Classification Technology Research Articles

Advancements in Emotion Classification via Facial and Body Gesture Analysis: A Survey

ABSTRACTMachine vision has had a substantial impact on human‐computer interaction and psychological research. The ability of robots to generate realistic facial expressions has been enhanced by advancements in artificial intelligence, neural networks, and deep learning, thereby nurturing more profound emotive connections between humans and machines. This paper offers an in‐depth look of the most recent developments in emotion classification technologies, with a specific focus on the period from 2019 to 2023. This research addresses the integration of facial and body gesture analysis into emotion detection, emphasising the development of methods such as partial transfer learning, sign‐based measurement systems, and lightweight convolutional neural networks. By analysing the most recent research, the paper not only provides a comprehensive overview of the most advanced methods, but also emphasises their superiority over previous approaches in terms of efficiency, and applicability. The integration of gestures into emotion analysis is underscored as a critical area for further investigation, providing novel opportunities for comprehending and interpreting the intricate layers of nonverbal communication. The objective of this survey is to provide a resource for researchers and practitioners who are interested in advancing the field of emotion classification by utilising innovative methodologies.

Classification of Rice Grains by Image Processing

General Background: The assessment of the surface quality of pre-treated rice grains is crucial for determining their market acceptability, storage stability, processing quality, and overall consumer satisfaction. Traditional evaluation methods are often time-consuming and yield subjective classifications. Specific Background: The lack of a comprehensive tagged image dataset hinders the application of advanced convolutional neural networks (CNN) for detailed damage classification of healthy rice grains. Knowledge Gap: Existing datasets and methods limit the effective exploration of sophisticated CNN models for categorizing rice types, particularly in identifying subtle damage characteristics. Aims: The study aims to create a robust rice grain classification system using image processing techniques, primarily deep learning algorithms, to improve the classification of rice varieties. Results: Utilizing a dataset of 75,000 images across five widely cultivated rice varieties in Turkey, we achieved classification accuracies of 100% for CNN, 99.95% for deep neural networks (DNN), and 99.87% for artificial neural networks (ANN). Novelty: The proposed approach represents a significant advancement in rice classification technology, employing a combination of image acquisition, feature extraction, and machine learning to streamline the process, effectively addressing the challenges faced in traditional methods. Implications: The findings underscore the potential for improved sorting and grading efficiency in the rice industry, facilitating better market outcomes and consumer satisfaction through enhanced quality control Highlights: Innovative: Uses CNN for accurate rice variety classification. Data-Driven: Analyzes 75,000 images for enhanced quality evaluation. Impactful: Increases efficiency in sorting and grading processes. Keywords: Rice Classification, Image Processing, CNN, Machine Learning, Agricultural Technology

Robot terrain classification based on improved Hilbert-Huang transform and long short-term memory network

Nowadays, with the rapid development of science and technology, the innovation and application of robot technology has become an important force to promote industrial development, which requires robots to have a high degree of autonomy and adaptability. Among them, terrain classification technology is one of the key technologies to achieve this goal. In order to improve the ground adaptability of robots in complex environments, this paper proposes a terrain classification algorithm based on improved Hilbert-Huang transform(HHT) combined with ensemble empirical mode decomposition(EEMD) and long short-term memory network(LSTM). Firstly, the signal data is processed by EEMD, and then the frequency domain features of the signal are extracted by Hilbert transform to expand the feature dimension. Finally, the features are learned and classified by the LSTM model, which effectively improves the classification accuracy. In this paper, we conducted sufficient experiments to compare the effects of EMD and EEMD and the effects of different neural network models, and verified the contribution of the Hilbert-Huang transform to improve the classification performance through ablation experiments, which proves the effectiveness and reliability of our proposed algorithm, and provided powerful technical support for the robot to adapt to the ground information in the complex environment.

Hazard Analysis for Massive Civil Aviation Safety Oversight Reports Using Text Classification and Topic Modeling

There are massive amounts of civil aviation safety oversight reports collected each year in the civil aviation of China. The narrative texts of these reports are typically short texts, recording the abnormal events detected during the safety oversight process. In the construction of an intelligent civil aviation safety oversight system, the automatic classification of safety oversight texts is a key and fundamental task. However, all safety oversight reports are currently analyzed and classified into categories by manual work, which is time consuming and labor intensive. In recent years, pre-trained language models have been applied to various text mining tasks and have proven to be effective. The aim of this paper is to apply text classification to the mining of these narrative texts and to show that text classification technology can be a critical element of the aviation safety oversight report analysis. In this paper, we propose a novel method for the classification of narrative texts in safety oversight reports. Through extensive experiments, we validated the effectiveness of all the proposed components. The experimental results demonstrate that our method outperforms existing methods on the self-built civil aviation safety oversight dataset. This study undertakes a thorough examination of the precision and associated outcomes of the dataset, thereby establishing a solid basis for furnishing valuable insights to enhance data quality and optimize information.

