At present, indoor localization is one of the core technologies of location-based services (LBS), and there exist numerous scenario-oriented application solutions. Visual features, as the main semantic information to help people understand the environment and thus occupy the dominant part, many techniques about indoor scene recognition are widely adopted. However, the engineering application problem of cell phone indoor scene recognition and localization has not been well solved due to insufficient semantic constraint information of building map and the immaturity of building map location anchors (MLA) matching positioning technology. To address the above problems, this paper proposes a cell phone indoor scene recognition and localization method with building map semantic constraints. Firstly, we build a library of geocoded entities for building map location anchors (MLA), which can provide users with "immersive" real-world building maps on the one hand and semantic anchor point constraints for cell phone positioning on the other. Secondly, using the improved YOLOv5s deep learning model carried on the mobile terminal, we recognize the universal map location anchors (MLA) elements in building scenes by cell phone camera video in real-time. Lastly, the spatial location of the scene elements obtained from the cell phone video recognition is matched with the building MLA to achieve real-time positioning and navigation. The experimental results show that the model recognition accuracy of this method is above 97.2%, and the maximum localization error is within the range of 0.775 m, and minimized to 0.5 m after applying the BIMPN road network walking node constraint, which can effectively achieve high positioning accuracy in the building scenes with rich MLA element information. In addition, the building map location anchors (MLA) has universal characteristics, and the positioning algorithm based on scene element recognition is compatible with the extension of indoor map data types, so this method has good prospects for engineering applications.

Fighting against the COVID-19 pandemic caused by the SARS-CoV-2 virus is one of the most critical challenges facing the global health system today. The possibility to identify the group of persons in the cohort of people under 50 years old, who are sensitive to the COVID-disease by non-invasive methods, is a very perspective approach for estimating the epidemiological state of the human population. The study aimed to identify the features of people's faces with COVID-19 that the most correlate with disease severity could serve as one of these approaches. For this aim, 525 photos of patients' faces with different outcomes of COVID-19 disease were analyzed using the Dlib face recognition convolutional neural network pre-trained for face recognition. Face descriptor vectors were obtained using the convolutional neural network. Facial features were found that predict a person's sensitivity to the SARS-CoV-2 virus (disease severity), and the contribution of each of the features to the risk of developing a severe form of COVID in a person was found. The accuracy of the binary classification of the individual severity of the COVID-19 course using the k-nearest neighbors algorithm on the test dataset was accuracy - 84%, AUC - 0.90.

Smart living, a concept that has gained increasing attention in recent years, revolves around integrating advanced technologies in homes and cities to enhance the quality of life for citizens. Sensing and human action recognition are crucial aspects of this concept. Smart living applications span various domains, such as energy consumption, healthcare, transportation, and education, which greatly benefit from effective human action recognition. This field, originating from computer vision, seeks to recognize human actions and activities using not only visual data but also many other sensor modalities. This paper comprehensively reviews the literature on human action recognition in smart living environments, synthesizing the main contributions, challenges, and future research directions. This review selects five key domains: Sensing Technology, Multimodality, Real-time Processing, Interoperability, and Resource-Constrained Processing, as they encompass the critical aspects required for successfully deploying human action recognition in smart living. These domains highlight the essential role that sensing and human action recognition play in successfully developing and implementing smart living solutions. This paper serves as a valuable resource for researchers and practitioners seeking to explore further and advance the field of human action recognition in smart living.

Mental stress state recognition using electroencephalogram (EEG) signals for real-life applications needs a conventional wearable device. This requires an efficient number of EEG channels and an optimal feature set. The main objective of the study is to identify an optimal feature subset that can best discriminate mental stress states while enhancing the overall performance. Thus, multi-domain feature extraction methods were employed, namely, time domain, frequency domain, time-frequency domain, and network connectivity features, to form a large feature vector space. To avoid the computational complexity of high dimensional space, a hybrid feature selection (FS) method of minimum Redundancy Maximum Relevance with Particle Swarm Optimization and Support Vector Machine (mRMR-PSO-SVM) is proposed to remove noise, redundant, and irrelevant features and keep the optimal feature subset. The performance of the proposed method is evaluated and verified using four datasets, namely EDMSS, DEAP, SEED, and EDPMSC. To further consolidate, the effectiveness of the proposed method is compared with that of the state-of-the-art heuristic methods. The proposed model has significantly reduced the features vector space by an average of 70% in comparison to the state-of-the-art methods while significantly increasing overall detection performance.

This paper proposes a novel approach, based on the adaptive rate processing and analysis, for the isolated speech recognition. The idea is to smartly combine the event-driven signal acquisition and windowing along with adaptive rate processing, analysis and classification for realizing an effective isolated speech recognition. The incoming speech signal is digitized with an event-driven A/D converter (EDADC). The output of EDADC is windowed with an activity selection process. These windows are later on resampled uniformly with an adaptive rate interpolator. The resampled windows are de-noised with an adaptive rate filter and their spectrum are computed with an adaptive resolution short time Fourier transform (ARSTFT). Later on, the magnitude, Delta and Delta-Delta spectral coefficients are extracted. The Dynamic Time Warping (DTW) technique is employed to compare these extracted features with the reference templates. The comparison outcomes are used to make the classification decision. The system functionality is tested for a case study and results are presented. An 8.2 times reduction in acquired number of samples is achieved by the devised approach as compared to the classical one. It aptitudes a significant computational gain and power consumption reduction of the proposed system over the counter classical ones. An average subject dependent isolated speech recognition accuracy of 96.8% is achieved. It shows that the proposed approach is a potential candidate for the automatic speech recognition applications like rehabilitation centers, smart call centers, smart homes, etc.

Speech emotion recognition remains a heavy lifting in natural language processing. It has strict requirements to the effectiveness of feature extraction and that of acoustic model. With that in mind, a Heterogeneous Parallel Convolution Bi-LSTM model is proposed to address these challenges. It consists of two heterogeneous branches: the left one contains two dense layers and a Bi-LSTM layer, while the right one contains a dense layer, a convolution layer, and a Bi-LSTM layer. It can exploit the spatiotemporal information more effectively, and achieves 84.65%, 79.67%, and 56.50% unweighted average recall on the benchmark databases EMODB, CASIA, and SAVEE, respectively. Compared with the previous research results, the proposed model achieves better performance stably.

This paper provides a review of an emerging field in the food processing sector, referring to efficient and safe food supply chains, ’from farm to fork’, as enabled by Artificial Intelligence (AI). Recent advances in machine and deep learning are used for effective food production, energy management and food labeling. Appropriate deep neural architectures are adopted and used for this purpose, including Fully Convolutional Networks, Long Short-Term Memories and Recurrent Neural Networks, Auto-Encoders and Attention mechanisms, Latent Variable extraction and clustering, as well as Domain Adaptation. Three experimental studies are presented, illustrating the ability of these AI methodologies to produce state-of-the-art performance in the whole food supply chain. In particular, these concern: (i) predicting plant growth and tomato yield in greenhouses, thus matching food production to market needs and reducing food waste or food unavailability; (ii) optimizing energy consumption across large networks of food retail refrigeration systems, through optimal selection of systems that can get shut-down and through prediction of the respective food de-freezing times, during peaks of power demand load; (iii) optical recognition and verification of food consumption expiry date in automatic inspection of retail packaged food, thus ensuring safety of food and people’s health.

Several studies have analyzed human gait data obtained from inertial gyroscope and accelerometer sensors mounted on different parts of the body. In this article, we take a step further in gait analysis and provide a methodology for predicting the movements of the missing parts of the legs. In particular, we propose a method, called GaIn, to control non-invasive, robotic, prosthetic legs. GaIn can infer the movements of both missing shanks and feet for humans suffering from double trans-femoral amputation using biologically inspired recurrent neural networks. Predictions are performed for casual walking related activities such as walking, taking stairs, and running based on thigh movement. In our experimental tests, GaIn achieved a 4.55 degree prediction error for shank movements on average. However, a patient's intention to stand up and sit down cannot be inferred from thigh movements. In fact, intention causes thigh movements while the shanks and feet remain roughly still. The GaIn system can be triggered by thigh muscle activities measured with electromyography (EMG) sensors to make robotic prosthetic legs perform standing up and sitting down actions. The GaIn system has low prediction latency and is fast and computationally inexpensive to be deployed on mobile platforms and portable devices.

Smart devices such as smartphones, smartwatches, etc. are promising platforms that are being used for automatic recognition of human activities. However, it is difficult to accurately monitor complex human activities due to inter-class pattern similarity, which occurs when different human activities exhibit similar signal patterns or characteristics. Current smartphone-based recognition systems depend on the traditional sensors such as accelerometer and gyroscope, which are inbuilt in these devices. Therefore, apart from using information from the traditional sensors, these systems lack contextual information to support automatic activity recognition. In this article, we explore environment contexts such as illumination(light conditions) and noise level to support sensory data obtained from the traditional sensors using a hybrid of Convolutional Neural Networks and Long Short Time Memory(CNN_LSTM) learning models. The models performed sensor fusion by augmenting the low-level sensor signals with rich contextual data to improve recognition and generalisation ability of the proposed solution. Two sets of experiments were performed to validate the proposed solution. The first set of experiments used inertial sensing data whilst the second set of extensive experiments combined inertial signals with contextual information from environment sensing data. Obtained results demonstrate that contextual information such as environment noise level and illumination using hybrid deep learning models achieved better recognition accuracy than the traditional activity recognition models without contextual information.

— In a smart healthcare system," Human Activity Recognition (HAR)" is considered as an efficient approach in pervasive computing from activity sensor readings. The "Ambient Assisted Living (AAL)" in the home or community helps the people to provide independent care and enhanced living quality. However, many AAL models are restricted to multiple factors that include both the computational cost and system complexity. Moreover, the HAR concept has more relevance because of its applications, such as content-based video search, sports play analysis, crowd behavior prediction systems, patient monitoring systems, and surveillance systems. This paper attempts to implement the HAR system using a popular deep learning algorithm, namely "Recurrent Neural Network (RNN)" with the activity data collected from smart activity sensors over time, and it is publicly available in the "UC Irvine Machine Learning Repository (UCI)". The proposed model involves three processes: (1) data collection, (b) optimal feature learning, and (c) activity recognition. The data gathered from the benchmark repository was initially subjected to optimal feature selection that helped to select the most significant features. The proposed optimal feature selection method is based on a new meta-heuristic algorithm called "Colliding Bodies Optimization (CBO)". An objective function derived from the recognition accuracy has been used for accomplishing the optimal feature selection. The proposed model on the concerned benchmark dataset outperformed the conventional models with enhanced performance.

In the field of computer vision, large-scale image classification tasks are both important and highly challenging. With the ongoing advances in deep learning and optical character recognition (OCR) technologies, neural networks designed to perform large-scale classification play an essential role in facilitating OCR systems. In this study, we developed an automatic OCR system designed to identify up to 13,070 large-scale printed Chinese characters by using deep learning neural networks and fine-tuning techniques. The proposed framework comprises four components, including training dataset synthesis and background simulation, image preprocessing and data augmentation, the process of training the model, and transfer learning. The training data synthesis procedure is composed of a character font generation step and a background simulation process. Three background models are proposed to simulate the factors of the background noise and anti-counterfeiting patterns on ID cards. To expand the diversity of the synthesized training dataset, rotation and zooming data augmentation are applied. A massive dataset comprising more than 19.6 million images was thus created to accommodate the variations in the input images and improve the learning capacity of the CNN model. Subsequently, we modified the GoogLeNet neural architecture by replacing the FC layer with a global average pooling layer to avoid overfitting caused by a massive amount of training data. Consequently, the number of model parameters was reduced. Finally, we employed the transfer learning technique to further refine the CNN model using a small number of real data samples. Experimental results show that the overall recognition performance of the proposed approach is significantly better than that of prior methods and thus demonstrate the effectiveness of proposed framework, which exhibited a recognition accuracy as high as 99.39% on the constructed real ID card dataset.

This study aims to develop an elderly care system for improving the interpersonal relationship of the elderly with mild cognitive impairment (MCI) by employing the speaker recognition technique and association functionality of social network platforms. Firstly, the speaker recognition units based on the Gaussian Mixture Model (GMM) and Gaussian Mixture Model-Universal Background Model (GMM-UBM) are implemented to identify the visitor via individual input utterance. After the visitor is identified, the proposed system will be linked to the private database and social network platforms to extract the associated message of two parties. Experimental results indicate that the speaker recognition unit based on GMM-UBM achieves the best performance. Finally, five elderly persons are invited to measure the usability of the proposed system. A questionnaire is used to survey the five elderly persons, and the result indicates that the proposed system is highly potentially applicable in improving the interpersonal relationship of the elderly with MCI.

