A vulnerability detection method for IoT protocol based on parallel fuzzy algorithm.

The Internet of Things communication protocol is prone to security vulnerabilities when facing increasing types and scales of network attacks, which can affect the communication security of the Internet of Things. It is crucial to effectively detect these vulnerabilities in order to improve the security of IoT communication protocols and promptly fix them. Therefore, this study proposes a distributed IoT communication protocol vulnerability detection method based on an improved parallelized fuzzy testing algorithm. Firstly, based on design principles and by comparing different communication protocols, a communication architecture for the distribution network's Internet of Things was constructed, and the communication protocols were formalized and decomposed. Next, preprocess the vulnerability detection samples, and then use genetic algorithm to improve the parallelized fuzzy testing algorithm to perform vulnerability detection. Through this improved algorithm, the missed detection rate and false detection rate can be effectively reduced, thereby improving the security of IoT communication protocols. The experimental results show that the highest missed detection rate of this method is only 4.0 %, and the false detection rate is low, with high detection efficiency. This indicates that the method has good performance and reliability in detecting vulnerabilities in IoT communication protocols.

Optimized Wasserstein Deep Convolutional Generative Adversarial Network fostered Groundnut Leaf Disease Identification System.

Groundnut is a noteworthy oilseed crop. Attacks by leaf diseases are one of the most important reasons causing low yield and loss of groundnut plant growth, which will directly diminish the yield and quality. Therefore, an Optimized Wasserstein Deep Convolutional Generative Adversarial Network fostered Groundnut Leaf Disease Identification System (GLDI-WDCGAN-AOA) is proposed in this paper. The pre-processed output is fed to Hesitant Fuzzy Linguistic Bi-objective Clustering (HFL-BOC) for segmentation. By using Wasserstein Deep Convolutional Generative Adversarial Network (WDCGAN), the input leaf images are classified into Healthy leaf, early leaf spot, late leaf spot, nutrition deficiency, and rust. Finally, the weight parameters of WDCGAN are optimized by Aquila Optimization Algorithm (AOA) to achieve high accuracy. The proposed GLDI-WDCGAN-AOA approach provides 23.51%, 22.01%, and 18.65% higher accuracy and 24.78%, 23.24%, and 28.98% lower error rate analysed with existing methods, such as Real-time automated identification and categorization of groundnut leaf disease utilizing hybrid machine learning methods (GLDI-DNN), Online identification of peanut leaf diseases utilizing the data balancing method along deep transfer learning (GLDI-LWCNN), and deep learning-driven method depending on progressive scaling method for the precise categorization of groundnut leaf infections (GLDI-CNN), respectively.

Bio-inspired compensatory strategies for damage to flapping robotic propulsors.

Natural swimmers and flyers can fully recover from catastrophic propulsor damage by altering stroke mechanics: some fish can lose even 76% of their propulsive surface without loss of thrust. We consider applying these principles to enable robotic flapping propulsors to autonomously repair functionality. However, direct transference of these alterations from an organism to a robotic flapping propulsor may be suboptimal owing to irrelevant evolutionary pressures. Instead, we use machine learning techniques to compare these alterations with those optimal for a robotic system. We implement an online artificial evolution with hardware-in-the-loop, performing experimental evaluations with a flexible plate. To recoup thrust, the learned strategy increased amplitude, frequency and angle of attack (AOA) amplitude, and phase-shifted AOA by approximately 110°. Only amplitude increase is reported by most fish literature. When recovering side force, we find that force direction is correlated with AOA. No clear amplitude or frequency trend is found, whereas frequency increases in most insect literature. These results suggest that how mechanical flapping propulsors most efficiently adjust to damage may not align with natural swimmers and flyers.

Image reconstruction of multispectral sparse sampling photoacoustic tomography based on deep algorithm unrolling.

