Search

The extraordinary success of convolutional neural networks (CNNs) in various computer vision tasks has revitalized the field of artificial intelligence. The out-sized expectations created by this extraordinary success have, however, been tempered by a recognition of CNNs' fragility. Importantly, the magnitude of the problem is unclear due to a lack of rigorous benchmark datasets. Here, we propose a solution to the benchmarking problem that reveals the extent of the vulnerabilities of CNNs and of the methods used to provide interpretability to their predictions. We employ cellular automata (CA) to generate images with rigorously controllable characteristics. CA allow for the definition of both extraordinarily simple and highly complex discrete functions and allow for the generation of boundless datasets of images without repeats. In this work, we systematically investigate the fragility and interpretability of the three popular CNN architectures using CA-generated datasets. We find a sharp transition from a learnable phase to an unlearnable phase as the latent space entropy of the discrete CA functions increases. Furthermore, we demonstrate that shortcut learning is an inherent trait of CNNs. Given a dataset with an easy-to-learn and strongly predictive pattern, CNN will consistently learn the shortcut even if the pattern occurs only on a small fraction of the image. Finally, we show that widely used attribution methods aiming to add interpretability to CNN outputs are strongly CNN-architecture specific and vary widely in their ability to identify input regions of high importance to the model. Our results provide significant insight into the limitations of both CNNs and the approaches developed to add interpretability to their predictions and raise concerns about the types of tasks that should be entrusted to them. [ABSTRACT FROM AUTHOR]

Featured Application: Increased cognitive demands during motor tasks emerged as a critical discriminator of functional patterns among older adults, shedding light on the intricate interplay between cognitive function and motor performance in fall prevention strategies in community-dwelling older adults. A wide range of outcomes makes identifying clinical and functional features distinguishing older persons who fall from non-fallers challenging, especially for professionals with less clinical experience. Thus, this study aimed to map a high-dimensional and complex clinical and functional dataset and determine which outcomes better discriminate older adults with and without self-reported falls. For this, clinical, functional, and cognitive outcomes of 60 community-dwelling older adults classified as fallers and non-fallers were selected based on self-report of a single fall in the last 12 months. An unsupervised intelligent algorithm (Self-Organizing Maps—SOM) was used to cluster and topographically represent the data studied. The SOM model mapped and identified two different groups (topographic error: 0.00; sensitivity: 0.77; precision: 0.42; accuracy: 0.53; F1-score: 0.55) based on self-report of a single fall. We concluded that although two distinct groups were mapped and clustered by the SOM, participants were not necessarily fallers or non-fallers. The increased cost of cognitive demands regarding a motor task (Timed Up and Go Test) and the effect of the Trail Making Test (TMT) Part B regarding TMT Part A could discriminate the functional and cognitive patterns in community-dwelling older adults. Therefore, in clinical practice, identifying patterns involving the interaction between cognition and motor skills, even in once-only faller older adults, can be an efficient approach to assessment and, consequently, to compound intervention programs to prevent falls in this population. [ABSTRACT FROM AUTHOR]

Neuromorphic computers optimized to utilize artificial intelligence are currently receiving much attention. In this study, neural network circuit simulations are performed by varying the nonlinearity and learning rate to understand better the characteristics of the individual and parallel-connected synaptic devices. The simulation results show that pattern recognition accuracy tends to decrease with increasing nonlinearity, while the accuracy is achieved more gradually when the learning rate is reduced. By comparing the simulation results with actual experimental results, I find an ideal learning rate and investigate how to optimize neuromorphic computers. These findings will help design new neuromorphic computers to determine the appropriate learning rate. [ABSTRACT FROM AUTHOR]

The article focuses on the integration of Artificial intelligence (AI) into service design, highlighting its role as a creative partner and offering guidance on effectively incorporating AI into the design process. Topics include understanding AI's capabilities, evolving communication and tools, and assigning specific roles to AI using the Analysis-Synthesis Bridge Model to enhance collaboration between humans and AI in service design.

