Integration Of Deep Learning Research Articles

Integrating deep learning for visual question answering in Agricultural Disease Diagnostics: Case Study of Wheat Rust.

This paper presents a novel approach to agricultural disease diagnostics through the integration of Deep Learning (DL) techniques with Visual Question Answering (VQA) systems, specifically targeting the detection of wheat rust. Wheat rust is a pervasive and destructive disease that significantly impacts wheat production worldwide. Traditional diagnostic methods often require expert knowledge and time-consuming processes, making rapid and accurate detection challenging. We drafted a new, WheatRustDL2024 dataset (7998 images of healthy and infected leaves) specifically designed for VQA in the context of wheat rust detection and utilized it to retrieve the initial weights on the federated learning server. This dataset comprises high-resolution images of wheat plants, annotated with detailed questions and answers pertaining to the presence, type, and severity of rust infections. Our dataset also contains images collected from various sources and successfully highlights a wide range of conditions (different lighting, obstructions in the image, etc.) in which a wheat image may be taken, therefore making a generalized universally applicable model. The trained model was federated using Flower. Following extensive analysis, the chosen central model was ResNet. Our fine-tuned ResNet achieved an accuracy of 97.69% on the existing data. We also implemented the BLIP (Bootstrapping Language-Image Pre-training) methods that enable the model to understand complex visual and textual inputs, thereby improving the accuracy and relevance of the generated answers. The dual attention mechanism, combined with BLIP techniques, allows the model to simultaneously focus on relevant image regions and pertinent parts of the questions. We also created a custom dataset (WheatRustVQA) with our augmented dataset containing 1800 augmented images and their associated question-answer pairs. The model fetches an answer with an average BLEU score of 0.6235 on our testing partition of the dataset. This federated model is lightweight and can be seamlessly integrated into mobile phones, drones, etc. without any hardware requirement. Our results indicate that integrating deep learning with VQA for agricultural disease diagnostics not only accelerates the detection process but also reduces dependency on human experts, making it a valuable tool for farmers and agricultural professionals. This approach holds promise for broader applications in plant pathology and precision agriculture and can consequently address food security issues.

Artificial neural networks and medieval music

Abstract This article delves into the integration of deep learning and medieval musicology. The article explores the use of deep learning in analyzing and transcribing medieval music manuscripts, offering insights into historical musical styles and compositions. It addresses the challenges and opportunities of applying AI in medieval musicology, and provides a critical analysis of deep learning’s potential in enhancing our understanding of medieval music heritage. The discussion encompasses the study of medieval music and its cultural context, emphasizing the significance of manuscripts, treatises and iconography in musicological research. The integration of digital humanities and computational advancements in medieval musicology is highlighted, revealing how technological progress has been incorporated systematically into the study of complex cultural objects.

Enhancing Skin Cancer Diagnosis through the Integration of Deep Learning and Machine Learning Approaches

Skin cancer is a disease characterized by the uncontrolled proliferation of skin cells, typically manifesting as lesions or abnormal growths. Early diagnosis is critical for improving treatment outcomes. This study proposes an innovative approach to skin cancer diagnosis by integrating modern deep learning models with traditional machine learning algorithms. A three-phase methodology was developed. In the first phase, meaningful features were extracted from skin lesion images using various transfer learning models, including Xception, VGG16, ResNet152V2, InceptionV3, InceptionResNetV2, MobileNetV2, EfficientNetB2, and DenseNet201. In the second phase, dimensionality reduction was performed using Principal Component Analysis (PCA). In the final phase, the reduced feature sets were classified using K-Nearest Neighbors (KNN) and Random Forest (RF) algorithms. Experimental results demonstrated that the highest accuracy of 91.28% was achieved through the combination of DenseNet201 for feature extraction, PCA for dimensionality reduction, and Random Forest for classification. These findings highlight the effectiveness of integrating transfer learning models, dimensionality reduction techniques, and machine learning algorithms in enhancing the accuracy of skin cancer diagnosis.