Forest fire identification is important for forest resource protection. Effective monitoring of forest fires requires the deployment of multiple monitors with different viewpoints, while most traditional recognition models can only recognize images from a single source. By ignoring the information from images with different viewpoints, these models produce high rates of missed and false alarms. In this paper, we propose a graph neural network model based on the similarity of dynamic features of multi-view images to improve the accuracy of forest fire recognition. The input features of the nodes on the graph are converted into relational features of different gallery pairs by establishing pairs (nodes) representing different viewpoint images and gallery images. The new feature library relationship is used to update the image gallery with dynamic features in order to achieve the estimation of similarity between images and improve the image recognition rate of the model. In addition, to reduce the complexity of image pre-processing process and extract key features in images effectively, this paper also proposes a dynamic feature extraction method for fire regions based on image segment ability. By setting the threshold value of HSV color space, the fire region is segmented from the image, and the dynamic features of successive frames of the fire region are extracted. The experimental results show that, compared with the baseline method Resnet, this paper's method is more effective in identifying forest fires, and its recognition accuracy is improved by 2%. And the scheme of this paper can adapt to different forest fire scenes, with better generalization ability and anti-interference ability.

The progressive impairment analysis in gait from neurological diseases patients such as Hereditary Ataxias (HA) has been carried out using gait data collected with movement sensors. This research is focused on finding the minimum amount required of gait features to recognize efficiently and less intrusive way, HA patients based on data collected with iPhone movement sensors placed on the ankles from 14 HA patients and 14 healthy people. A twofold proposal is made , first a local minimum prominent peak criterion to find out the starting point of each stride, to get 10-stride window about which 56 spatial-temporal features are derived; second a search strategy based on Hill Climbing algorithm to reduce the number of gait features and sensors. The main results were the findings that with two gait patterns a 96% of classification accuracy was achieved by using K-Nearest Neighbors (KNN) and Multi-Layer Perceptron (MLP) algorithms, but in addition, MLP only right ankle sensor patterns were required which also allows to reduce the intrusion.

The primary screening of hybridoma cells is a time-critical and laborious step during the development of monoclonal antibodies. Often critical errors occur in this phase, which supports the notion that the generation of monoclonal antibodies with hybridoma technology is difficult to control and hence a risky venture. We think that it is crucial to improve the screening process to eliminate most of the immanent deficits of the conventional approach. With this new microarray-based procedure, several advances could be achieved: Selectivity for excellent binders, high throughput, reproducible signals, avoidance of misleading avidity (multivalency) effects, and simultaneous performance of competition experiments. The latter can directly be used to select clones of desired cross-reactivity properties. In this paper, a model system with two excellent clones against carbamazepine, two weak clones and blank supernatant has been designed to examine the effectiveness of the new system. The excellent clones could be detected largely independent of the IgG concentration, which is unknown during the clone screening since the determination and subsequent adjustment of the antibody concentration is not possible in most cases. Furthermore, in this approach, the enrichment, isolation, and purification of IgG for characterization is not necessary. Raw cell culture supernatant can be used directly, even when fetal calf serum (FCS) or other complex media had been used. In addition, an improved method for the oriented antibody-immobilization on epoxy-silanized slides is presented. Based on the results of this model system, we conclude that this approach should be preferable to most other protocols leading to many of false positives, causing expensive and lengthy confirmation steps to weed out the poor clones.

This research aims to thoroughly understand the delicate interplay between stakeholders' perspectives, biometric data protection policies, and the deployment of face recognition technologies in Indonesia's dynamic digital world. Adopting a qualitative methodology, the study conducts Focus Group Discussions (FGDs) with various stakeholders, including government agencies, technology developers, regulatory agencies, civil society groups, and data subjects as end-users. Face-to-face group discussions facilitate an in-depth exploration of participants' perspectives, yielding rich qualitative data that reveals nuanced insights into the delicate balance between technological innovation, ethical considerations, and socioeconomic repercussions associated with implementing face recognition technology. The research comprehensively explains the difficulties and opportunities associated with responsible technological progress and biometric data security. The findings from the FGDs influence the development of strategies that effectively balance technical advancement with individual rights, privacy, and social well-being within the growing digital landscape of Indonesia. The regulatory function of the government seeks to bridge the gap between public expectations and technological advancements. Collaboration between academic institutions, government agencies, the private sector, and data subjects as end-users emerges as a crucial element, fostering an all-encompassing strategy integrating research, law, technology deployment, and user empowerment. This holistic approach is necessary to ensure that biometric data and facial recognition technology are utilized responsibly, thereby laying the way for Indonesia's technologically sophisticated and ethically aware digital future.

Nowadays, speed up development and use of digital devices such as smartphones have put people at risk of internet crimes. The evidence of present crimes in a computer file can be easily unreachable by changing the prefix of a file or other algorithms. In more complex cases, either file divided into different parts or the parts of a file that has information about the file type are deleted, where the file fragment recognition issue is discussed. The known files are divided into different fragments, and different classification algorithms to solve the problems of file fragment recognition. A confusion matrix measures the accuracy of type recognition. In the present study, first, the file is divided into different fragments. Then, the file fragment features, which are obtained from Binary Frequency Distribution (BFD), are reduced by 2 feature reduction algorithms; Sequential Forward Selection algorithm (SFS) as well as Sequential Floating Forward Selection algorithm (SFFS) to delete sparse features that result in increased accuracy and speed. Finally, the reduced features are given to 3 classifier algorithms, Multilayer Perceptron (MLP), Support Vector Machines (SVM), and K-Nearest Neighbor (KNN) for classification and comparison of the results. In this paper, we proposed the algorithm of file type recognition that can recognize 6 types of useful files ( pdf, txt, jpg, doc, html, exe), which may distinguish a type of file fragments with higher accuracy than the similar works done.

Over the years, there has been a significant rise in the world's scientific knowledge. However, most of it lacks structure and is often termed as Dark Data. Both humans and expert systems have continually faced difficulty in analyzing and comprehending such overwhelming amounts of information which is crucial in solving several real-world problems. Information and data visualization techniques proffer a promising solution to explore such data by allowing quick comprehension of information, the discovery of emerging trends, identification of relationships and patterns, etc. In this tutorial, we utilize the rich corpus of PubMed comprising of more than 30 million citations from biomedical literature to visually explore and understand the underlying key-insights using various information visualization techniques. With this study, we aim to diminish the limitation of human cognition and perception in handling and examining such large volumes of data by speeding up the process of decision making and pattern recognition and enabling decision-makers to fully understand data insights and make informed decisions.

This work is part of an ongoing research project to develop an unmanned flying social robot to monitor dependants at home in order to detect the person’s state and bring the necessary assistance. In this sense, this paper focuses on the description of a virtual reality (VR) simulation platform for the monitoring process of an avatar in a virtual home by a rotatory-wing autonomous unmanned aerial vehicle (UAV). This platform is based on a distributed architecture composed of three modules communicated through the Message Queue Telemetry Transport (MQTT) protocol: the UAV Simulator implemented in MATLAB/Simulink, the VR Visualiser developed in Unity, and the new emotion recognition (ER) System developed in Python. Using a face detection algorithm and a convolutional neural network (CNN), the ER System is able to detect the person’s face in the image captured by the UAV’s on-board camera and classify the emotion among seven possible ones (surprise, fear, happiness, sadness, disgust, anger or neutral expression). The experimental results demonstrate the correct integration of this new computer vision module within the VR platform, as well as the good performance of the designed CNN, with around 85% in the F1-score, a mean of the precision and recall of the model. The developed emotion detection system can be used in the future implementation of the assistance UAV that monitors dependent people in a real environment, since the methodology used is valid for images of real people.

Smart Living, an increasingly prominent concept, entails incorporating sophisticated technologies in homes and urban environments to elevate the quality of life for citizens. A critical success factor for Smart Living services and applications, from energy management to healthcare and transportation, is the efficacy of human action recognition (HAR). HAR, rooted in computer vision, seeks to identify human actions and activities using visual data and various sensor modalities. This paper extensively reviews the literature on HAR in Smart Living services and applications, amalgamating key contributions and challenges while providing insights into future research directions. The review delves into the essential aspects of Smart Living, the state of the art in HAR, and the potential societal implications of this technology. Moreover, the paper meticulously examines the primary application sectors in Smart Living that stand to gain from HAR, such as smart homes, smart healthcare, and smart cities. By underscoring the significance of the four dimensions of Context Awareness, Data Availability, Personalization, and Privacy in HAR, this paper serves as a valuable resource for researchers and practitioners striving to advance Smart Living services and applications.

We describe a selective and sensitive fluorescence platform for the detection of trinitrophenol (TNP) based on competitive host–guest recognition between pyridine-functionalized pillar[6]arene (PCP6) and probe (acridine orange, AO) that used PCP6-functionalized reduced graphene (PCP6-rGO) as the receptor. TNP is an electron-deficient and negative molecule which is captured by PCP6 via electrostatic interactions and π-π interactions. Therefore, a selective and sensitive fluorescence sensor for TNP detection is developed. It has a low detection limit of 0.0035 μM (S/N=3) and a wider linear response of 0.01−5.0 and 5.0−125.0 for TNP. The sensing platform is also used to test TNP in two water and soil samples with satisfying results. This suggests that this approach has potential applications for the determination of TNP.

Data augmentation techniques recently gained more adoption in speech processing, including speech emotion recognition. Although more data tends to be more effective, there may be a trade-off in which more data will not provide a better model. This paper reports experiments on investigating the effects of data augmentation in speech emotion recognition. The investigation aims at finding the most useful type of data augmentation and the number of data augmentations for speech emotion recognition. The experiments are conducted on the Japanese Twitter-based emotional speech corpus. The results show that for speaker-independent data, two data augmentations with glottal source extraction and silence removal exhibited the best performance among others, even with more data augmentation techniques. For the text-independent data (including speaker and text-independent), more data augmentations tend to improve speech emotion recognition performances. The results highlight the trade-off between the number of data augmentation and the performance of speech emotion recognition showing the necessity to choose a proper data augmentation technique for a specific application.

Insect herbivores have a wide range of life cycles and feeding habits, making them extremely diverse. With their host plants, they form close relationships and suppress their defense mecha-nisms. Molecular elicitors are the key bio-elements in detection and recognition of attacking enemies in tissue consumption. Insect oral secretion, frass, and fluid of egg deposition contain bio-logical active molecules called herbivore-associated elicitors (HAEs) are recognized by pattern recognition receptors (PRRs). However, in insect herbivores, little is known about the molecular basis of signal transduction and regulation of plant resistance. Many plants distinguish insect feeding from wounding by HAEs presenting in their oral secretions (OS) and induce local and systemic responses against arthropod feeding. PRRs perceive HAEs in the oral secretion of cater-pillars in a species-specific manner to elicit exclusive defense responses. HAEs-PRRs interactions induce plant resistance by reprogramming plant metabolism and transcriptional machinery. Quantitative, timely, and coordinated plant response initiate early signalling events including Ca+2, reactive oxygen species (ROS) and mitogen-activated protein kinases (MAPKs). We have discussed how early signalling cascades converge into the accumulation of phytohormones that regulate down-stream special metabolites against herbivores. In this review, we have drawn a hypothetical model of PPRs-HAEs mediated induced responses in plants and discussed how PRRs-HAEs interactions based on molecular mechanism that elicit short- and long-term induced defenses in plants. The identification of plant target insect herbivore PRRs-HAEs interactions will help to explore the fundamental molecular mechanisms of host manipulation and may generate prospects to develop novel pest resistance strategies.

We present improvements in n-best rescoring of code-switched speech achieved by n-gram augmentation as well as optimised pretraining of long short-term memory (LSTM) language models with larger corpora of out-of-domain monolingual text. In addition, we consider the application of large pretrained transformer-based architectures. Our experimental evaluation is performed on an under-resourced corpus of code-switched speech comprising four bilingual code-switched sub-corpora, each containing a Bantu language (isiZulu, isiXhosa, Sesotho, or Setswana) and English. We find in our experiments that, by combining n-gram augmentation with the optimised pretraining strategy, speech recognition errors are reduced for each individual bilingual pair by 3.51% absolute on average over the four corpora. Importantly, we find that even speech recognition at language boundaries improves by 1.14% even though the additional data is monolingual. Utilising the augmented n-grams for lattice generation, we then contrast these improvements with those achieved after fine-tuning pretrained transformer-based models such as distilled GPT-2 and M-BERT. We find that, even though these language models have not been trained on any of our target languages, they can improve speech recognition performance even in zero-shot settings. After fine-tuning on in-domain data, these large architectures offer further improvements, achieving a 4.45% absolute decrease in overall speech recognition errors and a 3.52% improvement over language boundaries. Finally, a combination of the optimised LSTM and fine-tuned BERT models achieves a further gain of 0.47% absolute on average for three of the four language pairs compared to M-BERT. We conclude that the careful optimisation of the pretraining strategy used for neural network language models can offer worthwhile improvements in speech recognition accuracy even at language switches, and that much larger state-of-the-art architectures such as GPT-2 and M-BERT promise even further gains.

