As AI models become more and more common in business and even in our daily lives, it is important to understand what the carbon impact of these models is. Recent papers have shown that this impact can be quite great, i.e., the training of a single high-end model can result in emissions of more than 500t of CO2eq. In this paper we discuss the factors that influence the carbon footprint of AI models, explore what impact different decisions have, and show how the footprint can be reduced. We also examine the footprint of different models to give a guideline on how urgent action is for different organizations.

One of the most common forms of dementia is Alzheimer’s disease (AD), which leads to progressive mental deterioration. Unfortunately, there is no definitive diagnosis and cure that can stop the condition progressing. The diagnosis is often performed based on the clinical history and neuropsychological data, including magnetic resonance imaging (MRI). Deep neural networks (DNN) algorithms are gaining popularity for medical diagnosis, and have been used widely for the analysis of MRI data. DNNs can extract hidden features from thousands of training images automatically. However, they cannot judge how confident they are about their predictions. To use DNNs in safety-critical applications such as medical diagnosis, uncertainty quantification of DNNs predictions is crucial. For this purpose, Monte Carlo dropout (MCD) has been widely used, however, it may lead to overconfident and miss calibrated results. This paper proposes a framework in which the MCD algorithm’s hyper-parameters are optimized during training using Bayesian optimization for the first time. The conducted optimization leads to assigning high predictive entropy to erroneous predictions and making it possible to recognize risky predictions. The proposed framework is used for AD diagnosis, which has not been done before. We compare our method with some existing methods in the literature based on different uncertainty quantification criteria. The results of comprehensive experiments on the Kaggle dataset using a deep model pre-trained on the ImageNet dataset show that the proposed algorithm can quantify uncertainty much better than the existing methods.

MicroRNAs (miRNAs) are small non-coding RNAs that play a central role in the post-transcriptional regulation of biological processes. miRNAs regulate transcripts by direct binding involving the Argonaute protein family. The exact rules of binding are not known, and several in silico miRNA target prediction methods have been developed to date. Deep Learning has recently revolutionized miRNA target prediction. However, the higher predictive power comes with decreased ability to interpret increasingly complex models. Here, we present a novel interpretation technique, called attribution sequence alignment, for miRNA target site prediction models that can interpret such Deep Learning models on a two-dimensional representation of miRNA and putative target sequence. Our method produces a human readable visual representation of miRNA:target interactions and can be used as a proxy for further interpretation of biological concepts learned by the neural network. We demonstrate applications of this method in clustering of experimental data into binding classes, as well as using the method to narrow down predicted miRNA binding sites on long transcript sequences. Importantly, the presented method works with any neural network model trained on a two-dimensional representation of interactions and can be easily extended to further domains such as protein-protein interactions.

Most machine learning and deep learning algorithms can only use low-dimensional data as input, but the data that must be processed in practical applications is diverse and irregular. There are two main problems with big dynamic data. (1) The size of the embedding table grows linearly with the vocabulary size, resulting in massive memory consumption. (2) For different newly added vocabularies. To solve these two problems, this paper proposes a novel embedding algorithm that can learn attribute associations with entities based on deep and hash algorithms. Taking movie data as an example, the encoding method and the specific flow of the algorithm are presented in detail, and the effect of dynamic reuse of data models is realized. Compared with the four existing embedding algorithms which can fuse entity attribute information, the deep hash embedding algorithm proposed in this paper has obvious optimization of time and space complexity.

Classical religious texts remain an essential part of human culture due to their undiminished influence on the advancement of civilization. Although their entirely divine origin is questioned repeatedly, explicit or implicit quoting and adherence to their basic guidelines are fundamental in modern society. In this respect, these documents’ inner structure and linguistic style appear to be pivotal. This paper considers the topic from the standpoint of small textual patterns classified using deep learning methods, traditionally applied to analyze short textual material like tweets. We divide the considered documents into small sequential chunks imitating tweets and categorizing them, classifying an entire text. The proposed method demonstrates that the religious text collections correspond to stable ”Twitter”-like structures that adequately reflect stylistic properties. So, concise word combinations seem to be an inborn textual attribute that adequately outlines the proposed multi-source authorship. This approach differs from traditional methods of analyzing classical religious documents, which are based on the consideration and interpretation of relatively long templates. The case study consists of three famous collections of Mosaic authorship in the Old Testament (Hebrew), Pauline authorship in the New Testament (Greek), and Al-Ghazali authorship (Arabic). The obtained results go well with most previously expressed evaluations and complement them with new implications, particularly in the authorship of two famous manuscripts attributed to Al-Ghazali.

Convolutional neural network architectures have become increasingly complex, which has improved the performance slowly on well-known benchmark datasets in the recent years. In this research, we have analyzed the true need for such complexity. We have introduced G-Net light, a lightweight modified GoogleNet with improved filter count per layer to reduce feature overlaps and complexity. Additionally, by limiting the amount of pooling layers in the proposed architecture, we have exploited the skip connections to minimize the spatial information loss. The investigations on the proposed architecture are evaluated on three retinal vessel segmentation publicly available datasets. The proposed G-Net light outperforms other vessel segmentation architectures by reducing the number of trainable parameters..

Globally, zoonotic diseases have been on the rise in recent years. Predictive modelling approaches have been successfully used in the literature to identify the underlying causes of these zoonotic diseases. We examine the latest research in the field of predictive modeling that verifies the growth of zoonotic pathogens and assesses the factors associated with their spread. The results of our survey indicate that popular mathematical models can successfully be used in modeling the growth rate of these pathogens under varying storage temperatures. Additionally, some of them are used for the assessment of the inactivation of these pathogens based on various conditions. Based on the results of our study, machine learning models and deep learning are commonly used to detect pathogens within food items and to predict the factors associated with the presence of the pathogens.

The classification of vessel types in SAR imagery is of crucial importance for maritime applications. However, the ability to use real SAR imagery for deep learning classification is limited, due to the general lack of such data and/or the labor-intensive nature of labeling them. Simulating SAR images can overcome these limitations, allowing the generation of an infinite number of datasets. In this contribution, we present a synthetic SAR imagery dataset with ship wakes, which comprises 46080 images for ten different real vessel models. The variety of simulation parameters includes 16 ship heading directions, 6 ship velocities, 8 wind directions, 2 wind velocities, and 3 incidence angles. In addition, we extensively investigate classification performance for noise-free, noisy, and denoised ship wake scenes. We utilize the standard AlexNet architecture and employ training from scratch. To achieve the best classification performance, we conduct Bayesian optimization to determine hyperparameters. Results demonstrate that the classification of vessel types based on their SAR signatures is highly efficient, with maximum accuracies of 96.16%, 92.7%, and 93.59%, when training using noise-free, noisy, and denoised datasets respectively. Thus, we conclude that the best strategy in practical applications should be to train convolutional neural networks on denoised SAR datasets. The results show that the versatility of the SAR simulator can open up new horizons in the application of machine learning to a variety of SAR platforms.

A common spinal condition, spondylolisthesis is the presence of a relative back or forth displacement between the upper and lower vertebra due to one vertebra being oriented away from the smooth curvature of a normal spine. Aging-related illnesses such as degenerative spondylolisthesis are especially burdensome on social welfare and health-care systems in an aging society, especially radiologists and clinical physicians. Therefore, we proposed a computer aided diagnosis algorithm, named LumbarNet, for vertebral slippage detection on clinical X-ray images. Collaborating with i) a P-grade, ii) a piecewise slope detection scheme, and iii) a dynamic shift detection routine, LumbarNet was thus specialized for analyzing complex structural patterns in lumbar spine X-ray images and outcompeted other U-Net based methods. Extensive experiments on lumbar spine X-ray images in standard clinical practices showed that LumbarNet achieved a mean intersection over union value of 0.88 in vertebral region detection and an accuracy of 88.83% in vertebral slippage detection.

COVID-19 has a severe risk of spreading rapidly, the quick identification of which is essential. In this regard, chest radiology images have proven to be a practical screening approach for COVID-19 affected patients. This study proposes a deep learning-based approach using Densenet-121 to detect COVID-19 patients effectively. We have trained and tested our model on the COVIDx dataset and performed both 2-class and 3-class classification, achieving 96.49% and 93.71% accuracy, respectively. By successfully utilizing transfer learning, we achieve comparable performance to the state-of-the-art method while using 15x fewer model parameters. Moreover, we performed an interpretability analysis using Grad-CAM to highlight the most significant image regions at test time. Finally, we developed a website that takes chest radiology images as input and detects the presence of COVID-19 or pneumonia and a heatmap highlighting the infected regions. Source code for reproducing results and model weights are available.

Recently, the use of drones/unmanned aerial vehicles (UAVs) has notably increased due to their broad commercial spread and low cost. The wide diffusion of drones increases the hazards of their misuse in illegitimate actions such as drug smuggling and terrorism. Thus, the surveillance and automated detection of drones are crucial for safeguarding restricted regions or special zones from illegal drone interventions. One of the most challenging issues in drone detection in surveillance videos is the apparent similarity of drones and birds against complex backgrounds. In this work, an automated image-based drone-detection system utilizing an advanced deep-learning-based object-detection method known as you only look once (YOLOv5) is introduced for protecting restricted regions or special zones from unlawful drone interventions. Due to the lack of sufficient data, transfer learning was utilized to pretrain the object-detection method to increase the performance. The experiments showed outstanding results, and an average precision of 94.7% was accomplished.

Scientists and astronomers have attached Scientists and astronomers have attached great importance to the task of discovering new exoplanets, even more so if they are in the habitable zone. To date, more than 4300 exoplanets have been confirmed by NASA, using various discovery techniques, including planetary transits, in addition to the use of various databases provided by space and ground-based telescopes. This article proposes the development of a deep learning system for detecting planetary transits in Kepler Telescope lightcurves. The approach is based on related work from the literature and enhanced to validation with real lightcurves. A CNN classification model is trained from a mixture of real and synthetic data, and validated only with real data and different from those used in the training stage. The best ratio of synthetic data is determined by the perform of an optimisation technique and a sensitivity analysis. The precision, accuracy and true positive rate of the best model obtained are determined and compared with other similar works. The results demonstrate that the use of synthetic data on the training stage can improve the transit detection performance on real light curves.

Convolutional Neural Networks (CNNs) have gained prominence in the research literature on image classification over the last decade. One shortcoming of CNNs, however, is their lack of generalizability and tendency to overfit when presented with small training sets. Augmentation directly confronts this problem by generating new data points providing additional information. In this paper, we investigate the performance of more than ten different sets of data augmentation methods, with two novel approaches proposed here: one based on the Discrete Wavelet Transform and the other on the Constant-Q Gabor transform. Pretrained ResNet50 networks are finetuned on each augmentation method. Combinations of these networks are evaluated and compared across three benchmark data sets of images representing diverse problems and collected by instruments that capture information at different scales: a virus data set, a bark data set, and a LIGO glitches data set. Experiments demonstrate the superiority of this approach. The best ensemble proposed in this work achieves state-of-the-art performance across all three data sets. This result shows that varying data augmentation is a feasible way for building an ensemble of classifiers for image classification (code available at https://github.com/LorisNanni).

Online social networks (OSNs) play an integral role in facilitating social interaction; however, these social networks increase antisocial behavior, such as cyberbullying, hate speech, and trolling. Aggression or hate speech that takes place through short message service (SMS) or the Internet (e.g., in social media platforms) is known as cyberbullying. Therefore, automatic detection utilizing natural language processing (NLP) is a necessary first step that helps prevent cyberbullying. This research proposes an automatic cyberbullying method to detect aggressive behavior using a consolidated deep learning model. This technique utilizes multichannel deep learning based on three models, namely, the bidirectional gated recurrent unit (BiGRU), transformer block, and convolutional neural network (CNN), to classify Twitter comments into two categories: aggressive and not aggressive. Three well-known hate speech datasets were combined to evaluate the performance of the proposed method. The proposed method achieved promising results. The accuracy of the proposed method was approximately 88%.

This paper proposes a neural network which fuses the data received from a camera system on a gantry, to detect moving objects and calculate relative position and velocity of the vehicles traveling on a freeway, this information is used to estimate the traffic flow. To estimate the traffic flow at both microscopic and macroscopic view, this paper used YOLO v4 and DeepSORT for vehicle detection and tracking, then counting the number of vehicles pass through the freeway by drawing virtual lines and hot zones, also counting the velocity of each vehicles. The information is then pass to the traffic control center, in order to monitoring and control traffic flow on freeways, and analyzing freeway conditions.