Enhancing streamflow prediction in the Wujiang River basin: a two-stage decomposition approach with deep learning integration

ABSTRACT Global climate change and human activities have profoundly impacted the geological and hydrological processes in watersheds, increasing the challenges in streamflow prediction. In this study, we propose a streamflow prediction model based on deep learning and dual-mode decomposition specifically tailored for the Wujiang River basin, a significant tributary on the southern bank of the upper Yangtze River. This model effectively addresses the prediction error issue caused by high-frequency components through dual-mode decomposition of time-series data. The results demonstrate that employing the coupled complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN)–variational mode decomposition (VMD)–temporal convolutional network (TCN)–long short-term memory network (LSTM) model reduces prediction errors by at least 35% compared to single decomposition models. Furthermore, compared to individual TCN or LSTM models, the TCN–LSTM coupled model exhibits greater stability and higher prediction accuracy during training, with reductions in mean absolute error and root mean square error by 43.13 and 24.57%, respectively. This model holds promising prospects for application and can provide crucial insights for water resource management.

A Comparative Analysis of Machine Learning Algorithms for Big Data Applications in Predictive Analytics

As the volume and complexity of data continue to grow, predictive analytics has emerged as a vital tool for extracting actionable insights from big data, driving decision-making across various domains such as healthcare, finance, and e-commerce. However, selecting an appropriate machine learning algorithm for predictive analytics applications is challenging due to differences in algorithmic performance, computational requirements, and scalability, especially in the context of big data. This paper provides a comprehensive comparative analysis of popular machine learning algorithms utilized in predictive analytics, specifically focusing on their effectiveness and feasibility in big data environments. The study categorizes algorithms based on learning types—supervised, unsupervised, and reinforcement learning—and evaluates their performance across multiple dimensions: prediction accuracy, computational efficiency, scalability, and suitability for real-time analytics. Through a detailed analysis of algorithms, including linear regression, decision trees, support vector machines, neural networks, and clustering techniques, we assess each method’s strengths and limitations in handling large datasets. Additionally, the study introduces a series of metrics, such as accuracy, F1-score, and training time, as benchmarks for assessing the algorithms’ predictive capabilities and computational viability. A hypothetical case study demonstrates the application of these algorithms on a sample big data set, providing insights into their real-world performance across different predictive analytics scenarios. Visual data representations, including comparative tables and performance graphs, offer a clearer perspective on the trade-offs among algorithm choices. The findings highlight that while certain algorithms like random forests and neural networks achieve higher accuracy in prediction tasks, they may also require substantial computational resources, posing limitations for real-time processing in big data applications. This paper concludes with recommendations for selecting machine learning algorithms based on specific predictive analytics objectives, data characteristics, and processing requirements. Furthermore, it discusses the challenges associated with implementing these algorithms in big data contexts and explores potential advancements, such as the integration of deep learning and the use of distributed computing, as promising directions for enhancing predictive analytics performance in future applications.

Geometric neural network based on phase space for BCI-EEG decoding.

\textbf{Objective:} 
The integration of Deep Learning (DL) algorithms on brain signal analysis is still in its nascent stages compared to their success in fields like Computer Vision. This is particularly true for BCI, where the brain activity is decoded to control external devices without requiring muscle control.
Electroencephalography (EEG) is a widely adopted choice for designing BCI systems due to its non-invasive and cost-effective nature and excellent temporal resolution. Still, it comes at the expense of limited training data, poor signal-to-noise, and a large variability across and within-subject recordings. 
Finally, setting up a BCI system with many electrodes takes a long time, hindering the widespread adoption of reliable DL architectures in BCIs outside research laboratories. To improve adoption, we need to improve user comfort using, for instance, reliable algorithms that operate with few electrodes. 
\textbf{Approach:} Our research aims to develop a DL algorithm that delivers effective results with a limited number of electrodes. Taking advantage of the Augmented Covariance Method and the framework of SPDNet, we propose the \method{} architecture and analyze its performance and the interpretability of the results. The evaluation is conducted on 5-fold cross-validation, using only three electrodes positioned above the Motor Cortex. The methodology was tested on nearly 100 subjects from several open-source datasets using the Mother Of All BCI Benchmark (MOABB) framework. 
\textbf{Main results:} The results of our \method{} demonstrate that the augmented approach combined with the SPDNet significantly outperforms all the current state-of-the-art DL architecture in MI decoding. 
\textbf{Significance:} This new architecture is explainable and with a low number of trainable parameters.