With the exponential growth in today’s technology and its expanding areas of application it has become vital to incorporate it in education. One such application is Knowledge Discovery in Databases (KDD) which is a subset of data mining. KDD deals with extracting useful information and meaningful patterns from the database that were not known before. This study is a detailed application of KDD and focuses on analyzing why a particular set of students performed better than others and what factors influenced the results. The study is conducted on a dataset of 480 students and across 16 different features. The authors implemented 4 major classification techniques namely Logistic Regression, Decision Tree, Random Forest and XGB classifier. Obtaining the key features from the top performing ML algorithms that have a major impact on the performance of the student, the study takes these features as a baseline for further analysis. Further data analysis highlights patterns in the data. The study concludes that there are a lot of non-academic factors that influence the overall performance of a student and should be taken into consideration by universities and other relevant bodies.

In this paper, PEN3 electronic nose was used to detect and recognize fresh and moldy apples (inoculated with Penicillium expansum and Aspergillusniger) taken Golden Delicious apples as model subject. Firstly, the apples were divided into two groups: apples only inoculated with different molds (Group A) and mixed apples of inoculated apples with fresh apples (Group B). Then the characteristic gas sensors of the PEN3 electronic nose that were most closely correlated with the flavor information of the moldy apples were optimized and determined, which can simplify the analysis process and improve the accuracy of results. Four pattern recognition methods, including linear discriminant analysis (LDA), backpropagation neural network (BPNN), support vector machines (SVM) and radial basis function neural network (RBFNN), were then applied to analyze the data obtained from the characteristic sensors, respectively, aiming at establishing the prediction model of flavor information and fresh/moldy apples. The results showed that only the gas sensors of W1S, W2S, W5S, W1W and W2W in the PEN3 electronic nose exhibited strong signal response to the flavor information, indicating were most closely correlated with the characteristic flavor of apples and thus the data obtained from these characteristic sensors was used for modeling. The results of the four pattern recognition methods showed that BPNN presented the best prediction performance for the training and validation sets for both the Group A and Group B, with prediction accuracies of 96.29% and 90.00% (Group A), 77.70% and 72.00% (Group B), respectively. Therefore, it first demonstrated that PEN3 electronic nose can not only effectively detect and recognize the fresh and moldy apples, but also can distinguish apples inoculated with different molds.

As recommended in the ICH Guidelines (S5-R2 and S6-R1), and based on bioethical concerns, we chose bovine embryos (BE) to check the in vitro embryo development considering the use of different amounts of rHGAL-1 as supplementations of in vitro embryo culture (IVP) mediums. Based on procedures for commercial BE in vitro production, using oocytes aspirated from slaughterhouse ovaries, the rHGAL-1 supplementation performed in two experiments (#01 on the oocyte maturation - IVM medium supplemented and experiment #2 on culture step IVC, supplemented SOF medium). There were IVP commercial procedures done, with 3 IVP batches per experiment and distributed the oocytes in four groups of treatment (one control group and three different dosages of rHGAL-1 to supplement both IVM and SOF mediums, using (2, 20 and 40µg.mL-1 respectively). A total of 962 (experiment 1) and 1,213 (experiment 2) oocytes were aspirated and submitted to IVP procedure. There was no damage to in vitro bovine embryos growth, considering cleavage percentage (%CLE), blastocysts development on day 7 (BlD7, BxD7, BhD7), or hatching blastocysts maturation on day 8 (BhD8%), regardless of rHGAL-1 supplementation. The immunohistochemistry assay with D8 embryos cultivated with rHGAL-1 supplementation on the culture medium (SOF medium) could demonstrate the presence of exogenous GAL-1, distributed in mass cell and trophoblastic cells, and the profile observed is dependent of exogenous supplementation and it was more evident in hatched embryos. The findings reassure the use of a reasonable amount of rHGAL-1 for in vitro embryonic development and make using rHGAL-1 in assisted reproduction in humans more reliable and safer.

Phenol is added to acetophenone (methyl phenyl ketone) and to six of its halogenated derivatives in a supersonic jet expansion to determine the hydrogen bonding preference of the cold and isolated 1:1 complexes by linear infrared spectroscopy. Halogenation is found to have a pronounced effect on the docking site in this intermolecular ketone balance experiment. The spectra unambiguously decide between competing variants of phenyl group stacking due to their differences in hydrogen bond strength. Structures where the phenyl group interaction strongly distorts the hydrogen bond are more difficult to quantify in the experiment. For unsubstituted acetophenone, phenol clearly prefers the methyl side despite a predicted sub-kJ/mol advantage which is nearly independent of zero point vibrational energy, turning this complex into a challenging benchmark system for electronic structure methods which include long range dispersion interactions in some way.

Indoor scene recognition and semantic information can be helpful for social robots. Recently, in the field of indoor scene recognition, researchers have incorporated object-level information and shown improved performances. This paper demonstrates that scene recognition can be performed solely using object-level information in line with these advances. A state-of-the-art object detection model was trained to detect objects typically found in indoor environments and then used to detect objects in scene data. These predicted objects were then used as features to predict room categories. This paper successfully combines approaches conventionally used in computer vision (YOLO) and Term Frequency-Inverse Document Frequency (TF-IDF). These approaches could be further helpful in the field of embodied research and dynamic scene classification, which we elaborate on.

Accuracy and computational cost are the main challenges of deep neural networks in image recognition. This paper proposes an efficient ranking reduction to binary classification approach using a new feed-forward network and feature selection based on ranking the image pixels. Preference net (PN) is a novel deep ranking learning approach based on Preference Neural Network (PNN), which uses new ranking objective function and positive smooth staircase (PSS) activation function to accelerate the image pixels’ ranking. PN has a new type of weighted kernel based on spearman ranking correlation instead of convolution to build the features matrix. The PN employs multiple kernels that have different sizes to partial rank image pixels’ in order to find the best features sequence. PN consists of multiple PNNs’ have shared output layer. Each ranker kernel has a separate PNN. The output results are converted to classification accuracy using the score function. PN has promising results comparing to the latest deep learning (DL) networks using the weighted average ensemble of each PN models for each kernel on CFAR-10 and Mnist-Fashion datasets in terms of accuracy and less computational cost.

The integration of Artificial Intelligence (AI) in dairy farm management through biometric facial recognition for cows is a significant stride in livestock management. This review critically evaluates the evolution, applications, and challenges of AI-driven biometric facial recognition in dairy farming. It emphasizes the role of this technology in enhancing individual monitoring of dairy cows, providing accurate health, behavior, and productivity tracking. Originally derived from human facial recognition systems, this approach utilizes distinctive bovine facial features for essential, non-invasive, real-time monitoring in large-scale operations. The progression of AI from elementary pattern recognition to advanced Convolutional Neural Networks (CNNs) and deep learning models marks a shift toward data-driven farming. This study addresses key challenges such as environmental variability, data collection hurdles, ethical concerns, and technological limitations. It also contrasts various AI models, spotlighting their unique strengths and practical utility in dairy farming scenarios. Despite these challenges, facial recognition technology holds promise for improving farm efficiency, animal welfare, and sustainable practices, highlighting the need for continuous research and development. The review concludes by advocating for future research focused on environmental adaptability, ethical AI application, cross-breed compatibility, and integration with other farming technologies. Ultimately, it underscores AI's transformative potential in modernizing dairy farming towards a more data-oriented, responsible agricultural future.

Leader-follower autonomy (LFA) systems have so far only focused on vehicles following other vehicles. Though there have been several decades of research into this topic, there has not yet been any work on human-vehicle leader-follower systems. We present a system in which an autonomous vehicle — our ACTor 1 platform — can follow a human leader who controls the vehicle through gestures. We successfully developed a modular pipeline that uses artificial intelligence/deep learning to recognize hand-and-body gestures from a user in view of the vehicle’s camera and translate those gestures into physical action by the vehicle. We demonstrate our work using our ACTor 1 platform, a modified Polaris Gem 2 electric vehicle. This work has numerous applications, such as material transport in industrial contexts.

Intrinsically disordered proteins mediate crucial biological functions through their interactions with other proteins. Mutual synergistic folding (MSF) occurs when all interacting proteins are disordered, folding into a stable structure in the course of the complex formation. In these cases, the folding and binding processes occur in parallel, lending the resulting structures uniquely heterogeneous features. Currently there are no dedicated classification approaches that would take into account the particular biological and biophysical properties of MSF complexes. Here we present a scalable clustering-based classification scheme, built on redundancy-filtered features that describe the sequence and structure properties of the complexes, and the role of the interaction, which is directly responsible for structure formation. Using this approach, we define six major types of MSF complexes, corresponding to biologically meaningful groups. Hence, the presented method also shows that differences in binding strength, subcellular localization, and regulation are encoded in the sequence and structural properties of proteins. While current structure classification methods can also handle complex structures, we show that the developed scheme is fundamentally different, and since it takes into account defining features of MSF complexes, it serves as a better representation of structures arising through this specific interaction mode.

Machine learning is a fundamental aspect of artificial intelligence that involves the development of algorithms and models that allow computers to learn and make predictions or decisions without explicit programming. With the development of neural networks, back-propagation algorithms and deep learning, machine learning has made breakthroughs in the fields of image recognition, natural language processing and handwriting recognition using machine learning techniques. The advent of deep learning has revolutionized the field of handwriting recognition, using convolutional neural networks, recurrent neural networks, and sequence-to-sequence models to provide solutions that go beyond machine learning methods and significantly improve the accuracy and robustness of handwriting recognition systems. But challenges remain, including the need for large labelled datasets, computational resources and addressing potential biases. As research in deep learning techniques continues to drive handwriting recognition closer towards realisability, machine learning approaches remain at the forefront.

In recent years, with the popularity of smart mobile devices, the interaction between devices and users, especially in the form of voice interaction, has become increasingly important. If smart devices can understand more users' emotional states through voice data, more customized services can be provided for users. This paper proposes a novel machine learning model for speech emotion recognition, which combines convolutional neural networks (CNN), long short-term memory neural networks (LSTM), and deep neural networks (DNN), called CLDNN. To make the designed system can recognize the audio signal closer to the human auditory system does, this article uses the Mel frequency cepstral coefficients (MFCCs) of audio data as the input of the machine learning model. First, the MFCCs of the voice signal is extracted as the input of the model, and the feature values of the data are calculated using several local feature learning blocks (LFLB) composed of one-dimensional CNN. Because the audio signals are time-series data, the feature values obtained from LFLBs then input into LSTM layer to enhance the learning on time-series level. Finally, fully connected layers are used for classification and prediction. Three databases RAVDESS, EMO-DB and IEMOCAP are used for the experiments in this paper. The experimental results show that the proposed method can improve the accuracy compared to other related researches in speech emotion recognition.

The ability to efficiently recognize the emotions on others’ faces is something that most of us take for granted. Children with callous-unemotional (CU) traits and impulsivity/conduct problems (ICP), such as attention-deficit hyperactivity disorder, have been previously described as being “fear blind”. This is also associated with looking less at the eye regions of fearful faces, which are highly diagnostic. Previous attempts to intervene into emotion recognition strategies have not had lasting effects on participants’ fear recognition abilities. Here we present both (a) additional evidence that there is a two-part causal chain, from personality traits to face recognition strategies using the eyes, then from strategies to rates of recognizing fear in others; and (b) a pilot intervention that had persistent effects for weeks after the end of instruction. Further, the intervention led to more change in those with the highest CU traits. This both clarifies the specific mechanisms linking personality to emotion recognition and shows that the process is fundamentally malleable. It is possible that such training could promote empathy and reduce the rates of antisocial behavior in specific populations in the future.

Animal welfare is not only an ethically important consideration in good animal husbandry, but can also have a significant effect on an animal’s productivity. The aim of this paper is to show that a reduction in animal welfare, in the form of increased stress, can be identified in pigs from frontal images of the animals. We train a Convolutional Neural Network (CNN) using a leave-one-out design and show that it is able to discriminate between stressed and unstressed pigs with an accuracy of >90% in unseen animals. Grad-CAM is used to identify the animal regions used, and these support those used in manual assessments such as the Pig Grimace Scale. This innovative work paves the way for further work examining both positive and negative welfare states with a view to the development of an automated system that can be used in precision livestock farming to improve animal welfare.

