Search

Manual annotation of video segmentation datasets requires an immense amount of human effort, thus, reduction of human annotation costs is an active topic of research. While many papers deal with the propagation of masks through frames of a video, only a few results attempt to optimize annotation task selection. In this paper we present a deep learning based solution to the latter problem and train it using Reinforcement Learning. Our approach utilizes a modified version of the Dueling Deep Q-Network sharing weight parameters across the temporal axis of the video. This technique enables the trained agent to select annotation tasks from the whole video. We evaluate our annotation task selection method by means of a hierarchical supervoxel segmentation based mask propagation algorithm.

The goal of this paper is to review the relevant literature on autism questionnaires, models, analytic tools, and subgrouping, focusing on the opportunities and limitations. We examined how the size and nature of the database and the number and type of parameters measured determine the use of analytic tools and the expected type of results. To support our position about the examined aspects, we rely on various parts of the reviewed articles. We emphasize that the individual results in each article can only be interpreted in the light of the methods that brought about the conclusions. The reviewed literature suggests a heterogeneous palette in autism subtypes instead of distinct, well-characterized subgroups, or a single-dimensional continuous spectrum.

According to the recently proposed omnigenic theory, all expressed genes in a relevant tissue are contributing directly or indirectly to the manifestation of complex disorders such as autism. Thus, holistic approaches can be complementary in studying genetics of these complex disorders to focusing on a limited number of candidate genes. Gene interaction networks can be used for holistic studies of the omnigenic nature of autism. We used Louvain clustering on tissue-specific gene interaction networks and their subgraphs exclusively containing autism-related genes to study the effects of peripheral gene interactions. We observed that the autism gene clusters are significantly weaker connected to each other and the peripheral genes in non-neuronal tissues than in brain-related tissues. The biological functions of the brain clusters correlated well with previous findings on autism, such as synaptic signaling, regulation of DNA methylation, or regulation of lymphocyte activation, however, on the other tissues they did not enrich as significantly. Furthermore, ASD subjects with disruptive mutations in specific gene clusters show phenotypical differences compared to other disruptive variants carrying ASD individuals. Our results strengthen the omnigenic theory and can advance our understanding of the genetic background of autism.

Human pose estimation is a crucial step towards understanding and characterizing people’s behavior in images and videos. Current state of the art results on human pose estimation were achieved by large Deep Learning models that are restricted to cloud computing for real time applications. However, with the development of edge computing, Deep Learning is moving more from the cloud to the edge. In this work we present DeepRehab, a Deep Learning based 2D pose estimator optimized for Edge TPU processing. We first improve an existing Edge TPU compatible model named PoseNet by refining its predictions with filtering methods. Subsequently, as the performance of the filters is limited by the model’s inaccuracies, specifically on the lower body parts, we developed DeepRehab, trained on 23 keypoints from the COCO-WholeBody dataset. We achieve 0.65 AP with DeepRehab and quantize it, such that, losing only 3% of AP it runs at a speed of 15 FPS on the Coral USB Accelerator that suits real time evaluations.

Continuous identification of objects with identical appearance is crucial to analyze the behavior of laboratory animals. Most existing methods attempt to avoid this problem by excluding direct social interactions or facilitating it by implants or artificial markers. Unfortunately, these techniques may distort the results as they can affect the behavior of the observed animals. In this paper, we present a simple, deep learning-based approach that can overcome these problems by providing reliable segmentation and tracking of similar instances. Recognition of frames where the system could not reliably locate the objects and mark them suggests human supervision is central to the system since there should be no mistake in instance tracking. Manual annotation of these data improves tracking and decreases annotation needs quickly. The proposed method achieves higher segmentation accuracy and more stable tracking than previous methods despite requiring only a small set of manually annotated data.

Tracking and segmentation of moving objects in videos continues to be the central problem in the separation and prediction of concurrent episodes and situation understanding. Along with critical issues such as collision avoidance, tracking and segmentation have numerous applications in other disciplines, including medicine research. To infer the potential side effects of a given treatment, behaviour analysis of la-boratory animals should be performed, which can be achieved via tracking. This presents a difficult task due to the special circumstances, such as the highly similar shape and the unpredictable movement of the subject creatures, but a precise solution would accelerate research by eliminating the need of manual supervision. To this end, we propose Cluster R-CNN, a deep architecture that uses clustering to segment object instances in a given image and track them across subsequent frames. We show that pairwise clustering coupled with a recurrent unit successfully extends Mask R-CNN to a model capable of tracking and segmenting highly similar moving and occluded objects, providing proper results even in certain cases where related networks fail. In addition to theoretical background and reasoning, our work also features experiments on a unique rat tracking data set, with quantitative results to compare the aforementioned model with other architectures. The proposed Cluster R-CNN serves as a baseline for future work towards achieving an automatic monitoring tool for biomedical research.

