Manual Work Research Articles

Few-shot sheep counting based on density map regression

With the continuous expansion of breeding scale, the automatic counting of sheep has attracted a lot of research attention in recent years, which aims to count the number of sheep in real time to rationally use grassland resources and design appropriate agricultural production policies. The traditional method of counting sheep mainly relies on manual work, which is time-consuming and labor-intensive. Thanks to the rapid development of image acquisition equipment and pattern recognition technology, the recognition and counting of sheep based on deep learning has become the current mainstream counting framework. However, for dense flocks of sheep, such as occlusions between sheep, the accuracy of existing methods cannot meet the needs of practical applications. In this paper, we suggest FamNet, a few-shot sheep counting method based on UAV images and density map regression. Specifically, we first collected 190 sheep images with different resolutions, aspect ratios, backgrounds, and sheep numbers; secondly, by selecting count samples to extract objects in the images, and using density map regression to predict the number of sheep, this enables sheep counting in small numbers of samples. A large number of experimental results have verified the effectiveness of the method in this paper, which can achieve an average counting accuracy of 91.02%. In addition, we discuss the impact of sample selection, backbone selection, and feature scaling on model accuracy. All the results show that the FamNet flock counting method proposed in this paper can be applied to flock counting, has good adaptability to flock counting under different background conditions and can count the number of flocks in a timely and effective manner.

Effective Disciplinary Strategies to Combating Indiscipline in Public Senior High Schools in Kumasi, Ghana

Purpose: The effective ways of handling misbehaviour in school is rarely deliberated upon by policy makers and educators. This research studied the effective strategies used in Public Senior High Schools in the Kumasi Metropolis of Ghana.
 Methodology: The mixed-method approach was used to gather both qualitative and quantitative data with structured questionnaires and interview guides.
 Findings: The analysis suggests that 92.21% of parents favoured suspension over rewards (9.03%). Teachers (86.74%) favoured referring students to the disciplinary committee over writing bad comments on students’ reports (34.8%). Students (86.13%) preferred use of reward to caning (57.07%) as most effective disciplinary strategy. The analysis of variance (ANOVA) further suggested a significant difference in the perspective of parents, teachers and students on the most effective disciplinary strategies like rewards (P≤0.001), inviting parents (P≤0.000), negative testimonials (P≤0.000), suspension (P≤0.000), disciplinary committee (P≤0.000), manual work (P≤0.000), and caning (P≤0.000). The managers support the use of counselling, cleaning, weeding, reflection and repeating a class as effective.
 Unique Contribution to theory and practice: This study concludes with the proposition that disciplinary committee processes, suspensions and rewards for students are effective in handling student misbehaviour. It is recommended that parents, teachers, students and managers work together as collaborators in ensuring effective discipline in the school.

Analisis Pengaruh Artificial Intelligence Berbasis Images Preprocessing dalam Implementasi Deteksi Kematangan Buah Tomat

Technological developments continue to increase not only in the industrial sector, but have also spread to the agricultural sector, including the tomato farming process. Currently, the stage of harvesting tomatoes no longer relies on manual work, but instead utilizes artificial intelligence technology based on images preprocessing. This research aims to see whether the independent variable (AI effectiveness) has an influence on the dependent variable (tomato ripeness level). The method used is qualitative with simple linear regression data analysis techniques which include the t test and f test. The sample used was a random sampling technique with data collection by distributing questionnaires to a total of 48 respondents. The research results show that the effectiveness of AI has a positive effect on the level of ripeness of tomato fruit. This can be proven from a simple linear regression analysis to obtain the equation Y = 3.498 + 0.787X. The findings from the ttest show that tcount (7.644) > ttable (2.012) with a significance of 0.001 < 0.05. Therefore, the conclusion drawn is to accept the alternative hypothesis (H1) while rejecting the null hypothesis (H0).