Photoacoustic tomography (PAT), as a novel medical imaging technology, provides structural, functional, and metabolism information of biological tissue in vivo. Sparse Sampling PAT, or SS-PAT, generates images with a smaller number of detectors, yet its image reconstruction is inherently ill-posed. Model-based methods are the state-of-the-art method for SS-PAT image reconstruction, but they require design of complex handcrafted prior. Owing to their ability to derive robust prior from labeled datasets, deep-learning-based methods have achieved great success in solving inverse problems, yet their interpretability is poor. Herein, we propose a novel SS-PAT image reconstruction method based on deep algorithm unrolling (DAU), which integrates the advantages of model-based and deep-learning-based methods. We firstly provide a thorough analysis of DAU for PAT reconstruction. Then, in order to incorporate the structural prior constraint, we propose a nested DAU framework based on plug-and-play Alternating Direction Method of Multipliers (PnP-ADMM) to deal with the sparse sampling problem. Experimental results on numerical simulation, in vivo animal imaging, and multispectral un-mixing demonstrate that the proposed DAU image reconstruction framework outperforms state-of-the-art model-based and deep-learning-based methods.

Human Factors in AI-Driven Digital Solutions for Increasing Physical Activity: Scoping Review.

BACKGROUND: Artificial intelligence (AI) has the potential to enhance physical activity (PA) interventions. However, human factors (HFs) play a pivotal role in the successful integration of AI into mobile health (mHealth) solutions for promoting PA. Understanding and optimizing the interaction between individuals and AI-driven mHealth apps is essential for achieving the desired outcomes. OBJECTIVE: This study aims to review and describe the current evidence on the HFs in AI-driven digital solutions for increasing PA. METHODS: We conducted a scoping review by searching for publications containing terms related to PA, HFs, and AI in the titles and abstracts across 3 databases-PubMed, Embase, and IEEE Xplore-and Google Scholar. Studies were included if they were primary studies describing an AI-based solution aimed at increasing PA, and results from testing the solution were reported. Studies that did not meet these criteria were excluded. Additionally, we searched the references in the included articles for relevant research. The following data were extracted from included studies and incorporated into a qualitative synthesis: bibliographic information, study characteristics, population, intervention, comparison, outcomes, and AI-related information. The certainty of the evidence in the included studies was evaluated using GRADE (Grading of Recommendations Assessment, Development, and Evaluation). RESULTS: A total of 15 studies published between 2015 and 2023 involving 899 participants aged approximately between 19 and 84 years, 60.7% (546/899) of whom were female participants, were included in this review. The interventions lasted between 2 and 26 weeks in the included studies. Recommender systems were the most commonly used AI technology in digital solutions for PA (10/15 studies), followed by conversational agents (4/15 studies). User acceptability and satisfaction were the HFs most frequently evaluated (5/15 studies each), followed by usability (4/15 studies). Regarding automated data collection for personalization and recommendation, most systems involved fitness trackers (5/15 studies). The certainty of the evidence analysis indicates moderate certainty of the effectiveness of AI-driven digital technologies in increasing PA (eg, number of steps, distance walked, or time spent on PA). Furthermore, AI-driven technology, particularly recommender systems, seems to positively influence changes in PA behavior, although with very low certainty evidence. CONCLUSIONS: Current research highlights the potential of AI-driven technologies to enhance PA, though the evidence remains limited. Longer-term studies are necessary to assess the sustained impact of AI-driven technologies on behavior change and habit formation. While AI-driven digital solutions for PA hold significant promise, further exploration into optimizing AI's impact on PA and effectively integrating AI and HFs is crucial for broader benefits. Thus, the implications for innovation management involve conducting long-term studies, prioritizing diversity, ensuring research quality, focusing on user experience, and understanding the evolving role of AI in PA promotion.

A/B Testing of User Enrollment Forms to Enhance Diversity in the Biomedical Workforce via the National Research Mentoring Network: User-Centered Design Case Study.