Alzheimer’s disease (AD) causes dementia and memory loss in the elderly. Deposits of beta-amyloid peptide and hyperphosphorylated tau protein are present in AD’s brain. A filtrate of Helicobacter pylori’s culture was previously found to induce hyperphosphorylation of tau in vivo, suggesting that bacterial exotoxins could permeate the blood brain barrier and directly induce tau’s phosphorylation. H. pylori, which infects ~60% of the world population and causes gastritis and gastric cancer, produces a pro-inflammatory urease (HPU). Here the neurotoxic potential of HPU was investigated in cultured cells and in rats. SH-SY5Y neuroblastoma cells exposed HPU (50-300 nM) produced reactive oxygen species (ROS) and had an increased [Ca2+]i. HPU-treated BV-2 microglial cells produced ROS, cytokines IL-1β and TNF-α, expressed Iba1 and showed reduced viability, consistent with a neurotoxic effect of HPU. Rats received daily i.p. HPU (5 µg) for 7 days. Hyperphosphorylation of tau at Thr205, Ser199 and Ser396 sites was seen in hippocampal homogenates of treated rats, with no alterations in total tau or GSK-3b levels. HPU was not detected in the brain homogenates. Behavioral tests were performed to assess cognitive impairments. Our findings support previous data suggesting an association between infection by H. pylori and tauopathies such as AD, possibly mediated by its urease.

The paper concludes the first research on mouth-based Emotion Recognition (ER), adopting a Transfer Learning (TL) approach. Transfer Learning results paramount for mouth-based emotion ER, because a few data sets are available, and most of them include emotional expressions simulated by actors, instead of adopting a real-world categorization. Using TL we can use fewer training data than training a whole network from scratch, thus more efficiently fine-tuning the network with emotional data and improving the convolutional neural network accuracy in the desired domain. The proposed approach aims at improving the Emotion Recognition dynamically, taking into account not only new scenarios but also modified situations with respect to the initial training phase, because the image of the mouth can be available even when the whole face is visible only in an unfavourable perspective. Typical applications include automated supervision of bedridden critical patients in an healthcare management environment, or portable applications supporting disabled users having difficulties in seeing or recognizing facial emotions. This work takes advantage from previous preliminary works on mouth-based emotion recognition using CNN deep-learning, and has the further benefit of testing and comparing a set of networks on large data sets for face-based emotion recognition well known in literature. The final result is not directly comparable with works on full-face ER, but valorizes the significance of mouth in emotion recognition, obtaining consistent performances on the visual emotion recognition domain.

Here we present a blockchain-backed token recognition system to reward the contributions that academics make to the scientific ecosystem. Recognition is important in science but current methods, systems and incentives are limited. Specifically, the traditional focus on narrow publication metrics means diverse contributions are not captured, while bias toward senior, established scientists is common. To tackle this challenge, we explore the potential of harnessing blockchain’s collaborative, decentralised and trust-brokering properties to develop a token reward system for use by research funders. Academics would be awarded tokens for undertaking common but vital tasks such as peer review, sitting on funding committees and submitting reports. These tokens would not be tradable or specifically monetisable but would serve as a validated record of scientific contribution. They would have value in professional recruitment and job placement, support grant and award applications, and inform performance appraisals and file reviews. Coordination and cooperation across multiple funding agencies in developing the platform would provide an opportunity to aggregate and standardise recognition, given academics often work with several funders. This system’s goals are to expand recognition metrics, promote efficiencies, improve the robustness of professional assessments and enable cross-funder collaboration, thereby optimising research processes and practices in a decentralised and democratised manner.

While the desire to uncover the neural correlates of consciousness has taken numerous directions, self-face recognition has been a constant in attempts to isolate aspects of self-awareness. The neuroimaging revolution of the 1990’s bought about systematic attempts to isolate the underlying neural basis self-face recognition. These studies, including some of the first fMRI (functional Magnetic Resonance Imaging) studies, revealed a right hemisphere bias for self-face recognition in a diverse set of regions including the insula, the Dorsal Frontal Lobe, the Temporal Parietal Junction and Medial Temporal Cortex. Confirmation of these data (which are correlational) was provided by TMS (Transcranial Magnetic Stimulation) and patients in which direct inhibition or ablation of right hemisphere regions leads to a disruption or absence of self-face recognition. These data are consistent with a number of theories including a right hemisphere dominance for self-awareness and/or a right hemisphere specialization for identifying significant social relationships including to oneself.

The influence of distant London dispersion forces on the docking preference of alcohols of different size between the two lone electron pairs of the carbonyl group in pinacolone is explored by infrared spectroscopy of the OH stretching fundamental in supersonic jet expansions of 1:1 solvate complexes. Experimentally, no pronounced tendency of the alcohol to switch from the methyl to the bulkier tert-butyl side with increasing size is found. In all cases, methyl docking dominates by at least a factor of two, whereas DFT-optimized structures suggest a very close balance for the larger alcohols, once corrected by CCSD(T) relative electronic energies. Together with inconsistencies when switching from a C4 to a C5 alcohol, this points at deficiencies of the investigated B3LYP and in particular TPSS functionals even after dispersion correction, which cannot be blamed on zero point energy effects. The search for density functionals which describe the harmonic frequency shift, the structural change and the energy difference between the docking isomers of larger alcohols to unsymmetric ketones in a satisfactory way is open.

One control challenge in prosthetic legs is seamless transition from one gait mode to another. User intent recognition (UIR) is a high-level controller that tells a low-level controller to switch to the identified activity mode, depending on the user’s intent and environment. We propose a new framework to design an optimal UIR system with simultaneous maximum performance and parsimony for gait mode recognition. We use multi-objective optimization (MOO) to find an optimal feature subset that creates a trade-off between these two conflicting objectives. The main contribution of this paper is two-fold: (1) a new gradient-based multi-objective feature selection (GMOFS) method for optimal UIR design; and (2) the application of advanced evolutionary MOO methods for UIR. GMOFS is an embedded method that simultaneously performs feature selection and classification by incorporating an elastic net in multilayer perceptron neural network training. Experimental data are collected from six subjects, including three able-bodied subjects and three transfemoral amputees. We implement GMOFS and four variants of multi-objective biogeography-based optimization (MOBBO) for optimal feature subset selection, and we compare their performances using normalized hypervolume and relative coverage. GMOFS demonstrates competitive performance compared to the four MOBBO methods. We achieve a mean classification accuracy of 97.14% ± 1.51% and 98.45% ± 1.22% with the optimal selected subset for able-bodied and amputee subjects, respectively, while using only 23% of the available features. Results thus indicate the potential of advanced optimization methods to simultaneously achieve accurate, reliable, and compact UIR for locomotion mode detection of lower-limb amputees with prostheses.

Cardiovascular disease (CVD) may sometimes unexpected loss of life. It affects the heart and blood vessels of body. CVD plays an important factor of life since it may cause death of human. It is necessary to detect early of this disease for securing patients life. In this chpter two exclusively different methods are proposed for detection of heart disease. The first one is Pattern Recognition Approach with grammatical concept and the second one is machine learning approach. In the syntactic pattern recognition approach initially ECG wave from different leads is decomposed into pattern primitive based on diagnostic criteria. These primitives are then used as terminals of the proposed grammar. Pattern primitives are then input to the grammar. The parsing table is created in a tabular form. It finally indicates the patient with any disease or normal. Here five diseases beside normal are considered. Different Machine Learning (ML) approaches may be used for detecting patients with CVD and assisting health care systems also. These are useful for learning and utilizing the patterns discovered from large databases. It applies to a set of information in order to recognize underlying relationship patterns from the information set. It is basically a learning stage. Unknown incoming set of patterns can be tested using these methods. Due to its self-adaptive structure Deep Learning (DL) can process information with minimal processing time. DL exemplifies the use of neural network. A predictive model follows DL techniques for analyzing and assessing patients with heart disease. A hybrid approach based on Convolutional Layer and Gated-Recurrent Unit (GRU) are used in the paper for diagnosing the heart disease.

In this work, we show that a late fusion approach to multi-modality in sign language recognition improves the overall ability of the model in comparison to the singular approaches of Computer Vision (88.14%) and Leap Motion data classification (72.73%). With a large synchronous dataset of 18 BSL gestures collected from multiple subjects, two deep neural networks are benchmarked and compared to derive a best topology for each. The Vision model is implemented by a CNN and optimised MLP and the Leap Motion model is implemented by an evolutionary optimised deep MLP topology search. Next, the two best networks are fused for synchronised processing which results in a better overall result (94.44%) since complementary features are learnt in addition to the original task. The hypothesis is further supported by application of the three models to a set of completely unseen data where a multi-modality approach achieves the best results relative to the single sensor method. When transfer learning with the weights trained via BSL, all three models outperform standard random weight distribution when classifying ASL, and the best model overall for ASL classification was the transfer learning multi-modality approach which scored 82.55% accuracy.

In this paper, we propose a robust video understanding model for activity recognition by learning the actor’s pair-wise correlations and relational reasoning, exploiting spatial and temporal information. In order to measure the similarity between the pair appearances and construct an actor relations map, the Zero Mean Normalized Cross-Correlation (ZNCC) and the Zero Mean Sum of Absolute Differences(ZSAD) is proposed to allow the Graph Convolution Network (GCN) to learn how to distinguish group actions. We recommend that MNASNet be used as the backbone to retrieve features. Experiments show a 38.50% and 23.7% reduction in training time in the 2-stage training process along with a 1.52% improvement in accuracy against traditional methods.

It is crucial to select the right machine learning classifier for image classification and face recog-nition. This study examines the effectiveness of four different face recognition classifiers - Support Vector Machines (SVM), Random Forest, K-Nearest Neighbors (KNN), and Neural Networks. An analysis of the Large Faces in the Wild (LFW) dataset was carried out using Principal Component Analysis (PCA). Classifiers are rigorously trained and evaluated based on the extracted features. Comparison of classifier performance is an insightful way to figure out their strengths and weaknesses. Having a visual representation of the classifier's performance gives a complete understanding of its capabilities. Through the selection of the most appropriate classifier, study results contribute to advancements in image classification, recognition, and biometric identification. The comparison study demonstrated that the Neural Network classifier was exceptionally accurate and proficient in recognizing faces from the LFW dataset when used in conjunction with PCA for feature extraction. According to the comparative analysis, the Neural Network classifier proved exceptionally accurate and proficient at identifying faces from the LFW dataset when combined with PCA for feature extraction.

In the last years, more and more studies highlight the advantages of complementing traditional master classes with additional activities that improve students´ learning experience. This combination of teaching techniques is specially advised in the field of structural engineering, where intuition of the structural response it is of vital importance to understand the studied concepts. This paper deals with the introduction of a new (and more encouraging) educational tool to introduce intuitively students in the dynamic response of structures excited with an educational shaking table. Most of the educational structural health monitoring systems use sensors to determine the dynamic response of the structure. The proposed tool is based on a radically different approach, as it is based on low-cost image-recognition techniques. In fact, it only requires the use an amateur camera, a black background and a computer. In this study, the effects of both the camera location and the image quality are also evaluated. Finally, to validate the applicability of the proposed methodology, the dynamic response of small-scale buildings with different typologies is analyzed. In addition, a series of surveys were conducted in order to evaluate the activity based on student´s satisfaction and the actual acquisition and strengthening of knowledge.

Background. False memories tend to increase in healthy and pathological aging, and their reduction could be useful in improving cognitive functioning. The objective was to use an active-placebo method to verify whether the application of tDCS in improving true recognition and reducing false memories in healthy older people. Method. Participants were 29 healthy older adults (65-78 years old) assigned to active or placebo group; active group received anodal stimulation at 2mA for 20 min over F7. An experimental task was used to estimate true and false recognition. The procedure took place in two sessions on two consecutive days. Results. A mixed ANOVA of true recognition showed a significant main effect of session (p = .004), indicating an increase from before treatment to after it. False recognition showed a significant main effect (p = .004), indicating a decrease from before treatment to after it and a significant session x group interaction (p < .0001). Conclusions. Overall, our results show that tDCS is an effective tool for increasing true recognition and reducing false recognition in healthy older people, and suggest that stimulation improves recall by increasing the number of items a participant can recall and reducing the number of memory errors.

The promised dataset was obtained from the daily Turkish words and phrases pronounced by various people in the videos posted on YouTube. The purpose of collecting the dataset is to provide detection of the spoken word by recognizing patterns or classifying lip movements with supervised, unsupervised, semi-supervised learning and machine learning algorithms. Most of the datasets related with lip reading consist of people recorded on camera with fixed backgrounds and the same conditions, but the dataset presented here consists of images compatible with machine learning models developed for real-life challenges. It contains a total of 2335 instances taken from TV series, movies, vlogs, and song clips on YouTube. The images in the dataset vary due to factors such as the way people say words, accent, speaking rate, gender and age. Furthermore, the instances in the dataset consist of videos with different angles, shadows, resolution, and brightness that are not created manually. The most important feature of our lip reading dataset is that we contribute to the non-synthetic Turkish dataset pool, which does not have wide dataset varieties. Machine learning studies can be carried out in many areas, such as the defense industry and social life, with this dataset.