The study aimed to identify different molds that grow on various food surfaces. As a result, we conducted a case study for the detection of mold on food surfaces based on the “you only look once (YOLO) v5” principle. In this context, a dataset of 2050 food images with mold growing on their surfaces was created. The dataset was trained using the pre-trained YOLOv5 algorithm. In comparison to YOLOv3 and YOLOv4, this current YOLOv5 model had better precision, recall, and average precision (AP), which were 98.10%, 100%, and 99.60%, respectively. The YOLOv5 algorithm was used for the first time in this study to detect mold on food surfaces. In conclusion, the proposed model successfully recognizes any kind of mold present on the food surface. Using YOLOv5, we are currently conducting research to identify the specific species of the detected mold.

The medial septum (MS), as part of the basal forebrain, supports many physiological functions, from sensorimotor integration to cognition. With often reciprocal connections with a broad set of peers at all major divisions of the brain, the MS orchestrates oscillatory neuronal activities throughout the brain. These oscillations are critical in generating sensory and emotional salience, locomotion, maintaining mood, supporting innate anxiety, and governing learning and memory. Accumulating evidence points out that the physiological oscillations under septal influence are frequently disrupted or altered in pathological conditions. Therefore, the MS may be a potential target for treating neurological and psychiatric disorders with abnormal oscillations (oscillopathies) to restore healthy patterns or erase undesired ones. Recent studies have revealed that the patterned stimulation of the MS alleviates symptoms of epilepsy. We discuss here that stimulus timing is a critical determinant of treatment efficacy on multiple time scales. On-demand stimulation may dramatically reduce side effects by not interfering with normal physiological functions. A precise pattern-matched stimulation through adaptive timing governed by the ongoing oscillations is essential to effectively terminate pathological oscillations. The time-targeted strategy for the MS stimulation may provide an effective way of treating multiple disorders including Alzheimer’s disease, anxiety/fear, schizophrenia, and depression, as well as pain.

In the concept of the process signature, the relationship between a material load and the modification remaining in the workpiece is used to better understand and optimize manufacturing processes. The basic prerequisite for this is to be able to measure the loads occurring during the machining process in the form of mechanical deformations. Speckle photography is suitable for this in-process measurement task and is already used in a variety of ways for in-plane deformation measurements. The shortcoming of this fast and robust measurement technique based on image correlation techniques is that out-of-plane deformations in the direction of the measurement system cannot be detected and increases the measurement error of in-plane deformations. In this paper, we investigate a method that infers local out-of-plane motions of the workpiece surface from the decorrelation of speckle patterns and is thus able to reconstruct three-dimensional deformation fields. The implementation of the evaluation method enables a fast reconstruction of 3D deformation fields, so that the in-process capability remains given. First measurements in a deep rolling process show that dynamic deformations underneath the die can be captured and demonstrate the suitability of the speckle method for manufacturing process analysis.

Many works have recently identified the need to combine deep learning with extreme learning to strike a performance balance with accuracy especially in the domain of multimedia applications. Considering this new paradigm, namely convolutional extreme learning machine (CELM), we present a systematic review that investigates alternative deep learning architectures that use extreme learning machine (ELM) for a faster training to solve problems based on image analysis. We detail each of the architectures found in the literature, application scenarios, benchmark datasets, main results, advantages, and present the open challenges for CELM. We follow a well structured methodology and establish relevant research questions that guide our findings. We hope that the observation and classification of such works can leverage the CELM research area providing a good starting point to cope with some of the current problems in the image-based computer vision analysis.

High temperatures (HT) and high hydrostatic pressures (HHP) are characteristic of deep-sea hydrothermal vents and other deep crustal settings. These environments host vast and diverse microbial populations, yet only a small fraction of those populations have been successfully cultured. This is due, in part, to the difficulty of sampling while maintaining these in situ conditions and also replicating those high-temperature and high-pressure conditions in the laboratory. In an effort to facilitate more HT-HHP cultivation, we present two HT-HHP batch culture incubation systems for cultivating deep-sea vent and subsurface (hyper)thermophilic microorganisms. One HT-HHP system can be used for batch cultivation up to 110 MPa and 121°C, and requires sample decompression during subsampling. The second HT-HHP system can be used to culture microorganisms up to 100 MPa and 160°C with variable-volume, pressure-retaining vessels that negate whole-sample decompression during subsampling. Here, we describe how to build cost effective heating systems for these two types of high-pressure vessels, as well as the protocols for HT-HHP microbial batch cultivation in both systems. Additionally, we demonstrate HHP transfer between the variable-volume vessels, which has utility in sampling and enrichment without decompression, laboratory isolation experiments, as well as HHP filtration.

We confirm that energy dissipation weighting provides the most accurate approach to determining the effective hydraulic conductivity (Keff) of a binary K grid. A deep learning algorithm (UNET) can infer Keff with extremely high accuracy (R2 > 0.99). The UNET architecture could be trained to infer the energy dissipation weighting pattern from an image of the K distribution with high fidelity, although it was less accurate for cases with highly localized structures that controlled flow. Furthermore, the UNET architecture learned to infer the energy dissipation weighting even if it was not trained on this information directly. However, the weights were represented within the UNET in a way that was not immediately interpretable by a human user. This reiterates the idea that even if ML/DL algorithms are trained to make some hydrologic predictions accurately, they must be designed and trained to provide each user-required output if their results are to be used to improve our understanding of hydrologic systems most effectively.

High-throughput screening technologies continues to produce large amounts of multiomics data from different populations and cell types for various diseases, such as cancer. However, analysis of such data encounters difficulties due to cancer heterogeneity, further exacerbated by human biological complexity and genomic variability. There is a need to redefine the drug discovery development pipeline, bringing an Artificial Intelligence (AI)-powered informational view that integrates relevant biological information and explores new ways to develop effective anticancer approaches. Here, we show SynPred, an interdisciplinary approach that leverages specifically designed ensembles of AI-algorithms, links omics and biophysical traits to predict synergistic anticancer drug synergy. SynPred exhibits state-of-the-art performance metrics: accuracy – 0.85, precision – 0.77, recall – 0.75, AUROC – 0.82, and F1-score - 0.76 in an independent test set. Moreover, data interpretability was achieved by deploying the most current and robust feature importance approaches. A simple web-based application available online at http://www.moreiralab.com/resources/synpred/ was constructed to predict synergistic anticancer drug combinations requiring only the upload of the two drug SMILES to be tested, allowing easy access by non-expert researchers.

White matter hyperintensity (WMH) has been considered the primary biomarker from small-vessel cerebrovascular disease to Alzheimer’s disease (AD) and has been reported for its correlation of brain structural changes. To perform WMH related analysis with brain structure, both T1-weighted (T1w) and (Fluid Attenuated Inversion Recovery(FLAIR) are required. However, in a clinical situation, it is limited to obtain 3D T1w and FLAIR images simultaneously. Also, the most of brain segmentation technique supports 3D T1w only. Therefore, we introduced the semi-supervised learning method that can perform brain segmentation using FLAIR image only. Our method achieved a dice overlap score of 0.86 for brain tissue segmentation on FLAIR, with the relative volume difference between T1w and FLAIR segmentation under 4.8%, which is just as reliable as the segmentation done by its paired T1w image. We believe our semi-supervised learning method has a great potential to be used to other MRI sequences and provide encouragement to people who seek brain tissue segmentation from a non-T1w image.

Hateful and abusive speech presents a major challenge for all online social media platforms. Recent advances in Natural Language Processing and Natural Language Understanding allow more accurate detection of hate speech in textual streams. This study presents a multimodal approach to hate speech detection by combining Computer Vision and Natural Language processing models for abusive context detection. Our study focuses on Twitter messages and, more specifically, on hateful, xenophobic and racist speech in Greek aimed at refugees and migrants. In our approach we combine transfer learning and fine-tuning of Bidirectional Encoder Representations from Transformers (BERT) and Residual Neural Networks (Resnet). Our contribution includes the development of a new dataset for hate speech classification, consisting of tweet ids, along with the code to obtain their visual appearance, as they would have been rendered in a web browser. We have also released a pre-trained Language Model trained on Greek tweets, which has been used in our experiments. We report a consistently high level of accuracy (accuracy score=0.970, f1-score=0.947 in our best model) in racist and xenophobic speech detection.

The exponential growth of biomedical data in recent years urged the application of numerous machine learning techniques to address emerging problems in biology and clinical research. By enabling automatic feature extraction, selection and generation of predictive models, these methods can be used to efficiently study complex biological systems. Machine learning techniques are frequently integrated with bioinformatic methods, as well as curated databases and biological networks, to enhance training and validation, identify the best interpretable features, and enable feature and model investigation. Here, we review recently developed methods that incorporate machine learning within the same framework with techniques from molecular evolution, protein structure analysis, systems biology and disease genomics. We outline the challenges posed for machine learning, and in particular, deep learning in biomedicine and suggest unique opportunities for machine learning techniques integrated with established bioinformatics approaches to overcome some of these challenges.

Identifying dust aerosols from passive satellite images is of great interest for many applications. In this study, we developed 5 different machine-learning (ML) and deep-learning (DL) based algorithms, including Logistic Regression, K Nearest Neighbor, Random Forest (RF), Feed Forward Neural Network (FFNN), and Convolutional Neural Network (CNN), to identify dust aerosols in the daytime satellite images from the Visible Infrared Imaging Radiometer Suite (VIIRS) under cloud-free conditions on a global scale. In order to train the ML and DL algorithms, we collocated the state-of-the-art dust detection product from the Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) with the VIIRS observations along the CALIOP track. The 16 VIIRS M-band observations with the center wavelength ranging from deep blue to thermal infrared, together with solar-viewing geometries and pixel time and locations, are used as the predictor variables. Four different sets of training input data are constructed based on different combinations of VIIRS pixel and predictor variables. The validation and comparison results based on the collocated CALIOP data indicates that the FFNN method based on all available predictor variables is the best performing one among all methods. It has an averaged dust detection accuracy of about 81 %, 89 % and 85 % over land, ocean and whole globe, respectively, compared with collocated CALIOP. When applied to off-track VIIRS pixels, the FFNN method retrieves geographical distributions of dust that are in good agreement with on-track results as well as CALIOP statistics. For further evaluation, we compared our results based on the ML and DL algorithms to NOAA’s Aerosol Detection Product (ADP) , which is a product that classifies dust, smoke and ash using physical-based methods. The comparison reveals both similarity and differences. Overall, this study demonstrates the great potential of ML and DL methods for dust detection and proves that these methods can be trained on the CALIOP track and then applied to the whole granule of VIIRS granule.

The evolution in imaging technologies and artificial intelligence algorithms, coupled with improvements in UAV technology, has enabled the use of unmanned aircraft in a wide range of applications. The feasibility of this kind of approach for cattle monitoring has been demonstrated by several studies, but practical use is still challenging due to the particular characteristics of this application, such as the need to track mobile targets and the extensive areas that need to be covered in most cases. The objective of this study was to investigate the feasibility of using a tilted angle to increase the area covered by each image. Deep Convolutional Neural Networks (Xception architecture) were used to generate the models for the experiments, which covered aspects like ideal input dimensions, effect of the distance between animals and sensor, effect of classification error on the overall detection process, and impact of physical obstacles on the accuracy of the model. Experimental results indicate that oblique images can be successfully used under certain conditions, but some practical limitations need to be addressed in order to make this approach appealing.

The explosion of data has transformed the world since much more information is available for collection and analysis than ever before. To extract valuable information from the data in different dimensions, various deep learning models have been developed in the past years. Although these models have demonstrated their strong capability on improving products and services in various applications, training them is still a time-consuming and resource-intensive process. Presently, cloud, one of the most powerful computing infrastructures, has been used for the training. However, how to manage cloud computing resources and to perform the training efficiently is still challenging current techniques. For example, general resource scheduling approaches, such as spread priority and balanced resource schedulers, actually do not work well with deep learning workloads. Besides, the resource allocation problem on a cluster can be divide into two subproblems: (1) local resource optimization: improve resource configuration for a single machine; (2) global resource optimization: improve the cluster-wide resource allocation. In this thesis, we propose two novel container schedulers, FlowCon and SpeCon, that are designed to address these two subproblems respectively and specifically to optimize performance of short-lived deep learning applications in the cloud. FlowCon focuses on resource configuration of single-node in a cluster, as show that it efficiently improves deep learning tasks completion time and resource utilization, and reduces the completion time of a specific job by up to 42.06\% without sacrificing the overall system time. SpeCon targets on cluster-wide resource configuration that speculatively migrate slow-growing models to release resources for fast-growing ones. Based on our experiments, SpeCon improves makespan for up to 24.7\%, compared to current approaches.

