Researching body experiences poses challenges due to their inherently subjective and intangible nature. In TEI, more broadly in HCI, methods like body maps capture these experiences. We advance body maps by developing and applying two extensions to body maps to address important dimensions of body experience. These were tested in two studies. The first focuses on design processes aimed at achieving more generalizable data through quantitative methods, while enabling analysis from an individual perspective. Here, we introduce a segmentation approach of body maps for quantifying and comparing body experiences. These maps feature subdivisions of various body areas, derived from a study reporting the effects of movement sonification intervention on body perception. The segmentation allows for precise measurement and comparison of these changes. In the second, we shift to the context in which body experiences take place, presenting context-sensitive body maps anchored in the environment. These maps explore the relationship between body and environment. We present methodologies for researching embodied interactions within TEI.

Knowledge distillation (KD) remains challenging due to the opaque nature of the knowledge transfer process from a Teacher to a Student, making it difficult to address certain issues related to KD. To address this, we proposed UniCAM, a novel gradient-based visual explanation method, which effectively interprets the knowledge learned during KD. Our experimental results demonstrate that with the guidance of the Teacher's knowledge, the Student model becomes more efficient, learning more relevant features while discarding those that are not relevant. We refer to the features learned with the Teacher's guidance as distilled features and the features irrelevant to the task and ignored by the Student as residual features. Distilled features focus on key aspects of the input, such as textures and parts of objects. In contrast, residual features demonstrate more diffused attention, often targeting irrelevant areas, including the backgrounds of the target objects. In addition, we proposed two novel metrics: the feature similarity score (FSS) and the rele-vance score (RS), which quantify the relevance of the dis-tilled knowledge. Experiments on the CIFAR10, ASIRRA, and Plant Disease datasets demonstrate that UniCAM and the two metrics offer valuable insights to explain the KD process.

Changes in body perception influence behavior and emotion and can be induced through multisensory feedback. Auditory feedback to one’s actions can trigger such alterations; however, it is unclear which individual factors modulate these effects. We employ and evaluate SoniWeight Shoes, a wearable device based on literature for altering one’s weight perception through manipulated footstep sounds. In a healthy population sample across a spectrum of individuals (n=84) with varying degrees of eating disorder symptomatology, physical activity levels, body concerns, and mental imagery capacities, we explore the effects of three sound conditions (low-frequency, high-frequency and control) on extensive body perception measures (demographic, behavioral, physiological, psychological, and subjective). Analyses revealed an impact of individual differences in each of these dimensions. Besides replicating previous findings, we reveal and highlight the role of individual differences in body perception, offering avenues for personalized sonification strategies. Datasets, technical refinements, and novel body map quantification tools are provided.

Glaucoma, a leading cause of irreversible blindness worldwide, poses significant diagnostic challenges due to its reliance on subjective evaluation. Recent advances in computer vision and deep learning have demonstrated the potential for automated assessment. This paper provides a comprehensive survey of studies on AI-based glaucoma diagnosis using fundus, optical coherence tomography, and visual field images, with a focus on deep learning-based methods. We searched Web of Science, PubMed, IEEE Xplore, and Google Scholar, applying specific selection criteria to identify relevant studies published from 2017 to 2023. Our analysis provides a structured overview of architectural paradigms, including convolutional neural networks, autoencoders, attention networks, generative adversarial networks, and geometric deep learning models. Additionally, we discuss approaches for extracting informative features, such as structural, statistical, and hybrid techniques. Furthermore, we outline key research challenges and future directions, emphasizing the need for larger, more diverse datasets, strategies for early disease detection, multi-modal data integration, model explainability, and clinical translation. This survey is expected to be useful for Artificial Intelligence (AI) researchers seeking to translate advances into practice and ophthalmologists aiming to improve clinical workflows and diagnosis using the latest AI outcomes.