Single sample face recognition (SSFR) is a computer vision challenge. In this scenario, there is only one example from each individual on which to train the system, making it difficult to identify persons in unconstrained environments, particularly when dealing with changes in facial expression, posture, lighting, and occlusion. This paper suggests a different method based on a variant of the Binarized Statistical Image Features (BSIF) descriptor called Multi-Block Color-Binarized Statistical Image Features (MB-C-BSIF) to resolve the SSFR Problem. First, the MB-C-BSIF method decomposes a facial image into three channels (e.g., red, green, and blue), then it divides each channel into equal non-overlapping blocks to select the local facial characteristics that are consequently employed in the classification phase. Finally, the identity is determined by calculating the similarities among the characteristic vectors adopting a distance measurement of the k-nearest neighbors (K-NN) classifier. Extensive experiments on several subsets of the unconstrained Alex &amp; Robert (AR) and Labeled Faces in the Wild (LFW) databases show that the MB-C-BSIF achieves superior results in unconstrained situations when compared to current state-of-the-art methods, especially when dealing with changes in facial expression, lighting, and occlusion. Furthermore, the suggested method employs algorithms with lower computational cost, making it ideal for real-time applications.

In this paper we use quantum machine learning to detect and classify ocular diseases across age related macular degradation, cataract, diabetic, glaucoma, hypertension, and patological myopia categories versus a control group. We analyze fundus imagery from 1000 patients. Early findings indicate there may be benefit in terms of accuracy and loss function minimization of 2.07% and 1.979x respectively compared to a similar method implemented using traditional computers.

The control of the three-dimensional (3D) polymer network structure is important for permselective materials when specific biomolecules detection is needed. Here we investigate conditions to obtain a tailored hydrogel network that combine both molecular filtering and molecular capture capabilities for biosensing applications. Along this line short oligonucleotide detection in a displacement assay is set within PEGDA hydrogels synthetized by UV radical photopolymerization. To provide insights on the molecular filter capability, diffusion studies of several probes (sulforhodamine G and dextrans) with different hydrodynamic radii were carried out using NMR technique. Moreover, fluorometric analyses of hybridization of DNA oligonucleotides inside PEGDA-hydrogels shed light on the mechanisms of recognition in 3D, highlighting that mesh size and crowding effect greatly impact of hybridization mechanism onto polymer network. Finally, we found the best probe density and diffusion transport conditions to allow the specific oligonucleotide capture and detection inside PEGDA-hydrogels for oligonucleotide detection and the filtering out of higher molecular weight molecules.

Table detection is a preliminary step in extracting reliable information from tables in scanned document images. We present CasTabDetectoRS, a novel end-to-end trainable table detection framework that operates on Cascade Mask R-CNN, including Recursive Feature Pyramid network and Switchable Atrous Convolution in the existing backbone architecture. By utilizing a comparatively lightweight backbone of ResNet-50, this paper demonstrates that superior results are attainable without relying on pre and post-processing methods, heavier backbone networks (ResNet-101, ResNeXt-152), and memory-intensive deformable convolutions. We evaluate the proposed approach on five different publicly available table detection datasets. Our CasTabDetectoRS outperforms the previous state-of-the-art results on four datasets (ICDAR-19, TableBank, UNLV, and Marmot) and accomplishes comparable results on ICDAR-17 POD. Upon comparing with previous state-of-the-art results, we obtain a significant relative error reduction of 56.36%, 20%, 4.5%, and 3.5% on the datasets of ICDAR-19, TableBank, UNLV, and Marmot, respectively. Furthermore, this paper sets a new benchmark by performing exhaustive cross-datasets evaluations to exhibit the generalization capabilities of the proposed method.

Recent advancements in Artificial Intelligence (AI), Deep Learning (DL), and computer vision have revolutionized various industrial processes through image classification and object detection. State-of-the-art Optical Character Recognition (OCR) and Object Detection (OD) technologies, such as YOLO and PaddleOCR, have emerged as powerful solutions for addressing challenges in recognizing textual and non-textual information on printed stickers. However, a well-established framework integrating these cutting-edge technologies for industrial applications still needs to be discovered. In this paper, we propose an innovative framework that combines advanced OCR and OD techniques to automate visual inspection processes in an industrial context. Our primary contribution is a comprehensive framework adept at detecting and recognizing textual and non-textual information on printed stickers within a company, harnessing the latest AI tools and technologies for sticker information recognition. Our experiments reveal an overall macro accuracy of 0.88 for the sticker OCR across three distinct patterns. Furthermore, the proposed system goes beyond traditional Printed Character Recognition (PCR) by extracting supplementary information, such as barcodes and QR codes present in the image, significantly streamlining industrial workflows and minimizing manual labor demands.

Wernicke-Korsakoff syndrome (WKS) is induced by thiamine deficiency (TD) and mainly related to alcohol consumption. Frontal cortex dysfunction has been associated to impulsivity and disinhibition in WKS patients. The pathophysiology involves oxidative stress, excitotoxicity and inflammatory responses leading to neuronal death, but the relative contributions of each factor (alcohol and TD, isolate or in interaction) to these phenomena are still poorly understood. A rat model was used by forced consumption of 20% (w/v) alcohol for 9 months (CA), TD hit (TD diet + pyrithiamine 0.25 mg/kg, i.p. daily injections the last 12 days of experimentation; TDD), and both combined treatments (CA+TDD). Motor and cognitive performance and cortical damage were examined. CA caused hyperlocomotion as a possible sensitization of ethanol-induced excitatory effects and recognition memory deficits. In addition, CA+TDD animals showed a disinhibited-like behavior, which appears to be dependent on TDD. Also, combined treatment led to more pronounced alterations in nitrosative stress, lipid peroxidation, apoptosis and cell damage markers. Correlations between injury signals and disinhibition suggest that CA+TDD disrupts behaviors dependent on the frontal cortex. Our study sheds light on the potential disease-specific mechanisms, reinforcing the need for neuroprotective therapeutic approaches along with preventive treatments for the nutritional deficiency in WKS.

Motivated by the way animals react in nature, we introduce a fully-connected neural-network model, which incorporates the external pattern presented to the system as a fundamental tool of the recognition process. In this new scenario, in the absence of this external field, memories are not attractors inside basins of attraction, as in usual attractor neural networks, although basins may be created according to the external pattern, thus allowing storing a much larger number of memories. The key point consists in calibrating the influence of the external pattern such as to cancel the noise generated by those memories not correlated with the external pattern.We illustrate how this proposal works by including this new contribution in the standard Hopfield model, showing a significant increase in its recognition capacity (typically by a factor $10^{2}$). As an additional feature of this model, we show its ability to react promptly to changes in the external environment, a crucial attribute of living beings. This procedure can be applied to a wide variety of neural-network models to increase considerably their recognition and reaction capabilities.

This article introduces a new way of using a Fibre Bragg Grating (FBG) sensor for detecting the presence and number of occupants in the monitored space in a Smart Home (SH). CO₂ sensors are used to determine the CO₂ concentration of the monitored rooms in an SH. CO₂ sensors can also be used for occupancy recognition of the monitored spaces in SH. To determine the presence of occupants in the monitored rooms of the SH, the newly devised method of CO₂ prediction, by means of an Artificial Neural Network (ANN) with a Scaled Conjugate Gradient (SCG) algorithm using measurements of typical operational technical quantities (indoor temperature, relative humidity indoor and CO₂ concentration in the SH) is used. The goal of the experiments is to verify the possibility of using the FBG sensor in order to unambiguously detect the number of occupants in the selected room (R104) and, at the same time, to harness the newly proposed method of CO₂ prediction with ANN SCG for recognition of the SH occupancy status and the SH spatial location (rooms R104, R203, and R204) of an occupant. The designed experiments will verify the possibility of using a minimum number of sensors for measuring the non-electric quantities of indoor temperature and indoor relative humidity and the possibility of monitoring the presence of occupants in the SH using CO₂ prediction by means of the ANN SCG method with ANN learning for the data obtained from only one room (R203). The prediction accuracy exceeded 90% in certain experiments. The uniqueness and innovativeness of the described solution lie in the integrated multidisciplinary application of technological procedures (the BACnet technology control SH, FBG sensors) and mathematical methods (ANN prediction with SCG algorithm, the Adaptive Filtration with of LMS algorithm) employed for the recognition of number persons and occupancy recognition of selected monitored rooms of SH.

A large part of our understanding of the biological substrates of sex-recognition and mate-recognition is derived by studying animal models. In performing those tasks, rodents rely mostly of pheromones and other olfactory cues, whereas humans rely mostly on visual cues. That may hinder the translation of rodents’ biology to humans’ biology, especially at the neural-networks level, where those cues traverse different networks in humans and rodents brains. That may be called the “pheromonal-visual gap”. A theoretical model presented here addresses those issues. The model merges observations from humans and model-animals, as reported in specific scientific reports, and general biological principles that are accepted by the scientific community. The model suggests that the voices of men and women are the innate cues based on which humans learn to use visual cues in sex-recognition and mate-recognition. Children learn the two tasks in associative learning mechanisms, by being immersed in their community, and observing adult role-models in innocuous, non-sexual scenarios. The model proposes that the human medial-geniculate-nucleus (MGN) is the analog of the rodents’ accessory-olfactory-bulb (AOB) and the main-olfactory-bulb (MOB), and that the human MASH pathway (MGN, amygdala, bnST, hypothalamus) is the analog of the rodents’ VNOP (Vomeronasal-organ-pathway). Considering the differences in the pathways should facilitate the translation from rodents’ brain nuclei and tracks to humans’. Also, the model hypothesizes that innate direct and indirect connections between auditory centers, e.g., MGN, and sex-control centers, e.g., hypothalamus, vary across three groups of children, and those variations determine the individual’s mate-recognition that emerges at puberty.

The emerging advancements in separation and classification of various biological matters (e.g., living cells and proteins) using magnetic levitation (MagLev) technology have proven to be effective for improving disease diagnostics. MagLev technique has the capacity to detect and separate useful diagnostic biomarkers from biocomplex environments (e.g., blood and plasma), minimizing the unpleasant daunting task of sample preparations and labeling procedures. Here, we demonstrate the capability of this technique combined with image analysis and machine learning approaches for discriminating the various types of multiple sclerosis (MS) as an important model disease. To arrive at a systematic expert system, we combined robust statistical analysis with machine learning to (1) detect and remove outliers from the raw MagLev image datasets; then (2) process the images and output a low dimensional representation of massive data without losing the main statistical features; and finally (3) predict the MS clinical disease type (Relapsing-Remitting, Primary–Progressive, or Secondary–Progressive) using a classifier. This is expected to improve MS diagnostics since the current practices rely solely on clinical observation and central nervous system imaging, making management approaches are often reactional and inefficient. Thus, there is a need to identify the disease type early on. MagLev is expected to improve MS diagnostics, thereby aiding in prognosis and guiding adequate treatment choices before the patient exhibits signs of permanent neurological deficits.

Artificial intelligence’s rapid advancement has enabled various applications, including intelligent video surveillance systems, assisted living, and human-computer interaction. These applications often require one core task: video-based human action recognition. Research in human video-based human action recognition is vast and ongoing, making it difficult to assess the full scope of available methods and current trends. This survey provides an in-depth exploration of the vision-based human action recognition field, comprehensively offering the available techniques and their evolution, highlighting the cutting-edge ideas driving its development. We also analyze the most used keywords in research papers over the past years to identify trends and predict possible future directions. Hence, this concise survey helps researchers understand the breadth of existing approaches, evaluate current research trends, and stay up-to-date on potential developments.

The multidrug efflux transporter ABCB1 is clinically important for drug absorption and distribution and can be a determinant of chemotherapy failure. Recent structure data shows that three glutamines donate hydrogen bonds to co-ordinate taxol in the drug binding pocket. This is consistent with earlier drug structure-activity relationships that implicated the importance of hydrogen bonds in drug recognition by ABCB1. By replacing the glutamines with alanines we have tested whether any or all of Q347, Q725 and Q990 are important for the transport of three different drug classes. Flow cytometric transport assays show that Q347A and Q990A act synergistically to reduce transport of Calcein-AM, BODIPY-verapamil and OREGON GREEN-taxol bisacetate but the magnitude of the effect was dependent on the test drug and no combination of mutations completely abrogated function. Surprisingly, Q725A mutants generally improved transport of Calcein-AM and BODIPY-verapamil, suggesting that engagement of the wild-type Q725 in a hydrogen bond is inhibitory for the transport mechanism. To test transport of unmodified taxol, stable expression of Q347/725A and the triple mutant was engineered and shown to confer equivalent resistance to the drug as the wild-type transporter, further indicating that none of these potential hydrogen bonds between transporter and transport substrate are critical for function of ABCB1. The implications of the data for plasticity of the drug binding pocket are discussed.