The advent of deep learning has completely reshaped our world. Now, our daily life is fulfilled with many well-known applications that adopt deep learning techniques, such as self-driving cars and face recognition. Furthermore, robotics developed more forms of technology which share the same principle with face recognition, such as hand pose recognition and fingerprint recognition. Image recognition technology requires a huge database and various learning algorithms, such as convolutional neural network and recurrent neural network, that requires lots of computational power, such as CPUs and GPUs. Thus, clients could not be satisfied with the computational resource of the local machine. The cloud resource platform emerged at a historic moment. Docker containers play a significant role of microservices-based applications in the next generation. However, it could not guarantee the quality of service. From clients’ perspective, they have to balance the budget and quality of experiences (e.g. response time). The budget leans on individual business owners and the required Quality of Experience (QoE) depends on usage scenarios of different applications, for instance, an autonomous vehicle requires real-time response, but, unlocking your smartphone can tolerate delays. Plenty of on-going projects developed user-oriented optimization resource allocation to improve the quality of the service. Considering the users’ specifications, including accelerating the training process and specifying the quality of experience, this thesis proposes two differentiate containers scheduling for deep learning applications: TRADL and DQoES .

Carbon dioxide capture and storage (CCS) is highly expected to be mitigating the discharges of carbon dioxide in a surrounding environment. Solvents are an integral part of CCS. So far, several solvents have been explored the interest of meeting the requirements such as accessibility, non-harmfulness, biocompatibility, recyclability, and inexpensiveness. However, most solvents face failure in fulfilling the requirements due to many factors, so, this review paper gives a brief discussion about another category of solvent, an analogue of ionic liquids (ILs) named deep eutectic solvent (DES). Extensive research has been done on DES in recent years because of their various attractive advantages, i.e., non-poisonousness, biodegradability, cheap cost and easy preparation, that make them as a promising green solvent for many industrial procedure and application, for instance, polymer synthesis, biodiesel treatment, green chemistry, electrochemistry etc. Therefore, this manuscript mainly focusses on CO2 capturing through DES in oil and gas field. In addition, the preparation and chemical structures of this novel solvent (DES) is also discussed. Moreover, a detailed study based on experimental solubility of CO2 in DESs is also reported in this article.

Deep learning machines are computational models composed of multiple processing layers of adaptive weights to learn representations of data with multiple levels of abstraction. Their structure is mainly reflecting the intuitive plausibility of decomposing a problem into multiple levels of computation and representation since it is believed that higher layers of representation allow a system to learn complex functions. Surprisingly, after decades of research, from learning and design perspectives these models are still deployed in a heuristic manner. In this paper, deep learning feed-forward machines are modeled from a statistical mechanics point of view as disordered physical systems where its macroscopic behavior is determined in terms of the interactions defined between the basic constituent of these models, namely, the artificial neuron. They are viewed as the equilibrium states of a theoretical body that is subject to the law of increase of the entropy. The study of the changes in energy of the body when passing from one equilibrium state to another is used to understand the structure and role of the phase space of the system, the stability of the equilibrium states, and the resulting degree of disorder. It is shown that the topology of these models is strongly linked to their stability and resulting level of disorder. Furthermore, the proposed theoretical characterization permit to assess the thermodynamic efficiency with which information can be processed by these models, and to provide a practical methodology to quantitatively estimate and compare their expected learning and generalization capabilities. These theoretical results provides new insights to the theory of deep learning and their implications are shown to be consistent through a set of benchmarks designed to experimentally assess their validity.

Invasive species are significant threats to global agriculture and food security being the major causes of crop loss. An operative biosecurity policy requires full automation of detection and habitat identification of the potential pests and pathogens. Unmanned Aerial Vehicles (UAVs) mounted thermal imaging cameras can observe and detect pest animals and their habitats, and estimate their population size around the clock. However, their effectiveness becomes limited due to manual detection of cryptic species in hours of captured flight videos, failure in habitat disclosure and the requirement of expensive high-resolution cameras. Therefore, the cost and efficiency trade-off often restricts the use of these systems. In this paper, we present an invasive animal species detection system that uses cost-effectiveness of consumer-level cameras while harnessing the power of transfer learning and an optimised small object detection algorithm. Our proposed optimised object detection algorithm named Optimised YOLO (OYOLO) enhances YOLO (You Only Look Once) by improving its training and structure for remote detection of elusive targets. Our system, trained on the massive data collected from New South Wales and Western Australia, can detect invasive species (rabbits, Kangaroos and pigs) in real-time with a higher probability of detection (85–100 %), compared to the manual detection. This work will enhance the visual analysis of pest species while performing well on low, medium and high-resolution thermal imagery, and equally accessible to all stakeholders and end-users in Australia via a public cloud.

In the Agriculture sector, control of plant leaf diseases is crucial as it influences the quality and production of plant species with an impact on the economy of any country. Therefore, automated identification and classification of plant leaf disease at an early stage is essential to reduce economic loss and to conserve the specific species. Previously, to detect and classify plant leaf disease, various Machine Learning models have been proposed; however, they lack usability due to hardware incompatibility, limited scalability and inefficiency in practical usage. Our proposed DeepLens Classification and Detection Model (DCDM) approach deal with such limitations by introducing automated detection and classification of the leaf diseases in fruits (apple, grapes, peach and strawberry) and vegetables (potato and tomato) via scalable transfer learning on A.W.S. SageMaker and importing it on AWS DeepLens for real-time practical usability. Cloud integration provides scalability and ubiquitous access to our approach. Our experiments on extensive image data set of healthy and unhealthy leaves of fruits and vegetables showed an accuracy of 98.78% with a real-time diagnosis of plant leaves diseases. We used forty thousand images for the training of deep learning model and then evaluated it on ten thousand images. The process of testing an image for disease diagnosis and classification using AWS DeepLens on average took 0.349s, providing disease information to the user in less than a second.

Face recognition is one of the most active research fields of computer vision and pattern recognition, with many practical and commercial applications including identification, access control, forensics, and human-computer interactions. However, identifying a face in a crowd raises serious questions about individual freedoms and poses ethical issues. Significant methods, algorithms, approaches, and databases have been proposed over recent years to study constrained and unconstrained face recognition. 2D approaches reached some degree of maturity and reported very high rates of recognition. This performance is achieved in controlled environments where the acquisition parameters are controlled, such as lighting, angle of view, and distance between the camera-subject. However, if the ambient conditions (e.g., lighting) or the facial appearance (e.g., pose or facial expression) change, this performance will degrade dramatically. 3D approaches were proposed as an alternative solution to the problems mentioned above. The advantage of 3D data lies in its invariance to pose and lighting conditions, which has enhanced recognition systems efficiency. 3D data, however, is somewhat sensitive to changes in facial expressions. This review presents the history of face recognition technology, the current state-of-the-art methodologies, and future directions. We specifically concentrate on the most recent databases, 2D and 3D face recognition methods. Besides, we pay particular attention to deep learning approach as it presents the actuality in this field. Open issues are examined and potential directions for research in facial recognition are proposed in order to provide the reader with a point of reference for topics that deserve consideration.

Learning to maintain postural balance while standing requires a significant fine coordination effort between the neuromuscular system and the sensory system. It is one of the key contributing factors towards fall prevention, especially in the older population. Using artificial intelligence (AI), we can similarly teach an agent to maintain a standing posture, and thus teach the agent not to fall. In this paper, we investigate the learning progress of an AI agent and how it maintains a stable standing posture through reinforcement learning. During training, the AI agent learnt three policies. First, it learnt to maintain the Centre-of-Gravity and Zero-Moment-Point in front of the body. Then, it learnt to shift the load of the entire body on one leg while using the other leg for fine tuning the balancing action. Finally, it started to learn the coordination between the two pre-trained policies. This study shows the potentials of using deep reinforcement learning in human movement studies. The learnt AI behaviour also exhibited attempts to achieve an unplanned goal because it correlated with the set goal (e.g. walking in order to prevent falling). The failed attempts to maintain a standing posture is an interesting by-product which can enrich the fall detection and prevention research efforts.

In the past years, various intelligent machine learning and deep learning algorithms have been developed and widely applied for gearbox fault detection and diagnosis. However, the real-time application of these intelligent algorithms has been limited, mainly due to the fact that the model developed using data from one machine or one operating condition has serious diagnosis performance degradation when applied to another machine or the same machine with a different operating condition. The reason for poor model generalization is the distribution discrepancy between the training and testing data. This paper proposes to address this issue using a deep learning based cross domain adaptation approach for gearbox fault diagnosis. Labelled data from training dataset and unlabeled data from testing dataset is used to achieve the cross-domain adaptation task. A deep convolutional neural network (CNN) is used as the main architecture. Maximum mean discrepancy is used as a measure to minimize the distribution distance between the labelled training data and unlabeled testing data. The study proposes to reduce the discrepancy between the two domains in multiple layers of the designed CNN to adapt the learned representations from the training data to be applied in the testing data. The proposed approach is evaluated using experimental data from a gearbox under significant speed variation and multiple health conditions. An appropriate benchmarking with both traditional machine learning methods and other domain adaptation methods demonstrates the superiority of the proposed method.

In this paper, our goal is to perform a virtual restoration of an ancient coin from its image. The present work is the first one to propose this problem, and it is motivated by two key promising applications. The first of these emerges from the recently recognised dependence of automatic image based coin type matching on the condition of the imaged coins; the algorithm introduced herein could be used as a pre-processing step, aimed at overcoming the aforementioned weakness. The second application concerns the utility both to professional and hobby numismatists of being able to visualise and study an ancient coin in a state closer to its original (minted) appearance. To address the conceptual problem at hand, we introduce a framework which comprises a deep learning based method using Generative Adversarial Networks, capable of learning the range of appearance variation of different semantic elements artistically depicted on coins, and a complementary algorithm used to collect, correctly label, and prepare for processing a large numbers of images (here 100,000) of ancient coins needed to facilitate the training of the aforementioned learning method. Empirical evaluation performed on a withheld subset of the data demonstrates extremely promising performance of the proposed methodology and shows that our algorithm correctly learns the spectra of appearance variation across different semantic elements, and despite the enormous variability present reconstructs the missing (damaged) detail while matching the surrounding semantic content and artistic style.

Using machine learning or deep learning to solve the problem of garbage recognition and classification is an important application in computer vision, but due to the incomplete establishment of garbage datasets and the poor performance of complex network models on smart terminal devices, the existing garbage classification models The effect is not good.This paper presents a waste classification and identification method base on transfer learning and lightweight neural network. By migrating the lightweight neural network MobileNetV2 and rebuild it, The reconstructed network is used for feature extraction, and the extracted features are introduced into the SVM to realize the identification of 6 types of garbage. The model was trained and verified by using 2527 pieces of garbage labeled data in the TrashNet dataset, which ultimately resulted in a classification accuracy of 98.4% of the method, which proves that the method can effectively improve the classification accuracy and time and overcome the problem of weak data and less labeling. The over-fitting phenomenon encountered by small data sets in deep learning makes the model robust.

Deep brain stimulation (DBS) of the subthalamic nucleus (STN) has become an effective and widely used tool in the treatment of Parkinson’s disease (PD). STN-DBS has varied effects on speech. Clinical speech ratings suggest worsening following STN-DBS, but quantitative intelligibility, perceptual, and acoustic studies have produced mixed and inconsistent results. Improvements in phonation and declines in articulation have frequently been reported during different speech tasks under different stimulation conditions. Questions remain about preferred STN-DBS stimulation settings. Seven right-handed, native speakers of English with PD treated with bilateral STN-DBS were studied off medication at three stimulation conditions: stimulators off, 60 Hz (low frequency stimulation - LFS), and the typical clinical setting of 185 Hz (High frequency - HFS). Spontaneous speech was recorded in each condition and excerpts were prepared for transcription (intelligibility) and difficulty judgements. Separate excerpts were prepared for listeners to rate abnormalities in voice, articulation, fluency, and rate. Intelligibility for spontaneous speech was reduced at both HFS and LFS when compared to STN-DBS off. Speech produced at HFS was more intelligible than that produced at LFS, but HFS made the intelligibility task (transcription) subjectively more difficult. Both voice quality and articulation were judged to be more abnormal with STN-DBS on. STN-DBS reduced the intelligibility of spontaneous speech at both LFS and HFS but lowering the frequency did not improve intelligibility. Voice quality ratings with STN-DBS were correlated with the ratings made without stimulation. This was not true for articulation ratings. STN-DBS exacerbated an existing voice disorder and may have introduced new articulatory abnormalities.