ИННОВАЦИОННАЯ ПАРАДИГМА В КОНТЕКСТЕ ВЫСШЕГО ТЕХНИЧЕСКОГО ОБРАЗОВАНИЯ

The purpose of the article is to describe the experience of using the technology of developing critical thinking in the practical course of the Russian language in the technical university. The article considers efficient ways of applying elements of technology of critical thinking development in practical classes in the Russian language. The classification technology of critical thinking development techniques carried out by the authors, which is based on three phases of learning, gradually replacing each other ("challenge — comprehension — reflection"), is successfully used in university practice. In technology of critical thinking development, the ability to work with questions occupy an important place. Technology of critical thinking development is focused on the questions which develops the mental activity of students. During reflection, students analyze the received information, exchange opinions, justify their point of view. At this stage, it is advisable to turn the acquired information into written form, since in the process of verbalization, new information is comprehended. In this aspect, it is important to instill in students the ability to summarize information. The use of technology of critical thinking development techniques in practical classes of the Russian language makes it possible to make students' educational activities more creative and productive. The organization of such classes, characterized by a certain logic of construction and sequence of combinations of specific tasks, develops the communicative competence of learners, teaches them to read thoughtfully and immerse themselves in information, organize and analyze information, define and solve problems, deal with a notion, conduct reasoned discussion, interpret, creatively process new information, reflect. The use of technology of critical thinking development techniques in Russian language classes contributes to the formation of students' skills to determine the value of an idea based on a critical and objective consideration of arguments.

Dry age-related macular degeneration classification from optical coherence tomography images based on ensemble deep learning architecture.

Dry age-related macular degeneration (AMD) is a retinal disease, which has been the third leading cause of vision loss. But current AMD classification technologies did not focus on the classification of early stage. This study aimed to develop a deep learning architecture to improve the classification accuracy of dry AMD, through the analysis of optical coherence tomography (OCT) images. We put forward an ensemble deep learning architecture which integrated four different convolution neural networks including ResNet50, EfficientNetB4, MobileNetV3 and Xception. All networks were pre-trained and fine-tuned. Then diverse convolution neural networks were combined. To classify OCT images, the proposed architecture was trained on the dataset from Shenyang Aier Excellence Hospital. The number of original images was 4,096 from 1,310 patients. After rotation and flipping operations, the dataset consisting of 16,384 retinal OCT images could be established. Evaluation and comparison obtained from three-fold cross-validation were used to show the advantage of the proposed architecture. Four metrics were applied to compare the performance of each base model. Moreover, different combination strategies were also compared to validate the merit of the proposed architecture. The results demonstrated that the proposed architecture could categorize various stages of AMD. Moreover, the proposed network could improve the classification performance of nascent geographic atrophy (nGA). In this article, an ensemble deep learning was proposed to classify dry AMD progression stages. The performance of the proposed architecture produced promising classification results which showed its advantage to provide global diagnosis for early AMD screening. The classification performance demonstrated its potential for individualized treatment plans for patients with AMD.

A Review of the Application of Hyperspectral Imaging Technology in Agricultural Crop Economics

China is a large agricultural country, and the crop economy holds an important place in the national economy. The identification of crop diseases and pests, as well as the non-destructive classification of crops, has always been a challenge in agricultural development, hindering the rapid growth of the agricultural economy. Hyperspectral imaging technology combines imaging and spectral techniques, using hyperspectral cameras to acquire raw image data of crops. After correcting and preprocessing the raw image data to obtain the required spectral features, it becomes possible to achieve the rapid non-destructive detection of crop diseases and pests, as well as the non-destructive classification and identification of agricultural products. This paper first provides an overview of the current applications of hyperspectral imaging technology in crops both domestically and internationally. It then summarizes the methods of hyperspectral data acquisition and application scenarios. Subsequently, it organizes the processing of hyperspectral data for crop disease and pest detection and classification, deriving relevant preprocessing and analysis methods for hyperspectral data. Finally, it conducts a detailed analysis of classic cases using hyperspectral imaging technology for detecting crop diseases and pests and non-destructive classification, while also analyzing and summarizing the future development trends of hyperspectral imaging technology in agricultural production. The non-destructive rapid detection and classification technology of hyperspectral imaging can effectively select qualified crops and classify crops of different qualities, ensuring the quality of agricultural products. In conclusion, hyperspectral imaging technology can effectively serve the agricultural economy, making agricultural production more intelligent and holding significant importance for the development of agriculture in China.