Machine learning is making substantial progress in diverse applications. The success is mostly due to advances in deep learning. However, deep learning can make mistakes and its generalization abilities to new tasks are questionable. We ask when and how one can combine network outputs, when (i) details of the observations are evaluated by learned deep components and (ii) facts and rules are available. The Deep Consistence Seeking (DCS) machine seeks for consistent and deterministic event descriptions and improves the representation accordingly. The machine has an anomaly detection component that may trigger coherence seeking. Coherence seeking resolves conflicts between computational modules by preferring components with higher scores. We illustrate that context can help in correcting recognitions and in deriving training samples for self-training. We put these concepts into a general framework of cognition, by distinguishing creativity, rule extraction, verification, and symbol grounding. We demonstrate our approach in a driving scenario.

Previously, we have put forth the concept of Cartesian abstraction and argued that it can yield ‘cognitive maps’. We suggested a general mechanism and presented deep learning based numerical simulations: an observed factor (head direction) was non-linearly projected to form a discretized representation (head direction cells). That representation, in turn, enabled the development of a complementing factor (place cells) from high dimensional (visual) inputs. It has been shown that a related metric, in the form of oriented hexagonal grids, may also be derived. Elements of the algorithms were connected to the entorhinal-hippocampal complex (EHC loop). Here, we make one step further in the mapping to the neural substrate. We consider (i) the features of signals arriving at deep and superficial CA1 pyramidal cells, (ii) the interplay between lateral and medial entorhinal cortex efferents, and the nature of ‘instructive’ input timing-dependent plasticity, a feature of the loop. We suggest that the circuitry corresponds to a special form of Residual Networks that we call Sparsified and Twisted Residual Autoencoder (ST-RAE). We argue that ST-RAEs can learn Cartesian Factors and fit the structure and the working of the entorhinal-hippocampal complex to a reasonable extent, including certain oscillatory properties. We put forth the idea that the factor learning architecture of ST-RAEs has a double role in serving goal-oriented behavior, such as (a) the lowering the dimensionality of the task and (b) the mitigation of the problem of partial observation.

Ever since the discovery of columnar structures, their function remained enigmatic. As a potential explanation for this puzzling function, we introduce the ‘Columnar Machine’. We join two neural network types, Structured Sparse Coding (SSC) of generative nature exploiting sparse groups of neurons and Feed-Forward Networks (FFNs) into one architecture. Memories supporting recognition can be quickly loaded into SSC via supervision or can be learned by SSC in a self-organized manner. However, SSC evaluation is slow. We train FFNs for predicting the sparse groups and then the representation is computed by fast undercomplete methods. This two step procedure enables fast estimation of the overcomplete group sparse representations. The suggested architecture works fast and it is biologically plausible. Beyond the function of the minicolumnar structure it may shed light onto the role of fast feed-forward inhibitory thalamocortical channels and cortico-cortical feed-back connections. We demonstrate the method for natural image sequences where we exploit temporal structure and for a cognitive task where we explain the meaning of unknown words from their contexts.

It has been long debated how the so called cognitive map, the set of place cells, develops in rat hippocampus. The function of this organ is of high relevance, since the hippocampus is the key component of the medial temporal lobe memory system, responsible for forming episodic memory, declarative memory, the memory for facts and rules that serve cognition in humans. Here, a general mechanism is put forth: We introduce the novel concept of Cartesian factors. We show a non-linear projection of observations to a discretized representation of a Cartesian factor in the presence of a representation of a complementing one. The computational model is demonstrated for place cells that we produce from the egocentric observations and the head direction signals. Head direction signals make the observed factor and sparse allothetic signals make the complementing Cartesian one. We present numerical results, connect the model to the neural substrate, and elaborate on the differences between this model and other ones, including Slow Feature Analysis [17] .