Speech signals are degraded in real-life environments, product of background noise or other factors. The processing of such signals for voice recognition and voice analysis systems presents important challenges. One of the conditions that make adverse quality difficult to handle in those systems is reverberation, produced by sound wave reflections that travel from the source to the microphone in multiple directions.To enhance signals in such adverse conditions, several deep learning-based methods have been proposed and proven to be effective. Recently, recurrent neural networks, especially those with long and short-term memory (LSTM), have presented surprising results in tasks related to time-dependent processing of signals, such as speech. One of the most challenging aspects of LSTM networks is the high computational cost of the training procedure, which has limited extended experimentation in several cases. In this work, we present a proposal to evaluate the hybrid models of neural networks to learn different reverberation conditions without any previous information. The results show that some combination of LSTM and perceptron layers produce good results in comparison to those from pure LSTM networks, given a fixed number of layers. The evaluation has been made based on quality measurements of the signal's spectrum, training time of the networks and statistical validation of results. Results help to affirm the fact that hybrid networks represent an important solution for speech signal enhancement, with advantages in efficiency, but without a significan drop in quality.

In this brief letter we report our initial results on the application of deep-learning to the massive MIMO channel estimation challenge. We show that it is possible to estimate wireless channels and that the possibility of mitigating pilot-contamination with deep-learning is possible given that the leaning model underwent an extensive training-phase and that it has been presented with a large number of different channel conditions.

With the increase of the Artificial Neural Network (ANN), machine learning has taken a forceful twist in recent times. One of the most spectacular kinds of ANN design is the Convolutional Neural Network (CNN). The Convolutional Neural Network (CNN) is a technology that mixes artificial neural networks and up to date deep learning strategies. In deep learning, Convolutional Neural Network is at the center of spectacular advances. This artificial neural network has been applied to several image recognition tasks for decades and attracted the eye of the researchers of the many countries in recent years as the CNN has shown promising performances in several computer vision and machine learning tasks. This paper describes the underlying architecture and various applications of Convolutional Neural Network.

To generate a probability density function (PDF) for fitting probability distributions of real data, this study proposes a deep learning method which consists of two stages: (1) a training stage for estimating the cumulative distribution function (CDF) and (2) a performing stage for predicting the corresponding PDF. The CDFs of common probability distributions can be adopted as activation functions in the hidden layers of the proposed deep learning model for learning actual cumulative probabilities, and the differential equation of trained deep learning model can be used to estimate the PDF. To evaluate the proposed method, numerical experiments with single and mixed distributions are performed. The experimental results show that the values of both CDF and PDF can be precisely estimated by the proposed method.

We overview recent progress in growth aspects of group III-nitride heterostructures for deep ultraviolet (DUV) light-emitting diodes (LEDs), with particular emphasis on the growth approaches for attaining high-quality AlN and high Al-molar fraction AlGaN. The discussion commences with the introduction of the current status of group III-nitride DUV LEDs and the remaining challenges. This segues into discussion of LED designs enabling high device performance followed by the review of advances in the methods for the growth of bulk single crystal AlN intended as a native substrate together with a discussion of its UV transparency. It should be stated, however, that due to the high-cost of bulk AlN substrates at the time of this writing, the growth of DUV LEDs on foreign substrates such as sapphire still dominates the field. On the deposition front, the heteroepitaxial growth approaches incorporate high-temperature metal organic chemical vapor deposition (MOCVD) and pulsed-flow growth, a variant of MOCVD, with the overarching goal of enhancing adatom surface mobility, and thus epitaxial lateral overgrowth which culminates in minimization the effect of lattice- and thermal-mismatches. This is followed by addressing the benefits of pseudomorphic growth of strained high Al-molar fraction AlGaN on AlN. Finally, methods utilized to enhance both p- and n-type conductivity of high Al-molar fraction AlGaN are reviewed.

Manipulating cloth-like deformable objects (CDOs) is a long-standing problem in the robotics community. CDOs are flexible (non-rigid) objects that do not show a detectable level of com- pression strength while two points on the article are pushed towards each otherand include objects such as ropes (1D), fabrics (2D) and bags (3D). In general, CDOs’ many degrees of freedom (DoF) introduce severe self-occlusion and complex state-action dynamics as significant obstacles for perception and manipulation systems. These challenges exacerbate existing issues of modern robotic control methods such as imitation learning (IL) and reinforcement learning (RL). This review focuses on the application details of data-driven control methods on four major task families in this domain: cloth-shaping, rope manipulation, dressing and bag manip- ulation. Furthermore, we identify specific inductive biases in these four domains that present challenges for more general IL and RL algorithms, and summarise the future direction for the development of the field.

This paper presents a two-dimensional mathematical model of compound eye vision. Such a model is useful for solving navigation issues for autonomous mobile robots on the ground plane. The model is inspired by the insect compound eye that consists of ommatidia, which are tiny independent photoreception units, each of which combines a cornea, lens, and rhabdom. The model describes the planar binocular compound eye vision, focusing on measuring distance and azimuth to a circular feature with an arbitrary size. The model provides a necessary and sufficient condition for the visibility of a circular feature by each ommatidium. On this basis, an algorithm is built for generating a training data set to create two deep neural networks (DNN): the first detects the distance, and the second detects the azimuth to a circular feature. The hyperparameter tuning and the configurations of both networks are described. Experimental results showed that the proposed method could effectively and accurately detect the distance and azimuth to objects.

The paper presents a study on optimizing leather defect detection using the YOLOv11 model. Traditional leather processing has faced challenges in quality control, where human inspection accuracy ranges between 70% to 85%, affecting leather utilization rates and resulting in significant material waste. This research introduces an automated solution to improve defect classification and detection accuracy. The study focuses on defects commonly found in leather, such as insect larvae damage and removal cuts, using a specialized light chamber to control environmental variables. By analyzing both grain and flesh sides of the leather, the researchers demonstrated a significant increase in defect detection accuracy, with the flesh side achieving a higher classification rate. YOLOv11's dual-side analysis allowed for clearer identification of subtle defects, leading to a more efficient classification process. The results suggest that integrating advanced AI models like YOLOv11 with controlled digitization environments could drastically reduce human error and improve leather utilization, providing a scalable solution for the leather industry.

This paper presents a novel privacy-preserving approach, Fed-CNN1D (Federated Convolutional Neural Network 1D), based on federated learning for monitoring air quality and classifying different activities of daily living in indoor spaces. The system employs six different types of sensors to collect measurement parameters, which are then used to train a 1D CNN model locally for activity recognition. The proposed model is lightweight and edge deployable, making it suitable for real-time applications. Experiments were conducted using an air quality dataset specifically curated for Activity of Daily Living (ADL) classification. The results demonstrate that our approach Fed-CNN1D achieves 96.50% accuracy, 96.27% F1-Score, 96.54% precision, 96.21% recall, 0.11% loss, with low communication cost of 0.099Mb, and a swift detection time of 15 ms.

This paper presents a novel machine learning framework that applies evolutionary ensembles of artificial agents to mineralogical analysis and classification. The approach is based on hybridiza-tion techniques that combine diverse machine learning algorithms, creating large and effective communities of agents. These progressively mute and improve through crossover, hybridization, and selection, addressing the challenges of mineral recognition and classification from thin section images. By combining multiple machine learning techniques, the ensemble of agents autono-mously improves by evolving to adapt and enhance its ability to identify mineral species and classify different types of alterations. We detail the method, provide examples using synthetic and real data, and explore the potential to improve mineralogical analysis workflows through this dynamic, self-improving system.

Brain-Computer Interfaces (BCIs) are essential in advancing medical diagnosis and treatment by providing non-invasive tools to assess neurological states. Among these, Motor Imagery (MI), where patients mentally simulate motor tasks without physical movement, has proven to be an effective paradigm for diagnosing and monitoring neurological conditions. Electroencephalography (EEG) is widely used for MI data collection due to its high temporal resolution, cost-effectiveness, and portability. However, EEG signals can be noisy from a number of sources, including physiological artifacts and electromagnetic interference. They can also vary from person to person, which makes it harder to extract features and understand the signals. Additionally, this variability, influenced by genetic and cognitive factors, presents challenges for developing subject-independent solutions. To address these limitations, this paper presents a Multimodal and Explainable Deep Learning (MEDL) approach for MI-EEG classification and physiological interpretability. Our approach involves: i) evaluating different deep learning (DL) models for subject-dependent MI-EEG discrimination; ii) employing Class Activation Mapping (CAM) to visualize relevant MI-EEG features; and iii) utilizing a Questionnaire-MI Performance Canonical Correlation Analysis (QMIP-CCA) to provide multidomain interpretability. On the GIGAScience MI dataset, experiments show that shallow neural networks are good at classifying MI-EEG data, while the CAM-based method finds spatio-frequency patterns. Moreover, the QMIP-CCA framework successfully correlates physiological data with MI-EEG performance, offering an enhanced, interpretable solution for BCIs.

This paper considers the question of what kind of knowledge is produced by deep learning. Ryle’s concept of knowledge how is examined and is contrasted with knowledge with a rationale. It is then argued that deep neural networks do produce knowledge how, but, because of their opacity, they do not in general, though there may be some special cases to the contrary, produce knowledge with a rationale. It is concluded that the distinction between knowledge how and knowledge with a rationale is a useful one for judging whether a particular application of deep learning AI is appropriate.

The evaluation of wrinkles in deep-drawn fiber-based materials is crucial for the assessment of product quality and the optimization of manufacturing processes. Wrinkles, a common phenomenon in deep-drawing paper materials with high drawing depths, significantly impair the appearance and mechanical properties of the final product. The objective of this study is to identify the key process parameters affecting wrinkling and to deepen the understanding of their roles and interactions using wrinkle data for deep-drawn paper products. Image analysis techniques are employed, supported by a specially constructed darkroom platform to ensure uniform light intensity for capturing photographs. An automated program is developed for the detection and evaluation of wrinkle characteristics and distribution, which allows the free choice of the region to be detected and the representation of the wrinkle geometry not limited by the number. To enhance the precision of this program, the ellipticity is initially rectified for products without flanges, specifically cup-shaped deep-drawn products. The ellipticity is caused by the pronounced springback effect of the paperboard. The approach is employed to investigate the impact of material properties, blank holder force, drawing depth, drawing clearance, and punch speed on wrinkling formation after the deep drawing process. The findings reveal that the blank holder force and drawing clearance are critical factors in wrinkle formation, with higher forces generally leading to increased wrinkle numbers.

Since its origin in the thermodynamics of the 19th century, the concept of entropy has also permeated other fields of physics and mathematics, such as Classical and Quantum Statistical Mechanics, Information Theory, Probability Theory, Ergodic Theory and the Theory of Dynamical Systems. Specifically, we are referring to the classical entropies: the Boltzmann-Gibbs, von Neumann, Shannon, Kolmogorov-Sinai and topological entropies. In addition to their common name, which is historically justified (as we briefly describe in this review), other commonality of the classical entropies is the important role that they have played and are still playing in the theory and applications of their respective fields and beyond. Therefore, it is not surprising that, in the course of time, many other instances of the overarching concept of entropy have been proposed, most of them tailored to specific purposes. Following the current usage, we will refer to all of them, whether classical or new, simply as entropies. Precisely, the subject of this review is their applications in data analysis and machine learning. The reason for these particular applications is that entropies are very well suited to characterize probability mass distributions, typically generated by finite-state processes or symbolized signals. Therefore, we will focus on entropies defined as positive functionals on probability mass distributions and provide an axiomatic characterization that goes back to Shannon and Khinchin. Given the plethora of entropies in the literature, we have selected a representative group, including the classical ones. The applications summarized in this review finely illustrate the power and versatility of entropy in data analysis and machine learning.

Robot grasp modeling and implementation is one of essential abilities for a robot with embodied artificial intelligence. However, most existing deep learning-based grasp methods suffer a large number of parameters and heavy computation overheads. To address this issue, by fully exploiting the complementary capabilities of both CNNs and Transformers, we propose a smart grasp deep network with one-way fusion strategy via context path and spatial path (SGNet), which enjoys a lightweight structure, fast inference speed and easy deployment on devices with limited computation resources. Specifically, the context path employs lightweight depthwise separable convolution to achieve fast down-sampling while a novel DSFormer module mainly by integrating Transformer is to extract global and context-rich features. The spatial path efficiently fuses feature information from the context path in one-way manner and generate high-resolution feature maps via point-by-point convolution operations. Experimental results show the proposed model with only 1M parameters has a significantly overall performance, achieving 99.4% accuracy on Cornell dataset and 93.4% accuracy on Jacquard dataset, as well as within 12.5ms inference time.