Digitalization of accounting: advantages and challenges in the era of digital technologies

Introduction. In the conditions of the development of society and the transition of enterprises to the information type of economy, there is a need to generate ideas, and creative thinking of personnel, release innovative products, increase the company's intangible assets, and create a positive image as a basis for ensuring the development of entrepreneurial skills. Therefore, the issue of the formation and development of entrepreneurial competencies in the modern conditions of digitalization of the economy is gaining special importance and relevance. The driving force of the digital economy is the demand for innovative digital technologies, which today are used in completely different spheres of social and economic life. Digital transformation of a business, which is a transformation through the revision of its business strategy, models, operations, goals, marketing approaches, and products through the adoption of digital technologies, is impossible without the implementation of digital technologies in the development of the accounting system. However, the digitalization of accounting opens not only new opportunities for enterprises but also creates additional risks. The purpose of the paper is to specify the advantages and disadvantages of using digital technologies in accounting. Results. The conducted research has allowed defining the essence of digitization and outlining the possibilities of its application for the development of accounting in modern Ukrainian enterprises. The state of utilization of contemporary digital technologies in the context of accounting has been diagnosed. The opportunities provided by the implementation of modern digital technologies in the field of accounting have been specified, and the risks associated with the use of such technologies have been identified. The obtained results can be useful for enterprise managers to substantiate the possible directions of digitization of accounting, taking into account the advantages and disadvantages outlined in the paper. Conclusions. The key conclusion from the study is a generalization of the advantages and disadvantages of digitization of accounting. Accordingly, the automation of manual work and optimization of data storage are the main advantages, and the high cost of implementation and provision of technical support is a disadvantage.

AddBiomechanics: Automating model scaling, inverse kinematics, and inverse dynamics from human motion data through sequential optimization.

Creating large-scale public datasets of human motion biomechanics could unlock data-driven breakthroughs in our understanding of human motion, neuromuscular diseases, and assistive devices. However, the manual effort currently required to process motion capture data and quantify the kinematics and dynamics of movement is costly and limits the collection and sharing of large-scale biomechanical datasets. We present a method, called AddBiomechanics, to automate and standardize the quantification of human movement dynamics from motion capture data. We use linear methods followed by a non-convex bilevel optimization to scale the body segments of a musculoskeletal model, register the locations of optical markers placed on an experimental subject to the markers on a musculoskeletal model, and compute body segment kinematics given trajectories of experimental markers during a motion. We then apply a linear method followed by another non-convex optimization to find body segment masses and fine tune kinematics to minimize residual forces given corresponding trajectories of ground reaction forces. The optimization approach requires approximately 3-5 minutes to determine a subject's skeleton dimensions and motion kinematics, and less than 30 minutes of computation to also determine dynamically consistent skeleton inertia properties and fine-tuned kinematics and kinetics, compared with about one day of manual work for a human expert. We used AddBiomechanics to automatically reconstruct joint angle and torque trajectories from previously published multi-activity datasets, achieving close correspondence to expert-calculated values, marker root-mean-square errors less than 2 cm, and residual force magnitudes smaller than 2% of peak external force. Finally, we confirmed that AddBiomechanics accurately reproduced joint kinematics and kinetics from synthetic walking data with low marker error and residual loads. We have published the algorithm as an open source cloud service at AddBiomechanics.org, which is available at no cost and asks that users agree to share processed and de-identified data with the community. As of this writing, hundreds of researchers have used the prototype tool to process and share about ten thousand motion files from about one thousand experimental subjects. Reducing the barriers to processing and sharing high-quality human motion biomechanics data will enable more people to use state-of-the-art biomechanical analysis, do so at lower cost, and share larger and more accurate datasets.