GPT-Driven Radiology Report Generation with Fine-Tuned Llama 3.

The integration of deep learning into radiology has the potential to enhance diagnostic processes, yet its acceptance in clinical practice remains limited due to various challenges. This study aimed to develop and evaluate a fine-tuned large language model (LLM), based on Llama 3-8B, to automate the generation of accurate and concise conclusions in magnetic resonance imaging (MRI) and computed tomography (CT) radiology reports, thereby assisting radiologists and improving reporting efficiency. A dataset comprising 15,000 radiology reports was collected from the University of Medicine and Pharmacy of Craiova's Imaging Center, covering a diverse range of MRI and CT examinations made by four experienced radiologists. The Llama 3-8B model was fine-tuned using transfer-learning techniques, incorporating parameter quantization to 4-bit precision and low-rank adaptation (LoRA) with a rank of 16 to optimize computational efficiency on consumer-grade GPUs. The model was trained over five epochs using an NVIDIA RTX 3090 GPU, with intermediary checkpoints saved for monitoring. Performance was evaluated quantitatively using Bidirectional Encoder Representations from Transformers Score (BERTScore), Recall-Oriented Understudy for Gisting Evaluation (ROUGE), Bilingual Evaluation Understudy (BLEU), and Metric for Evaluation of Translation with Explicit Ordering (METEOR) metrics on a held-out test set. Additionally, a qualitative assessment was conducted, involving 13 independent radiologists who participated in a Turing-like test and provided ratings for the AI-generated conclusions. The fine-tuned model demonstrated strong quantitative performance, achieving a BERTScore F1 of 0.8054, a ROUGE-1 F1 of 0.4998, a ROUGE-L F1 of 0.4628, and a METEOR score of 0.4282. In the human evaluation, the artificial intelligence (AI)-generated conclusions were preferred over human-written ones in approximately 21.8% of cases, indicating that the model's outputs were competitive with those of experienced radiologists. The average rating of the AI-generated conclusions was 3.65 out of 5, reflecting a generally favorable assessment. Notably, the model maintained its consistency across various types of reports and demonstrated the ability to generalize to unseen data. The fine-tuned Llama 3-8B model effectively generates accurate and coherent conclusions for MRI and CT radiology reports. By automating the conclusion-writing process, this approach can assist radiologists in reducing their workload and enhancing report consistency, potentially addressing some barriers to the adoption of deep learning in clinical practice. The positive evaluations from independent radiologists underscore the model's potential utility. While the model demonstrated strong performance, limitations such as dataset bias, limited sample diversity, a lack of clinical judgment, and the need for large computational resources require further refinement and real-world validation. Future work should explore the integration of such models into clinical workflows, address ethical and legal considerations, and extend this approach to generate complete radiology reports.

Sibling Discrimination Using Linear Fusion on Deep Learning Face Recognition Models

