.010 g for CS-g-CN@Fe3O4 NC, with an MPB concentration of 17.20 mg L-1 at 42.85 °C; and a sonication time of 10.25 min and a 0.011 g dose for g-CN@Cu/Zn NC, with an MPB concentration of 13.45 mg L-1 at 36.50 °C. The predictive accuracy of the RBFNN and GRNN models was confirmed to be satisfactory. Our findings demonstrate the significant capabilities of these synthesized adsorbents in effectively removing MPB from water, paving the way for optimized applications in water purification.

pyDarwin machine learning algorithms application and comparison in nonlinear mixed-effect model selection and optimization.

Forward addition/backward elimination (FABE) has been the standard for population pharmacokinetic model selection (PPK) since NONMEM® was introduced. We investigated five machine learning (ML) algorithms (Genetic algorithm [GA], Gaussian process [GP], random forest [RF], gradient boosted random tree [GBRT], and particle swarm optimization [PSO]) as alternatives to FABE. These algorithms were applied to PPK model selection with a focus on comparing the efficiency and robustness of each of them. All machine learning algorithms included the combination of ML algorithms with a local downhill search. The local downhill search consisted of systematically changing one or two "features" at a time (a one-bit or a two-bit local search), alternating with the ML methods. An exhaustive search (all possible combinations of model features, N = 1,572,864 models) was the gold standard for robustness, and the number of models examined leading prior to identification of the final model was the metric for efficiency.All algorithms identified the optimal model when combined with the two-bit local downhill search. GA, RF, GBRT, and GP identified the optimal model with only a one-bit local search. PSO required the two-bit local downhill search. In our analysis, GP was the most efficient algorithm as measured by the number of models examined prior to finding the optimal (495 models), and PSO exhibited the least efficiency, requiring 1710 unique models before finding the best solution. Additionally, GP was also the algorithm that needed the longest elapsed time of 2975.6 min, in comparison with GA, which only required 321.8 min.

Subgroup identification-based model selection to improve the predictive performance of individualized dosing.

Currently, model-informed precision dosing uses one population pharmacokinetic model that best fits the target population. We aimed to develop a subgroup identification-based model selection approach to improve the predictive performance of individualized dosing, using vancomycin in neonates/infants as a test case. Data from neonates/infants with at least one vancomycin concentration was randomly divided into training and test dataset. Population predictions from published vancomycin population pharmacokinetic models were calculated. The single best-performing model based on various performance metrics, including median absolute percentage error (APE) and percentage of predictions within 20% (P20) or 60% (P60) of measurement, were determined. Clustering based on median APEs or clinical and demographic characteristics and model selection by genetic algorithm was used to group neonates/infants according to their best-performing model. Subsequently, classification trees to predict the best-performing model using clinical and demographic characteristics were developed. A total of 208 vancomycin treatment episodes in training and 88 in test dataset was included. Of 30 identified models from the literature, the single best-performing model for training dataset had P20 26.2-42.6% in test dataset. The best-performing clustering approach based on median APEs or clinical and demographic characteristics and model selection by genetic algorithm had P20 44.1-45.5% in test dataset, whereas P60 was comparable. Our proof-of-concept study shows that the prediction of the best-performing model for each patient according to the proposed model selection approaches has the potential to improve the predictive performance of model-informed precision dosing compared with the single best-performing model approach.

Classification of Motor Imagery Tasks Derived from Unilateral Upper Limb based on a Weight-optimized Learning Model.

BACKGROUND: The accuracy of decoding fine motor imagery (MI) tasks remains relatively low due to the dense distribution of active areas in the cerebral cortex. METHODS: To enhance the decoding of unilateral fine MI activity in the brain, a weight-optimized EEGNet model is introduced that recognizes six types of MI for the right upper limb, namely elbow flexion/extension, wrist pronation/supination and hand opening/grasping. The model is trained with augmented electroencephalography (EEG) data to learn deep features for MI classification. To address the sensitivity issue of the initial model weights to classification performance, a genetic algorithm (GA) is employed to determine the convolution kernel parameters for each layer of the EEGNet network, followed by optimization of the network weights through backpropagation. RESULTS: The algorithm's performance on the three joint classification is validated through experiment, achieving an average accuracy of 87.97%. The binary classification recognition rates for elbow joint, wrist joint, and hand joint are respectively 93.92%, 90.2%, and 94.64%. Thus, the product of the two-step accuracy value is obtained as the overall capability to distinguish the six types of MI, reaching an average accuracy of 81.74%. Compared to commonly used neural networks and traditional algorithms, the proposed method outperforms and significantly reduces the average error of different subjects. CONCLUSIONS: Overall, this algorithm effectively addresses the sensitivity of network parameters to initial weights, enhances algorithm robustness and improves the overall performance of MI task classification. Moreover, the method is applicable to other EEG classification tasks; for example, emotion and object recognition.