A Review on Smart Canteen Management System

Abstract: The Smart Canteen App is a cutting-edge digital solution designed to revolutionize the traditional canteen experience in educational institutions, corporate offices, and other food service environments. This innovative mobile application leverages technology to streamline the entire process of ordering, payment, and food pickup, enhancing convenience and efficiency for both customers and canteen operators. By integrating modern technology, the Smart Canteen App offers an efficient, convenient, and user-centric dining experience, benefiting both customers and canteen operators. In today’s fast-moving world, there is a need of quick and efficient service in every sector of life for public in general. There are many employees and students use canteen and food facilities in their workplace and institutions on daily basis, there is a need to provide quick service at billing counters. This work is focused at developing an efficient smart canteen management system. As canteen in colleges get extremely crowded nowadays, so in this project, concentrate on fast service of food to the users to reduce paper work and save the time of the student by avoiding long queue and to keep things organized. This will satisfy all the customers need and overall sale of the canteen will increase. This application program reduces the manual work for managing the Canteen. Students can place their order through the emenu available on the mobile application which would be further transferred to the canteen. The student can therefore know their order details and the order progress through the mobile application. The canteen manages the students order and keeps updating the progress of the order through their web application. The admin manages the student and canteen through the web application. The app boasts an intuitive user interface that enables users to browse through menus, select food items, and customize their orders with ease. The app facilitates online ordering, enabling customers to place their orders remotely, reducing waiting times, and ensuring their meals are ready when they arrive. Users can customize their orders to accommodate dietary restrictions, allergies, and personal preferences, ensuring a personalized dining experience. Secure payment options are integrated into the app, allowing users to make cashless

Mendelian randomization analysis reveals the impact of physical and occupational activities on the risk of gastroesophageal reflux disease and Barrett’s esophagus

Background Recent studies have indicated that participating in physical activity may provide a safeguard against gastroesophageal reflux disease (GERD). Nevertheless, the precise links between physical and occupational activity and the occurrence of GERD and Barrett’s esophagus (BE) are still uncertain. Methods Conducting univariate and multivariate Mendelian randomization investigations to examine the causal relationship between exposures and outcomes. Genetic variation simulation was used in randomized experiments. Data on physical and occupational activity were obtained from the UK Biobank and GWAS catalog. In the meantime, data on GERD and BE were extracted from a high quality meta-analysis. Results The results of univariate Mendelian randomization analysis using multiple methods suggest a causal relationship between strenuous sports or other forms of exercise (as a protective factor) and GERD/BE. At the same time, three types of occupational related physical activities, including heavy manual or physical work, shift work and walking or standing work, are risk factors for GERD/BE and have a causal relationship with them. These results were reconfirmed through multivariate Mendelian randomization analysis, which excluding the influence of other potential confounding factors. Conclusions The findings indicated that strenuous sports or other forms of exercise could lower the likelihood of GERD/BE, while excessive physical strain in the workplace, prolonged periods of standing or walking, and shift work could raise the risk of GERD/BE. Acknowledging this risk and implementing suitable measures can contribute to the prevention of GERD and BE, thus mitigating the associated health burden.

The fuzzy human-robot collaboration assembly line balancing problem

Consideration is given to the assembly line balancing problem (ALBP) in production lines employed collaborative robots. Human–robot collaboration promises high advantages in manufacturing regarding automation, productivity, accuracy as well as flexibility in production. This technology is really challenging but requires redesigning of assembly lines to effectively involve the available human- and robot-resources. As robots can collaborate with humans sharing the assembly tasks in the same workstation, production managers experience an increasingly complex ALBP setting. Moreover, a crucial issue raised within this context is the variance and uncertainty in processing times for manual (human) work. Processing times for human work are subject to the nature and skills of the human worker. We explore the heuristic solution of this NP-hard problem using a problem-specific metaheuristic. Our aim is to investigate the effects of utilizing collaborate robots in manual assembly lines with respect to both production rate and workload smoothing. Simulation experiments on a real-life case study borrowed from the literature show how to tackle the problem under uncertainty (fuzziness) in task processing times.

Point Cloud-Based Smart Building Acceptance System for Surface Quality Evaluation

The current expansion of building structures has created a demand for efficient and smart surface quality evaluation at the acceptance phase. However, the conventional approach mainly relies on manual work, which is labor-intensive, time-consuming, and unrepeatable. This study presents a systematic and practical solution for surface quality evaluation of indoor building elements during the acceptance phase using point cloud. The practical indoor scanning parameters determination procedure was proposed by analyzing the project requirements, room environment, and apparatus. An improved DBSCAN algorithm was developed by introducing a plane validation and coplanar checking to facilitate the surface segmentation from the point cloud. And a revised Least Median of Square-based algorithm was proposed to identify the best-fit plane. Afterwards, the flatness, verticality, and squareness were evaluated and depicted using a color-coded map based on the segmented point cloud. The experiment on an apartment showcases how the system improves the information flow and accuracy during building acceptance, resulting in a potentially smart acceptance activity.