Heart rate and blood pressure, along with body temperature and respiratory rate, are two of the four parameters used to assess the state of bodily functions, as both measures are indicators of heart activity. Therefore, these measurements become a basic procedure in patient diagnosis, necessitating techniques that can obtain them accurately and reliably, while being as non-intrusive as possible for the patient. Using video data, these two vital signs can be determined at any time and place. To achieve this, artificial intelligence techniques such as machine learning and deep learning 6 can be applied to overcome the main limitations of conventional remote photoplethysmography (rPPG). This document explains the technical and methodological aspects involved, including the acquisition and preprocessing of video data, the extraction of the rPPG signal, and its subsequent processing, as well as the artificial intelligence model for heart rate estimation and the mathematical modeling for blood pressure estimation. We compared the results for heart rate and blood pressure extracted from videos recorded by a basic smartphone front-camera to a blood pressure monitor and achieved results with reasonable accuracy and correlation. These results are part of the AIVA project, grant agreement 2021/C005/00145071. This project has been funded by Red.es through the Spanish 2021 call for grants aimed at research and development projects in artificial intelligence and other digital technologies.

Detecting people and technical objects in various situations, such as natural disasters and warfare, is critical to search and rescue operations and the safety of the civilian. A fast and accurate detection for people and equipment can significantly increase the effectiveness of search and rescue missions and provide timely assistance to people. Computer vision and deep learning technologies play a key role in detecting the required objects due to their ability to analyse big volumes of visual data in real time. The performance of the neural networks such as YOLOv4-v8, Faster R-CNN, SSD, and EfficientDet has been analysed using COCO2017, SARD, SeaDronesSee, and VisDrone2019 datasets. Main criteria for comparison were mAP, Precision, Recall, F1-Score, and the ability of the neural network to work in real time. The most important metrics for evaluating the efficiency and performance of models for a given task are accuracy (mAP), F1-Score, and processing speed (FPS). These metrics allow us to evaluate both the accuracy of object recognition and the ability to use the models in real-world environments where high processing speed is important. Although different neural networks perform better on certain types of metrics, YOLO outperforms them on all metrics, showing the best results of mAP-0.88, F1 - 0.88, and FPS - 48, so the focus was on these models.

The growing use of drones in precision agriculture highlights the need for enhanced operational efficiency. Despite the ability of computer vision based on deep learning has made remarkable progress in the past ten years, when it comes to segmentation task on UAVs, there is always a conflict between the demand of high precision and low inference latency. Due to such a dilemma, we propose the IRB-YOLO, an efficiency model based on Inverted Residual Block, devoting to provide constructive strategies in real-time detection tasks of UAV camera. The working details of this paper are as follows: (1) This paper innovates with a IR-Block(Inverted Residual Block), integrated into a refined YOLOv8-seg structure to create IRB-YOLO. This model specializes in pixel-level classification of UAV-acquired RGB images, facilitating the creation of exact maps to guide agricultural strategies. (2)When it comes to the experiments on a Vatica dataset with any other light-weight segmentation model, IRB-YOLO achieve at least a 3.3% increase in mAP. Further validation using a diverse species dataset confirms its robust generalization. (3)Without overloading the complex attention mechanism and deeper and deeper network, a stem that incorporates efficient feature extraction components, inverted residual block, can still possess outstanding modeling capabilities. IRB-YOLO builds a bridge between academic research and edge deployment of drones, making it applicable in real-world scenarios.

Predicting credit default risk is important to financial institutions, as accurately predicting the likelihood of a borrower defaulting on their loans will help to reduce financial losses, thereby maintaining profitability and stability. Although machine learning models have been used in assessing large applications with complex attributes for these predictions, there is still a need to identify the most effective techniques and to also address the issue of data imbalance. In this research, we conducted a comparative analysis of random forest, decision tree, SVM (Support Vector Machine), XGBoost (eXtreme Gradient Boosting), ADABoost (ADAptive Boosting) and multilayered perceptron with three-hidden layers, to predict credit default using loan data from LendingClub. Additionally, we also combined the model predictions using voting and stacking ensemble methods to enhance the models' performance. Furthermore, various sampling techniques was explored to handle the issue of class imbalance observed in the dataset, with the result showing that the balanced data performs better than the imbalanced data. Our proposed model achieved an accuracy of 93.7%, a precision of 95.6% and a recall of 95.5%, which shows the potential of ensemble methods in improving credit default predictions and can provide lending platforms with the tool to reduce default rates and financial losses. In conclusion, the findings from this study have broader implications for financial institutions, offering a robust approach to risk assessment beyond the Lend-ingClub dataset.

Drought and water scarcity are significant factors limiting the development of China's maize industry. Deep sowing, as a method to mitigate drought and preserve soil moisture and seedlings, can effectively mitigate the adverse effects of drought stress on their growth. However, deep sowing can influence the emergence of maize seedlings and has a certain impact on their growth and development. To investigate the physiological and transcriptomic changes in maize inbred lines under deep sowing stress, and the alleviation effects of exogenous hormones, this study investigated the response of mesocotyl in deep-seeding tolerant maize inbred line Qi319 and deep-seeding sensitive maize inbred line Zi330 to deep-seeding stress under exogenous MeJA treatment. The physiological and transcriptomic mechanisms underlying the alleviation of deep-seeding stress by exogenous MeJA were elucidated. Results showed that compared to normal sowing depth, mesocotyl length (MES), mesocotyl and coleoptile length (MESCOL) significantly increased under deep-seeding stress for both inbred lines, while seedling length (SDL) was significantly inhibited. However, after adding 1.5 μmol·L^-1 MeJA, MES, MESCOL, and SDL significantly increased compared to deep-seeding stress alone. Exogenous MeJA promoted cell elongation, enhanced mesocotyl length, and improved seedling emergence ability. RNA-Seq sequencing revealed differentially expressed genes (DEGs). Under deep-seeding stress compared to normal sowing depth conditions, 1248 DEGs were identified in Qi319 and 1288 DEGs were identified in Zi330. After adding exogenous MeJA under deep-seeding stress compared to normal sowing depth with exogenous MeJA treatment conditions, 538 DEGs were identified in Qi319 and 2284 DEGs were identified in Zi 330. GO enrichment analysis showed that differentially expressed genes were mainly concentrated in biological processes, cell components and molecular functions. KEGG enrichment analysis showed that differentially expressed genes were mainly concentrated in transport and catabolism, signal transduction, amino acid metabolism and lipid metabolism processes. Compared with the deep-seeded treatment, 12 differentially expressed genes were co-expressed in the two inbred lines under exogenous MeJA treatment, and 10 key genes, including ornithine decarboxylase, terpene synthase 7 and ethylene reaction transcription factor 11, were screened out. Our findings elucidate the molecular mechanism underlying maize's tolerance response to deep seeding and offer valuable insights into candidate gene resources for improving deep seeding tolerance in maize.

Crawling robots are the focus of intelligent inspection research, and the main feature of this type of robot is the flexibility of in-plane attitude adjustment. The crawling robot HIT_Spibot is a new type of steam generator heat transfer tube inspection robot with a unique mobility capability different from traditional quadrupedal robots. This paper introduces a hierachical motion planning approach for HIT_Spibot, aiming to achieve efficient and agile maneuverability. The proposed method integrates three distinct planners to handle complex motion tasks: a nonlinear optimization-based base motion planner, a TOPSIS-based base orientation planner, and a Mask-D3QN (MD3QN) algorithm-based gait motion planner. Initially, the robot's base and foot workspace are delineated through envelope analysis, followed by trajectory computation using Larangian methods. Subsequently, the TOPSIS algorithm is employed to establish an evaluation framework conducive to foundational turning planning. Finally, the MD3QN algorithm trains foot points to facilitate robot movement along predefined paths. Experimental results demonstrate the method's adaptability across diverse tube structures, showcasing robust performance even in environments with random obstacles. Compared to the D3QN algorithm, MD3QN achieves a 100% success rate, enhances average overall scores by 6.27%, reduces average stride lengths by 39.04%, and attains a stability rate of 58.02%. These results not only validate the effectiveness and practicality of the method but also showcase the significant potential of HIT_Spibot in the field of industrial inspection.

Increasing concerns on animal welfare in commercial pig industry include aggression between pigs as it affects their health and growth. Early detection of aggressive behaviors is essential for optimizing their living environment. A major challenge for detection is that these behaviors are observed occasionally in normal conditions. Under this circumstance, a limited amount of aggressive behavior data will lead to class imbalance issue, making it difficult to develop an effective classification model for the detection of aggressive behaviors. To overcome this problem, we approach the aggressive behavior detection problem as a case of anomaly detection rather than classification and propose a model based on anomaly detection, which can better handle unbalanced class distribution and effectively detect the infrequent, aggressive episodes of pigs. The model consists of a convolutional neural network (CNN) and a variational long short-term memory (LSTM) autoencoder. Additionally, we adopted a training method similar to weakly supervised anomaly detection and included a few aggressive behavior data in the training set for prior learning. To effectively utilize the aggressive behavior data, we created Reconstruction Loss Inversion, a novel objective function, to train the autoencoder-based model to increase the reconstruction error of aggressive behaviors by inverting the loss function. Our anomaly detection approach significantly outperforms traditional classification-based methods, effectively identifying aggressive behaviors in a natural farming environment. This method offers a robust solution for detecting aggressive animal behaviors and contributes to improving their welfare.

Large-scale deep learning models have produced significant results in underwater visual image target detection. However, deploying these models on underwater embedded devices poses a series of issues and challenges. Firstly, underwater devices have limited communication capabilities and carry relatively short supply of energy, resulting in constrained computing power for edge devices. Secondly, the large scale of deep neural networks creates a conflict in power demands with unmanned underwater equipment. Thirdly, insufficient underwater light and turbid water quality will lead to degradation problems in the images acquired by the device. In this paper, we build an offline system to complete the task of underwater scene target recognition. This paper introduces several innovations: 1) The new YOLO-TN model is developed by compressing the target recognition model based on YOLO-V5. The model use a model compression algorithm replace the YOLO-V5’s backbone network with a lightweight network, then perform parameter pruning on the model detection head, while reduce the size of the input image. The model uses a Teacher-guided Neural Architecture Search method based on YOLO-V5, named as YOLO-TN. 2)A method for constructing and processing real underwater environment data sets is designed. The datasets are all captured using underwater unmanned vehicles in real underwater environments, addressing issues present in existing underwater datasets, such as unbalanced target volume and single-image environment. Experimental results demonstrate that the YOLO-TN model significantly reduces the model size while maintaining the original recognition accuracy. Furthermore, it achieves 28.6 FPS on embedded devices, which is 12 times that of the original model.

As computer networks develop in size and complexity, the need for equipment that can characterize, inspect, monitor, and summarize the features of a transmission in real time grows. Many transmission and packet inspection theories are required to examine network traffic. Unfortunately, loss the track or traceability of one traffic scenarios against others over real-time network. Deep packet inspection (DPI) approaches can be used to alleviate the problem but still face flexibility constraints in the sense that it will be difficult to keep track of prior occurrences. There have been significant theoretical improvements in packet inspection, but the problem of event tracking flexibility remains unsolved. A novel approach for “integrating blockchain with DPI” in summarizing computer network traffic flow events has emerged as a result of this research: This technique captured traffic flows in the network, DPI report, and the entire transmission session header and load them into a smart-contract based- Blockchain. Two experimental scenarios are used to test the validity of the system. The first scenarios involve analysis of DPI transmission without integrating blockchain, follow by the captured of transmission session involving DPI with blockchain. The finding indicates that DPI transmission with blockchain is more secured against "Tampering Incidents", "Unauthorized Access Attempts", “Auditability” and many other security concern. Whereas, the performance overhead introduced by blockchain-based DPI indicate an increase in "DPI Processing Time from 68ms to 150ms, a "CPU Usage increment by 20%, Network Latency increment of 15ms from 20ms to 35ms, and almost all other computational resources increase. Therefore, the finding can be summarized that the performance overhead introduced by integrating blockchain with DPI increases, but it provides a secure DPI reports for decision making.

Gastrointestinal (GI) tract disorders, ranging from benign polyps to aggressive forms of cancer, pose significant health challenges globally. Early detection and precise classification of these conditions are crucial for effective treatment and improving patient survival rates. This study employs the Hyper-Kvasir dataset, a comprehensive collection of endoscopic images, to develop deep learning models that harness the power of the YOLO (You Only Look Once) architecture for real-time detection and classification of GI abnormalities. The focus is on overcoming inherent challenges such as class imbalance and limited annotated data availability. Advanced machine learning strategies, including data augmentation and semi-supervised learning, are utilized to enhance the model's performance. Our experiments demonstrate notable improvements in the detection of pre-cancerous lesions and other GI abnormalities, confirming the potential of integrating AI into endoscopic practices to support clinicians, reduce diagnostic errors, and contribute to more accurate and timely diagnoses. The implications of these findings are significant, offering a pathway to more reliable diagnostic processes and ultimately, better patient management in gastroenterology.