Nowadays, a significant part of our time is spent sharing multimodal data on social media sites such as Instagram, Facebook and Twitter. The particular way through which users present themselves to social media can provide useful insights into their behaviours, personalities, perspectives, motives and needs. This article proposes to use multimodal data collected from Instagram accounts to predict the five basic prototypical needs described in Glasser's choice theory (i.e.,Survival,Power,Freedom,Belonging, andFun). We automate the identification of the unconsciously perceived needs from Instagram profiles by using both visual and textual contents. The proposed approach aggregates the visual and textual features extracted using deep learning and constructs a homogeneous representation for each profile through the proposedBag-of-Content. Finally, we perform multi-label classification on the fusion of both modalities. We validate our proposal on a large database, consensually annotated by two expert psychologists, with more than 30,000 images, captions and comments. Experiments show promising accuracy and complementary information between visual and textual cues.

Early diagnosis of Alzheimer's disease and its prodromal stage, also known as mild cognitive impairment (MCI), is critical since some patients with progressive MCI will develop the disease. We propose a multi-stream deep convolutional neural network fed with patch-based imaging data to classify stable MCI and progressive MCI. First, we compare MRI images of Alzheimer's disease with cognitively normal subjects to identify distinct anatomical landmarks using a multivariate statistical test. These landmarks are then used to extract patches that are fed into the proposed multi-stream convolutional neural network to classify MRI images. Next, we train the architecture in a separate scenario using samples from Alzheimer's disease images, which are anatomically similar to the progressive MCI ones and cognitively normal images to compensate for the lack of progressive MCI training data. Finally, we transfer the trained model weights to the proposed architecture in order to fine-tune the model using progressive MCI and stable MCI data. Experimental results on the ADNI-1 dataset indicate that our method outperforms existing methods for MCI classification, with an F1-score of 85.96%.

Malware is defined as any type of malicious code that is the potent to harm a computer or a network. Modern malwares are accompanied with mutation characteristics, namely polymorphism and metamorphism. They let malwares to generate enormous number of variants. Rising number of metamorphic malwares entails hardship in analyzing them for signature extraction and database updates. In spite of the broad use of signature-based methods in the security products, they are not able detect the new unseen morphs of malware, and it is stemmed from changing the structure of malware as well as the signature in each infection. In this paper, a novel method is proposed in which the proportion of opcodes is used for detecting the new morphs. Decision trees are utilized for classification and detection of malware variants based on the rate of opcode frequencies. Three metrics for evaluating the proposed method are speed, efficiency and accuracy. It was observed in the course of experiments that speed and time complexity will not be challenging factors; because of the fast nature of extracting the frequencies of opcodes from source assembly file. Empirical validation reveals that the proposed method outperforms the entire commercial antivirus programs with a high level of efficiency and accuracy.

Viseme (Visual Phoneme) clustering and analysis in every language is among the most important preliminaries for conducting various multimedia researches as talking head, lip reading, lip synchronization and computer assisted pronunciation training applications. With respect to the fact that clustering and analyzing visemes are language dependent processes, we concentrated our research on Persian language, which indeed has suffered from lack of such study. In this paper, we used a hierarchical approach for clustering visemes in Persian language based on principal component analysis of a polynomial kernel matrix considering coarticulation effect. Having obtained feature vector of each phoneme, we applied unweighted pair group method with arithmetic mean to each projected viseme on constructed manifold. Then furthest neighbor of the weight value as a result of reconstruction is set as the criterion for comparing viseme dissimilarity. In order to indicate the robustness of the proposed algorithm, a set of experiments was conducted on Persian databases in which two syllables were examined. Comparing the results of the clustering algorithm with that of the perceptual test given by an expert proves a reasonable evaluation of the proposed algorithm.

In this paper, we propose a method for kernel-based object tracking in order to deal with partial occlusion. We use particle filter to estimate target position accurately. The incremental Bhattacharyya Dissimilarity (IBD) based stage is designed to consistently distinguish the particles located in the object region from the others placed in the background. While the target is occluded by background or other objects, the kernel parameters change which adaptively improves the target model. In addition, the number of particles increases in the next frame. To attain the appropriate accuracy in tracking, we use multi-feature to describe the target. The color histogram feature is robust to scale, orientation, partial occlusion and non-rigidity of the object. However, this feature is sensitive to illumination variations. Therefore, we utilize the combination of color histogram and generalized LBP for object edge points to describe an appropriate target model. The performance of this method is evaluated for real world scenarios such as PETS benchmark.