Stable unilamellar dipalmitoylphosphatidylcholine vesicles were produced by using oligo(malic acid) and cholesterol. Detailed physico-chemical characterization prove that by using oligo(malic acid) the substitution of PEGylated lipids for sterically stabilization comes possible. The polymer molecules cover the outer surface of spherical-shaped vesicles, and an asymmetrical composition occurs in the two leaflets of the phospholipid bilayer. The oligo(malic-acid) and cholesterol are enriched in the outer side assuring the stabilization of vesicles. Cholesterol plays an important role in the self-assembly of components as it makes the entering of oligomers possible deep into the polar head-region of lipids. The presence of oligo(malic acid) molecules does not induce degradation by hydrolysis of lipid molecules but the vesicle system turns into a sensitive form giving a possibility for pH sensitive targeting. Preliminary investigation on the investigated oligo(malic acid)-stabilized vesicles do not show any toxic effect promising their applicability in the field of liposomal drug delivery.

In this study we investigate the strategies of subjects in a complex divided attention task. We conducted a series of experiments with ten participants and evaluated their performance. After an extensive analysis, we identified four strategic measures that justify the achievement of the participants, by highlighting the individual differences and predicting performance in a regression analysis using generalized estimating equations. Selecting the more urgent task and user action between multiple simultaneous possibilities form two of the strategic decisions, respectively. The third one refers to choosing a response within the same task when the opportunity is present. The fourth and most important measure of strategy involves thinking ahead and executing an action before a situation would become critical. This latter one has the effect of reducing later cognitive load or timing constraints and it is shown to explain almost as much variance in performance as the other three, more straightforward predictors together. In addition to determining these strategic predictors, we also show how manipulating task difficulty induces a shift in strategy, thus impairing human performance in the rehearsed task. The results of this study indicate that considerable differences in the divided attention ability of normal subjects can be identified early and with simple measurements. The importance of describing and analyzing strategies is also emphasized, which can substantially influence performance in complex tasks and may serve training needs.

In monocular 3D human pose estimation a common setup is to first detect 2D positions and then lift the detection into 3D coordinates. Many algorithms suffer from overfitting to camera positions in the training set. We propose a siamese architecture that learns a rotation equivariant hidden representation to reduce the need for data augmentation. Our method is evaluated on multiple databases with different base networks and shows a consistent improvement of error metrics. It achieves state-of-the-art cross-camera error rate among algorithms that use estimated 2D joint coordinates only., Comment: Accepted to Neurocomputing

We argue that recent technology developments hold great promises for health and wellbeing. In our view, recent advances of (1) smart tools and wearable sensors of diverse kinds, (2) data collection and data mining methods, (3) 3D visual recording and visual processing methods, (4) 3D models of the environment with robust physics engine, and last but not least, (5) new applications of human computing and crowdsourcing started the revolution. We are neither claiming nor excluding that human intelligence will be reached in some years from now, but make the above claim, which is both weaker and stronger. We believe that fast developments for health and wellbeing are the question of active collaboration between health and wellbeing experts and motivated engineers.

The existence of place cells (PCs), grid cells (GCs), border cells (BCs), and head direction cells (HCs) as well as the dependencies between them have been enigmatic. We make an effort to explain their nature by introducing the concept of Cartesian Factors. These factors have specific properties: (i) they assume and complement each other, like direction and position and (ii) they have localized discrete representations with predictive attractors enabling implicit metric-like computations. In our model, HCs make the distributed and local representation of direction. Predictive attractor dynamics on that network forms the Cartesian Factor “direction.” We embed these HCs and idiothetic visual information into a semi-supervised sparse autoencoding comparator structure that compresses its inputs and learns PCs, the distributed local and direction independent (allothetic) representation of the Cartesian Factor of global space. We use a supervised, information compressing predictive algorithm and form direction sensitive (oriented) GCs from the learned PCs by means of an attractor-like algorithm. Since the algorithm can continue the grid structure beyond the region of the PCs, i.e., beyond its learning domain, thus the GCs and the PCs together form our metric-like Cartesian Factors of space. We also stipulate that the same algorithm can produce BCs. Our algorithm applies (a) a bag representation that models the “what system” and (b) magnitude ordered place cell activities that model either the integrate-and-fire mechanism, or theta phase precession, or both. We relate the components of the algorithm to the entorhinal-hippocampal complex and to its working. The algorithm requires both spatial and lifetime sparsification that may gain support from the two-stage memory formation of this complex.