Speech emotion recognition (SER) is a key branch in the field of artificial intelligence, focusing on the analysis and understanding of emotional content in human speech. It involves a multidisciplinary knowledge of acoustics, phonetics, linguistics, pattern recognition, and neurobiology, aiming to establish a connection between human speech and emotional expression. This technology has shown broad application prospects in the medical, educational, and customer service fields. With the evolution of deep learning and neural network technologies, SER research has shifted from relying on manually designed low-level descriptors (LLDs) to utilizing complex neural network models for extracting high-dimensional features. A perennial challenge for researchers has been how to comprehensively capture the rich emotional features. Given that emotional information is present in both time and frequency domains, our study introduces a novel time–frequency domain convolution module (TFCM) based on Mel-frequency cepstral coefficient (MFCC) features to deeply mine the time–frequency information of MFCCs. In the deep feature extraction phase, for the first time, we have introduced hybrid dilated convolution (HDC) into the SER field, significantly expanding the receptive field of neurons, thereby enhancing feature richness and diversity. Furthermore, we innovatively propose the residual attention-gated multilayer perceptron (RA-GMLP) structure, which combines the global feature recognition ability of GMLP with the concentrated weighting function of the multihead attention mechanism, effectively focusing on the key emotional information within the speech sequence. Through extensive experimental validation, we have demonstrated that TFCM, HDC, and RA-GMLP surpass existing advanced technologies in enhancing the accuracy of SER tasks, fully showcasing the powerful advantages of the modules we proposed. [ABSTRACT FROM AUTHOR]

Humans can be recognized by their distinctive walking patterns, which have been established using a variety of techniques, including the use of sensors. Footstep recognition, which analyzes the distinctive characteristics of a person's footsteps, can be applied in a range of scenarios, including security, criminal investigations, human behavior security applications, and healthcare for monitoring and analyzing gait abnormalities. This paper discusses the most recent work on footstep analysis and identification systems in terms of using the floor-based approach. It explains the various artificial intelligence methods as well as the machine learning and deep learning algorithms applied to the recognition and analysis of footsteps, the various feature engineering techniques applied to each type of sensor, the affection of the engineered features on the footstep identification and analysis systems, and the best suitable features for each type of sensor and application, which provide researchers in this domain with an appropriate grounding in footstep identification and analysis utilizing the floor-based technique. [ABSTRACT FROM AUTHOR]

The article discusses the incorporation of Artificial Intelligence (AI) in colorectal surgery, focusing on its potential applications, limitations, and medicolegal implications. AI systems can process data, learn from outcomes, and make predictions without explicit programming, offering opportunities to optimize quality, outcomes, and safety in surgery. However, challenges such as lack of transparency, liability issues, and patient consent arise when using AI in clinical decision-making. While AI can enhance surgical education and performance, it is emphasized that AI is a tool and not a replacement for human decision-making, empathy, and accountability in patient care. [Extracted from the article]

Aerial targets grouping is an important content of air battlefield situation awareness, and intelligent aerial targets grouping is an urgent need for intelligent air combat. Traditional aerial targets grouping methods have problems such as difficulty extracting air target features, difficulty designing formation similarity measures, and lack of data samples. To solve the above problems, this paper proposes a relational network based aerial targets grouping method to achieve end‐to‐end grouping under small sample conditions. Firstly, an adaptive clustering algorithm is proposed to preliminarily cluster the aerial targets in the air battlefield situation to obtain the group to be tested. Then, a representation of aerial target groups is designed, which unifies the multi‐dimensional features of the group's temporal, spatial, and attribute. Next, based on this representation, combining 3D convolutional neural networks (3DCNN) and long short‐term memory (LSTM), a neural network structure that can automatically extract multi‐dimensional features of groups is designed. After that, the relation module is used to learn the distance metric between groups. After training the relation network, the type of group to be tested can be identified, thereby achieving the goal of grouping. A dataset of 30 types of aerial target group patterns was established through simulation. The ablation experiments were conducted to verify the performance of each module, and the experimental results showed that the designed feature extraction module can effectively extract temporal sample features, while the designed relationship module performs better in extracting temporal sample information. By comparing several typical traditional aerial target grouping methods, the proposed method improves the grouping accuracy by 11.2% to 13.4%, achieving an accuracy of 91.1% in the 5‐way 1‐shot task and 95.6% in the 5‐way 5‐shot task. [ABSTRACT FROM AUTHOR]