Advanced concept for noise monitoring in smart cities through wireless sensor units with AI classification technologies

The rapid urbanization in the cities has indicated the importance of sustainable development for creating smart cities with high quality of life. Environmental noise as one of the main concerns has to be addressed according to International Directives and Legislation. Traditional noise estimation methods are costly and time-consuming, but the emerging technologies like low-cost wireless sensor units (WSUs) offer more granular data collection and analysis. Requirements for more accurate assessment of the noise pollution by detecting the dominant noise sources impose the need to apply novel approaches in the technical systems for noise monitoring. To this aim, this paper investigates the advanced methods for noise monitoring through WSUs with AI classification technologies. The proposed concept of the device not only quantitively describes the noise pollution, but also tends to recognize the class of the disturbing sound events. The accuracy of the WSUs are configured by comparing the results with professional hand-held analyzer, showing powerful and affordable low-cost units able to publish results through cloud and fog computing based on the IoT and smart city technologies. The paper discusses the challenges for merging noise measurement technology and the AI algorithms to classify and quantify the different classes of sound events.

A-169 Artificial Intelligence based Complete Blood Count

Abstract Background The OLO device (Sight diagnostics, Israel) is an artificial intelligence based blood counter. OLO contains a fluorescent microscope and a camera embedded inside it. The pictures are processed by an image processing algorithm based on “machine-vision technology” to identify and quantify cells. The measurement analysis is accompanied by messages (flags) that are used to warn of deviations in the counted parameters, which help the operator refer the sample for microscopic analysis. In this study, we compared the results of 19 complete blood count (CBC) parameters obtained from OLO to the CBC parameters obtained from the ADVIA 2120 device (Siemens, USA). In addition we examined the reliability of OLO alerts (flags) by comparing it to the microscopic analysis findings. Methods 99 blood samples from patients aged >3 months were sampled by the ADVIA and OLO devices. Regression analysis was performed in comparing the results of 19 parameters between the devices. Specificity and sensitivity values ​​of the OLO device alerts were calculated. Results A good correlation was found for CBC parameters between OLO and ADVIA with Pearson correlation (R) of 0.992 (WBC), 0.985 (RBC), 0.991 (HB) and 0.983 (PLT). A fundamental difference in measurement and classification technologies between OLO and ADVIA lead to low correlation measured for monocytes. By comparing OLO alerts against blood smears findings, a total of 14 samples were alerted by OLO but only slight left shift/single pathological cell were found in the smears which is below threshold defined by the manufacturer. These 14 samples were transferred to the true positive category, therefore OLO device alerts showed sensitivity and specificity of 81.8% and 90% (respectively) in identifying pathological cells. Conclusions The comparison findings present a technology based on image processing and artificial intelligence that have a good correlation to the ADVIA reference device. In addition, OLO has the ability to warn of pathological findings even below the threshold defined by the manufacturer. The artificial learning is expected to be improved so that this device can integrate CBC and microscopic differentiation simultaneously, a great advantage to the hematology laboratories workflow.

The Functional Mechanisms through Which Artificial Intelligence Influences the Innovation of Green Processes of Enterprises

Green process innovation is an important strategy in the high-quality development of enterprises. Digital technology is becoming a key factor in helping businesses address environmental issues and contributes to their green process innovation and sustainable growth. Nevertheless, there is a lack of studies on how particular digital technology categories affect corporate green process innovation. Artificial intelligence (AI) is an important part of digitalization as it can provide new technical means and guidance for enterprise’s innovation of green processes. This study aims to fills this research gap by revealing the logical relationship between digital technology and the green development of enterprises. Using China’s A-share-listed companies as the research object from 2013 to 2022, this study employed a two-way fixed-effects model and investigated the impact of artificial intelligence (AI) on corporate green process innovation and the moderating effect of multidimensional intellectual capital. The results revealed that AI positively impacts corporate green process innovation. Human capital, structural capital, employed capital, and relational capital strengthen this positive effect. Robustness tests validated these conclusions. This study expands the literature on digital technology and corporate green innovation and provides a reference for enterprises to implement green practices using digital technology.