Background: The National Research Mentoring Network (NRMN) is a National Institutes of Health-funded program for diversifying the science, technology, engineering, math, and medicine research workforce through the provision of mentoring, networking, and professional development resources. The NRMN provides mentoring resources to members through its online platform-MyNRMN. Objective: MyNRMN helps members build a network of mentors. Our goal was to expand enrollment and mentoring connections, especially among those who have been historically underrepresented in biomedical training and the biomedical workforce. Methods: To improve the ease of enrollment, we implemented the split testing of iterations of our user interface for platform registration. To increase mentoring connections, we developed multiple features that facilitate connecting via different pathways. Results: Our improved user interface yielded significantly higher rates of completed registrations (P<.001). Our analysis showed improvement in completed enrollments that used the version 1 form when compared to those that used the legacy form (odds ratio 1.52, 95% CI 1.30-1.78). The version 2 form, with its simplified, 1-step process and fewer required fields, outperformed the legacy form (odds ratio 2.18, 95% CI 1.90-2.50). By improving the enrollment form, the rate of MyNRMN enrollment completion increased from 57.3% (784/1368) with the legacy form to 74.5% (2016/2706) with the version 2 form. Our newly developed features delivered an increase in connections between members. Conclusions: Our technical efforts expanded MyNRMN's membership base and increased connections between members. Other platform development teams can learn from these efforts to increase enrollment among underrepresented groups and foster continuing, successful engagement.

Tailoring Phonon Dispersion of a Genetically Designed Nanophononic Metasurface.

Phonon engineering at the nanoscale holds immense promise for a myriad of applications. However, the design of phononic devices continues to rely on regular shapes chosen according to long-established simple rules. Here, we demonstrate an inverse design approach to create a two-dimensional phononic metasurface exhibiting a highly anisotropic phonon dispersion along the main axes of the Brillouin zone. A partial hypersonic bandgap of approximately 3.5 GHz is present along one axis, with gap closure along the orthogonal axis. Such a level of control is achieved through genetically optimized unit cells, with shapes exceeding conventional intuition. We experimentally validated our theoretical predictions using Brillouin light scattering, confirming the effectiveness of the inverse design method. Our approach unlocks the potential for automated engineering of phononic metasurfaces with on-demand functionalities, thus leading toward innovative phononic devices beyond the limitations of traditional design paradigms.

DNN-BP: a novel framework for cuffless blood pressure measurement from optimal PPG features using deep learning model.

Continuous blood pressure (BP) provides essential information for monitoring one's health condition. However, BP is currently monitored using uncomfortable cuff-based devices, which does not support continuous BP monitoring. This paper aims to introduce a blood pressure monitoring algorithm based on only photoplethysmography (PPG) signals using the deep neural network (DNN). The PPG signals are obtained from 125 unique subjects with 218 records and filtered using signal processing algorithms to reduce the effects of noise, such as baseline wandering, and motion artifacts. The proposed algorithm is based on pulse wave analysis of PPG signals, extracted various domain features from PPG signals, and mapped them to BP values. Four feature selection methods are applied and yielded four feature subsets. Therefore, an ensemble feature selection technique is proposed to obtain the optimal feature set based on major voting scores from four feature subsets. DNN models, along with the ensemble feature selection technique, outperformed in estimating the systolic blood pressure (SBP) and diastolic blood pressure (DBP) compared to previously reported approaches that rely only on the PPG signal. The coefficient of determination ( R 2 ) and mean absolute error (MAE) of the proposed algorithm are 0.962 and 2.480 mmHg, respectively, for SBP and 0.955 and 1.499 mmHg, respectively, for DBP. The proposed approach meets the Advancement of Medical Instrumentation standard for SBP and DBP estimations. Additionally, according to the British Hypertension Society standard, the results attained Grade A for both SBP and DBP estimations. It concludes that BP can be estimated more accurately using the optimal feature set and DNN models. The proposed algorithm has the potential ability to facilitate mobile healthcare devices to monitor continuous BP.

Modeling and optimization of dyeing process of polyamide 6 and woolen fabrics with plum-tree leaves using artificial intelligence.

The dyeing process of textile materials is inherently intricate, influenced by a myriad of factors, including dye concentration, dyeing time, pH level, temperature, type of dye, fiber composition, mechanical agitation, salt concentration, mordants, fixatives, water quality, dyeing method, and pre-treatment processes. The intricacy of achieving optimal settings during dyeing poses a significant challenge. In response, this study introduces a novel algorithmic approach that integrates response surface methodology (RSM), artificial neural network (ANN), and genetic algorithm (GA) techniques for the precise fine-tuning of concentration, time, pH, and temperature. The primary focus is on quantifying color strength, represented as K/S, as the response variable in the dyeing process of polyamide 6 and woolen fabric, utilizing plum-tree leaves as a sustainable dye source. Results indicate that ANN (R2 ~ 1) performs much better than RSM (R2 > 0.92). The optimization results, employing ANN-GA integration, indicate that a concentration of 100 wt.%, time of 86.06 min, pH level of 8.28, and a temperature of 100 °C yield a K/S value of 10.21 for polyamide 6 fabric. Similarly, a concentration of 55.85 wt.%, time of 120 min, pH level of 5, and temperature of 100 °C yield a K/S value of 7.65 for woolen fabric. This proposed methodology not only paves the way for sustainable textile dyeing but also facilitates the optimization of diverse dyeing processes for textile materials.