It is a challenging problem that air-written Arabic letters has received a lot of attention in the past decades when compared to commonly spoken languages like English languages. To fill this gap, we propose a strong model that brings together machine learning (ML) and optical character recognition (OCR) methods. The model applied several ML methods, (i.e., Neural Networks (NN), Random Forest (RF), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM), with deep convolutional neural networks (CNNs) such as VGG16, VGG19, and SqueezeNet for effective feature extraction. Our study utilizes the AHAWP dataset, which consists of varied writing styles and variations in hand signs, to train and evaluate the model. Preprocessing systems are applied to improve data quality by reduction bias. Besides, OCR methods are combined into our model to sequestrate individual letters from continuous air-written gestures and refine recognition results. Results of this study show that the proposed model has achieved the extreme accuracy of 88.8% using NN with VGG16. This study presents an inclusive approach that combines ML, deep CNNs, and OCR methods to address the issue of Arabic in air writing recognition research.

This paper presents a framework to recognize the affective state of children with Autism Spectrum Disorder (ASD) in an in-the-wild setting using Heart Rate (HR) information. Our algorithm classifies a child’s emotion into positive, negative, or neutral states by analyzing the heart rate signal. The HR signal is obtained from a smartwatch in real-time using our smartwatch application. The heart rate data is acquired when the child learns to code a robot while interacting with an avatar that assists the child in communications skills and programming the robot. In this paper, we also present a comparison of using HR data for the classification of emotions with classification based on features extracted from HR signals using Discrete Wavelet Transform (DWT). Our experimental results show that the proposed method produces a comparable performance with the state-of-the-art HR-based emotion recognition techniques, despite the fact that our experiments are performed in an uncontrolled setting as opposed to a lab environment. This work contributes to real-world affect analysis of children with ASD using HR information.

Patients with heart failure have difficulty in self-care management, as daily monitoring and recognizing symptoms do not readily triggers an action to avoid hospital admissions. The purpose of this study was to understand the impact of a nurse-led complex intervention on symptom recognition and fluid restriction. A latent growth model was designed to estimate self-care management and quality of life changes on patients with heart failure and assessed by a pilot study, for three months, to sixty-three patients (33 control, 30 intervention). Patients in the control group had a higher risk of hospitalisation (IRR 11.36; p<.001) and emergency admission (IRR 4.24; p<.001) at three-months follow-up. Analysis of the time scores demonstrated that the intervention group had a clear improvement in self-care behaviours (βSlope. Assignment_group=-.881; p<.001) and in the quality of life (βSlope. Assignment_group=1.739; p<.001). This study supports that a nurse-led program on symptom recognition and fluid restriction can have a positive impact on self-care behaviours and quality of life in patients with heart failure.

Studies on crop response to light quality [red (R) to far-red (FR) light ratio] often recommend early weed removal to reduce the effects of shade avoidance responses on crop yield. However, it is unclear whether crops are able to distinguish reflected light quality of kin from that of non-kin. We evaluated the response of sugarbeet (Beta vulgaris L.) to reflected FR light from sugarbeet, common lambsquarters (Chenopodium album L.), Kentucky bluegrass (Poa pratensis L.), alfalfa (Medicago sativa L.), and bare soil (control) under outdoor conditions in 2016 and 2017. Treatments were completely randomized with 10 replications per treatment. The study methods ensured there was no direct resource competition. The reflected R:FR of plant species ranged from 0.06 (common lambsquarters) to 0.24 (sugarbeet) compared to 0.7 for the bare soil. In both 2016 and 2017, there were 2 to 4 more leaves in the sugarbeet surrounded by soil compared to sugarbeet surrounded by neighboring species. There was up to 47, 57, 43, and 23% reduction in sugarbeet leaf area, shoot dry weight, root diameter, and root dry weight, respectively, due to reflected R:FR light from neighboring species. Sugarbeet did not respond differently to reflected light quality of kin compared to non-kin.

Cyber-physical security is vital for protecting key computing infrastructure against cyber attacks. Individuals, corporations, and society can all suffer considerable digital asset losses due to cyber attacks, including Data loss, theft, financial loss, reputation harm, company interruption, infrastructure damage, ransomware attacks, and espionage. A cyber-physical attack harms both digital and physical assets. Cyber-physical system security is more challenging than software-level cyber security because it requires physical inspection and monitoring. This paper proposes an innovative and effective algorithm to strengthen Cyber-Physical Security (CPS) with minimal human intervention. It is a Human Activity Recognition (HAR)-based approach where a GoogleNet-BiLSTM network hybridization has been used to recognize suspicious activities in cyber-physical infrastructure perimeter. The proposed HAR-CPS algorithm classifies suspicious activities from real-time video surveillance with an average accuracy of 73.15%. It incorporates Machine Vision at the IoT Edge (Mez) technology to make the system latency tolerant. Dual-layer security has been ensured by operating the proposed algorithm and GoogleNet-BiLSTM hybrid network from a cloud server, which ensures the security of the proposed security system. The innovative optimization scheme makes it possible to strengthen cyber-physical security with $4.29 per month only.

Patients with heart failure have difficulty in self-care management, as daily monitoring and recognizing symptoms do not readily trigger an action to avoid hospital admissions. The purpose of this study was to understand the impact of a nurse-led complex intervention on symptom recognition and fluid restriction. A latent growth model was designed to estimate self-care management and quality of life changes on patients with heart failure and assessed by a pilot study, for three months, to sixty-three patients (33 control, 30 intervention). Patients in the control group had a higher risk of hospitalisation (IRR 11.36; p<.001) and emergency admission (IRR 4.24; p<.001) at three-months follow-up. Analysis of the time scores demonstrated that the intervention group had a clear improvement in self-care behaviours (βSlope. Assign-ment_group=-.881; p<.001) and in the quality of life (βSlope. Assignment_group=1.739; p<.001). This study supports that a nurse-led program on symptom recognition and fluid restriction can have a positive impact on self-care behaviours and quality of life in patients with heart failure.

In this paper, a framework for simultaneous tracking and recognizing drone targets using a low-cost and small-sized millimeter-wave radar is presented. The radar collects the reflected signals of multiple targets in the field of view including drone and non-drone targets. The analysis of the received signals allows multiple targets to be distinguished because of the different reflection patterns. The proposed framework consists of four processes including signal processing, cloud points clustering, target tracking, and target recognition. Signal processing translates the raw signals into spare cloud points. These points are merged into several clusters, each representing a single target. Target tracking estimates the new locations of each detected target. A novel convolutional neural network model is developed for drone and/or non-drone targets feature extraction and recognition. For performance evaluation, a dataset collected with an IWR6843ISK mmWave sensor by Texas Instruments is used for training and testing the convolutional neural network. The proposed recognition model achieves an accuracy of 98.4% for one target and 98.1% for two targets.

Facial expressions play a key role in interpersonal communication when it comes to negotiating our emotions and intentions, as well as interpreting those of others. Research has shown that we can connect to other people better when we exhibit signs of empathy and facial mimicry. However, the relationship between empathy and facial mimicry is still debated. Among the factors contributing to the difference in results across existing studies is the use of different instruments for measuring both empathy and facial mimicry, as well as often ignoring the differences across various demographic groups. This study first looks at the differences in empathetic abilities of people across different demographic groups based on gender, ethnicity and age. The empathetic ability is measured based on the Empathy Quotient capturing a balanced representation of both emotional and cognitive empathy. Using statistical and machine learning methods, the study then investigates the correlation between the empathetic ability and facial mimicry of subjects in response to images portraying different emotions displayed on a computer screen. Unlike the existing studies measuring facial mimicry using electromyography, this study employs a technology detecting facial expressions based on video capture and deep learning. This choice was made in the context of increased online communication during and post the COVID-19 pandemic. The results of this study confirm the previously reported difference in the empathetic ability between females and males. However, no significant difference in the empathetic ability was found across different age and ethnic groups. Furthermore, no strong correlation was found between empathy and facial reactions to faces portraying different emotions shown on a computer screen. Overall, the results of this study can be used to inform the design of online communication technologies and tools for training empathy team leaders, educators, social, and health care providers.

The utilization of Pig Emotion Recognition (PER) driven by Artificial Intelligence (AI) promises to mitigate labor costs and alleviate stress among domestic pigs, thereby minimizing the need for consistent human intervention. Nevertheless, this research acknowledges the inherent limitations within the raw PER datasets, which often include irrelevant porcine features, hence impeding genuine progress in real-world evaluations. A significant proportion of PER datasets derive from sequential pig imagery obtained from video recordings, and a common pitfall in these studies is the unregulated shuffling of data. This lack of control can result in the overlap of data samples between training and testing groups, thereby yielding skewed experimental evaluations. To address these challenges, this paper introduces a novel solution in the form of the Semi-Shuffle-Pig Detector (SSPD) for PER datasets, with the intent to facilitate a less biased experimental output. By applying the SSPD, we can ensure that all testing data samples remain distinct from the training datasets, and any superfluous information from raw images is systematically discarded. This optimized method enhances the true performance of classification, providing unbiased experimental evaluations. Notably, our approach has led to a remarkable improvement in the Isolation After Feeding (IAF) metric by 20.2\% and achieved higher accuracy in segregating IAF and Paired After Feeding (PAF) classifications exceeding 92\%. This methodology, thereby, ensures the preservation of pertinent data within the PER system and eliminates potential biases in experimental evaluations. Consequently, it elevates the accuracy and reliability of real-world PER applications, resulting in a tangible positive impact on both pig welfare management and food safety standards.

Osteosarcoma is the most common subtype of primary bone cancers, affecting mostly adolescents. In recent years, several studies have focused on elucidating the molecular mechanisms of this sarcoma; however, its molecular etiology has still not been determined with precision. Therefore, we applied a consensus strategy with the use of several bioinformatics tools to prioritize genes involved in its pathogenesis. Subsequently, we assessed the physical interactions of the previously selected genes and applied a communality analysis to this protein-protein interaction network. The consensus strategy prioritized a total list of 553 genes. Our enrichment analysis validates several studies that describe the signaling pathways PI3K/AKT and MAPK/ERK as pathogenic. The gene ontology described TP53 as a principal signal transducer that chiefly mediates processes associated with cell cycle and DNA damage response It is interesting to note that the communality analysis clusters several members involved in metastasis events such as MMP2 and MMP9 and genes associated with DNA repair complexes, like ATM, ATR, CHEK1, and RAD51. In this study, we could identify well-known pathogenic genes for osteosarcoma and prioritized genes that need to be further explored.

Identification of plants is a challenging task which aims to identify the family, genus, and species level according to morphological features. Automated deep learning-based computer vision algorithms are widely used for identifying plants and can help users to narrow down the possibilities. However, numerous morphological similarities between and within species make the classification difficult. In this paper, we tested a custom convolution neural network (CNN) and vision transformer (ViT) based models using the PyTorch framework to classify plants. We used a large dataset of 88K and 16K images for classifying plants at genus and species levels respectively. Our results show that for classifying plants at the genus level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420, and other state-of-the-art CNN-based models suggested in previous studies on a similar dataset. The ViT model achieved top accuracy of 83.3% for classifying plants at the genus level. ViT models also perform better for classifying plants at the species level compared to CNN-based models ResNet50 and ResNet-RS-420, with a top accuracy of 92.5%. We show that the correct set of augmentation techniques plays an important role in classification success.

This paper documents the development of a special case of multilingual Automatic Speech Recognition model, specifically tailored to attend two languages spoken by the majority of Latin America, Portuguese and Spanish. The bilingual model combines Language Identification and Speech Recognition developed with the Wav2Vec2.0 architecture and trained on several open and private speech datasets. In this model, the feature encoder is trained jointly for all tasks and different context encoders are trained for each task. The model is evaluated separately on two tasks: language identification and speech recognition. The results indicate that this model achieves good performance on speech recognition and average performance on language identification, training on a low quantity of speech material. The average accuracy of the language identification module on the MLS dataset is 66.75%. The average Word Error Rate in the same scenario is 13.89%, which is better than average 22.58% achieved by the commercial speech recognizer developed by Google.

The automatic classification of bird sounds is an ongoing research topic and several results have been reported for the classification of selected bird species. In this contribution we use an artificial neural network fed with pre-computed sound features to study the robustness of bird sound classification. We investigate in detail if and how classification results are dependent on the number of species and the selection of species in the subsets presented to the classifier. In more detail, a bag-of-birds approach is employed to randomly create balanced subsets of sounds from different species for repeated classification runs. The number of species present in each subset is varied between 10 and 300, randomly drawing sounds of species from a dataset of 659 bird species taken from Xeno-Canto database. We observe that the shallow artificial neural network trained on pre-computed sound features is able to classify the bird sounds relatively well. The classification performance is evaluated using several common measures such as precision, recall, accuracy, mean average precision and area under the receiver operator characteristics curve. All of these measures indicate a decrease in classification success as the number of species present in the subsets is increased. We analyze this dependence in detail and compare the computed results to an analytic explanation assuming dependencies for an idealized perfect classifier. Moreover, we observe that the classification performance depends on the individual composition of the subset and varies across 20 randomly drawn subsets.