We introduce a learning architecture that can serve compression while it also satisfies the constraints of factored reinforcement learning. Our novel Cartesian factors enable one to decrease the number of variables being relevant for the ongoing task, an exponential gain in the size of the state space. We demonstrate the working, the limitations and the promises of the abstractions: we develop a representation of space in allothetic coordinates from egocentric observations and argue that the lower dimensional allothetic representation can be used for path planning. Our results on the learning of Cartesian factors indicate that (a) shallow autoencoders perform well in our numerical example and (b) if deeper networks are needed, e.g., for classification or regression, then sparsity should also be enforced at (some of) the intermediate layers.

Facial expression communicates emotion, intention, and physical state, and regulates interpersonal behavior. Automated face analysis (AFA) for the detection, synthesis, and understanding of facial expression is a vital focus of basic research with applications in behavioral science, mental and physical health and treatment, marketing, and human-robot interaction among other domains. In previous work, facial action unit (AU) detection becomes seriously degraded when head orientation exceeds \(15^{\circ }\) to \(20^{\circ }\). To achieve reliable AU detection over a wider range of head pose, we used 3D information to augment video data and a deep learning approach to feature selection and AU detection. Source video were from the BP4D database (n = 41) and the FERA test set of BP4D-extended (n = 20). Both consist of naturally occurring facial expression in response to a variety of emotion inductions. In augmented video, pose ranged between \(-18^{\circ }\) and \(90^{\circ }\) for yaw and between \(-54^{\circ }\) and \(54^{\circ }\) for pitch angles. Obtained results for action unit detection exceeded state-of-the-art, with as much as a 10 % increase in \(F_1\) measures.

Serious games for mental health is seen as the groundwork for assistive technology to maintain and improve mental health. We present a technical system layout we partly implemented for demonstration purposes and highlight vision-based perception and manipulation capabilities. These include physical interactions employing artificial general intelligence in virtual reality applications. We employ hand gesture tracking, as well as an Oculus Rift integrated gaze and eye tracking system. The resulting serious games should eventually cover daily life activities, which we additionally monitor. The dynamic and contextual modelling of obstacles are central issues, and capabilities required for serious games include knowledge about the 3D world. Such knowledge include gaze and hand sensors interpretations for multimedia information extraction in causal relationships. Towards this goal, we envision to make use of virtual reality with a physics engine (rigid and soft body dynamics including collision detection) for the observed objects. We also exploit semantic networks to enable the machine to filter information and infer ongoing complex events including hidden BDI (beliefs, desires, intentions) variables. We see this combination of employed technology as the relevant groundwork for reaching human-level general intelligence and to enable real-world applications. Future applications and user groups we target on include dementia patients.

[This corrects the article DOI: 10.1371/journal.pone.0195131.].

We treat the problem of searching for hidden multi-dimensional independent auto-regressive processes (auto-regressive independent process analysis, AR-IPA). Independent subspace analysis (ISA) can be used to solve the AR-IPA task. The so-called separation theorem simplifies the ISA task considerably: the theorem enables one to reduce the task to one-dimensional blind source separation task followed by the grouping of the coordinates. However, the grouping of the coordinates still involves two types of combinatorial problems: (a) the number of the independent subspaces and their dimensions, and then (b) the permutation of the estimated coordinates are to be determined. Here, we generalize the separation theorem. We also show a non-combinatorial procedure, which—under certain conditions—can treat these two combinatorial problems. Numerical simulations have been conducted. We investigate problems that fulfill sufficient conditions of the theory and also others that do not. The success of the numerical simulations indicates that further generalizations of the separation theorem may be feasible.

In this paper we extend the conditions of dynamic team constitution in simple eco–grammar systems, motivated by the bottom–up–clustering algorithm. The relationships of simple eco–grammar systems formed according to the newly introduced conditions to each other as well as to certain language classes of the Chomsky hierarchy and L systems are established. We prove that any recursively enumerable language can be obtained as the intersection of a regular language and the language of simple eco–grammar systems where the active teams are organized according to different conditions of team constitution. We also propose some further research directions.