Two-step machine learning-assisted label-free surface-enhanced Raman spectroscopy for reliable prediction of dissolved furfural in transformer oil.

Accurate detection of dissolved furfural in transformer oil is crucial for real-time monitoring of the aging state of transformer oil-paper insulation. While label-free surface-enhanced Raman spectroscopy (SERS) has demonstrated high sensitivity for dissolved furfural in transformer oil, challenges persist due to poor substrate consistency and low quantitative reliability. Herein, machine learning (ML) algorithms were employed in both substrate fabrication and spectral analysis of label-free SERS. Initially, a high-consistency Ag@Au substrate was prepared through a combination of experiments, particle swarm optimization-neural network (PSO-NN), and a hybrid strategy of particle swarm optimization and genetic algorithm (Hybrid PSO-GA). Notably, a two-step ML framework was proposed, whose operational mechanism is classification followed by quantification. The framework adopts a hierarchical modeling strategy, incorporating simple algorithms such as kernel support vector machine (Kernel-SVM), k-nearest neighbors (KNN), etc., to independently establish lightweight regression models on each cluster, which allows each model to focus more effectively on fitting the data within its cluster. The classification model achieved an accuracy of 100%, while the regression models exhibited an average correlation coefficient (R2) of 0.9953 and the root mean square errors (RMSE) consistently below 10-2. Thus, this ML framework emerges as a rapid and reliable method for detecting dissolved furfural in transformer oil, even in the presence of different interfering substances, which may also have potentiality for other complex mixture monitoring systems.

Automatic summarization model based on clustering algorithm.

Extractive document summary is usually seen as a sequence labeling task, which the summary is formulated by sentences from the original document. However, the selected sentences usually are high redundancy in semantic space, so that the composed summary are high semantic redundancy. To alleviate this problem, we propose a model to reduce the semantic redundancy of summary by introducing the cluster algorithm to select difference sentences in semantic space and we improve the base BERT to score sentences. We evaluate our model and perform significance testing using ROUGE on the CNN/DailyMail datasets compare with six baselines, which include two traditional methods and four state-of-art deep learning model. The results validate the effectiveness of our approach, which leverages K-means algorithm to produce more accurate and less repeat sentences in semantic summaries.

Myelofibrosis and allogeneic transplantation: critical points and challenges.

New available drugs allow better control of systemic symptoms associated with myelofibrosis (MF) and splenomegaly but they do not modify the natural history of progressive and poor prognosis disease. Thus, hematopoietic stem cell transplantation (HSCT) is still considered the only available curative treatment for patients with MF. Despite the increasing number of procedures worldwide in recent years, HSCT for MF patients remains challenging. An increasingly complex network of the patient, disease, and transplant-related factors should be considered to understand the need for and the benefits of the procedure. Unfortunately, prospective trials are often lacking in this setting, making an evidence-based decision process particularly arduous. In the present review, we will analyze the main controversial points of allogeneic transplantation in MF, that is, the development of more sophisticated models for the identification of eligible patients; the need for tools offering a more precise definition of expected outcomes combining comorbidity assessment and factors related to the procedure; the decision-making process about the best transplantation time; the evaluation of the most appropriate platform for curative treatment; the impact of splenomegaly; and splenectomy on outcomes.

A Rehabilitation Algorithm After Lateral Ankle Sprains in Professional Football (Soccer): An Approach Based on Clinical Practice Guidelines.