The ensemble learning method is considered a meaningful yet challenging task. To enhance the performance of binary classification and predictive analysis, this paper proposes an effective ensemble learning approach by applying multiple models to produce efficient and effective outcomes. In these experimental studies, three base learners, J48, Multilayer Perceptron (MP), and Support Vector Machine (SVM) are being utilized. Moreover, two meta-learners, Bagging and Rotation Forest are being used in this analysis. Firstly, to produce effective results and capture productive data, the base learner, the J48 decision tree is aggregated with the rotation forest. Secondly, machine learning and ensemble learning classification algorithms along with the five UCI Datasets are being applied to progress the robustness of the system. Whereas, the recommended mechanism is evaluated by implementing five performance standards concerning the accuracy, AUC (Area Under Curve), precision, recall and F-measure values. In this regard, extensive strategies and various approaches were being studied and applied to obtain improved results from the current literature; however, they were insufficient to provide successful results. We present experimental results which demonstrate the efficiency of our approach to well-known competitive approaches. This method can be applied to image identification and machine learning problems, such as binary classification. [ABSTRACT FROM AUTHOR]

The article emphasizes the importance of clinical morphology, or the visual recognition of skin diseases, as a biomarker in dermatology. It argues that morphology is essential because it is inexpensive, fast, and fosters important qualities in physicians such as imagination and creativity. The article also discusses the historical development of morphology-based classification and the potential benefits of incorporating art into medical education to enhance visual literacy skills. It cautions against neglecting clinical morphology in favor of machine learning and AI, as these technologies rely on human input and data. The authors advocate for the preservation and advancement of clinical morphology alongside biological and digital biomarkers in dermatology. [Extracted from the article]

Artificial intelligence (AI) and machine learning (ML) are near-ubiquitous in day-to-day life; from cars with automated driver-assistance, recommender systems, generative content platforms, and large language chatbots. Implementing AI as a tool for international safeguards could significantly decrease the burden on safeguards inspectors and nuclear facility operators. The use of AI would allow inspectors to complete their in-field activities quicker, while identifying patterns and anomalies and freeing inspectors to focus on the uniquely human component of inspections. Sandia National Laboratories has spent the past two and a half years developing on-device machine learning to develop both a digital and robotic assistant. This combined platform, which we term inspecta , has numerous on-device machine learning capabilities that have been demonstrated at the laboratory scale. This work describes early successes implementing AI/ML capabilities to reduce the burden of tedious inspector tasks such as seal examination, information recall, note taking, and more. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) has come a long way in the last several years, both in hardware implementation and software algorithms and applications. This paper examines recent advances in artificial intelligence applications in biomedicine, such as living aid, illness diagnosis, biomedical research, and biomedical information processing. It also reviews deep learning as a technique in Artificial intelligence in healthcare and compares it to traditional methods. This review will better comprehend technology availability, keep the pace of new scientific developments, appreciate the enormous potential of artificial intelligence in biomedicine, and inspire researchers working in related domains. It is fair to say that the use of AI in biomedicine is in its early stages, like artificial intelligence itself. Artificial intelligence will continue to push the boundaries and broaden the scope of its applications as new improvements and discoveries are made, and substantial advancements are projected shortly. [ABSTRACT FROM AUTHOR]