To what extent does the communication make a goal-oriented community efficient in different topologies? In order to gain insight into this problem, we study the influence of learning method as well as that of the topology of the environment on the communication efficiency of crawlers in quest of novel information in different topics on the Internet. Individual crawlers employ selective learning, function approximation-based reinforcement learning (RL), and their combination. Selective learning, in effect, modifies the starting URL lists of the crawlers, whilst RL alters the URL orderings. Real data have been collected from the web and scale-free worlds, scale-free small world (SFSW), and random world environments (RWEs) have been created by link reorganization. In our previous experiments [ Zs. Palotai, Cs. Farkas, A. Lőrincz, Is selection optimal in scale-free small worlds?, ComPlexUs 3 (2006) 158–168], the crawlers searched for novel, genuine documents and direct communication was not possible. Herein, our finding is reproduced: selective learning performs the best and RL the worst in SFSW, whereas the combined, i.e., selective learning coupled with RL is the best—by a slight margin—in scale-free worlds. This effect is demonstrated to be more pronounced when the crawlers search for different topic-specific documents: the relative performance of the combined learning algorithm improves in all worlds, i.e., in SFSW, in SFW, and in RWE. If the tasks are more complex and the work sharing is enforced by the environment then the combined learning algorithm becomes at least equal, even superior to both the selective and the RL algorithms in most cases, irrespective of the efficiency of communication. Furthermore, communication improves the performance by a large margin and adaptive communication is advantageous in the majority of the cases.

Background The ATP-Binding Cassette (ABC)-transporter MultiDrug Resistance Protein 1 (MDR1) and Multidrug Resistance Related Protein 1 (MRP1) are expressed on the surface of enterocytes, which has led to the belief that these high capacity transporters are responsible for modulating chemosensitvity of colorectal cancer. Several immunohistochemistry and reverse transcription polymerase chain reaction (RT-PCR) studies have provided controversial results in regards to the expression levels of these two ABC-transporters in colorectal cancer. Our study was designed to determine the yet uninvestigated functional activity of MDR1 and MRP1 transporters in normal human enterocytes compared to colorectal cancer cells from surgical biopsies. Methods 100 colorectal cancer and 28 adjacent healthy mucosa samples were obtained by intraoperative surgical sampling. Activity of MDR1 and MRP1 of viable epithelial and cancer cells were determined separately with the modified calcein-assay for multidrug resistance activity and sufficient data of 73 cancer and 11 healthy mucosa was analyzed statistically. Results Significantly decreased mean MDR1 activity was found in primary colorectal cancer samples compared to normal mucosa, while mean MRP1 activity showed no significant change. Functional activity was not affected by gender, age, stage or grade and localization of the tumor. Conclusion We found lower MDR activity in cancer cells versus adjacent, apparently, healthy control tissue, thus, contrary to general belief, MDR activity seems not to play a major role in primary drug resistance, but might rather explain preferential/selective activity of Irinotecan and/or Oxaliplatin. Still, this picture might be more complex since chemotherapy by itself might alter MDR activity, and furthermore, today limited data is available about MDR activity of cancer stem cells in colorectal cancers. Virtual slides The virtual slide(s) for this article can be found here: http://www.diagnosticpathology.diagnomx.eu/vs/1675739129145824

The problem of anomaly detection is a critical topic across application domains and is the subject of extensive research. Applications include finding frauds and intrusions, warning on robot safety, and many others. Standard approaches in this field exploit simple or complex system models, created by experts using detailed domain knowledge.

It is an intriguing task to develop efficient connectionist representations for learning long time series. Recurrent neural networks have great promises here. We model the learning task as a minimization problem of a nonlinear least-squares cost function, that takes into account both one-step and multi-step prediction errors. The special structure of the cost function is constructed to build a bridge to reinforcement learning. We exploit this connection and derive a convergent, policy iteration-based algorithm, and show that RNN training can be made to fit the reinforcement learning framework in a natural fashion. The relevance of this connection is discussed. We also present experimental results, which demonstrate the appealing properties of the unique parameter structure prescribed by reinforcement learning. Experiments cover both sequence learning and long-term prediction.

Identification of mixed independent subspaces is thought to suffer from combinatorial explosion of two kinds: the minimization of mutual information between the estimated subspaces and the search for the optimal number and dimensions of the subspaces. Here we show that independent autoregressive process analysis, under certain conditions, can avoid this problem using a two-phase estimation process. We illustrate the solution by computer demonstration.