An ultra lightweight neural network for automatic modulation classification in drone communications

Unmanned aerial vehicle (UAV)-assisted communication based on automatic modulation classification (AMC) technology is considered an effective solution to improve the transmission efficiency of wireless communication systems, as it can adaptively select the most suitable modulation method according to the current communication environment. However, many existing deep learning (DL)-based AMC methods cannot be directly applied to UAV platform with limited computing power and storage space, because of the contradiction between accuracy and efficiency. This paper mainly studies the lightweight of DL-based AMC networks to improve adaptability in resource-constrained scenarios. To address this challenge, we propose an ultra-lightweight neural network (ULNN). This network incorporates a lightweight convolutional structure, attention mechanism, and cross-channel feature fusion technique. Additionally, we introduce data augmentation (DA) based on signal phase offsets during the model training process, aimed at improving the model’s generalization ability and preventing overfitting. Through experimental validation on the public dataset RML2016.10 A, the ULNN we proposed achieves an average precision of 62.83% with only 8815 parameters and reaches a peak classification accuracy of 92.11% at SNR = 10 dB. The experimental results show that ULNN can achieve high recognition accuracy while keeping the model lightweight, and is suitable for UAV platform with limited resources.

Metadata augmented deep neural networks for wild animal classification

Camera trap imagery has become an invaluable asset in contemporary wildlife surveillance, enabling researchers to observe and investigate the behaviors of wild animals. While existing methods rely solely on image data for classification, this may not suffice in cases of suboptimal animal angles, lighting, or image quality. This study introduces a novel approach that enhances wild animal classification by combining specific metadata (temperature, location, time, etc) with image data. Using a dataset focused on the Norwegian climate, our models show an accuracy increase from 98.4% to 98.9% compared to existing methods. Notably, our approach also achieves high accuracy with metadata-only classification, highlighting its potential to reduce reliance on image quality. This work paves the way for integrated systems that advance wildlife classification technology.

Pemasaran dan Peningkatan Kualitas Produk Intellimice Classifier dengan Implementasi Strategi STP (Segementasi, Targeting, Positioning)

The STAS-RG laboratory recently launched the Intellimice Classifier product, a groundbreaking innovation in biomedical and pharmaceutical research that offers advanced laboratory mouse classification technology to enhance research efficiency and accuracy. Although this product promises great potential, STAS-RG faces challenges in identifying the right market for this product. This study aims to identify optimal market opportunities by applying the STP (Segmenting, Targeting, Positioning) strategy and using qualitative methods, including in-depth interviews and field observations. The study results show that the most effective market segmentation includes healthcare institutions, particularly pharmaceutical companies, focusing on individuals aged 20-50, including students and professionals in related fields. The primary target market is pharmaceutical institutions that require efficient and accurate laboratory mouse classification tools to support their research. Intellimice Classifier is positioned as an advanced solution with competitive pricing, utilizing Sensor Computer Vision technology to meet various specific needs in genetic research, such as classifying the gender, weight, color, and size of mice. This study emphasizes the importance of a deep understanding of the market to design effective marketing strategies and tailor the product to customer needs. These findings provide valuable strategic insights for STAS-RG to formulate a more targeted and adaptive marketing approach, aiming to maximize the product's adoption and success in the ever-evolving market. This approach not only allows STAS-RG to effectively introduce the product but also to meet the specific needs of their target market.

Bibliometric Analysis of Smartwatches Adoption Using Scopus

Using the Scopus database, this report provides a bibliometric analysis of studies focusing on the adoption of smartwatches. Smartwatches have become a popular category of wearable technology, providing more features than just keeping track of the time. These features include productivity boosts, communication, and health monitoring. Although their growing appeal, a thorough examination of the academic literature on smartwatch adoption is necessary. This study's bibliometric analysis provides information about publishing patterns, well-known authors, and the development of this field's knowledge. This study improves our understanding of the factors affecting smartwatch adoption while highlighting areas for future research and improvement in this quickly developing sector by looking through a large dataset of academic articles.

Overview of Wind and Photovoltaic Data Stream Classification and Data Drift Issues

The development in the fields of clean energy, particularly wind and photovoltaic power, generates a large amount of data streams, and how to mine valuable information from these data to improve the efficiency of power generation has become a hot spot of current research. Traditional classification algorithms cannot cope with dynamically changing data streams, so data stream classification techniques are particularly important. The current data stream classification techniques mainly include decision trees, neural networks, Bayesian networks, and other methods, which have been applied to wind power and photovoltaic power data processing in existing research. However, the data drift problem is gradually highlighted due to the dynamic change in data, which significantly impacts the performance of classification algorithms. This paper reviews the latest research on data stream classification technology in wind power and photovoltaic applications. It provides a detailed introduction to the data drift problem in machine learning, which significantly affects algorithm performance. The discussion covers covariate drift, prior probability drift, and concept drift, analyzing their potential impact on the practical deployment of data stream classification methods in wind and photovoltaic power sectors. Finally, by analyzing examples for addressing data drift in energy-system data stream classification, the article highlights the future prospects of data drift research in this field and suggests areas for improvement. Combined with the systematic knowledge of data stream classification techniques and data drift handling presented, it offers valuable insights for future research.