Facial recognition technology has revolutionised human identification, providing a non-invasive alternative to traditional biometric methods like signatures and voice recognition. The integration of deep learning has significantly enhanced the accuracy and adaptability of these systems, now widely used in criminal identification, access control, and security. Initial research focused on recognising full-frontal facial features, but recent advancements have tackled the challenge of identifying partially visible faces, a scenario that often reduces recognition accuracy. This study aims to identify siblings based on facial features, particularly in cases where only partial features like eyes, nose, or mouth are visible. Utilising advanced deep learning models such as VGG19, VGG16, VGGFace, and FaceNet, the research introduces a framework to differentiate between sibling images effectively. To boost discrimination accuracy, the framework employs a linear fusion technique that merges insights from all the models used. The methodology involves preprocessing image pairs, extracting embeddings with pre-trained models, and integrating information through linear fusion. Evaluation metrics, including confusion matrix analysis, assess the framework's robustness and precision. Custom datasets of cropped sibling facial areas form the experimental basis, testing the models under various conditions like different facial poses and cropped regions. Model selection emphasises accuracy and extensive training on large datasets to ensure reliable performance in distinguishing subtle facial differences. Experimental results show that combining multiple models' outputs using linear fusion improves the accuracy and realism of sibling discrimination based on facial features. Findings indicate a minimum accuracy of 96% across different facial regions. Although this is slightly lower than the accuracy achieved by a single model like VGG16 with full-frontal poses, the fusion approach provides a more realistic outcome by incorporating insights from all four models. This underscores the potential of advanced deep learning techniques in enhancing facial recognition systems for practical applications.

Improved Breast Cancer Detection using Modified ResNet50-Based on Gradient-Weighted Class Activation Mapping

Breast cancer is a prevalent and serious disease that affects many women around the world every year. Detecting breast cancer early is crucial for improving survival rates and treating the illness effectively. Researchers are exploring various methods, including neural networks and machine learning, to assist in detecting the disease. However, due to limited data availability, leveraging pre-trained models trained on diverse image datasets has become a common practice. This article introduces a novel approach to identifying breast cancer that involves the utilization of a deep learning model utilizing the ResNet50 framework, coupled with heat mapping and gradient-weighted class activation mapping (Grad-CAM). The suggested method was primarily assessed using the FDDM dataset of Subtracted Contrast Enhanced Spectral Mammography (CDD-CESM) images. The outcomes from this model were then contrasted with those of five other well-known models: VGG16, VGG19, MobileNetV2, EfficientNet-B7, and standard ResNet50. The newly proposed model yielded an accuracy of 0.8920, which was better than the other models. Additionally, Grad-CAM showed nearly flawless feature extraction in a breast cancer classification assignment. In the discussion section, the suggested method was utilized with the MIAS dataset to ensure thoroughness and scalability, and to allow for comparison with prior research. The results demonstrated the effectiveness of the suggested approach, with an accuracy of 0.9830 achieved on the MIAS dataset, surpassing previous works. This study significantly enhances the improvement of breast cancer detection through the integration of deep learning, the ResNet50 architecture, and visualization methods including heat maps and Grad-CAM.

Recent Advancements in High-Frequency Ultrasound Applications from Imaging to Microbeam Stimulation.

Ultrasound is a versatile and well-established technique using sound waves with frequencies higher than the upper limit of human hearing. Typically, therapeutic and diagnosis ultrasound operate in the frequency range of 500 kHz to 15 MHz with greater depth of penetration into the body. However, to achieve improved spatial resolution, high-frequency ultrasound (>15 MHz) was recently introduced and has shown promise in various fields such as high-resolution imaging for the morphological features of the eye and skin as well as small animal imaging for drug and gene therapy. In addition, high-frequency ultrasound microbeam stimulation has been demonstrated to manipulate single cells or microparticles for the elucidation of physical and functional characteristics of cells with minimal effect on normal cell physiology and activity. Furthermore, integrating machine learning with high-frequency ultrasound enhances diagnostics, including cell classification, cell deformability estimation, and the diagnosis of diabetes and dysnatremia using convolutional neural networks (CNNs). In this paper, current efforts in the use of high-frequency ultrasound from imaging to stimulation as well as the integration of deep learning are reviewed, and potential biomedical and cellular applications are discussed.