Machine learning (ML) has transformed the financial industry by enabling advanced applications such as credit scoring, fraud detection, and market forecasting. At the core of this transformation is deep learning (DL), a subset of ML that is robust at processing and analyzing complex and large datasets. This paper provides a concise overview of key deep learning models, including Convolutional Neural Networks (CNNs), Long Short-Term Memory networks (LSTMs), Deep Belief Networks (DBNs), Transformers, Generative Adversarial Networks (GANs), and Deep Reinforcement Learning (Deep RL). The study examines their learning processes, mathematical foundations, and practical applications in finance. It also explores recent advances and emerging trends in the financial industry alongside critical challenges such as data quality, model interpretability, and computational complexity, offering insights into future research directions that can guide the development of more robust and explainable financial models.

Deep brain stimulation of the subthalamic nucleus (STN-DBS) is a recognized treatment in Parkinson’s disease (PD), but knowledge is still limited regarding its possible impact on patients with behavioral addiction (BA) who undergo surgery. To assess this effect of STN-DBS, we prospectively studied the follow-up from 3-months pre-surgery to 12-months post-surgery of 12 PD patients with pre-existing BA (9 with pathological gambling disorder, 2 with hypersexual disorder, and 1 with compulsive shopping disorder) in a multicenter study. Patients were assessed for BA, for mental status with anxiety, depression, mania, emotional process and for PD, using the Unified Parkinson’s Disease Rating Scale motor examination (UPDRS3) and cumulative daily L-dopa equivalent daily dose (LEDD). Mean 6 and 12-month post-surgery scores were compared to baseline. After one year of STN-DBS, our results indicated that the treatment remained generally effective and stable. There was no effect on mania state or negative impact on motor signs. A significant improvement of the anxiety score was also observed. The STN is an interesting target for new therapeutic stimulation in BA and works to investigate the precise target in this neurobiological architecture should be performed in the future.

This research aims to explore the integration method of deep learning and large language models in speech recognition to improve the system’s recognition accuracy and ability to handle complex contexts. Deep neural network (DNN), convolutional neural network (CNN), long short-term memory network (LSTM) and Transformer-based large language model are used to build an integrated acoustic and language model framework. Experiments on TIMIT, LibriSpeech and Common Voice datasets show that the ensemble model shows significant improvements in both word error rate (WER) and real-time factor (RTF) compared to traditional models. Especially in terms of adaptability to multiple languages and accent changes, the model shows superior performance. The conclusion shows that through technology integration, the performance of the speech recognition system in complex environments can be effectively improved, providing a new direction for the future development of speech recognition technology.

Pakistan is an agricultural country, and an exporter of crops in many countries. The crop production is an important factor to earn revenue for the country. But the agriculture of Pakistan is still not revolutionized and no modern system has been deployed commonly. Whereas the farmers face difficulty in growing some crops because those crops needs more care and calculated steps. Moreover the farmers face difficulty at different stages of the crop growth like to check fertility of soil and if the soil is non-fertile then which chemical property is lacking. The objective of this research is to provide digitize the agriculture of Pakistan. An emerging technology IoT and Deep learning based system will be developed. The IoT part contains some devices like sensors,gateways and communication technologies whereas the software part consists of Deep learning models that can make predictions about the fertility of the soil. The motive of this system is to provide best results in term of accuracy. Whereas the dataset used is publicly available on kaggle but it was of non-fertile values, so data augmentation is also performed to generate data for fertile values. We have implemented LSTM,RNN,CNN among them LSTM performed best for the prediction of soil fertility.

Gastric cancer has become a serious worldwide health concern, emphasizing the cru-cial importance of early diagnosis measures to improve patient outcomes. While tradi-tional histological image analysis is regarded as the clinical gold standard, it is la-bor-intensive and manual. Recognizing this problem, there has been a rise in interest in using computer-aided diagnostics tools to help pathologists with their diagnostic ef-forts. In particular, deep learning (DL) has emerged as a promising solution in this sector. However, current DL models are still restricted in their ability to extract exten-sive visual characteristics for correct categorization. To tackle this limitation, this study proposes the use of ensemble models, which incorporate the capabilities of sev-eral deep learning architectures and use aggregate knowledge of many models to im-prove classification performance, allowing for more accurate and efficient gastric cancer detection. To see how well these proposed models performed, this study com-pared them to other works, all of which were based on the Gastric Histopathology Sub-size Images Database, a publicly available dataset for gastric cancer. This research demonstrated that the ensemble models achieved high detection accuracy across all sub-databases, with an average accuracy exceeding 99%. Specifically, ResNet50, VGGNet, and ResNet34 performed better than EfficientNet and VitNet. For the 80 × 80 pixel sub-database, ResNet34 exhibited an accuracy of approximately 93%, VGGNet achieved 94%, and the ensemble model excelled with 99%. In the 120 × 120 pixel sub-database, the ensemble model showed 99% accuracy, VGGNet 97%, and ResNet50 approximately 97%. For the 160 × 160 pixel sub-database, the ensemble model again achieved 99% accuracy, VGGNet 98%, ResNet50 98%, and EfficientNet 92%, high-lighting the ensemble model's superior performance across all resolutions. Overall, the ensemble model consistently provided an accuracy of 99% across the three sub-pixel categories. These findings showed that ensemble models may successfully detect criti-cal characteristics from smaller patches and achieve high performance. The findings will help pathologists diagnose gastric cancer using histopathological images, leading to earlier identification and higher patient survival rates.

The rapidly evolving domain of multimodal sentiment analysis is crucial for unraveling the intricate layers of emotional expression in social media content, customer service interactions, and personal vlogs. This research introduces a cutting-edge Advanced Cross-Modal Gating (ACMG) framework that significantly enhances the precision of sentiment analysis by refining the interplay among textual, auditory, and visual modalities. Our approach addresses three foundational aspects of sentiment analysis: (1) Advanced learning of cross-modal interactions, which focuses on extracting and synthesizing sentiment from varied modal inputs, thus providing a holistic view of expressed emotions; (2) Mastery over the temporal dynamics of multimodal data, enabling the model to maintain context and sentiment continuity over extended interactions; and (3) Deployment of a novel fusion strategy that not only integrates unimodal and cross-modal cues but also dynamically adjusts the influence of each modality based on its contextual relevance to the sentiment being expressed. The exploration of these dimensions reveals that the nuanced modeling of cross-modal interactions is crucial for enhancing model responsiveness and accuracy. By applying the ACMG model to two highly regarded datasets—CMU Multimodal Opinion Level Sentiment Intensity (CMU-MOSI) and CMU Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI)—we achieve groundbreaking accuracies of 83.9\% and 81.1\%, respectively. These results represent significant improvements of 1.6\% and 1.34\% over the current state-of-the-art, showcasing the superior performance and potential of our approach in navigating the complexities of multimodal sentiment analysis.

Colorectal cancer is third most common malignancy. For metastasis of rectal cancer, metastasis to skeletal muscle tissue is rare. In this case report, we describe a 51-year-old male patient with rectal cancer with neoadjuvant concurrent radiotherapy and chemotherapy followed by transanal total mesorectal excision with ileostomy. However, he had deep venous thrombosis of left leg after operation and skeletal muscle metastasis was diagnosed via tissue proof. Therefore, less possibility of metastasis increased included brain, duodenum, bone, and nervous system. The prognosis of metastasis to skeletal muscle is poor in contrast to liver or lung metastasis.

The aim of the present study was to predict the response of non-small cell lung cancer (NSCLC) patients to immune checkpoint inhibitors (ICIs) by leveraging computed tomography (CT) images using deep learning techniques. Retrospectively, 624 sequential CT images were gathered from 156 patients at Jiangsu Province Hospital, along with their clinical data. The dataset was subsequently partitioned into three groups: training (n=547), validation (n=64), and test (n=64). Moreover, an external validation cohort included 37 CT images from patients at Nanjing Pukou Peoples' Hospital, accompanied by comprehensive clinical data. An advanced Video Vision Transformer (ViViT) model incorporating global self-attention was utilized to analyse patients treated with ICIs and predict their response. The ViViT model's efficacy was evaluated using a confusion matrix and a receiver operating characteristic curve (ROC). Notably, the ViViT model demonstrated predictive prowess for ICIs response, yielding respective areas under the receiver operating characteristic curve (AUC) of 0.74 (95% CI: 0.69-0.78), 0.74 (95% CI: 0.61-0.86), 0.76 (95% CI: 0.62-0.88), and 0.69 (95% CI: 0.5-0.87) in the training, validation, test, and external validation cohorts. The present study illustrates how a deep learning model can provide a non-invasive means to predict clinical outcomes in NSCLC patients undergoing ICIs, potentially transforming personalized treatment approaches for individuals with NSCLC.

This study evaluates the effectiveness of Darknet53 and VGG16 pretrained models to develop a hybrid ensemble model named HybridPlantNet23 deep learning model for effective plant disease classification, using the publicly available dataset ‘A Dataset of Leaf Images’ from Mendeley webpage. The preprocessing of the dataset involved resizing the images to the respective requirements of the pretrained models to develop a combined datastore which served as the input. All experiments were conducted using MATLAB R2023b deep network designer interface. Model performances were evaluated based on the conventional accuracy, precision, recall, and F1-score. VGG16 achieved the highest accuracy (97.25%), precision (96.30%), recall (96.96%), and F1-score (96.55%), outperforming both Darknet53 and the ensemble HybridPlantNet23 model. Despite the advanced architecture of the ensemble model, its performance (accuracy: 95.37%, precision: 93.56%, recall: 94.20%, F1-score: 93.74%) was not significantly superior, thus highlighting scientific reasons behind this development. Recommendations for future works were provided accordingly.

Objectives: To assess the concordance of the preoperative application of the #Enzian classification (#ENZIANi) with the postoperative result (#ENZIANs) using surgical findings as the reference standard. Methods: This retrospective study included 282 consecutive patients with deep endometriosis undergoing surgical treatment. Preoperative assessment with transvaginal sonography and magnetic resonance imaging was compared with postoperative assessment. Concordance and diagnostic test evaluation were calculated. Results: The highest concordance was observed in the F (abdominal wall endometriosis) with k Cohen of 0.837, following the values for pelvic locations, with 0.795 for T left, 0.791 for T right, 0.776 for F (adenomyosis), 0.766 for C (rectum), and 0.75 and 0.72 for O right k and O left, respectively. The highest sensitivity was demonstrated for the P compartment *(98%), T compartment (both sides 97%), and A, B, C (94%- 96%), corresponding with deep endometriosis. Conclusions: Preoperative assessment using TVS/TAS+MRI with the ENZIANi score correlates well with the ENZIANs postoperative score and demonstrates good concordance in the detection and localization of deep endometriosis, thereby minimizing false negative results and ensuring accurate preoperative staging. The ENZIAN classification is well-suited to surgeons' needs and benefits from continuous development. Future improvements, such as adding the expanded C module, may be considered in the next edition.

Microscopic and ultra-microscopic vascular sutures are indispensable in the surgical procedures such as arm transplantation and finger reattachment. The state of the blood vessels after suturing, such as vascular patency, narrow, and blocked, determines the success rate of the operation. If we can grasp the golden window period after blood vessel suture and before muscle tissue suture to achieve accurate and objective assessment of blood vessel status, it can not only reduce medical costs but also improve social benefits. Doppler optical coherence tomography enables high-speed, high-resolution imaging of biological tissues, especially microscopic and ultra-microscopic blood vessels. Using Doppler optical coherence tomography to image the sutured blood vessels, not only the three-dimensional structure of the blood vessels, but also the blood flow information can be obtained. By extracting the contour of blood vessel wall and the contour of blood flow area, the three-dimensional shape of blood vessel can be reconstructed in three dimensions, which provides parameter support for the assessment of blood vessel status. In this work, we propose a neural network-based multi-classification deep learning model that can simultaneously and automatically extract blood vessel boundaries from Doppler OCT vessel intensity images and the contours of blood flow regions from corresponding Doppler OCT vessel phase images. Compared with the traditional random walk segmentation algorithm and cascade neural network method, the proposed model has better performance. This method is easier to realize system integration and has great potential for clinical evaluation. It is expected to be applied to the evaluation of microscopic and ultra-microscopic vascular status in microvascular anastomosis.

Dementia, primarily caused by neurodegenerative diseases like Alzheimer’s disease (AD), affects millions worldwide, making detection and monitoring crucial. To enable these tasks, we propose encoding in-text pauses and filler words (i.e., “uh” and “um”) in text-based language models, and thoroughly evaluate their effect in performance. Additionally, we suggest using contrastive learning to improve performance in a multi-task framework. Our results demonstrated the effectiveness of our approaches in enhancing the model’s performance, achieving 87% accuracy and an 86% F1-score. Compared to the state-of-the-art, our approach has similar performance despite having significantly fewer parameters. This highlights the importance of pause and filler word encoding on the detection of dementia.