Utilizing Phase Locking Value to Determine Neurofeedback Treatment Responsiveness in Attention Deficit Hyperactivity Disorder.

BACKGROUND: Neurofeedback is a non-invasive brain training technique used to enhance and treat hyperactivity disorder by altering the patterns of brain activity. Nonetheless, the extent of enhancement by neurofeedback varies among individuals/patients and many of them are irresponsive to this treatment technique. Therefore, several studies have been conducted to predict the effectiveness of neurofeedback training including the theta/beta protocol with a specific emphasize on slow cortical potential (SCP) before initiating treatment, as well as examining SCP criteria according to age and sex criteria in diverse populations. While some of these studies failed to make accurate predictions, others have demonstrated low success rates. This study explores functional connections within various brain lobes across different frequency bands of electroencephalogram (EEG) signals and the value of phase locking is used to predict the potential effectiveness of neurofeedback treatment before its initiation. METHODS: This study utilized EEG data from the Mendelian database. In this database, EEG signals were recorded during neurofeedback sessions involving 60 hyperactive students aged 7-14 years, irrespective of sex. These students were categorized into treatable and non-treatable. The proposed method includes a five-step algorithm. Initially, the data underwent preprocessing to reduce noise using a multi-stage filtering process. The second step involved extracting alpha and beta frequency bands from the preprocessed EEG signals, with a particular emphasis on the EEG recorded from sessions 10 to 20 of neurofeedback therapy. In the third step, the method assessed the disparity in brain signals between the two groups by evaluating functional relationships in different brain lobes using the phase lock value, a crucial data characteristic. The fourth step focused on reducing the feature space and identifying the most effective and optimal electrodes for neurofeedback treatment. Two methods, the probability index (p-value) via a t-test and the genetic algorithm, were employed. These methods showed that the optimal electrodes were in the frontal lobe and central cerebral cortex, notably channels C3, FZ, F4, CZ, C4, and F3, as they exhibited significant differences between the two groups. Finally, in the fifth step, machine learning classifiers were applied, and the results were combined to generate treatable and non-treatable labels for each dataset. RESULTS: Among the classifiers, the support vector machine and the boosting method demonstrated the highest accuracy when combined. Consequently, the proposed algorithm successfully predicted the treatability of individuals with hyperactivity in a short time and with limited data, achieving an accuracy of 90.6% in the neurofeedback method. Additionally, it effectively identified key electrodes in neurofeedback treatment, reducing their number from 32 to 6. CONCLUSIONS: This study introduces an algorithm with a 90.6% accuracy for predicting neurofeedback treatment outcomes in hyperactivity disorder, significantly enhancing treatment efficiency by identifying optimal electrodes and reducing their number from 32 to 6. The proposed method enables the prediction of patient responsiveness to neurofeedback therapy without the need for numerous sessions, thus conserving time and financial resources.

PDSFit: PDS data analysis in the presence of orientation selectivity, g-anisotropy, and exchange coupling.

Pulsed dipolar electron paramagnetic resonance spectroscopy (PDS), encompassing techniques such as pulsed electron-electron double resonance (PELDOR or DEER) and relaxation-induced dipolar modulation enhancement (RIDME), is a valuable method in structural biology and materials science for obtaining nanometer-scale distance distributions between electron spin centers. An important aspect of PDS is the extraction of distance distributions from the measured time traces. Most software used for this PDS data analysis relies on simplifying assumptions, such as assuming isotropic g-factors of ~2 and neglecting orientation selectivity and exchange coupling. Here, the program PDSFit is introduced, which enables the analysis of PELDOR and RIDME time traces with or without orientation selectivity. It can be applied to spin systems consisting of up to two spin centers with anisotropic g-factors and to spin systems with exchange coupling. It employs a model-based fitting of the time traces using parametrized distance and angular distributions, and parametrized PDS background functions. The fitting procedure is followed by an error analysis for the optimized parameters of the distributions and backgrounds. Using five different experimental data sets published previously, the performance of PDSFit is tested and found to provide reliable solutions.

Improved production of RNA-inhibiting antimicrobial peptide by Bacillus licheniformis MCC 2514 facilitated by a genetic algorithm optimized medium.