Named Entity Recognition for Equipment Fault Diagnosis Based on RoBERTa-wwm-ext and Deep Learning Integration

Equipment fault diagnosis NER is to extract specific entities from Chinese equipment fault diagnosis text, which is the premise of constructing an equipment fault diagnosis knowledge graph. Named entity recognition for equipment fault diagnosis can also provide important data support for equipment maintenance support. Equipment fault diagnosis text has complex semantics, fuzzy entity boundaries, and limited data size. In order to extract entities from the equipment fault diagnosis text, this paper presents an NER model for equipment fault diagnosis based on RoBERTa-wwm-ext and Deep Learning network integration. Firstly, this model uses the RoBERTa-wwm-ext to extract context-sensitive embeddings of text sequences. Secondly, the context feature information is obtained through the BiLSTM network. Thirdly, the CRF is combined to output the label sequence with a constraint relationship, improve the accuracy of sequence labeling task, and complete the entity recognition task. Finally, experiments and predictions are carried out on the constructed dataset. The results show that the model can effectively identify five types of equipment fault diagnosis entities and has higher evaluation indexes than the traditional model. Its precision, recall, and F1 value are 94.57%, 95.39%, and 94.98%, respectively. The case study proves that the model can accurately recognize the entity of the input text.

Integration of deep learning and computational fluid dynamics for rapid aerodynamic force prediction of compressor blades

The distribution of flow fields around compressor blades is crucial for the performance and reliability of aircraft engines. To effectively obtain aerodynamic loads, this study combines deep learning with computational fluid dynamics (CFD) to develop an efficient aerodynamic prediction model. Initially, CFD is used to acquire detailed flow field data for the blade surface and its surrounding environment. Subsequently, a distance field parameterization method is applied to process the blade geometry, and deep learning models are used to capture the complex relationship between blade geometry and aerodynamic parameters with high precision. The results indicate that the proposed model can predict aerodynamic loads within seconds with a mean squared error of less than 2%. Compared to traditional parameterization methods and other deep learning approaches, this model exhibits higher accuracy. The findings highlight the effectiveness of integrating deep learning with CFD to enhance aerodynamic predictions and provide a promising approach for future aerodynamic modeling research.

Optimization and correction of breast dynamic optical imaging projection data based on deep learning

Breast cancer poses a significant health threat to women, necessitating advancements in diagnostic technologies. Breast dynamic optical imaging (DOI) technology, recognized for its non-invasive and radiation-free properties, is extensively utilized for the early screening and quantitative analysis of breast tumors. The integration of deep learning, a robust technology for automatic image feature extraction, with breast DOI has the potential to enhance tumor detection and diagnosis significantly. This paper introduces a deep learning-enhanced image optimization approach to overcome challenges such as poor image quality and distorted projection data commonly encountered in existing DOI methods. The approach utilizes convolutional neural networks (CNNs) to extract features from raw images and employs generative adversarial networks (GANs) to enhance these images, thereby improving their quality and contrast. Additionally, a novel correction algorithm is developed to address projection data distortion, enabling the reconstruction and correction of this data for more accurate and reliable imaging results. Experimental findings confirm that the proposed method markedly enhances both image quality and projection data accuracy in breast DOI, offering a reliable foundation for clinical diagnosis. This study not only provides a new perspective and methodology for the early screening and diagnosis of breast cancer but also holds substantial clinical importance and prospective applications.

Integration of deep learning in the diagnosis, chemical analysis, and therapeutic approaches for neurodegenerative disorders

Neurodegenerative disorders (NDD) are a group of progressive conditions that primarily affect neurons in the brain. The diseases gradually impair cognitive function, movement, and other neurological processes, leading to a decline in the individual’s quality of life. Reliable biomarkers that accurately detect and track the growth of neurological disorders are crucial for the development of effective therapeutics. People with NDDs have damage to the brainneurons, which causes strange walking patterns. To overcome this problem we proposed Chemical reaction optimization based improved generative adversarial network (CRO-IGAN) method is to improve the patient’s conditions that are affected in neurodegenerative diseases. The patient’s dataset is gathered, here we utilized min max normalization for data preprocessing is used to clean the data. Principal component analysis (PCA) is employed for feature extraction to extract the pre-processed data and remove the unwanted data. The appropriate data is selected using linear discriminant analysis (LDA) for feature selection. The parameter metrics used in this study are recall, sensitivity and specificity. The suggest techniques CRO-IGAN provides high performance of accuracy for diagnosing NDD to improve the patient health which provides a superior performance than other existing methods.