Abstract This study delved into the application of various machine learning (ML) models for the classification of lung cancer levels. Through meticulous monitoring of parameters such as minimum child weight and learning rate, efforts were made to mitigate overfitting while optimizing model performance. The Deep Neural Network (DNN) emerged as a standout performer, showcasing robust performance across training, validation, and testing stages. Ensemble methods like voting and bagging also demonstrated promising results. However, Support Vector Machine (SVM) models with the Sigmoid kernel faced challenges in achieving satisfactory performance. Overall, the investigation sheds light on the efficacy of different ML models in lung cancer level classification and underscores the importance of parameter tuning to address overfitting concerns.

Prochlorococcus, a cyanobacteria genus of the smallest and most abundant oceanic phototrophs, encompasses ecotype strains adapted to high-light (HL) and low-light (LL) niches. To elucidate the adaptive evolution of this genus, we analyzed 40 Prochlorococcus marinus ORFeomes, including two cornerstone strains, MED4 and NATL1A. Employing deep learning with robust statistical methods, we detected new protein family distributions in the strains and identified key genes differentiating HL and LL strains. HL strains harbor genes (ABC-2 transporters) related to stress resistance, such as DNA repair and RNA processing, while LL strains exhibit unique chlorophyll adaptations (ion transport proteins, HEAT repeats). We report variable, depth-dependent endogenous viral elements in the 40 strains. We constructed the ORFeomes of MED4 and NATL1A covering 99 % of the annotated protein-coding sequences of the two species, totaling 3976 cloned, sequence-verified ORFs. These comparative genomics analyses, paired with MED4 and NATL1A ORFeomes, will facilitate future genotype-to-phenotype mappings and systems biology exploration of Prochlorococcus ecology.

Deep eutectic solvents have emerged as a greener alternative and have attracted so much interest in the last two decades. This paper present alternative synthesis method to classical heating-stirring. The ultrasound method is one of the most promising syntheses DESs in terms of yield and energy. So, ultrasound synthesis method was studied to obtain hydrophobic (Aliquat 336: L-Menthol 3:7; Li-docaine: decanoic acid 1:2) and hydrophilic DESs based on Choline chloride and urea, ethylene glycol and oxalic acid. The physical characterization of DESs by comparison of FTIR spectra no show difference between DESs obtained by heating-stirring and ultrasound synthesis methods. The RMN spectra of the DESs obtained by heating-stirring revealed the DESs formation. Density and viscosity properties of DESs were evaluated. The density values are similar for both synthesis methods. However, lower viscosity values are obtained to the hydrophilic DESs prepared by ul-trasound methods.

A surprising insight from the advent of genomic sequencing was that many genes are deeply conserved during evolution. With a particular focus on genes that interact with light in animals, I explore the metaphor of genetic toolkits, which can be operationalized as lists of genes involved in a trait of interest. A fascinating observation is that genes of a toolkit are often used again and again during convergent evolution, sometimes across vast phylogenetic distances. Such a pattern in the evolution of toolkits requires three different stages: origin, maintenance, and redeployment of the genes. The functional origins of toolkit genes might often be rooted in interactions with external environments. The origins of light interacting genes in particular may be tied to ancient responses to photo-oxidative stress, inspiring questions about the extent to which the evolution of other toolkits were also impacted by stress. Maintenance of genetic toolkits over long evolutionary timescales requires gene multifunctionality to prevent gene loss when a trait of interest is absent. Finally, the deployment of toolkit genes in convergently evolved traits like eyes sometimes involves the repeated use of similar, ancient genes but other times involves different genes specific to each convergent origin. How often a particular gene family is used time and again for the same function may depend on how many possible biological solutions are available. When few solutions exist and are maintained, evolution is constrained to use the same genes over and over. However, when many different solutions are possible, the innovative possibilities of evolution are often on display. Therefore, a focus on genetic toolkits highlights the combination of legacy plus innovation that drives the evolution of biological diversity.

Underwater visual detection technology plays a pivotal role in fields such as marine exploration. With the increasing demand for underwater monitoring, the quest for efficient and reliable methods for underwater target recognition has become particularly significant. To address this requirement, this study developed an innovative underwater object detection architecture based on YOLOv8, named YOLOv8-MU, aimed at significantly enhancing detection accuracy.By integrating the LarK module proposed in UniRepLKNet to optimize the backbone network, YOLOv8-MU aims to achieve a larger receptive field without increasing the model’s depth. Further, this research introduces C2fSTR, an innovative method that combines Swin Transformer with the C2f module. Additionally, we have incorporated the SPPFCSPC_EMA module, which combines Cross-Stage Partial Fast Spatial Pyramid Pooling (SPPFCSPC) with attention mechanisms, significantly improving the detection accuracy and robustness of various biological targets. Moreover, by introducing a fusion block based on DAMO-YOLO into the neck of the model, we further enhanced the model’s capability in multi-scale feature extraction. Finally, the adoption of the MPDIoU loss function, designed around vertex distance, effectively tackles the challenges of localization accuracy and boundary clarity in underwater organism detection. Experimental results on the URPC2019 dataset demonstrate that the YOLOv8-MU model achieved an mAP@0.5 of 78.4%, marking improvements of 5.6%, 1.1%, and 4.0% over YOLOv5s, YOLOv7, and YOLOv8n respectively, indicating the leading performance (SOTA) of this method. On the other hand, further evaluation on the URPC2020 dataset confirmed the generalization capability of the YOLOv8-MU architecture, with its mAP@0.5 reaching 80.4%, surpassing various models including YOLOv5x and YOLOv8n, showcasing the wide applicability of our proposed improved model architecture.

Stagnation at local optima represents a significant challenge in bio–inspired optimization algorithms, often leading to suboptimal solutions. This paper addresses this issue by proposing a hybrid model that combines the Orca Predator Algorithm with Deep Q–Learning. Orca Predator Algorithm is an optimization technique that mimics the hunting behavior of orcas. It solves complex optimization problems by exploring and exploiting search spaces efficiently. Deep Q–Learning is a reinforcement learning technique that combines Q–Learning with deep neural networks. This integration aims to turn the stagnation problem into an opportunity for more focused and effective exploitation, enhancing the optimization technique’s performance and accuracy. The proposed hybrid model leverages the biomimetic strengths of Orca Predator Algorithm to identify promising regions nearby in the search space, complemented by the fine–tuning capabilities of Deep Q–Learning to navigate these areas precisely. The practical application of this approach is evaluated using the high–dimensional Heartbeat Categorization Dataset, focusing on the feature selection problem. This dataset, comprising complex electrocardiogram signals, provided a robust platform for testing the feature selection capabilities of our hybrid model. Our experimental results are encouraging, showcasing the hybrid strategy capability to identify relevant features without significantly compromising the performance metrics of machine learning models. This analysis was performed by comparing the improved method of Orca Predator Algorithm against its native version and a set of state–of–the–art algorithms.

X-ray Fluorescence Computed Tomography (XFCT) is an emerging non-invasive imaging technique providing molecular-level data, gaining attention for high-resolution imaging. However, increased sensitivity with benchtop X-ray sources raises radiation exposure. Artificial Intelligence (AI), particularly deep learning (DL), has revolutionized medical imaging by delivering high-quality images in the presence of noise. In XFCT, traditional methods rely on complex algorithms for noise reduction, but AI holds promise in addressing high-dose concerns. We present an optimized SCUNet model for noise reduction in low-concentration XRF images. Compared to higher-dose images, our method’s effectiveness is evaluated. While various denoising techniques exist for X-ray and CT, few address to XFCT. The DL model is trained and assessed using the augmented data, focusing on background noise reduction. Image quality is measured using PSNR and SSIM, comparing outcomes with 100% X-ray dose images. Results show the proposed algorithm achieves high-quality images from low-dose and low-contrast agents, with a maximum PSNR of 39.05 and SSIM of 0.86. The model outperforms BM3D, NLM, DnCNN, and SCUNet in both visual inspection and quantitative analysis, particularly in high-noise scenarios. This indicates the potential of AI, specifically the SCUNet model, in significantly improving XFCT imaging by mitigating the trade-off between sensitivity and radiation exposure.

The recently explored synergistic combination of graphene-based materials and deep eutectic solvents (DESs) is opening novel and effective avenues for developing sensing devices with optimized features. In more detail, remarkable potential in terms of simplicity, sustainability, and cost-effectiveness have been demonstrated for sensors, resulting in the creation of hybrid devices with enhanced signal-to-noise ratio, linearity, and selectivity. Therefore, this review aims to provide a comprehensive overview of the currently available scientific literature discussing investigations and applications of sensors that integrate graphene-based materials and deep eutectic solvents, with an outlook for the most promising developments of this approach.

Unmanned aerial vehicle (UAV) photogrammetry allows the generation of orthophoto and digital surface model (DSM) rasters of a terrain. However, DSMs of water bodies mapped using this technique often reveal distortions in the water surface, thereby impeding the accurate sampling of water surface elevation (WSE) from DSMs. This study investigates the capability of deep neural networks to accommodate the aforementioned perturbations and effectively estimate WSE from photogrammetric rasters. Convolutional neural networks (CNNs) were employed for this purpose. Two regression approaches utilizing CNNs were explored: direct regression employing an encoder and solution based on prediction of the weight mask by an encoder-decoder architecture, subse-quently used to sample values from the photogrammetric DSM. The dataset employed in this study comprises data collected from five case studies of small lowland streams in Poland and Denmark, consisting of 322 DSM and orthophoto raster samples. Each sample corresponds to a 10 by 10 meter area of the stream channel and adjacent land. A grid search was employed to identify the optimal combination of encoder, mask generation architecture, and batch size among multiple candidates. Solutions were evaluated using two cross-validation methods: stratified k-fold cross-validation, where validation subsets maintained the same proportion of samples from all case studies, and leave-one-case-out cross-validation, where the validation dataset originates entirely from a single case study, and the training set consists of samples from other case studies. The proposed solution was compared with existing methods for measuring WSE in small streams using a drone. The results indicate that the solution outperforms previous photogrammetry-based methods and is second only to the radar-based method, which is considered the most accurate method available. The solution is characterized by a high degree of explainability and generalization.

Despite UAV multi-target detection exhibits considerable developmental potential worldwide, it suffers distinct challenges compared with traditional tasks in this field. These challenges include insufficient feature extraction capabilities for small targets, limited capabilities for multi-dimensional feature fusion, as well as constraints on hardware computation parameters. Especially in mission scenarios such as disaster detection, these challenges will be further amplified. Consequently, this paper introduces SSE-YOLO, an innovative YOLO framework algorithm specially designed to address these challenges. To enhance the model's feature extraction capability, we employ the SPDConv module to replace the original Conv in the backbone section, utilizing depth-separable convolution instead of traditional convolution pooling. Concurrently, we eliminate the SPPF module at the bottom and address a new Separate Kernel Attention Pyramid Pooling (SKAPP) module, substantially enhancing the feature fusion capability at the model's core. Moreover, to address the challenge of multi-dimensional feature fusion, we replace the Concat module of the neck and head with E-BiFPN, transmitting feature information from the backbone to the lower network through four CBS blocks, which effectively resolves the issue of lost contextual information in the model. Meanwhile, SSE-YOLO undergoes ablation experiments on the VisDrone2019 dataset to evaluate its effectiveness against alternative methods, and experimental results illustrate the model's exceptional precision in detecting UAV targets. In comparison to models with comparable experimental accuracy, SSE-YOLO requires remarkably fewer parameters. On the VisDrone2019-DET-test-dev dataset, SSE-YOLO enhances mAP by 17.3%, with a 42.5% reduction in the parameter amounts. Therefore, the proposed method effectively tackles the challenge of reconciling low parameters and high accuracy, presenting a novel pathway for deep learning-based UAV multi-target detection.

To ensure the security of highly sensitive remote sensing images (RSI) during their transmission, it is essential to implement effective content security protection methods. Generally, secure distribution schemes for remote sensing images often employ cryptographic techniques. However, sending encrypted data exposes communication behavior, which poses significant security risks to the distribution of remote sensing images. Therefore, this paper introduces deep information hiding to achieve secure distribution of remote sensing images, which can serve as an effective alternative in certain specific scenarios. Specifically, the Deep Information Hiding for RSI Distribution (hereinafter referred to as DIH4RSID) based on encoder-decoder network architecture with Parallel Attention Mechanisms (PAM) by adversarial training was proposed. Our model is constructed with four main components: a preprocessing network (PN), an embedding network (EN), a revealing network (RN) and a discriminating network (DN). The PN module is primarily based on Inception to capture more details of RSI and targets of different scales. The PAM module obtains features in two spatial directions to realize feature enhancement and context information integration. The experimental results indicate that our proposed algorithm achieves relatively higher visual quality and secure level compared to related methods. Additionally, after extracting the concealed content from hidden images, the average classification accuracy is unaffected.