Contemporary Methodologies for Identifying and Categorizing Microalgae: A Comprehensive Review and Future Perspectives

As more people become connected to the grid and the energy demand continues to increase, non-renewable energy sources are being consumed at a faster rate than they are being replaced. Microalgae, often referred to as "green gold" have shown great potential as a renewable energy source due to their unique characteristics. However, not all microalgae are suitable to use as replacements for traditional fossil fuels. Therefore, it is essential for researchers to accurately identify and classify microalgae based on their species and energy-producing capabilities. The main objective of this paper is to present a detailed summary of the current technologies employed in the classification and detection of microalgae. Both traditional manual microscopy and advanced artificial intelligence techniques such as machine learning and deep learning are covered in this overview. Furthermore, this paper offers a critical analysis of these technologies and provides suggestions for enhancing their effectiveness. Despite deep learning being the most advanced technology for microalgae classification and detection, there is still significant potential for future improvements that could further increase the accuracy.

Can technology-based intervention improve collaboration skills: a meta-analysis study

ABSTRACT Collaboration skills are essential in the 21st century. As technology becomes increasingly integrated into teamwork, many studies have found that technology plays an important role in the development of collaboration skills. However, it is difficult to determine the effect of technology-based intervention in this respect. To explore the relationship between technology-based intervention and collaboration skills, we conducted a meta-analysis of 39 studies of this topic reported in 34 articles. The results show that technology-based intervention has a positive correlation with collaboration skills. Moreover, multiple factors, including technology category, learning space, learning stage, discipline, and collaboration skills dimension, significantly moderate the relationship. These findings suggest that collaboration skills are closely related to technology and its application methods. Overall, this study not only comprehensively reveals the complex effect of technology-based intervention on collaboration skills, but the findings also have important implications for research on technology-based intervention in promoting such skills.

Application of deep learning-based Intrusion Detection System (IDS) in network anomaly traffic detection

This study discusses the application of deep learning technology in network intrusion detection systems (IDS) and focuses on a new model named CNN-Focal. First, reviewing traditional IDS technology, it analyzes its limitations in dealing with complex network traffic. Then, the design principle of the CNN-Focal model is described in detail, which uses threshold convolution and SoftMax multi-class classification technology to improve abnormal traffic detections accuracy and efficiency effectively. The experimental results show that CNN-Focal performs well on the open data set, demonstrating the potential and advantages of its application in the natural network environment and providing a new perspective and method for further research of deep learning in the field of network security in the future.

Deep learning and pre-training technology for encrypted traffic classification: A comprehensive review

Network traffic classification has long been a pivotal topic in network security. In the past two decades, methods like port-based classification, deep packet inspection, and machine learning approaches have significantly progressed. Still, they are now facing reduced effectiveness due to the evolving complexity of the Internet, new encryption protocols, and advanced defense strategies. Given the problem that traditional models cannot efficiently generalize encrypted traffic, two promising technology paths are currently: deep learning and pre-training. On the one hand, deep learning-based methods effectively dissect complex network structures and unearth pivotal relational patterns. These approaches excel due to the neural networks’ robust generalization capabilities, significantly boosting the accuracy and efficiency of recognition processes. Graph representation learning stands out as the most compelling contemporary model for such intricate analysis, adeptly revealing the critical relationships within network communication structures. We emphatically introduce mainstream deep learning-based methods, and the mechanism and scenarios are also analyzed. On the other hand, recognizing that although the analysis based on large models is the trend of the field, the application is truly limited now, we underscore the importance of pre-training, which aligns with the future trajectory toward the adoption of large-scale models in encrypted traffic analysis. The pre-trained model can overcome various defects of previous models and achieve more remarkable performance through its low labeled data dependency and strong scenario adaptability. We provide a comprehensive overview of existing pre-training-based approaches from the three stages of operation: input, pre-training, fine-tuning, and comparing representative relevant work. Finally, because of the current needs and the improvement space of the existing pre-training methods in the field, we synthetically analyze the challenges and opportunities for interested researchers to explore.

Perceptions of OT & OTA Practitioners on Assistive Technology Education

Abstract Date Presented 03/22/24 What assistive technology categories did you learn about in your OT or OTA program, and which do you use in practice? We will share the outcomes of our first and second larger-scale research studies. Primary Author and Speaker: Karen Dishman Additional Authors and Speakers: Juliana Bell, Leslie J. Hardman, Julie A. Duckart