Facial image analysis is one of the areas that have been received considerable attention in recent decades. In addition to areas such as face recognition, gender classification, emotion recognition, and age estimation, there are new applications that have not been studied yet. Family similarity recognition is a new trend that has been studied in this paper for the first time. Local Gabor Binary Pattern Histogram Sequence (LGBPHS) has led to many important advances in face recognition, including over looking generalizability and training issues. Given the current status of this study, two approaches were considered: (1) holistic approach and (2) component-based approach, which embodies the practical principles of theory. In order to model facial family manifold, LGBP is used both for the holistic view and components of the face. For recognition, histogram intersection is used to measure the similarity of different LGBPHSes and the nearest neighborhood is exploited for final clustering. In order to prove the efficiency of the proposed method three set of experiments are conducted in which both subjective and algorithmic issues are considered. It is observed in the course of experiments that the proposed method outperforms the subjective test up to 15%, and outperforms the observed state of the art face recognition methods up to 25.06%.

Immunocytochemistry (ICC) is a microscopic imaging technique that is used to assess the presence of a specific antigen in cells utilizing a specific antibody for allowing visualization and examination processes. Number of cells in an ICC image is considered as one of the most important indicators in the examination process. In this paper, an image analysis approach is proposed in order to count the number of cells in an ICC images. For this purpose, morphological filtering is done to clean up noise. Then, nucleuses and antibodies are separated by classifying relevant colors using a Nearest Neighbor classifier. Finally, the adherent cells are segmented by learning a Genetic model and the number of cells has been counted. The experiments have been conducted on a dataset of ICC images which are collected for this research. The results show the high efficiency of the proposed method.

Objective function or the constraints and consequently the optimal value of the problem can be changed during time in Dynamic optimization problems. There are several challenges in dynamic environments, so that algorithms designed for optimization in these environments would utilize several mechanisms in order to conquer the challenges. In this paper, a novel hybrid algorithm for optimization in dynamic environments, called HPSOLS, is proposed based on particle swarm optimization and local search approaches. In this approach, it aims to increase the ability of local search around optimum with focusing on best found peak in each environment. The results of the proposed approach are evaluated using moving peak benchmark, which is currently the most well-known benchmark for evaluating dynamic environments, and are compared with results of several state-of-the-art algorithms in this domain. Experimental results show that the efficiency of the proposed method outperforms that of other algorithms in this domain.

Swarm intelligence algorithms have been extensively used in clustering based applications e.g. image segmentation which is one of the fundamental components in image analysis and pattern recognition domains. Particle swarm optimization is amongst swarm intelligence algorithms that performs based on population and random search. In this paper, a hybrid algorithm based on PSO, k-means and learning automata is proposed for image segmentation. In the proposed algorithm, learning automata is responsible for activating and deactivating PSO and k-means methods based on current conditions of the segmentation problem. The proposed approach along with other comparative studies has been applied for segmenting benchmark images. Efficiency of the proposed method has been compared with that of other methods and experimental results show the superiority proposed algorithm.

In this paper we present a novel and efficient method, called shoulder point detection (SPD), for computing a planar rational quadratic Bézier curve to approximate a target shape defined by a set of dense and noisy data points. Our contribution is utilizing from one of the exclusive properties of Conic Splines, called the shoulder point(SP) for speed up of the curve fitting process. The SPD can be summarized in the following two steps: first, one data point of input data set is detected as a shoulder point through a heuristic approach. Then in step2, detected shoulder point is utilized to generate a quadratic rational Bézier curve as fitting result of data set. Splitting the input data points into the some segments and applying the proposed method locally can guarantee the accuracy of fitting process. We show that SPD is significantly faster than other data fitting methods used currently in the field of curve fitting since the fitting results are reasonably accurate.