Sign Language Recognition (SLR) aims to bridge speech-impaired and general communities by recognizing signs from given videos. Researchers still face challenges developing efficient SLR systems because of the video’s complex background, light illumination, and subject structures. Recently many researchers developed a skeleton-based sign language recognition system to overcome the subject and background variation of hand gesture signs. However, skeleton-based SLR is still under exploration due to the lack of information and annotations on hand key points. More recently, researchers included body and face information with the hand gesture for the SLR, but their performance and efficiency are unsatisfactory. We proposed a Multi-Stream Graph-based Deep Neural Network (SL-GDN) for a skeleton-based SLR system to overcome the problems. The main purpose of the proposed SL-GDN approach is to improve the efficiency and performance of the SLR system with a low computational cost based on the human body pose in the form of 2D landmark locations. In the procedure, firstly, we constructed a skeleton graph based on the selected 27 whole-body key points among 67 key points to solve the inefficiency problems. Then we proposed multi-stream SL-GDN to extract features from the whole-body skeleton graph for four streams. Finally, we concatenated the four different features and applied a classification module to refine the feature and recognize corresponding sign classes. Our data-driven and graph construction method increases the system’s flexibility and brings high generability to adapt various data samples. We used three large-scale benchmark SLR datasets to evaluate the proposed model: WLASL, AUTSL and CSL. The demonstrated performance accuracy table proved the superiority of the proposed model, and we believe this will be considered a great invention in the SLR domain.

The recent advances in Human-Computer Interaction and Artificial Intelligence have significantly increased the importance of identifying human emotions from different sensory cues. Hence, understanding the underlying relationships between emotions and sensory cues have become a subject of study in many fields including Acoustics, Psychology, Psychiatry, Neuroscience and Biochemistry. This work is a preliminary step towards investigating cues for human emotion on a fundamental level by aiming to establish relationships between tonal frequencies of sound and emotions. For that, an online perception test is conducted, in which participants are asked to rate the perceived emotions corresponding to each tone. The results show that a crossover point for four primary emotions lies in the frequency range of 417–440 Hz, thus consolidating the hypothesis that the frequency range of 432–440 Hz is neutral from human emotion perspective. It is also observed that the frequency dependant relationships between emotion pairs Happy—Sad, and Anger—Calm are approximately mirrored symmetric in nature.

The level of ambiguity in describing glycan structure has significantly increased with the upsurge of large scale glycomics and glycoproteomics experiments. Consequently, an ontology-based model appears as an appropriate solution for navigating this data. However, navigation is not sufficient and the model should also enable advanced search and comparison. A new ontology with a tree logical structure is introduced to represent glycan structures irrespective of the precision of molecular details. The model heavily relies on the GlycoCT encoding of glycan structures. Its implementation in the GlySTreeM knowledge base was validated with GlyConnect data and benchmarked with the Glycowork library. GlySTreeM is shown to be fast, consistent, reliable and more flexible than existing solutions for matching parts of or whole glycan structures. The model is also well suited to painless future expansion. Availability:https://glyconnect.expasy.org/glystreem/wiki

In modern security situations, tracking multiple human objects in real-time within challenging urban environments is a critical capability for enhancing situational awareness, minimizing response time, and increasing overall operational effectiveness. Tracking multiple entities enables informed decision-making, risk mitigation, and the safeguarding of civil-military operations to ensure safety and mission success. This paper presents a multi-modal electro-optical/infrared (EO/IR) and radio frequency (RF) fused sensing (MEIRFS) platform for real-time human object detection, recognition, classification, and tracking in challenging environments. By utilizing different sensors in a complementary manner, the robustness of the sensing system is enhanced, enabling reliable detection and recognition results across various situations. Specifically designed Radar tag and thermal tag can be used to discriminate friendly and non-friendly objects. The system incorporates deep learning-based image fusion and human object recognition and tracking (HORT) algorithms to ensure accurate situation assessment. After integrating into an all-terrain robot, multiple ground tests were conducted to verify the consistent HORT in various environments. The MEIRFS sensor system has been designed to meet the Size, Weight, Power, and Cost (SWaP-C) requirements for installation on autonomous ground and aerial vehicles.

Electroencephalography (EEG) signals provide valuable insights into various activities of the human brain, including the detection of mental stress, which is a complex physiological and psychological response. However, the challenge lies in identifying mental stress accurately while mitigating the limitations associated with a large number of EEG channels. This includes issues such as computational complexity, the risk of overfitting, and the increased setup time for electrode placement, which can be cumbersome for real-life applications. Therefore, it is crucial to develop EEG channel selection algorithms that enable the creation of a wearable device capable of assessing mental stress in real-life scenarios. This study introduces a novel channel selection method aimed at identifying highly accurate channels for detecting mental stress. Our approach, known as the Correlation Coefficient of Hjorth Parameters (CCHP), assesses the correlation between activity, mobility, and complexity in the time domain to nominate the most relevant channels. By selecting channels that exhibit high correlation with the stress task while being uncorrelated with each other, CCHP significantly reduces the number of EEG channels required, without compromising accuracy or performance. To evaluate the effectiveness of CCHP, we conducted experiments using the DEAP public dataset. Comparing our results with other recent algorithms that utilize the full set of EEG channels, CCHP achieved a superior classification accuracy of 81.56% using only eight EEG channels. Furthermore, CCHP outperformed existing channel selection methods by an impressive 8%. These findings strongly indicate that the CCHP algorithm shows great promise in the design of a wearable application for mental stress detection, utilizing a minimal number of EEG channels.

In response to the growing inspection demand exerted by process automation in component manufacturing, Non-destructive testing (NDT) continues to explore automated approaches that utilize deep learning algorithms for defect identification, including within digital X-ray radiography images. This necessitates a thorough understanding of the implication of image quality parameters on the performance of these deep learning models. This study investigates the influence of two image quality parameters, namely Signal-to-Noise Ratio (SNR) and Contrast-to-Noise Ratio (CNR), on the performance of U-net deep learning segmentation model. Input images were acquired with varying combinations of exposure factors such as kilovoltage, milli-ampere, and exposure time, which altered the resultant quality. The data was sorted into 5 different datasets according to their measured SNR and CNR values. The deep learning model was trained 5 distinct times, utilizing a unique dataset for each training session. Training the model with high CNR values yielded an intersection over Union (IoU) metric of 0.9594 on test data of the same category but drops to 0.5875 when tested on lower CNR test data. The result in this study emphasizes the importance of achieving a balance in training dataset according to the investigated quality parameters, to enhance the performance of deep learning segmentation models in NDT radiography applications.

We employed the Riemannian Face Manifold (RFM) as an alternative approach to the conventional linear Euclidean space for explaining the atypicality bias in face likeliness judgments. The RFM posits that the mental representation of faces is better captured as a manifold of stable states, accounting for the nonlinearity in the physical properties of faces. To examine the relationship between physical and psychological distance of morph and typical/atypical faces, we manipulated the parameter k and incorporated a weight function in the Riemannian metric. Our results indicate that the psychological distance between the morph and typical face was longer than that between the morph and atypical face, consistent with prior research on the atypicality bias in perceptual similarity. The RFM approach provides mathematical support and is a powerful tool for studying face perception and recognition, offering potential implications for explaining the other-race effect. Future research can utilize the RFM to investigate individual differences in face recognition abilities and expertise, and how they impact psychological distance and face processing.

This research article investigates the effectiveness of digital forensics analysis (DFA) techniques in identifying patterns and trends in malicious failed login attempts linked to public data breaches or compromised email addresses in Microsoft 365 (M365) environments. Pattern recognition techniques are employed to analyze security logs, revealing insights into negative behavior patterns. The findings contribute to the literature on digital forensics, opposing behavior patterns, and cloud-based cybersecurity. Practical implications include the development of targeted defense strategies and the prioritization of prevalent threats. Future research should expand the scope to other cloud services and platforms, capture evolving trends through more prolonged, more extended analysis periods, and assess the effectiveness of specific mitigation strategies for identified tactics, techniques, and procedures (TTPs).

Purpose: School-age children with autism spectrum conditions (ASC) often experience difficulties in speech-in-noise (SiN) perception, leading to increased listening effort that impacts their well-being and academic performance. This study aimed to investigate the SiN processing challenges faced by Mandarin-speaking children with ASC and its impact on their listening effort. Methods: Participants completed sentence recognition tests in both quiet and noisy conditions, with a steady-state noise masker presented at 0 dB signal-to-noise ratio in the noisy condition. We compared recognition accuracy and task-evoked pupil responses from 23 Mandarin-speaking children with ASC to 19 age-matched neurotypical (NT) counterparts to gauge their behavioral performance and listening effort during these auditory tasks. Results: The ASC group demonstrated notably decreased accuracy in noise compared to their NT peers, suggesting poorer SiN perception. Pupillometric data further revealed significantly larger peak dilations in the ASC group than in the NT group under comparable conditions. Importantly, the ASC group's peak dilation in quiet mirrored the NT group's in noise. However, the ASC group exhibited shorter peak latencies and reduced mean dilations than the NT group in similar conditions. Such patterns indicate the ASC group might initially experience a heightened cognitive load but utilize fewer cognitive resources as the task continued, indicating an atypical allocation of cognitive resources and a potential tendency towards relatively superficial and automated auditory processing. Conclusion: Our findings highlight the unique SiN processing challenges children with ASC face, underscoring the importance of a nuanced, individual-centric approach for interventions and support.

A major challenge of augmented and mixed reality applications is identifying the context and semantics of the real environment. Studies on object and action recognition were developed based on the improvement of machine learning techniques, allowing them to be annotated and recognized. This study aims to characterize current knowledge on the use of machine learning for recognizing objects and actions in augmented and mixed reality environments, increasing context awareness. Therefore, a systematic literature review of works related to these topics was made, using the Scopus and Web of Science knowledge bases. We searched articles and conference reviews or papers published between 2018 and 2022 and selected fifteen studies to be reviewed. The results indicate that there is a great demand for using machine learning to immersive technologies in factories, engineering, entertainment, education, health, among other application domains. However, these real-time interactive systems still have challenges and limitations to be solved, involving network communication, prediction time and the creation of a model that recognize objects and actions in broad contexts. Furthermore, additional research is needed to investigate how object and action recognition can increase context awareness in augmented reality applications.

The multi-modal data fusion method based on IA-net and CHMM technical proposed is designed to solve the problem that the incompleteness of target behavior information in complex family environment leads to the low accuracy of human behavior recognition.The two improved neural networks(STA-ResNet50、STA-GoogleNet)are combined with LSTM to form two IA-Nets respectively to extract RGB and skeleton modal behavior features in video. The two modal feature sequences are input CHMM to construct the probability fusion model of multi-modal behavior recognition.The experimental results show that the human behavior recognition model proposed in this paper has higher accuracy than the previous fusion methods on HMDB51 and UCF101 datasets. New contributions: attention mechanism is introduced to improve the efficiency of video target feature extraction and utilization. A skeleton based feature extraction framework is proposed, which can be used for human behavior recognition in complex environment. In the field of human behavior recognition, probability theory and neural network are cleverly combined and applied, which provides a new method for multi-modal information fusion.

The real challenge in Human Robot Interaction (HRI) is to build machines capable of perceiving human emotions so that robots can interact with humans in a proper manner. It is well known from the literature that emotion varies accordingly to many factors. Among these, gender represents one of the most influencing one, and so an appropriate gender-dependent emotion recognition system is recommended. In this paper, a two-level hierarchical Speech Emotion Recognition (SER) system is proposed: the first level is represented by the Gender Recognition (GR) module for the speaker’s gender identification; the second is a gender-specific SER block. Specifically for this work, the attention was focused on the optimisation of the first level of the proposed architecture. The system was designed to be installed on social robots for hospitalised and living at home elderly patients monitoring. Hence, the importance of reducing the software computational effort of the architecture also minimizing the hardware bulkiness, in order for the system to be suitable for social robots. The algorithm was executed on the Raspberry Pi hardware. For the training, the Italian emotional database EMOVO was used. Results show a GR accuracy value of 97.8%, comparable with the ones found in literature.

This study aimed to investigate the possibility of using one-shot hyperspectral airborne images to recognize crops for an area with many small plots. The results showed that unsupervised clustering methods could classify crops with an accuracy of 80%, which improved to 90% when restricted to only grain crops, using a single airborne hyperspectral recording. However, additional layers such as NDVI, DTM, slope, and aspect did not improve classification accuracy. For comparison, the accuracy of clustering time series Sentinel-2 images with NDVI layers and DTM-derived data yielded an accuracy of: 74% ,Sentinel-2 time series 68% and single one registration before harvest - 39%. The results of the random forest classification were slightly less accurate due to a lack of sufficient reference data. However, it is challenging to verify the reported accuracy of crop recognition in the literature above 90% due to differences in analysis methodologies, reference data selection, pixel/object approaches, metric choice, and calculation formulas used.