Applying a Deep Learning Model for Total Kidney Volume Measurement in Autosomal Dominant Polycystic Kidney Disease.

Autosomal dominant polycystic kidney disease (ADPKD) is the most common hereditary renal disease leading to end-stage renal disease. Total kidney volume (TKV) measurement has been considered as a surrogate in the evaluation of disease severity and prognostic predictor of ADPKD. However, the traditional manual measurement of TKV by medical professionals is labor-intensive, time-consuming, and human error prone. In this investigation, we conducted TKV measurements utilizing magnetic resonance imaging (MRI) data. The dataset consisted of 30 patients with ADPKD and 10 healthy individuals. To calculate TKV, we trained models using both coronal- and axial-section MRI images. The process involved extracting images in Digital Imaging and Communications in Medicine (DICOM) format, followed by augmentation and labeling. We employed a U-net model for image segmentation, generating mask images of the target areas. Subsequent post-processing steps and TKV estimation were performed based on the outputs obtained from these mask images. The average TKV, as assessed by medical professionals from the testing dataset, was 1501.84 ± 965.85 mL with axial-section images and 1740.31 ± 1172.21 mL with coronal-section images, respectively (p = 0.73). Utilizing the deep learning model, the mean TKV derived from axial- and coronal-section images was 1536.33 ± 958.68 mL and 1636.25 ± 964.67 mL, respectively (p = 0.85). The discrepancy in mean TKV between medical professionals and the deep learning model was 44.23 ± 58.69 mL with axial-section images (p = 0.8) and 329.12 ± 352.56 mL with coronal-section images (p = 0.9), respectively. The average variability in TKV measurement was 21.6% with the coronal-section model and 3.95% with the axial-section model. The axial-section model demonstrated a mean Dice Similarity Coefficient (DSC) of 0.89 ± 0.27 and an average patient-wise Jaccard coefficient of 0.86 ± 0.27, while the mean DSC and Jaccard coefficient of the coronal-section model were 0.82 ± 0.29 and 0.77 ± 0.31, respectively. The integration of deep learning into image processing and interpretation is becoming increasingly prevalent in clinical practice. In our pilot study, we conducted a comparative analysis of the performance of a deep learning model alongside corresponding axial- and coronal-section models, a comparison that has been less explored in prior research. Our findings suggest that our deep learning model for TKV measurement performs comparably to medical professionals. However, we observed that varying image orientations could introduce measurement bias. Specifically, our AI model exhibited superior performance with axial-section images compared to coronal-section images.

Research Progress of Machine Learning in Extending and Regulating the Shelf Life of Fruits and Vegetables.

Fruits and vegetables are valued for their flavor and high nutritional content, but their perishability and seasonality present challenges for storage and marketing. To address these, it is essential to accurately monitor their quality and predict shelf life. Unlike traditional methods, machine learning efficiently handles large datasets, identifies complex patterns, and builds predictive models to estimate food shelf life. These models can be continuously refined with new data, improving accuracy and robustness over time. This article discusses key machine learning methods for predicting shelf life and quality control of fruits and vegetables, with a focus on storage conditions, physicochemical properties, and non-destructive testing. It emphasizes advances such as dataset expansion, model optimization, multi-model fusion, and integration of deep learning and non-destructive testing. These developments aim to reduce resource waste, provide theoretical basis and technical guidance for the formation of modern intelligent agricultural supply chains, promote sustainable green development of the food industry, and foster interdisciplinary integration in the field of artificial intelligence.