Lateral ankle sprain (LAS) is one of the most common types of injury in professional football (soccer) players with high risk of recurrence. The rehabilitation after LAS in professional football players is often still time-based and relies on anecdotal experience of clinicans. There is still a lack of utilization of criteria-based rehabilitation concepts after LAS in professional football. The aims of this clinical commentary are (1) to critically discuss the need for criteria-based rehabilitation concepts after LAS in professional football players, (2) to highlight the current lack of these approaches and (3) to present a novel clinical guideline-based rehabilitation algorithm. Short time-loss (15 days) and high recurrence rate (17%) raise the question of trivialization of LAS in professional football. Despite consequences for many stakeholders involved (players, teams, clubs, insurers), there is still a lack of of criteria-based, step-by-step approaches. The use of a criteria-based rehabilitation approach might reduce the high recurrence rate after LAS in professional football players and will lead, in turn, to increased long-term player availability. Practical experiences of he authors demonstrate the feasibility of such an approach. The effectiveness of this novel rehabilitation algorithm remains to be evaluated in future studies. Level of Evidence: 5.

Artificial intelligence derived categorizations significantly improve HOMA IR/ß indicators: Combating diabetes through cross-interacting drugs.

Improvements in the homeostasis model assessment of insulin resistance (HOMA-IR) and homeostasis model assessment of beta-cell function (HOMA-ß) significantly reduce the risk of disabling diabetic pathies. Nanoparticle (AuNP-AgNP)-metformin are concentration dependent cross-interacting drugs as they may have a synergistic as well as antagonistic effect(s) on HOMA indicators when administered concurrently. We have employed a blend of machine learning: Artificial Neural Network (ANN), and evolutionary optimization: multiobjective Genetic Algorithms (GA) to discover the optimum regime of the nanoparticle-metformin combination. We demonstrated how to successfully employ a tested and validated ANN to classify the exposed drug regimen into categories of interest based on gradient information. This study also prescribed standard categories of interest for the exposure of multiple diabetic drug regimen. The application of categorization greatly reduces the time and effort involved in reaching the optimum combination of multiple drug regimen based on the category of interest. Exposure of optimum AuNP, AgNP and Metformin to Diabetic rats significantly improved HOMA ß functionality (∼63 %), Insulin resistance (HOMA IR) of Diabetic animals was also reduced significantly (∼54 %). The methods explained in the study are versatile and are not limited to only diabetic drugs.

NeuroHealth Guardian: A Novel Hybrid Approach for Precision Brain Stroke Prediction and Healthcare Analytics.

Stroke is a severe illness, that requires early stroke detection and intervention, as this would help prevent the worsening of the condition. The research is done to solve stroke prediction problem, which may be divided into a number of sub-problems such as an individual's predisposition to develop stroke. To attain this objective, a multiturn dataset consisting of various health features, such as age, gender, hypertension, and glucose levels, takes a central role. A multiple approach was put forward concentrating on integrating the machine learning techniques, such as Logistic Regression, Naive Bayes, K-Nearest Neighbors, and Support Vector Machine (SV), together to develop an ensemble machine called Neuro-Health Guardian. The hypothesis "Neuro-Health Guardian Model" integrates these algorithms into one, purported to make stroke prediction more accurate. The topic dives into each instance of preparation of data for analysis, data visualization techniques, selection of the right model, training, testing, ensembling, evaluation, and prediction. The models are validated with error rate accounted from their accuracy, precision, recall, F1 score, and finally confusion matrices for a look. The study's result is showing that the ensemble model that combines the multiple algorithms has the edge over them and this is evidently by the fact that it can predict stroke rises. Additionally, accuracy, precision, recall, and F1 scores are measured in all models and the comparison is done to provide a clear comparison of the models' performance. In short, the article presented the formation of the ongoing stroke prediction that revealed the ensemble model as a good anticipation. Precise stroke predisposition forecasting can assist in early intervention thereby preventing stroke-related deaths, and limiting disability burden by stroke. The conclusions that have come out of this study offer a great action item for the development of predictive models related to stroke prevention and treatment.

Identifying interactions among factors related to death occurred at the scene of traffic accidents: Application of "logic regression" method.