Diabetes is a chronic disease wherein the body doesn't produce enough or any insulin, doesn't properly utilize the insulin that is produced, or shows a combination of both. When any of these occur the body is unable to get sugar from the blood into the cells which lead to rise in blood sugar levels. Diabetes is characterized by increase in blood glucose level either because of insufficient insulin discharge (type I diabetes) or impeded insulin action (type II diabetes). It is a vital health problem which can cause physical disability and even death in some cases. Diabetes has affected over 246 million people worldwide as indicated by the World Health Organization (WHO) report, and this number is predicted to ascend to more than 592 million in 2035. In India, the type of diabetes differs considerably from the western world i.e. Type I diabetes is considerably rarer, while more than 90% of the people are diagnosed with Type II diabetes. Due to the high occurrence of Type II diabetes in recent years, the forecast and early prediction of the disease have become more important. An artificial neural network (ANN) is a network of artificial neurons, similar to the ones found in human brain which is used for solving artificial intelligence problems such as image identification, pattern recognition, classification, prediction, data compression and optimization. A number of ANN techniques have been applied for prediction and classification of diabetes. After reviewing various literature papers, this study is aimed to identify the technique among different artificial neural network techniques that can be used to predict accurate blood sugar level of Type II diabetes. [ABSTRACT FROM AUTHOR]

Nowadays our society is mostly depending on the digitalization and automation. The main aim of this project is developed OCR code for decoding the pan card number. OCR is an optical character recognition and is the mechanical or electronic translation of images. OCR is a field of researching pattern recognition, artificial intelligence and machine vision. In this project we can decode the pan card number and it gives the details such as income tax transactions, number of loans taken, cibil score, returns and loan status of the card holder so that we can know the every information of the holder. We can get the information easily about how many are paying the income tax to the government regularly. For this we are using MATLAB software. In this we can track the details of owner by taking the photograph of pan card and that will be stored, processed in the OCR and details will be displayed. [ABSTRACT FROM AUTHOR]

Although Artificial Intelligence (AI) has become a buzzword for self-organizing IT applications, its relevance to software engineering has hardly been analyzed systematically. This study combines a systematic review of previous research in the field and five qualitative interviews with software developers who use or want to use AI tools in their daily work routines, to assess the status of development, future development potentials and equally the risks of AI application to software engineering. The study classifies the insights in the software development life cycle. The analysis results that major achievements and future potentials of AI are a) the automation of lengthy routine jobs in software development and testing using algorithms, e.g. for debugging and documentation, b) the structured analysis of big data pools to discover patterns and novel information clusters and c) the systematic evaluation of these data in neural networks. AI thus contributes to speed up development processes, realize development cost reductions and efficiency gains. AI to date depends on man-made structures and is mainly reproductive, but the automation of software engineering routines entails a major advantage: Human developers multiply their creative potential when using AI tools effectively. [ABSTRACT FROM AUTHOR]

In recent past, there has been a steep increase in the use of online platforms for the search of desired products. Real estate industry is no exception and has started initiating rent/sale of houses through online platforms. In this paper, we propose a deep neural network framework to facilitate automatic search of homes based on their floor plans. The salient features of this framework are that the query can be either an image (existing floor plan) or a sketch through a sketch pad interface. Our proposed framework automatically determines the type of query (image or sketch) and retrieves similar floor plan images from the database. The critical contributions of our proposed approach are: (1) a novel unified floor plan retrieval framework using multimodal query, i.e., an intuitive and convenient sketch query mode as well as a query by example mode ; (2) a conjunction of autoencoder, Cyclic GAN and CNN for the task of domain mapping and floor plan image retrieval. We have reported results of extensive experimentation and comparison with baseline results to establish the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

The article focuses on the theory of control of the Soviet economy by Emmanuil Braverman. It mentions public engagement of scientists and engineers in favor of economic reforms aimed at rationalizing Soviet governance and intellectual motivation and political legitimacy to invest their time in economic and social analysis. It also mentions pioneer of pattern recognition domain of artificial intelligence dealing with teaching computers.

Many artificial intelligence applications are dealing with large amount of data. The essence is to identify and recognize the structure in data and classify them according to similar attributes, features and patterns. Often, these data are fuzzy and do not belong to one cluster only. Presented is a method for optimum partitioning of fuzzy data which uses a concept of n -dimensional Euclidian space to determine the geometric closeness of data. Numeric examples, based on a prototype software, present clustering and pattern recognition algorithms including defuzzification founded on the maximum membership, cluster similarity analysis and classification metrics of the data sets decomposition. [ABSTRACT FROM AUTHOR]