One of the significant challenges during the purification and characterization of antimicrobial peptides (AMPs) from Bacillus sp. is the interference of unutilized peptides from complex medium components during analytical procedures. In this study, a semi-synthetic medium was devised to overcome this challenge. Using a genetic algorithm, the production medium of AMP is optimized. The parent organism, Bacillus licheniformis MCC2514, produces AMP in very small quantities. This AMP is known to inhibit RNA biosynthesis. The findings revealed that lactose, NH4Cl and NaNO3 were crucial medium constituents for enhanced AMP synthesis. The potency of the AMP produced was studied using bacterium, Kocuria rhizophila ATCC 9341. The AMP produced from the optimized medium was eightfold higher than that produced from the unoptimized medium. Furthermore, activity was increased by 1.5-fold when cultivation conditions were standardized using the optimized medium. Later, AMP was produced in a 5 L bioreactor under controlled conditions, which led to similar results as those of shake-flask production. The mode of action of optimally produced AMP was confirmed to be inhibition of RNA biosynthesis. Here, we demonstrate that improved production of AMP is possible with the developed semi-synthetic medium recipe and could help further AMP production in an industrial setup.

Enhancing Camera Calibration for Traffic Surveillance with an Integrated Approach of Genetic Algorithm and Particle Swarm Optimization.

Recent advancements in sensor technologies, coupled with signal processing and machine learning, have enabled real-time traffic control systems to effectively adapt to changing traffic conditions. Cameras, as sensors, offer a cost-effective means to determine the number, location, type, and speed of vehicles, aiding decision-making at traffic intersections. However, the effective use of cameras for traffic surveillance requires proper calibration. This paper proposes a new optimization-based method for camera calibration. In this approach, initial calibration parameters are established using the Direct Linear Transformation (DLT) method. Then, optimization algorithms are applied to further refine the calibration parameters for the correction of nonlinear lens distortions. A significant enhancement in the optimization process is achieved through the integration of the Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) into a combined Integrated GA and PSO (IGAPSO) technique. The effectiveness of this method is demonstrated through the calibration of eleven roadside cameras at three different intersections. The experimental results show that when compared to the baseline DLT method, the vehicle localization error is reduced by 22.30% with GA, 22.31% with PSO, and 25.51% with IGAPSO.

Machine Learning for the Design and the Simulation of Radiofrequency Magnetic Resonance Coils: Literature Review, Challenges, and Perspectives.

Radiofrequency (RF) coils for magnetic resonance imaging (MRI) applications serve to generate RF fields to excite the nuclei in the sample (transmit coil) and to pick up the RF signals emitted by the nuclei (receive coil). For the purpose of optimizing the image quality, the performance of RF coils has to be maximized. In particular, the transmit coil has to provide a homogeneous RF magnetic field, while the receive coil has to provide the highest signal-to-noise ratio (SNR). Thus, particular attention must be paid to the coil simulation and design phases, which can be performed with different computer simulation techniques. Being largely used in many sectors of engineering and sciences, machine learning (ML) is a promising method among the different emerging strategies for coil simulation and design. Starting from the applications of ML algorithms in MRI and a short description of the RF coil's performance parameters, this narrative review describes the applications of such techniques for the simulation and design of RF coils for MRI, by including deep learning (DL) and ML-based algorithms for solving electromagnetic problems.

Research on a Calculation Model of Ankle-Joint-Torque-Based sEMG.

The purpose of this article is to establish a prediction model of joint movements and realize the prediction of joint movemenst, and the research results are of reference value for the development of the rehabilitation equipment. This will be carried out by analyzing the impact of surface electromyography (sEMG) on ankle movements and using the Hill model as a framework for calculating ankle joint torque. The table and scheme used in the experiments were based on physiological parameters obtained through the model. Data analysis was performed on ankle joint angle signal, movement signal, and sEMG data from nine subjects during dorsiflexion/flexion, varus, and internal/external rotation. The Hill model was employed to determine 16 physiological parameters which were optimized using a genetic algorithm. Three experiments were carried out to identify the optimal model to calculate torque and root mean square error. The optimized model precisely calculated torque and had a root mean square error of under 1.4 in comparison to the measured torque. Ankle movement models predict torque patterns with accuracy, thereby providing a solid theoretical basis for ankle rehabilitation control. The optimized model provides a theoretical foundation for precise ankle torque forecasts, thereby improving the efficacy of rehabilitation robots for the ankle.