In this paper we propose a novel architecture and approach to provide accountability for Web communities that require a high-level of privacy. A two-layered privacy protection architecture is proposed, that supports (i) registration of participants and enforcement of community rules, called internal accountability , and (ii) rule-based interaction with real world organizations, called external accountability . Our security protocols build upon community-based trust and limit the exposure of private data on trusted third parties. The two-layered architecture protects the mappings between real users and their virtual identities, and among the virtual users, while guaranteeing internal and external accountability. We target Web communities that are dynamic and self-organizing, i.e. roles and contributions of participants may change over time. The proposed concepts and protocols are implemented in our SyllabNet project that supports anonymous course evaluations by university students.

In this paper, we present a probabilistic method that can improve the efficiency of document classification when applied to structured documents. The analysis of the structure of a document is the starting point of document classification. Our method is designed to augment other classification schemes and complement pre-filtering information extraction procedures to reduce uncertainties. To this end, a probabilistic distribution on the structure of XML documents is introduced. We show how to parameterise existing learning methods to describe the structure distribution efficiently. The learned distribution is then used to predict the classes of unseen documents. Novelty detection making use of the structure-based distribution function is also discussed. Demonstration on model documents and on Internet XML documents are presented.

The slogan that "information is power" has undergone a slight change. Today, "information updating" is in the focus of interest. The largest source of information today is the World Wide Web. Fast search methods are needed to utilize this enormous source of information. In this paper our novel crawler using support vector classification and on-line reinforcement learning is described. We launched crawler searches from different sites, including sites that offer, at best, very limited information about the search subject. This case may correspond to typical searches of non-experts. Results indicate that the considerable performance improvement of our crawler over other known crawlers is due to its on-line adaptation property. We used our crawler to characterize basic topic-specific properties of WWW environments. It was found that topic-specific regions have a broad distribution of valuable documents. Expert sites are excellent starting points, whereas mailing lists can form trape for the crawler. These properties of the WWW and the emergence of intelligent "high-performance" crawlers that monitor and search for novel information together predict a significant increase of communication load on the WWW in the near future.

The slogan that information is powerhas undergone a slight change. Today, information updatingis in the focus of interest. The largest source of information is the world-wide web. Fast search methods are in need for this enormous source. In this paper a hybrid architecture that combines soft support vector classification and reinforcement learning for value estimation is introduced for the evaluation of a link (a document) and its neighboring links (or documents), called the context of a document. The method is motivated by (i) large differences between such contexts on the web, (ii) the facilitation of goal oriented search using context classifiers, and (iii) attractive fast adaptation properties, that could counteract diversity of web environments. We demonstrate that value estimation-based fast adaptation offers considerable improvement over other known search methods. © 2002 Elsevier Science B.V. All rights reserved.

Cikkemben érveket hozok fel amellett, hogy, hogy a technológiai fejlődés ma nagy lehetőségeket kínálnak az egészségügy és a jólét számára. Nézetem szerint (1) az „okos” eszközök (smart tools) és a különböző viselhető érzékelők, (2) az adatgyűjtés és az adatbányászati módszerek, (3) a három dimenziós (3D-s) képi rögzítési és képi feldolgozási eszközök, (4) a 3D-s, bonyolult fizikai motorral rendelkező, például grafikai modellek, valamint (5) a crowdsourcing-on (outsourcing: külső erőforrások igénybevétele, crowdsourcing: külső emberi erőforrások tömeges igénybevétele) alapuló emberalapú számítások (human-based computing), terén történő nagy és sikeres erőfeszítések hatalmas változásokat indítanak el. Nem állítom, bár tagadni sem tudom azt, hogy a mesterséges intelligencia eszközei néhány év múlva elérik az emberi intelligencia szintjét, mert ez lehetséges. Véleményem szerint, az egészségügy és a jólét területén gyors fejlődés lehetséges az egészségügyi és jóléti szakértők, és a motivált mérnökök közötti aktív együttműködés útján. --- Artificial Intelligence, Health and Wellbeing: prospects for machine learning, crowdsourcing and self-annotation We argue that recent technology developments – e.g. smart tools and wearable sensors of diverse kinds, data collection and data mining methods, 3D visual recording and visual processing methods, 3D models of the environment with robust physics engine – and new applications of human computing and crowdsourcing hold great promises for health and wellbeing. We are neither claiming nor excluding that human intelligence will be reached in some years from now, but make the above claim, which is both weaker and stronger. We believe that fast developments for health and wellbeing are the question of active collaboration between health and wellbeing experts and motivated engineers.