Copyright of Problems / Problemos is the property of Vilnius University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Fine-grained recognition is a challenging task due to small intra-category variances. Most of the top-performing fine-grained recognition methods leverage parts of objects for better performance. Therefore, part annotations which are extremely computationally expensive are required. In this paper, we propose a novel cascaded deep CNN detection framework for fine-grained recognition which is trained to detect a whole object without considering parts. Nevertheless, most of the current top-performing detection networks use N + 1 class (N object categories plus background) softmax loss. The background category with much more training samples dominates the feature learning progress where the features are not suitable for object categorisation with fewer samples. To address this issue, we here introduce two strategies: 1) We leverage a cascaded structure to eliminate the background. 2) We introduce a novel one-vs-rest loss function to capture more minute variances from different subordinate categories. Experiments show that our proposed recognition framework achieves comparable performance against the state-of-the-art, part-free, fine-grained recognition methods on the CUB-200-2011 Bird dataset. Meanwhile, our method outperforms most of the existing part annotation based methods and does not need part annotations at the training stage whilst being free from any annotations at the test stage. [ABSTRACT FROM AUTHOR]

Do-it-yourself trends, such as self-broadcasting, music self-publishing and personal manufacturing, involve combining human imagination and automated engineering. In particular, automated engineering enabled by artificial intelligence algorithms is used for pattern recognition and other highly complex tasks across physical, virtual and social media. Together, multiple do-it-yourself trends driven by human imagination combined with automated engineering bring mass imagineering. It has been claimed that this new potential for individuals to create what they imagine will bring revolutionary disruption to existing paradigms for production and consumption, which will benefit individuals greatly. Conversely, others have claimed that whatever change occurs will advance organizations within existing paradigms at the expense of individuals. In this article, it is explained that mass imagineering has limited potential to bring revolutionary disruption to mass production and mass customization. Rather, it can facilitate their enrichment for the benefit of both organizations and individuals by better enabling complementary cultures for creativity, choice and convenience. [ABSTRACT FROM AUTHOR]

It is demonstrated that cells can be classified by pattern recognition of the subcellular structure of non-stained live cells, and the pattern recognition was performed by machine learning. Human white blood cells and five types of cancer cell lines were imaged by quantitative phase microscopy, which provides morphological information without staining quantitatively in terms of optical thickness of cells. Subcellular features were then extracted from the obtained images as training data sets for the machine learning. The built classifier successfully classified WBCs from cell lines (area under ROC curve = 0.996). This label-free, non-cytotoxic cell classification based on the subcellular structure of QPM images has the potential to serve as an automated diagnosis of single cells. [ABSTRACT FROM AUTHOR]

OCR is an artificial intelligence, recognition English characters have been solved by a huge number of studies last 3 decades, but Arabic letters which used by at least one billion people have not been definitively resolved yet, therefore In this study proposes an effective approach to the recognition of off-line of 121 Arabic characters which is involves of creating database (DB), contains standard image for 59 main character target and Characters Indexing Table (CIT), contains indices of 62 main character target to be used in recognition process. The (DB) is designed to identify the main body of the 59 unknown characters. The (CIT) is responsible of identifying the secondary components, the number of dots or hamza that is associated with the body of character and their position. The mean square error classifier (MSE) is used in the recognition stage, where each character is assigned the best 6 matches with the lowest MSE. The lowest MSE value is 0.025 and the highest value is 0.09. [ABSTRACT FROM AUTHOR]

Feature selection plays an important role in pattern recognition and machine learning. Feature selection based on information theory intends to preserve the feature relevancy between features and class labels while eliminating irrelevant and redundant features. Previous feature selection methods have offered various explanations for feature relevancy, but they ignored the relationships between candidate feature relevancy and selected feature relevancy. To fill this gap, we propose a feature selection method named Feature Selection based on Weighted Relevancy (WRFS). In WRFS, we introduce two weight coefficients that use mutual information and joint mutual information to balance the importance between the two kinds of feature relevancy terms. To evaluate the classification performance of our method, WRFS is compared to three competing feature selection methods and three state-of-the-art methods by two different classifiers on 18 benchmark data sets. The experimental results indicate that WRFS outperforms the other baselines in terms of the classification accuracy, AUC and F1 score. [ABSTRACT FROM AUTHOR]