Aim: Traffic accidents are caused by several interacting risk factors. This study aimed to investigate the interactions among risk factors associated with death at the accident scene (DATAS) as an indicator of the crash severity, for pedestrians, passengers, and drivers by adopting "Logic Regression" as a novel approach in the traffic field. Method: A case-control study was designed based on the police data from the Road Traffic Injury Registry in northwest of Iran during 2014-2016. For each of the pedestrians, passengers, and drivers' datasets, logic regression with "logit" link function was fitted and interactions were identified using Annealing algorithm. Model selection was performed using the cross-validation and the null model randomization procedure. Results: regarding pedestrians, "The occurrence of the accident outside a city in a situation where there was insufficient light" (OR = 6.87, P-value<0.001) and "the age over 65 years" (OR = 2.97, P-value<0.001) increased the chance of DATAS. "Accidents happening in residential inner-city areas with a light vehicle, and presence of the pedestrians in the safe zone or on the non-separate two-way road" combination lowered the chance of DATAS (OR = 0.14, P-value<0.001). For passengers, "Accidents happening in outside the city or overturn of the vehicle" combination (OR = 8.55, P-value<0.001), and "accidents happening on defective roads" (OR = 2.18, P-value<0.001) increased the odds of DATAS; When "driver was not injured or the vehicle was two-wheeled", chance of DATAS decreased for passengers (OR = 0.25, p-value<0.001). The odds of DATAS were higher for "drivers who had a head-on accident, or drove a two-wheeler vehicle, or overturned the vehicle" (OR = 4.03, P-value<0.001). "Accident on the roads other than runway or the absence of a multi-car accident or an accident in a non-residential area" (OR = 6.04, P-value<0.001), as well "the accident which occurred outside the city or on defective roads, and the drivers were male" had a higher risk of DATAS for drivers (OR = 5.40, P-value<0.001). Conclusion: By focusing on identifying interaction effects among risk factors associated with DATAS through logic regression, this study contributes to the understanding of the complex nature of traffic accidents and the potential for reducing their occurrence rate or severity. According to the results, the simultaneous presence of some risk factors such as the quality of roads, skill of drivers, physical ability of pedestrians, and compliance with traffic rules play an important role in the severity of the accident. The revealed interactions have practical significance and can play a significant role in the problem-solving process and facilitate breaking the chain of combinations among the risk factors. Therefore, practical suggestions of this study are to control at least one of the risk factors present in each of the identified combinations in order to break the combination to reduce the severity of accidents. This may have, in turn, help the policy-makers, road users, and healthcare professionals to promote road safety through prioritizing interventions focusing on effect size of simultaneous coexistence of crash severity determinants and not just the main effects of single risk factors or their simple two-way interactions.

Different type of pay later facility for green product with selling price dependent demand using grey wolf optimizer.

The use of trade credit finance is becoming more widely acknowledged as a crucial approach to improving inventory system profitability. We review an inventory model with depending on permitted payment delays for which, if the retailer place an orders higher than or equal to a predefined quantity S 1 , then the supplier will provide a fully pay in later facility of ξ periods (i.e., there will be no charge of interest until ξ ). On the other hand the retailer need to pay a partial amount of payment to the supplier if the order quantity is less than S 1 , and the remaining amount may be deferred for up to ξ periods. Main objective of this study is to investigate the inventory model with different situations under delayed payment facility. In addition, determining the product's demand also involves taking into account the item's greenness and selling price. We have also considered the fact that the cost of buying is influenced by the product's degree of greenness. We employ the meta heuristic algorithm Grey Wolf Optimizar (GWO) to assist us in solving the problem, and we compare the outcomes with the aid of a few other algorithms (Whale optimisation algorithm (WOA) and Artificial electric field algorithm (AEFA)). In the end, we resolve several numerical cases to support the model. The concavity of the desired function is graphically displayed using MATLAB software.

Utilizing AI and IoT technologies for identifying risk factors in sports.

A dynamic cooperation is poised to redefine the limits of athlete safety and performance optimization in the dynamic field of sports science. A new age in sports analysis is promised by the combination of artificial intelligence (AI) and the internet of things (IoT), one in which data-driven insights not only improve our comprehension of athletic performance but also aid to reduce hazards. This academic work explores the complex interactions between AI and IoT in the context of sports. The IoT and AI integration appear to be a strong mix that has the potential to redefine the standards for athlete safety and performance improvement. This study explores the complex interactions between AI and IoT in the field of sports, emphasizing their combined potential for identifying risk factors in a variety of fields. There is a chance to proactively solve sports-related difficulties by utilizing the data-driven capabilities of IoT and the analytical power of AI, opening the door for better informed tactics and decision-making. Through an exploration of this symbiotic relationship, this paper seeks to underline the transformative potential of these technologies in fostering a safer and more performance-oriented sports environment.