Solar energy adoption worldwide has expanded exponentially due to a surge in international interest in producing clean energy and the declining cost of solar power plants and their technology. It is anticipated that by 2050, solar will have surpassed fossil fuels to become the primary source of energy. However, one of the main challenges associated with solar energy production is the instability of photovoltaic (PV) power generation because of weather changes. Short-term forecasting of the power output of photovoltaic systems is essential for efficient management of the power grid and energy markets. This paper aims to evaluate the ability of deep learning (DL) models to provide accurate forecasting of hourly global horizontal irradiance (GHI) using different sets of features, including weather and aerosol variables along with solar radiation components. The results show that the best forecast skills are achieved by the long short-term memory autoencoder (LSTM-AE) model.

To support pathologists in breast tumor diagnosis, deep learning plays a crucial role in the development of histological whole slide image (WSI) classification methods. However, automatic classification is challenging due to the high-resolution data and the scarcity of representative training data. To tackle these limitations, we propose a deep learning-based breast tumor gigapixel histological image multi-classifier integrated with a high-resolution data augmentation model to process the entire slide by exploring its local and global information and generating its different synthetic versions. The key idea is to perform classification and augmentation in feature latent space, reducing the computational cost while preserving the class label of the input. We adopt a deep learning-based multi-classification method and evaluate the contribution given by a Conditional Generative Adversarial Network-based data augmentation model on the classifier’s performance for three tumor classes in the BRIGHT Challenge dataset. The proposed method has allowed us to achieve an average F1 equal to 69.5, considering only the WSI dataset of the Challenge. The results are comparable to those obtained by the Challenge winning method (71.6), also trained on the annotated tumor region dataset of the Challenge.

A high-resolution catalog for the 2014 Ms6.5 Ludian aftershocks was constructed based on the deep learning phase-picking model (CERP) and the seismic-phase association technology (PALM). A specific training strategy, which combines the advantages of the conventional short-long window average energy ratio algorithm (STA/LTA) and AI algorithm, is employed to retrain the CERP model. The P & S phases were accurately detected and picked on continuous seismic waveforms by the retained AI model. Hypoinverse and HypoDD were utilized for precise location of 3286 events. Compared to the previous results, our new catalog exhibits superior performances in terms of location accuracy and the number of aftershock events, thereby enabling a more de-tailed depiction of the deep-seated tectonic features. According to the distribution of aftershocks, it can be inferred that, (1) the seismogenic fault of Ludian earthquake is the NW-trending Baogunao-Xiaohe Fault. (2) the Ludian aftershocks interconnected the discontinuous NW-trending Baogunao-Xiaohe Fault, and intersected with the Zhaotong-Ludian Fault. (3) It suggests that the NE-trending Zhaotong-Ludian Fault may have been intersected by the NW-trending Baogunao -Xiaohe Fault, indicating that the Baogunao-Xiaohe Fault is likely a rela-tively young Neogene fault.

This paper introduces an innovative approach to lipreading, leveraging a web application designed to generate subtitles for videos where the speaker's mouth is visible and a comprehensive literature review that precedes the discussion, encompassing a thorough examination of various lipreading methods employed over the past decade. Our method employs a powerful deep learning model, featuring a 3D-convolution network and bidirectional LSTM, enabling accurate sentence-level predictions based solely on visual lip movements. With an impressive accuracy of 97%, our model is trained using pre-segmented lips regions, transformed into animated GIFs for effective pre-training. This work stands as a significant contribution to the evolving landscape of lipreading research, offering a practical and accurate solution for real-world applications.

Our daily activities hinge on the flexibility of our fingers, and a fractured finger can significantly disrupt these routines. The finger bones enable us to bend and fold the fingers and thumb to pick up or grasp objects and do all of our daily activities. A broken finger can cause adverse effects on our daily life activities. It is important to treat broken finger as soon as possible. Swift and precise treatment begins with capturing multiple X-rays, followed by the critical step of fracture detection in these images. Relying on the naked eye for this task carries the risk of overlooking small fractures. To address this issue an automated diagnoses of fractured fingers from images is required for which the current research employs advanced deep learning models—ResNet34, ResNet50, ResNet101, ResNet152, VGG-16, and VGG-19—to classify finger images from the Musculoskeletal Radiographs (MURA) dataset as either fractured or non-fractured. The results emphasize the consistently strong performance of ResNet models, attaining an impressive accuracy of 81.9%. This surpasses VGG models by 3.4% and establishes ResNet as the new benchmark for state-of-the-art accuracy.

The importance of radar-based human activity recognition increased significantly over the last two decades in safety and smart surveillance applications due to its superiority towards vision-based sensing in the presence of poor environmental conditions, like illumination, increased radiative heat, occlusion, and fog. An increased public sensitivity for privacy protection, and the progress of cost-effective manufacturing, led to a higher acceptance and distribution. Deep learning approaches proved that the manual feature extraction that relies heavily upon process knowledge can be avoided by its hierarchical, non-descriptive nature. On the other hand, ML techniques based on manual feature extraction provide a robust, yet empirical based approach where the computational effort is comparatively low. This review outlines the basics of classical ML- and DL-based human activity recognition and its advances while taking recent progress of both categories into regard. For every category, state-of-the-art methods are introduced, briefly explained and discussed in terms of their pros, cons and gaps. A comparative study is performed to evaluate the performance and computational effort based on a benchmarking data set to provide a common basis for the assessment of the techniques’ degree of suitability.

With the development of remote sensing satellite technology for Earth observation, remote sensing stereo images have been used for three-dimensional reconstruction in various fields, such as urban planning and construction. However, remote sensing images often include noise, occluded regions, weakly textured areas and repeated textures, which can lead to reduced accuracy in stereo matching and affect the quality of the 3D reconstruction results. To reduce the impact of complex scenes in remote sensing images on stereo matching and to ensure both speed and accuracy, we propose a new end-to-end stereo matching network based on convolutional neural networks (CNNs). The proposed stereo matching network can learn features at different scales from the original images and construct cost volumes with varying scales to obtain richer scale information. Additionally, when constructing the cost volume, we introduce negative disparity to adapt to the common occurrence of both negative and nonnegative disparities in remote sensing stereo image pairs. For cost aggregation, we employ a 3D convolution-based encoder-decoder structure that allows the network to adaptively aggregate information. Before feature aggregation, we also introduce an attention module to retain more valuable feature information, enhance feature representation, and obtain a higher-quality disparity map. By training on the publicly available US3D dataset, we obtain the accuracy that 1.115 pixel in end-point error (EPE) and 5.32% in the error pixel ratio (D1) on the test dataset, and the inference speed is 92 ms. Comparing our model with existing state-of-the-art models, we achieve higher accuracy, and the network is beneficial for the three-dimensional reconstruction of remote sensing images.

Neutral facial expression recognition is of great importance in various domains and applications. This study introduces a data-centric approach for neutral facial expression recognition, presenting a comprehensive study that explores different methodologies, techniques, and challenges in the field to foster a deeper understanding. The results show that data augmentation plays a crucial role in improving dataset performance. Additionally, the study investigates different model architectures and training techniques to identify the most effective approach, with the InceptionV3 model achieving the highest accuracy of 72%. Furthermore, the research examines the influence of preprocessing methods on the performance of both InceptionV3 and a simplified CNN model. Interestingly, the results indicate that preprocessing techniques positively affect the performance of the simpler CNN model but negatively impact the InceptionV3 model. The implemented system, used to evaluate the findings, demonstrates promising results, correctly classifying 77% of neutral expressions. However, there are still areas for improvement. Creating a specialized dataset that includes both neutral and non-neutral expressions would greatly enhance the accuracy of the system. By addressing limitations and implementing suggested improvements, neutral facial expression recognition can be significantly enhanced, leading to more effective and accurate results.

Tropical cyclones (TC) are dangerous weather events and accurate monitoring and forecasting can provide significant early warning to reduce loss of life and property. However, the study of tropical cyclone intensity remains challenging, both in terms of theory and forecasting. ERA5 reanalysis is benchmark data set for tropical cyclone studies, yet the maximum wind speed error is very large (68 kts) and still 19 kts after simple linear correction even in the better sampled North Atlantic. Here, we develop an adaptive learning approach to correct the intensity in the ERA5 reanalysis, by optimising the inputs to overcome the problems because of the poor data quality and updating the features to improve the generalisability of the deep learning-based model. Specifically, we use TC knowledge to increase the representativeness of the inputs so that the general features can be learned with deep neural networks in the sample space, and then use domain adaptation to update the general features from the known domain with historical storms to the specific features for the unknown domain of new storms. This approach can reduce the error to only 6 kts which is within the uncertainty of the best track data in IBTrACS in the North Atlantic. The method may have wide applicability, such as extending it to the correction of intensity estimation from satellite imagery and intensity prediction from dynamical models.

Oral Squamous Cell Carcinoma is one among the most common cancer and early detection is the main key to avoid deaths. Automated diagnostic tools that process the histopathological images of a patient to detect abnormal oral lesions will be very much useful for the clinicians. A deep learning framework have been designed with an intermediate layer between feature extraction layers and classification layers for classifying the histopathological images into two categories, namely normal and oral squamous cell carcinoma. The intermediate layer is constructed using the proposed Swarm Intelligence technique called Modified Gorilla Troops Optimizer. Various optimization algorithms are implemented in literature for optimal parameter identification, weights updating and feature selection in deep learning models, but this work focuses on usage of optimization algorithm as intermediate layer that transforms the extracted features into the features that are more suitable for classification. Three datasets totally comprising 2784 normal and 3632 oral squamous cell carcinoma subjects are considered in this work. Three popular CNN architectures namely InceptionV2, MobileNetV3, and EfficientNetB3 are investigated as feature extraction layers. Two fully connected Neural Network layers along with batch normalization and dropout are used as classification layers. Among the investigated feature extraction models, MobileNetV3 performs well in all the three datasets with the highest accuracy of 0.89. Usage of the proposed Modified Gorilla Troops Optimizer as an intermediate layer boosts this accuracy to 0.95.

A long time has passed since COVID-19 was discovered and widely disseminated. Both machine learning and deep learning have moved towards the research of diagnosing COVID-19. Compared to deep learning, traditional machine learning-based methods can also achieve good diagnostic results if they are improved based on innovative points. And deep learning remains a more popular research object. Based on the deep neural network in the field of deep learning, the convolutional neural network, recurrent neural network, long and short-term memory network, and Transformer model have been extended. These models improve the performance and processing power of neural networks by introducing new structures and algorithms. This paper will introduce the basic concepts of machine learning and deep learning, as well as the details of using the relevant methods of both to help diagnose COVID-19.

Articular cartilage lacks intrinsic regenerative capabilities, and the current treatments fail to regenerate damaged tissue and lead only to temporary pain relief. These limitations have prompted the development of tissue engineering approaches, including 3D culture systems. Thanks to their regenerative properties and capacity to recapitulate embryonic processes, spheroids obtained from mesenchymal stromal cells are increasingly studied as building blocks to obtain functional tissues. The aim of this study was to investigate the capacity of adipose stromal cells to assemble in spheroids and differentiate toward chondrogenic lineage from the perspective of cartilage repair. Spheroids were generated by two different methods (3D chips vs Ultra-Low Attachment plates), differentiated toward chondrogenic lineage, and their properties were investigated by: molecular biology analyses, biophysical measurement of mass density, weight, and size of spheroids, and confocal imaging. Overall, spheroids showed the ability to differentiate by expressing specific cartilaginous markers that correlate with their mass density, defining a critical point at which they start to mature. Considering the spheroid generation method, this pilot study suggested that spheroids obtained with chips are a promising tool for the generation of cartilage organoids that could be used for preclinical/clinical approaches, including the realization of personalized therapy.

Real-time tracking is one of the most challenging problems in computer vision. Most Transformer-based trackers usually require expensive computational and storage power, which leads to the inability of these robust trackers to achieve real-time performance in resource-constrained devices. In this work, we propose a lightweight tracker, AnteaTrack. To localize the target more precisely, we develop a scaling-invariant max-filtering operator employing a sliding window combined with local max-pooling, which filters out the suspected target from the feature and performs an augmented representation while suppressing the background. For a more tight bounding box, we employ Pixel-Shuffle to increase the resolution of the feature map and get a more fine-grained representation of the target. In addition, AnteaTrack can run in real-time at 47 frames per second(FPS) on the CPU. We tested AnteaTrack on 5 datasets, and a large number of experiments have shown that AnteaTrack provides the most efficient solution compared to the same type of CPU real-time trackers. The code will be available at https://github.com/cnchange/AnteaTrack.