Rare bird has long been considered an important in the field of airport security, biological conservation, environmental monitoring, and so on. With the development and popularization of IOT-based video surveillance, all day and weather unattended bird monitoring becomes possible. However, the current mainstream bird recognition methods are mostly based on deep learning. These will be appropriate for big data applications, but the training sample size for rare bird is usually very short. Therefore, this paper presents a new sparse recognition model via improved part detection and our previous dictionary learning. There are two achievements in our work: (1) after the part localization with selective search, the gist feature of all bird image parts will be fused as data description; (2) the fused gist feature needs to be learned through our proposed intraclass dictionary learning with regularized K-singular value decomposition. According to above two innovations, the rare bird sparse recognition will be implemented by solving one 11-norm optimization. In the experiment with Caltech-UCSD Birds-200- 2011 dataset, results show the proposed method can have better recognition performance than other SR methods for rare bird task with small sample size. [ABSTRACT FROM AUTHOR]

Multivoxel pattern analysis (MVPA) typically begins with the estimation of single trial activation levels, and several studies have examined how different procedures for estimating single trial activity affect the ultimate classification accuracy of MVPA. Here we show that the currently preferred estimation procedures impart spurious positive correlations between the means of different category activity estimates within the same scanner run. In other words, if the mean of the estimates for one type of trials is high (low) in a given scanner run, then the mean of the other type of trials is also high (low) for that same scanner run, and the run-level mean across all trials therefore shifts from run to run. Simulations show that these correlations occur whenever there is a need to deconvolve overlapping trial activities in the presence of noise. We show that subtracting each voxel’s run-level mean across all trials from all the estimates within that run (i.e., run-level mean centering of estimates), by cancelling out these mean shifts, leads to robust and significant improvements in MVPA classification accuracy. These improvements are seen in both simulated and real data across a wide variety of situations. However, we also point out that there could be cases when mean activations are expected to shift across runs and that run-level mean centering could be detrimental in some of these cases (e.g., different proportion of trial types between different runs). [ABSTRACT FROM AUTHOR]

We show that adversarial training of supervised learning models is in fact a robust optimization procedure. To do this, we establish a general framework for increasing local stability of supervised learning models using robust optimization. The framework is general and broadly applicable to differentiable non-parametric models, e.g., Artificial Neural Networks (ANNs). Using an alternating minimization-maximization procedure, the loss of the model is minimized with respect to perturbed examples that are generated at each parameter update, rather than with respect to the original training data. Our proposed framework generalizes adversarial training, as well as previous approaches for increasing local stability of ANNs. Experimental results reveal that our approach increases the robustness of the network to existing adversarial examples, while making it harder to generate new ones. Furthermore, our algorithm improves the accuracy of the networks also on the original test data. [ABSTRACT FROM AUTHOR]

This paper designed and developed the image processing system of integrating feature extraction and matching by using convolutional neural network (CNN), rather than relying on the simple method of processing feature extraction and matching separately in the image processing of conventional image recognition system. To implement it, the proposed system enables CNN to operate and analyze the performance of conventional image processing system. This system extracts the features of an image using CNN and then learns them by the neural network. The proposed system showed 84% accuracy of recognition. The proposed system is a model of recognizing learned images by deep learning. Therefore, it can run in batch and work easily under any platform (including embedded platform) that can read all kinds of files anytime. Also, it does not require the implementing of feature extraction algorithm and matching algorithm therefore it can save time and it is efficient. As a result, it can be widely used as an image recognition program. [ABSTRACT FROM AUTHOR]