Transcription factors must scan genomic DNA, recognize the cognate sequence of their control element(s), and bind tightly to them. The DNA recognition process is primarily carried out by their DNA binding domains (DBD), which interact with the cognate site with high affinity and more weakly with any other DNA sequence. DBDs are generally thought to bind to their cognate DNA without changing conformation (lock-and-key). Here we used nuclear magnetic resonance and circular dichroism to investigate the interplay between DNA recognition and DBD conformation in the Engrailed homeodomain (EnHD), as model case for the homeodomain family of eukaryotic DBDs. We found that the conformational ensemble of EnHD is rather flexible and becomes more structured as ionic strength increases following a Debye-Hückel’s dependence. Our analysis indicates that EnHD’s response to ionic strength is mediated by a built-in electrostatic spring-loaded latch that operates as conformational transducer. We also found that, at moderate ionic strengths, EnHD changes conformation upon binding to cognate DNA. This change is of larger amplitude and somewhat orthogonal to the response to ionic strength. As a consequence, very high ionic strengths (e.g. 700 mM) block the electrostatic-spring-loaded latch and binding to cognate DNA becomes lock-and-key. However, the interplay between EnHD conformation and cognate DNA binding is robust across a range of ionic strengths (i.e. 45 to 300 mM) that covers the most physiologically-relevant conditions. Therefore, our results demonstrate the presence of a mechanism for the conformational control of cognate DNA recognition on a eukaryotic DBD. This mechanism can function as a signal transducer that immediately locks the DBD in place upon encountering the cognate site during active DNA scanning. The electrostatic-spring-loaded latch of EnHD can also enable the fine control of DNA recognition in response to local/temporal changes in ionic strength induced by variate physiological processes.

The integration of deep learning methods, especially Convolutional Neural Networks (CNN), and Synthetic Aperture Radar Automatic Target Recognition (SAR ATR) has been widely deployed in the field of radar signal processing. Nevertheless, these methods are frequently regarded as black-box models due to the limited visual interpretation of their internal feature representation and parameter organization. In this paper, we propose an innovative approach named C-RISE, which builds upon the RISE algorithm to provide a post-hoc interpretation technique for black-box models used in SAR Images Target Recognition. C-RISE generates saliency maps that effectively visualize the significance of each pixel. Our algorithm outperforms RISE by clustering masks that capture similar fusion features into distinct groups, enabling more appropriate weight distribution and increased focus on the target area. Furthermore, we employ Gaussian blur to process the masked area, preserving the original image structure with optimal consistency and integrity. C-RISE has been extensively evaluated through experiments, and the results demonstrate superior performance over other interpretation methods based on perturbation when applied to neural networks for SAR image target recognition. Furthermore, our approach is highly robust and transferable compared to other interpretable algorithms, including white-box methods.

We introduce the Open Research Knowledge Graph Agriculture Named Entity Recognition (the ORKG Agri-NER) corpus and service for contribution-centric scientific entity extraction and classification. The ORKG Agri-NER corpus is a seminal benchmark for the evaluation of contribution-centric scientific entity extraction and classification in the agricultural domain. It comprises titles of scholarly papers that are available as Open Access articles on a major publishing platform. We describe the creation of this corpus and highlight the obtained findings in terms of the following features: 1) a generic conceptual formalism focused on capturing scientific entities in agriculture that reflect the direct contribution of a work; 2) a performance benchmark for named entity recognition of scientific entities in the agricultural domain by empirically evaluating various state-of-the-art sequence labeling neural architectures and transformer models; and 3) a delineated 3-step automatic entity resolution procedure for the resolution of the scientific entities to an authoritative ontology, specifically AGROVOC that is released in the Linked Open Vocabularies cloud. With this work we aim to provide a strong foundation for future work on the automatic discovery of scientific entities in the scholarly literature of the agricultural domain.

Capsule endoscopy (CE) has been a widely used medical imaging tool for the diagnosis of gastrointestinal tract abnormalities like bleeding. But the CE captures a huge number of image frames that are time-consuming and tedious tasks for medical experts to diagnose manually. To address this issue, researchers focused on the computer-aided bleeding detection system to identify bleeding automatically in real-time. This paper presents a systematic review of the available state-of-the-art computer-aided bleeding detection algorithms for capsule endoscopy. The review was carried out by searching five different repositories: Scopus, PubMed, IEEE Xplore, ACM Digital Library, and ScienceDirect for all original publications on computer-aided bleeding detection published between 2001 and 2021. The PRISMA methodology was used to perform the review, and 112 full-texts of scientific papers were reviewed. The contributions of this paper are I) a taxonomy for computer-aided bleeding detection algorithms for capsule endoscopy is identified, II) the available state-of-the-art computer-aided bleeding detection algorithms including various color spaces (RGB, HSV, etc.), feature extraction techniques, and classifiers are discussed, and III) identify the most effective algorithm for practical use cases. Finally, the paper is concluded by providing future direction for computer-aided bleeding detection research.

In the context of Shared Autonomous Vehicles, the need to monitor the environment inside the car will be crucial. This article focuses on the application of deep learning algorithms to detect objects, namely lost/forgotten items to inform the passengers, and aggressive items to monitoring if violent actions may arise between passengers. For object detection algorithms was used public datasets (COCO and TAO) to train state-of-the-art algorithms, such as YOLOv5. For violent action detection was used the MoLa InCar dataset to train on state-of-the-art algorithms such as I3D, R(2+1)D, SlowFast, TSN and TSM. At the end an embedded automotive solution was used to demonstrate both methods running in real-time.

In this paper I tentatively answer 50 questions sampled from a pool of over 10,000 weekly questions formulated by students in a course entitled “The Self”. The questions pertain to various key topics about self-processes, such as self-awareness, self-knowledge, self-regulation, self-talk, self-esteem, and self-regulation. The students’ weekly questions and their answers highlight what is currently know about the self. Answers to the student questions also allow for the identification of some recurrent lessons about the self. Some of these lessons include: all self-processes are interconnected (e.g., prospection depends on autobiography), self-terms must be properly defined (e.g., self-rumination and worry are not the same), inner speech plays an important role in self-processes, controversies are numerous (are animals self-aware?), measurement issues abound (e.g., self-reflection as an operationalization of self-awareness), deficits in some self-processes can have devastating effects (e.g., self-regulatory deficits may lead to financial problems), and there are lots of unknowns about the self (e.g., gender differences in Theory-of-Mind).

Teachability has been extensively studied under the context of making industrial robots to be programmable and reprogrammable. However, it is only recently that the artificial intelligence (AI) research community is accelerating the research works with the objective of making humanoid robots and many other robots to be teachable under the context of using natural languages. We human beings spend many years to learn knowledge and skills despite our extraordinary mental capabilities of being teachable with the use of natural languages. Therefore, if we would like to develop human-like robots such as humanoid robots, it is inevitable for us to face the issue of making future humanoid robots to be teachable with the use of natural languages as well. In this paper, we present the key details of a top-down design for achieving a teachable mind which consists of two major processes: the first one is the process which enables humanoid robots to gain innate mental capabilities of transforming incoming signals into meaningful crisp data, and the second one is the process which enables humanoid robots to gain innate mental capabilities of undertaking incremental and deep learning with the main focus of associating conceptual labels in a natural language to meaningful crisp data. These two processes consist of the two necessary and sufficient conditions for future humanoid robots to be teachable with the use of natural languages. In addition, this paper outlines a very likely new finding underlying human brain’s neural systems as well as the obvious mathematics underlying artificial deep neural networks. These outlines provide us the strong reason to separate the study of mind from the study of brain. Hopefully, the content discussed in this paper will help the AI research community to venture into the right direction which is to make future humanoid robots, non-humanoid robots, and many other systems to achieve human-like self-intelligence at cognitive level with the use of natural languages.

Micro-expression (ME) is one of the key psychological stress reactions. It is a modest, spontaneous facial mechanism. ME has significant applicability in a variety of psychologically-related sectors because to its precision and unpredictability with regard to psychological manifestations. Nevertheless, the current Micro-expression recognition (MER) algorithms have poor accuracy and a limited quantity of ME data, and this study issue has not been thoroughly investigated. Therefore, we present an approach for deep learning based on a Spatio-temporal capsule network (STCP-Net). STCP-Net has four components: a jitter reduction module, a differential feature extraction module, an STCP module, and a fully linked layer. The first two modules are aimed to extract diversifying differential features more precisely and to limit the influence of head jitter. The STCP module is used to extract Spatio-temporal features layer by layer, taking the temporal and geographical connection between features into account. This research runs sufficient trials using the Leave One Subject Out (LOSO) methodology for cross-validation using the CASMEII dataset. The conclusion and analysis demonstrate that the algorithm is innovative and efficient.

Hand and arm gesture recognition using radio frequency (RF) sensing modality proves valuable in man-machine interface and smart environment. In this paper, we use time series analysis method for accurately measuring the similarity of the micro-Doppler (MD) signatures between the training and test data, thus providing improved gesture classification. We characterize the MD signatures by the maximum instantaneous Doppler frequencies depicted in the spectrograms. In particular, we apply the dynamic time warping (DTW) method and compare its performance with that of the long short-term memory (LSTM) network. Both methods take into account the values as well as the temporal evolution and trends of time series data. It is shown that the DTW method achieves high gesture classification rates and is robust to time misalignment.

Prereactive complexes in noncovalent organocatalysis are sensitive to the relative chirality of the binding partners and to hydrogen bond isomerism. Both effects are present when a transiently chiral alcohol docks on a chiral α-hydroxy ester, turning such 1:1 complexes into elementary, non-reactive model systems for chirality induction in the gas phase. With the help of linear infrared and Raman spectroscopy in supersonic jet expansions, conformational preferences are investigated for benzyl alcohol in combination with methyl lactate, also exploring p-chlorination of the alcohol and the achiral homolog methyl glycolate to identify potential London dispersion and chirality effects on the energy sequence. Three of the four combinations prefer barrierless complexation via the hydroxy group of the ester (association). In contrast, the lightest complex shows predominantly insertion into the intramolecular hydrogen bond, like the analogous lactate and glycolate complexes of methanol. The experimental findings are rationalized with computations and a uniform helicality induction in the alcohol by the lactate is predicted, independent on insertion into or association with the internal lactate hydrogen bond. p-Chlorination of benzyl alcohol has a stabilizing effect on association, because the insertion motif prevents a close contact between the chlorine and the hydroxy ester. After simple anharmonicity and substitution corrections, the B3LYP-D3 approach offers a fairly systematic description of the known spectroscopic data on alcohol complexes with α-hydroxy esters.

Creating intelligent systems capable of recognizing emotions is a difficult task, especially when looking at emotions in animals. This paper describes the process of designing a “proof of concept” system to recognize emotions in horses. This system is formed by two elements, a detector and a model. The detector is a fast region-based convolutional neural network that detects horses in an image. The model is a convolutional neural network that predicts the emotions of those horses. These two elements were trained with multiple images of horses until they achieved high accuracy in their tasks. 400 images of horses were collected and labeled to train both the detector and the model while 80 were used to validate the system. Once the two components were validated, they were combined into a testable system that would detect equine emotions based on established behavioral ethograms indicating emotional affect through head, neck, ear, muzzle and eye position. The system showed an accuracy of between 69% and 74% on the validation set, demonstrating that it is possible to predict emotions in animals using autonomous intelligent systems. Such a system has multiple applications including further studies in the growing field of animal emotions as well as in the veterinary field to determine the physical welfare of horses or other livestock.

The angle of seismic excitation is a significant factor of the seismic response of RC buildings. The procedure required for the calculation of the angle for which the potential seismic damage is maximized (critical angle) contains multiple nonlinear time history analyses using in each one of them different angles of incidence. Moreover, the seismic codes recommend the application of more than one accelerograms for the evaluation of seismic response. Thus, the whole procedure becomes time consuming. Herein, a method to reduce the time required for the estimation of the critical angle based on Multilayered Feedforward Perceptron Neural Networks is proposed. The basic idea is the detection of cases in which the critical angle increases the class of seismic damage compared to the class which arises from the application of the seismic motion along the buildings’ structural axes. To this end, the problem is expressed and solved as Pattern Recognition problem. As inputs of networks the ratios of seismic parameters’ values along the two horizontal seismic records' components, as well as appropriately chosen structural parameters, were used. The results of analyses show that the neural networks can reliably detect the cases in which the calculation of the critical angle is essential.