We extend the scope of Wikification to novel words by relaxing two premises of Wikification: (i) we wikify without using the surface form of the word (ii) to a mixture of Wikipedia senses instead of a single sense. We identify two types of “novel” words: words where the connection between their surface form and their meaning is broken (e.g., a misspelled word), and words where there is no meaning to connect to—the meaning itself is also novel. We propose a method capable of wikifying both types of novel words while also dealing with the inherently large-scale disambiguation problem. We show that the method can disambiguate between up to 1,000 Wikipedia senses, and it can explain words with novel meaning as a mixture of other, possibly related senses. This mixture representation compares favorably to the widely used bag of words representation.

Effects of ursolic acid on the structural and morphological characteristics of dipalmitoyl lecithin(DPPC)-water system was studied by using differential scanning calorimetry (DSC), small- and wide-angle X-ray scattering (SWAXS), freeze-fracture method combined with transmission electron-microscopy (FF-TEM) and infrared spectroscopy (FT-IR). The surface of the uncorrelated lipid system is rippled or grained and a huge number of small, presumably unilamellar vesicles are present if the UA/DPPC molar ratio is 0.1 mol/mol or higher. Besides the destroyed layer packing of regular multilamellar vesicles, non-bilayer (e.g. cubic or hexagonal) local structures are evidenced by SAXS and FF-TEM methods. The ability of UA to induce non-bilayer structures in hydrated DPPC system originates from the actual geometry form of associated lipid and UA molecules as concluded from the FT-IR measurements and theoretical calculations. Beside numerous beneficial e.g. chemopreventive and chemotherapeutic effect of ursolic acid against cancer, their impact to modify the lipid bilayers can be utilized in liposomal formulations.

In many behavioral domains, such as facial expression and gesture, sparse structure is prevalent. This sparsity would be well suited for event detection but for one problem. Features typically are confounded by alignment error in space and time. As a consequence, high-dimensional representations such as SIFT and Gabor features have been favored despite their much greater computational cost and potential loss of information. We propose a Kernel Structured Sparsity (KSS) method that can handle both the temporal alignment problem and the structured sparse reconstruction within a common framework, and it can rely on simple features. We characterize spatio-temporal events as time-series of motion patterns and by utilizing time-series kernels we apply standard structured-sparse coding techniques to tackle this important problem. We evaluated the KSS method using both gesture and facial expression datasets that include spontaneous behavior and differ in degree of difficulty and type of ground truth coding. KSS outperformed both sparse and non-sparse methods that utilize complex image features and their temporal extensions. In the case of early facial event classification KSS had 10% higher accuracy as measured by F1 score over kernel SVM methods1.

Recently, computer simulation aided work has become a standard routine in all engineering fields. Accordingly, simulation plays a fundamental role even in road traffic engineering. A reliable simulator is able to provide effective analysis of a given traffic network if the applied simulation scenarios properly converge to the real-word situation. This requirement can be achieved based on the mixed use of prior real-world traffic measurements and proper simulation settings. The latter one, however, is not straightforward. Accordingly, the paper investigates a potential calibration technique to create realistic simulations. Basically, a tuning method with genetic algorithm is proposed to reproduce true-to-life traffic based on floating car speed data.

The ability to communicate with others is of paramount importance for mental well-being. In this paper, we describe an interaction system to reduce communication barriers for people with severe speech and physical impairments (SSPI) such as cerebral palsy. The system consists of two main components: (i) the head-mounted human-computer interaction (HCI) part consisting of smart glasses with gaze trackers and text-to-speech functionality (which implement a communication board and the selection tool), and (ii) a natural language processing pipeline in the backend in order to generate complete sentences from the symbols on the board. We developed the components to provide a smooth interaction between the user and the system thereby including gaze tracking, symbol selection, symbol recognition, and sentence generation. Our results suggest that such systems can dramatically increase communication efficiency of people with SSPI.

It has been suggested that sensory information processing makes use of a factorial code. It has been shown that the major components of the hippocampal-entorhinal loop can be derived by conjecturing that the task of this loop is forming and encoding independent components (ICs), one type of factorial codes. However, continuously changing environment poses additional requirements on the coding that can be (partially) satisfied by extending the analysis to the temporal domain and performing IC analysis on concatenated inputs of time slices. We use computer simulations to decide whether IC analysis on temporal sequences can produce place fields in labyrinths or not.