Automatic craniomaxillofacial landmarks detection in CT images of individuals with dentomaxillofacial deformities by a two-stage deep learning model

BackgroundAccurate cephalometric analysis plays a vital role in the diagnosis and subsequent surgical planning in orthognathic and orthodontics treatment. However, manual digitization of anatomical landmarks in computed tomography (CT) is subject to limitations such as low accuracy, poor repeatability and excessive time consumption. Furthermore, the detection of landmarks has more difficulties on individuals with dentomaxillofacial deformities than normal individuals. Therefore, this study aims to develop a deep learning model to automatically detect landmarks in CT images of patients with dentomaxillofacial deformities.MethodsCraniomaxillofacial (CMF) CT data of 80 patients with dentomaxillofacial deformities were collected for model development. 77 anatomical landmarks digitized by experienced CMF surgeons in each CT image were set as the ground truth. 3D UX-Net, the cutting-edge medical image segmentation network, was adopted as the backbone of model architecture. Moreover, a new region division pattern for CMF structures was designed as a training strategy to optimize the utilization of computational resources and image resolution. To evaluate the performance of this model, several experiments were conducted to make comparison between the model and manual digitization approach.ResultsThe training set and the validation set included 58 and 22 samples respectively. The developed model can accurately detect 77 landmarks on bone, soft tissue and teeth with a mean error of 1.81 ± 0.89 mm. Removal of region division before training significantly increased the error of prediction (2.34 ± 1.01 mm). In terms of manual digitization, the inter-observer and intra-observer variations were 1.27 ± 0.70 mm and 1.01 ± 0.74 mm respectively. In all divided regions except Teeth Region (TR), our model demonstrated equivalent performance to experienced CMF surgeons in landmarks detection (p > 0.05).ConclusionsThe developed model demonstrated excellent performance in detecting craniomaxillofacial landmarks when considering manual digitization work of expertise as benchmark. It is also verified that the region division pattern designed in this study remarkably improved the detection accuracy.

Comparative descriptive analysis of socio-demographic status in immunocompetent and immunocompromised patients with mycoses of the skin, hair and nails

BACKGROUND: Despite the achievements of modern medicine, people's susceptibility to fungal infections is only increasing. In this regard, it is extremely important to understand which social factors are most characteristic of people suffering from mycoses of the skin, hair and nails.
 AIM: to study the socio-demographic status of immunocompetent and immunocompromised patients with mycoses of skin, hair and nails.
 MATERIALS AND METHODS: A multicenter prospective cohort observational study of the social and demographic characteristics of immunocompetent and immunocompromised individuals with mycoses of the skin of hair and nails was conducted. Four groups of patients were formed: immunocompetent persons, persons with diabetes mellitus, patients with autoimmune diseases while taking immunosuppressants, patients with infection human immunodeficiency virus (HIV). A total of 646 people were examined. To ensure the quality of research and information processing, questionnaires were developed to be filled in for each examined patient. At the time of inclusion in the study, data concerning the place of residence and living conditions of patients, their lifestyle, marital status, bad habits and profession were entered into the questionnaires.
 RESULTS: Significant differences (p 0.0001) were revealed between the studied socio- demographic characteristics in the study groups. The age of immunocompetent patients with mycoses of skin, hair and nails was 914 years lower than the age of immunocompromised. Female persons prevailed in the case of autoimmune diseases ― 71.1%. Harmful habits were registered in 60% of patients with superficial mycoses and HIV. 83.33% of autoimmune patients were married. Urban residents prevailed over rural residents in the case of diabetes mellitus and autoimmune pathology. Persons of manual work professions in 48.48% of cases were identified among patients with HIV infection, which was more than in other study groups.
 CONCLUSION: When studying the socio- demographic characteristics of patients with mycoses of skin, hair and nails, significant differences were revealed in all the factors studied. The obtained results indicate the need to develop a personalized approach to the diagnosis, prevention and treatment of these infections.