EfficientMaize: A Lightweight Dataset for Maize Classification on Resource-Constrained Devices.

Hyperspectral imaging, combined with deep learning techniques, has been employed to classify maize. However, the implementation of these automated methods often requires substantial processing and computing resources, presenting a significant challenge for deployment on embedded devices due to high GPU power consumption. Access to Ghanaian local maize data for such classification tasks is also extremely difficult in Ghana. To address these challenges, this research aims to create a simple dataset comprising three distinct types of local maize seeds in Ghana. The goal is to facilitate the development of an efficient maize classification tool that minimizes computational costs and reduces human involvement in the process of grading seeds for marketing and production. The dataset is presented in two parts: raw images, consisting of 4,846 images, are categorized into bad and good. Specifically, 2,211 images belong to the bad class, while 2,635 belong to the good class. Augmented images consist of 28,910 images, with 13,250 representing bad data and 15,660 representing good data. All images have been validated by experts from Heritage Seeds Ghana and are freely available for use within the research community.

Collaborative Human-Computer Vision Operative Video Analysis Algorithm for Analyzing Surgical Fluency and Surgical Interruptions in Endonasal Endoscopic Pituitary Surgery: Cohort Study.

BACKGROUND: The endonasal endoscopic approach (EEA) is effective for pituitary adenoma resection. However, manual review of operative videos is time-consuming. The application of a computer vision (CV) algorithm could potentially reduce the time required for operative video review and facilitate the training of surgeons to overcome the learning curve of EEA. OBJECTIVE: This study aimed to evaluate the performance of a CV-based video analysis system, based on OpenCV algorithm, to detect surgical interruptions and analyze surgical fluency in EEA. The accuracy of the CV-based video analysis was investigated, and the time required for operative video review using CV-based analysis was compared to that of manual review. METHODS: The dominant color of each frame in the EEA video was determined using OpenCV. We developed an algorithm to identify events of surgical interruption if the alterations in the dominant color pixels reached certain thresholds. The thresholds were determined by training the current algorithm using EEA videos. The accuracy of the CV analysis was determined by manual review, and the time spent was reported. RESULTS: A total of 46 EEA operative videos were analyzed, with 93.6%, 95.1%, and 93.3% accuracies in the training, test 1, and test 2 data sets, respectively. Compared with manual review, CV-based analysis reduced the time required for operative video review by 86% (manual review: 166.8 and CV analysis: 22.6 minutes; P<.001). The application of a human-computer collaborative strategy increased the overall accuracy to 98.5%, with a 74% reduction in the review time (manual review: 166.8 and human-CV collaboration: 43.4 minutes; P<.001). Analysis of the different surgical phases showed that the sellar phase had the lowest frequency (nasal phase: 14.9, sphenoidal phase: 15.9, and sellar phase: 4.9 interruptions/10 minutes; P<.001) and duration (nasal phase: 67.4, sphenoidal phase: 77.9, and sellar phase: 31.1 seconds/10 minutes; P<.001) of surgical interruptions. A comparison of the early and late EEA videos showed that increased surgical experience was associated with a decreased number (early: 4.9 and late: 2.9 interruptions/10 minutes; P=.03) and duration (early: 41.1 and late: 19.8 seconds/10 minutes; P=.02) of surgical interruptions during the sellar phase. CONCLUSIONS: CV-based analysis had a 93% to 98% accuracy in detecting the number, frequency, and duration of surgical interruptions occurring during EEA. Moreover, CV-based analysis reduced the time required to analyze the surgical fluency in EEA videos compared to manual review. The application of CV can facilitate the training of surgeons to overcome the learning curve of endoscopic skull base surgery. TRIAL REGISTRATION: ClinicalTrials.gov NCT06156020; https://clinicaltrials.gov/study/NCT06156020.