EEG-based epileptic seizure detection using deep learning techniques: A survey

Epilepsy is a complex neurological disorder marked by recurrent seizures, often stemming from abnormal discharge of the brain. Electroencephalogram (EEG) captures temporal and spatial shifts in cerebral electrical activity, holding pivotal diagnostic and therapeutic value for epilepsy. Deep learning techniques have made remarkable progress in EEG-based seizure detection over recent years. This review is dedicated to exploring seizure detection approaches based on deep learning, focusing on three distinct avenues. Primarily, we delve into the application of canonical deep learning methods in epilepsy detection. Subsequently, a more in-depth study was conducted on the hybrid models of deep learning. Next, the third is the integration of deep learning and traditional machine learning strategies. Finally, the challenges and future prospects related to this topic are put forward. The uniqueness of this review lies in its novel and comprehensive perspective on the latest research on deep learning-based epilepsy detection by systematically classifying methods, visualizing research progress, and addressing challenges and gaps in current research. It can provide valuable guidance for researchers who want to delve into the field of epileptic seizure detection based on EEG signals.

Iris Detection Using Deep Learning and OpenCV

The proposed system's efficacy is evaluated through extensive simulations and real- world testing, demonstrating high accuracy in accident detection and timely activation of the emergency response. This integration of deep learning with OpenCV and an automated alert system aims to reduce response times and enhance the chances of survival and support in the critical moments following a car accident. Keywords--- Deep Learning, OpenCV

Multimodal fusion: A study on speech-text emotion recognition with the integration of deep learning

Recognition of various human emotions holds significant value in numerous real-world scenarios. This paper focuses on the multimodal fusion of speech and text for emotion recognition. A 39-dimensional Mel-frequency cepstral coefficient (MFCC) was used as a feature for speech emotion. A 300-dimensional word vector obtained through the Glove algorithm was used as the feature for text emotion. The bidirectional gate recurrent unit (BiGRU) method in deep learning was added for extracting deep features. Subsequently, it was combined with the multi-head self-attention (MHA) mechanism and the improved sparrow search algorithm (ISSA) to obtain the ISSA-BiGRU-MHA method for emotion recognition. It was validated on the IEMOCAP and MELD datasets. It was found that MFCC and Glove word vectors exhibited superior recognition effects as features. Comparisons with the support vector machine and convolutional neural network methods revealed that the ISSA-BiGRU-MHA method demonstrated the highest weighted accuracy and unweighted accuracy. Multimodal fusion achieved weighted accuracies of 76.52 %, 71.84 %, 66.72 %, and 62.12 % on the IEMOCAP, MELD, MOSI, and MOSEI datasets, suggesting better performance than unimodal fusion. These results affirm the reliability of the multimodal fusion recognition method, showing its practical applicability.

Biotechnological studies towards improvement of finger millet using multi-omics approaches.

A plethora of studies have uncovered numerous important genes with agricultural significance in staple crops. However, when it comes to orphan crops like minor millet, genomic research lags significantly behind that of major crops. This situation has promoted a focus on exploring research opportunities in minor millets, particularly in finger millet, using cutting-edge methods. Finger millet, a coarse cereal known for its exceptional nutritional content and ability to withstand environmental stresses represents a promising climate-smart and nutritional crop in the battle against escalating environmental challenges. The existing traditional improvement programs for finger millet are insufficient to address global hunger effectively. The lack of utilization of high-throughput platforms, genome editing, haplotype breeding, and advanced breeding approaches hinders the systematic multi-omics studies on finger millet, which are essential for pinpointing crucial genes related to agronomically important and various stress responses. The growing environmental uncertainties have widened the gap between the anticipated and real progress in crop improvement. To overcome these challenges a combination of cutting-edge multi-omics techniques such as high-throughput sequencing, speed breeding, mutational breeding, haplotype-based breeding, genomic selection, high-throughput phenotyping, pangenomics, genome editing, and more along with integration of deep learning and artificial intelligence technologies are essential to accelerate research efforts in finger millet. The scarcity of multi-omics approaches in finger millet leaves breeders with limited modern tools for crop enhancement. Therefore, leveraging datasets from previous studies could prove effective in implementing the necessary multi-omics interventions to enrich the genetic resource in finger millet.