Work-related factors and risk of amyotrophic lateral sclerosis: A multivariable Mendelian randomization study.

The causal relationship between work-related factors and amyotrophic lateral sclerosis (ALS) is unclear. We used a Mendelian randomization (MR) analysis to investigate the unconfounded association between work-related factors and ALS. Univariable MR analyses were conducted to evaluate the causal effects of work-related factors on ALS. Instrumental variables from the UK Biobank on work-related factors (n=263,615) were used as proxies. The outcome dataset used ALS (n case=20,806, n control=59,804) summary-level data from a large-scale genome-wide association study based on European ancestry. MR analysis used inverse variance weighted (IVW), MR-Egger, and weighted median (WM) to assess causal effects and other methods of MR for sensitivity analysis. Further multivariable MR analyses were performed to explore potential mediating effects. In univariable MR, IVW methods support evidence that genetically determined job involves heavy manual or physical work (OR=2.04, 95% CI: 1.26-3.31; p=.004) was associated with an increased risk of ALS, and the WM methods also confirm this result (OR=2.36, 95% CI: 1.30-4.28; p=.005). No evidence of heterogeneity or horizontal pleiotropy was found in the results. In multivariable MR, the association was absent after adjusting for smoking and blood pressure. Our MR analysis results demonstrate the potential causal relationship between jobs that involve heavy manual or physical work and ALS, which might be mediated by smoking and high systolic blood pressure.

The use of post-cycle therapy is associated with reduced withdrawal symptoms from anabolic-androgenic steroid use: a survey of 470 men

BackgroundAnabolic–androgenic steroids (AAS) mimic the effects of testosterone and may include testosterone itself; they are used for body enhancement within the general population. AAS use has been linked with increased mortality, cardiovascular disease, mental health disorders, and infertility. AAS-induced hypogonadism can persist for an uncertain time period despite cessation, during which men may report physical and neuropsychiatric symptoms. In an attempt to mitigate these symptoms and expedite testicular recovery, many men self-administer post-cycle-therapy (PCT), typically involving human chorionic gonadotrophin (hCG) and selective oestrogen receptor modulators (SERMs), which are known to potently stimulate testicular function. However, this practice has no objective evidence of effectiveness to lessen the severity or duration of hypogonadal symptoms.MethodsAn anonymous survey of four-hundred-and-seventy men using AAS explored the symptoms they experienced when ceasing AAS use; the effect of PCT on relieving their symptoms, and their perceived role for health service support.ResultsThe majority of respondents were white, aged 18–30 years old, and working in skilled manual work. 51.7% (n = 243) reported no issues with AAS use, but 35.3% reported increased aggression. 65.1% (n = 306) of respondents had attempted AAS cessation and 95.1% of these experienced at least one symptom upon AAS cessation. Low mood, tiredness and reduced libido were reported in 72.9%, 58.5% and 57.0% of men stopping AAS use, respectively, with only 4.9% reporting no symptoms. PCT had been used by 56.5% of respondents with AAS cessation and mitigated cravings to restart AAS use, withdrawal symptoms and suicidal thoughts by 60%, 60% and 50%, respectively. The effect of stopping AAS on body composition and recovery of testosterone or fertility was a concern in 60.5% and 52.4%, respectively. Most respondents felt PCT should be prescribed under medical supervision in the community.ConclusionsOur survey suggests that the majority of men stopping AAS use are using some form of PCT. Some self-reported symptoms of AAS-induced hypogonadism such as cravings to restart AAS use reduce by 60% and suicidal thoughts reduce by 50%. These individuals are concerned about the negative effect of AAS use and cessation. This study provides crucial information for planning future research to evaluate the effects of PCT on symptoms when men stop AAS use.