Making inferences from partial information constitutes a critical aspect of cognition. During visual perception, pattern completion enables recognition of poorly visible or occluded objects. We combined psychophysics, physiology, and computational models to test the hypothesis that pattern completion is implemented by recurrent computations and present three pieces of evidence that are consistent with this hypothesis. First, subjects robustly recognized objects even when they were rendered <15% visible, but recognition was largely impaired when processing was interrupted by backward masking. Second, invasive physiological responses along the human ventral cortex exhibited visually selective responses to partially visible objects that were delayed compared with whole objects, suggesting the need for additional computations. These physiological delays were correlated with the effects of backward masking. Third, state-of-the-art feed-forward computational architectures were not robust to partial visibility. However, recognition performance was recovered when the model was augmented with attractor-based recurrent connectivity. The recurrent model was able to predict which images of heavily occluded objects were easier or harder for humans to recognize, could capture the effect of introducing a backward mask on recognition behavior, and was consistent with the physiological delays along the human ventral visual stream. These results provide a strong argument of plausibility for the role of recurrent computations in making visual inferences from partial information. [ABSTRACT FROM AUTHOR]

Functional connectivity (FC) characterizes brain activity from a multivariate set of N brain signals by means of an NxN matrix A, whose elements estimate the dependence within each possible pair of signals. Such matrix can be used as a feature vector for (un)supervised subject classification. Yet if N is large, A is highly dimensional. Little is known on the effect that different strategies to reduce its dimensionality may have on its classification ability. Here, we apply different machine learning algorithms to classify 33 children (age [6-14 years]) into two groups (healthy controls and Attention Deficit Hyperactivity Disorder patients) using EEG FC patterns obtained from two phase synchronisation indices. We found that the classification is highly successful (around 95%) if the whole matrix A is taken into account, and the relevant features are selected using machine learning methods. However, if FC algorithms are applied instead to transform A into a lower dimensionality matrix, the classification rate drops to less than 80%. We conclude that, for the purpose of pattern classification, the relevant features should be selected among the elements of A by using appropriate machine learning algorithms. [ABSTRACT FROM AUTHOR]

Student modeling is a central problem in Intelligent Tutoring Systems design and development. In this way, the characteristic that distinguishes this type of system is the ability to determine as accurately and quickly as possible the student's cognitive and affective-motivational state in order to personalize the educational process. Therefore, the fundamental problem is to select data structure to represent all relative information to student and to choose the procedure to make the diagnosis. This paper describes a model for knowledge engineering inherent to all intelligent tutoring system, using the LC-Conceptual clustering algorithm, from logical combinatorial pattern recognition. This algorithm builds the objects clusters based on their similarity, using a grouping criterion, and it also builds the property (or concept) that meets each group of objects. [ABSTRACT FROM AUTHOR]

Plant recognition is one of important research areas of pattern recognition. As plant leaves are extremely irregular, complex and diverse, many existing plant classification and recognition methods cannot meet the requirements of the automatic plant recognition system. A plant recognition approach is proposed by combining singular value decomposition (SVD) and sparse representation (SR) in this paper. The difference from the traditional plant classification methods is that, instead of establishing a classification model by extracting the classification features, the proposed method directly reduces the image dimensionality and recognizes the test samples based on the sparse coefficients, and uses the class-specific dictionary learning for sparse modeling to reduce the recognition time. The proposed method is verified on two plant leaf datasets and is compared with other four existing plant recognition methods The overall recognition accuracy of the proposed approach for the 6 kinds of plant leaves is over 96%, which is the best classification rate. The experimental results show the feasibility and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In recent years, machine learning algorithms are commonly used in the field of digital image processing for interpreting images based on domain specific knowledge in terms of different aspects like image classification, object/pattern recognition, clinical image diagnosing, traffic control systems, satellite imaging, geomorphological and agriculture sectors etc. to analyse ROI from large amount of captured electronic images via different modalities. Machine Learning (ML) is an outlet of Artificial Intelligence (AI). It has ability to learn by itself without any extra effort like explicit programming. In this paper, we will deliberate the emerged expanse of ML -- Deep Learning (DL) which is basically a group of concepts with high level of data abstraction. Its application areas are especially analytical study of medical images such as anatomical structure detection, image registration and enhancement, computer aided disease diagnosis, tissue segmentation, and so on. DL based architecture provides exhilarating results with moral accuracy and enhanced performance for medical image segmentation and classification. [ABSTRACT FROM AUTHOR]