Automatic detection of charcoal kilns on Very High Resolution images with a computer vision approach in Somalia

In Somalia’s drylands, charcoal production is a major driver of forest degradation enabled by civil conflict and institutional weakness. Up to now, the extent and exact location of charcoal production has usually been estimated by visually detecting charcoal kilns on Very High Resolution (VHR) images. Taking advantage of the availability of a dataset of charcoal kilns delineated on VHR images by the Food and Agriculture Organization (FAO) experts, we designed a computer vision (CV) approach to automatically identify charcoal kilns on VHR images. The methodology relies on a curated subset of the expert-labeled dataset and a collection of panchromatic and pan-sharpened multispectral Natural Color (RGB) VHR for the years 2018 and 2019. Kiln delineations paired with the VHR images are visually reviewed and used with a Faster R-CNN model, an object detection deep learning method. A two-stage methodology is used to train the best models for panchromatic and RGB images, respectively. The first stage uses a small number of high quality pairs to define the best parameters of the models while the second stage uses a larger set of pairs to fine tune the previous models. The results indicates that charcoal kilns are detected with a precision of 90% in panchromatic images and of 80% in RGB images. The models are then used to predict the presence of kilns over the available VHR images. Omission errors are prioritized over commission errors to mitigate the difficulty in detecting kilns in some specific situations. Comparison between the FAO expert kiln dataset and objects predicted by the CNN model is giving encouraging results. With a visual screening complementing the proposed workflow, CV can aid charcoal kiln monitoring in Somalia while alleviating manual work.

A Computational Tool for Geometric Characterization of Pores and Fractures in Microtomography Rock Images

Pores and fractures are important structures for the study and characterization of fluid flow inside rocks. It is through them that there can be the propagation and conduction of fluids and chemical substances inside the reservoirs, since the connections between these spaces provide the existence of flow. To understand the behavior of these structures, we have developed a computational tool that, through the use of high resolution images derived from computed microtomography, aims to detect and characterize the geometry of pores and faults with the objective of being an environment that allows the detailed understanding of these structures. For this task, image processing techniques were applied to identify the structure of the contours, obtained through data segmentation, and to evaluate their geometric parameters in conjunction with the algorithms implemented in this work. With this, we seek to provide a tool capable of assisting in the characterization of reservoirs and fluid analysis, and to reduce the uncertainties found in manual work through a computational approach, prioritizing the preservation of important samples collected in the field.

Convolutional neural network in rice disease recognition: accuracy, speed and lightweight.

There are many rice diseases, which have very serious negative effects on rice growth and final yield. It is very important to identify the categories of rice diseases and control them. In the past, the identification of rice disease types was completely dependent on manual work, which required a high level of human experience. But the method often could not achieve the desired effect, and was difficult to popularize on a large scale. Convolutional neural networks are good at extracting localized features from input data, converting low-level shape and texture features into high-level semantic features. Models trained by convolutional neural network technology based on existing data can extract common features of data and make the framework have generalization ability. Applying ensemble learning or transfer learning techniques to convolutional neural network can further improve the performance of the model. In recent years, convolutional neural network technology has been applied to the automatic recognition of rice diseases, which reduces the manpower burden and ensures the accuracy of recognition. In this paper, the applications of convolutional neural network technology in rice disease recognition are summarized, and the fruitful achievements in rice disease recognition accuracy, speed, and mobile device deployment are described. This paper also elaborates on the lightweighting of convolutional neural networks for real-time applications as well as mobile deployments, and the various improvements in the dataset and model structure to enhance the model recognition performance.

Second chance: The paradox of felony convictions.

Every year, hundreds of thousands of individuals with felony convictions are released into the community with the expectation that those reentering society will be "successful" upon reentry. Society tells persons with criminal backgrounds they have a "second chance" upon release, yet we are reluctant to provide the resources necessary to make this happen. Stigma is frequently identified as a potential obstacle to reentry (DeFina & Hannon, 2009; Shivy et al., 2007); however, research examining stigma surrounding conviction and obstacles to employment for felony convictions is lacking. Interviews with 14 men with felonies were examined to identify how the stigma associated with felony convictions has affected their perceived choice of employment options, including the potential barriers they experience to employment. Participants reported postconviction obstacles, specifically employment/job-related obstacles. They discussed experiencing stigma related to their felony convictions and described strategies employed to mitigate that stigma. Participants' work history involved largely manual labor work, and they discussed having work aspirations despite their felony convictions. Implications for counseling, future research, and limitations are discussed. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

A White-Box Testing for Deep Neural Networks Based on Neuron Coverage.

With the introduction of neuron coverage as a testing criterion for deep neural networks (DNNs), covering more neurons to detect more internal logic of DNNs became the main goal of many research studies. While some works had made progress, some new challenges for testing methods based on neuron coverage had been proposed, mainly as establishing better neuron selection and activation strategies influenced not only obtaining higher neuron coverage, but also more testing efficiency, validating testing results automatically, labeling generated test cases to extricate manual work, and so on. In this article, we put forward Test4Deep, an effective white-box testing DNN approach based on neuron coverage. It is based on a differential testing framework to automatically verify inconsistent DNNs' behavior. We designed a strategy that can track inactive neurons and constantly triggered them in each iteration to maximize neuron coverage. Furthermore, we devised an optimization function that guided the DNN under testing to deviate predictions between the original input and generated test data and dominated unobservable generation perturbations to avoid manually checking test oracles. We conducted comparative experiments with two state-of-the-art white-box testing methods DLFuzz and DeepXplore. Empirical results on three popular datasets with nine DNNs demonstrated that compared to DLFuzz and DeepXplore, Test4Deep, on average, exceeded by 32.87% and 35.69% in neuron coverage, while reducing 58.37% and 53.24% testing time, respectively. In the meantime, Test4Deep also produced 58.37% and 53.24% more test cases with 23.81% and 98.40% fewer perturbations. Even compared with the two highest neuron coverage strategies of DLFuzz, Test4Deep still enhanced neuron coverage by 4.34% and 23.23% and achieved 94.48% and 85.67% higher generation time efficiency. Furthermore, Test4Deep could improve the accuracy and robustness of DNNs by merging generated test cases and retraining.

A Comprehensive Approach for Monitoring Student Satisfaction in Blended Learning Courses

Abstract Due to the great importance of student satisfaction with educational services, many HEIs conduct annual surveys. Analyzing the results of such surveys, tracking trends, and comparing the evaluation results to help governing bodies make data-driven decisions to take measures to improve the quality of courses is time-consuming and requires a lot of manual work. As a solution to the problem, this paper proposes a comprehensive approach to monitoring student satisfaction with the quality of blended learning courses. The developed software tool analyzes results and enables users with different roles to generate reports with aggregated results at different levels, allowing them to make informed decisions and take measures to ensure a higher quality of courses. The generated reports during the pilot experiments proved the tool’s applicability. This tool can be implemented in any HEI, regardless of the software systems used.

Medicine-Shelf matching strategy based on Bayesian convolutional neural network with fuzzy analytic hierarchy process

In pharmaceutical warehousing operations, a scientific and reasonable medicine and shelf matching strategy can improve medicine shelving efficiency and manual work efficiency. However, the traditional matching strategy has the problems of static matching and low matching efficiency, so this paper proposes the matching algorithm for drugs and shelves based on the fuzzy analytic hierarchy process and Bayesian convolutional neural network (FAHP-BCNN). First, we propose a drug-shelf matching degree model and discuss the influence of the dynamic matching process on the matching results by studying two parts: the attribute matching degree and the dynamic matching influence degree. Secondly, this paper quantitatively assessed the importance of the two matches by means of the fuzzy analytic hierarchy process. Finally, we mapped the massive matching information onto Bayesian convolutional neural network nodes, constructed a dynamic matching network model, and obtained competitive matching strategies and results. The experimental results show that the FAHP-BCNN algorithm exhibits better matching results in all three scenarios with different quantity ratios of drugs and shelf matching. Compared with the fixed cargo matching strategy of the ABC classification method, the FAHP-BCNN algorithm shows excellent performance in both the manual walking distance index and fatigue index. In summary, the drug-shelf matching algorithm based on FAHP-BCNN is effective and can provide theoretical support for pharmaceutical warehousing enterprises to perform drug-shelf matching.