New markov chain based methods for single and cross-domain sentiment classification

Nowadays communication is switching from a centralized scenario, where communication media like newspapers, radio, TV programs produce information and people are just consumers, to a completely different decentralized scenario, where everyone is potentially an information producer through the use of social networks, blogs, forums that allow a real-time worldwide information exchange. These new instruments, as a result of their widespread diffusion, have started playing an important socio-economic role. They are the most used communication media and, as a consequence, they constitute the main source of information enterprises, political parties and other organizations can rely on. Analyzing data stored in servers all over the world is feasible by means of Text Mining techniques like Sentiment Analysis, which aims to extract opinions from huge amount of unstructured texts. This could lead to determine, for instance, the user satisfaction degree about products, services, politicians and so on. In this context, this dissertation presents new Document Sentiment Classification methods based on the mathematical theory of Markov Chains. All these approaches bank on a Markov Chain based model, which is language independent and whose killing features are simplicity and generality, which make it interesting with respect to previous sophisticated techniques. Every discussed technique has been tested in both Single-Domain and Cross-Domain Sentiment Classification areas, comparing performance with those of other two previous works. The performed analysis shows that some of the examined algorithms produce results comparable with the best methods in literature, with reference to both single-domain and cross-domain tasks, in $2$-classes (i.e. positive and negative) Document Sentiment Classification. However, there is still room for improvement, because this work also shows the way to walk in order to enhance performance, that is, a good novel feature selection process would be enough to outperform the state of the art. Furthermore, since some of the proposed approaches show promising results in $2$-classes Single-Domain Sentiment Classification, another future work will regard validating these results also in tasks with more than $2$ classes.

Fully Automatic Segmentation of Brain Tumor Images using Support Vector Machine Classiffication in Combination with Hierarchical Conditional Random Field Regularization

Delineating brain tumor boundaries from magnetic resonance images is an essential task for the analysis of brain cancer. We propose a fully automatic method for brain tissue segmentation, which combines Support Vector Machine classification using multispectral intensities and textures with subsequent hierarchical regularization based on Conditional Random Fields. The CRF regularization introduces spatial constraints to the powerful SVM classification, which assumes voxels to be independent from their neighbors. The approach first separates healthy and tumor tissue before both regions are subclassified into cerebrospinal fluid, white matter, gray matter and necrotic, active, edema region respectively in a novel hierarchical way. The hierarchical approach adds robustness and speed by allowing to apply different levels of regularization at different stages. The method is fast and tailored to standard clinical acquisition protocols. It was assessed on 10 multispectral patient datasets with results outperforming previous methods in terms of segmentation detail and computation times.

Cognitive binding in schizophrenia: weakened integration of temporal intersensory information

Cognitive functioning is based on binding processes, by which different features and elements of neurocognition are integrated and coordinated. Binding is an essential ingredient of, for instance, Gestalt perception. We have implemented a paradigm of causality perception based on the work of Albert Michotte, in which 2 identical discs move from opposite sides of a monitor, steadily toward, and then past one another. Their coincidence generates an ambiguous percept of either "streaming" or "bouncing," which the subjects (34 schizophrenia spectrum patients and 34 controls with mean age 27.9 y) were instructed to report. The latter perception is a marker of the binding processes underlying perceived causality (type I binding). In addition to this visual task, acoustic stimuli were presented at different times during the task (150 ms before and after visual coincidence), which can modulate perceived causality. This modulation by intersensory and temporally delayed stimuli is viewed as a different type of binding (type II). We show here, using a mixed-effects hierarchical analysis, that type II binding distinguishes schizophrenia spectrum patients from healthy controls, whereas type I binding does not. Type I binding may even be excessive in some patients, especially those with positive symptoms; Type II binding, however, was generally attenuated in patients. The present findings point to ways in which the disconnection (or Gestalt) hypothesis of schizophrenia can be refined, suggesting more specific markers of neurocognitive functioning and potential targets of treatment.

Towards Self-Learning Radio-Based Localization Systems

Location-awareness indoors will be an inseparable feature of mobile services/applications in future wireless networks. Its current ubiquitous availability is still obstructed by technological challenges and privacy issues. We propose an innovative approach towards the concept of indoor positioning with main goal to develop a system that is self-learning and able to adapt to various radio propagation environments. The approach combines estimation of propagation conditions, subsequent appropriate channel modelling and optimisation feedback to the used positioning algorithm. Main advantages of the proposal are decreased system set-up effort, automatic re-calibration and increased precision.

UMTS base station-like exposure, well-being, and cognitive performance

BACKGROUND: Radio-frequency electromagnetic fields (RF EMF) of mobile communication systems are widespread in the living environment, yet their effects on humans are uncertain despite a growing body of literature. OBJECTIVES: We investigated the influence of a Universal Mobile Telecommunications System (UMTS) base station-like signal on well-being and cognitive performance in subjects with and without self-reported sensitivity to RF EMF. METHODS: We performed a controlled exposure experiment (45 min at an electric field strength of 0, 1, or 10 V/m, incident with a polarization of 45 degrees from the left back side of the subject, weekly intervals) in a randomized, double-blind crossover design. A total of 117 healthy subjects (33 self-reported sensitive, 84 nonsensitive subjects) participated in the study. We assessed well-being, perceived field strength, and cognitive performance with questionnaires and cognitive tasks and conducted statistical analyses using linear mixed models. Organ-specific and brain tissue-specific dosimetry including uncertainty and variation analysis was performed. RESULTS: In both groups, well-being and perceived field strength were not associated with actual exposure levels. We observed no consistent condition-induced changes in cognitive performance except for two marginal effects. At 10 V/m we observed a slight effect on speed in one of six tasks in the sensitive subjects and an effect on accuracy in another task in nonsensitive subjects. Both effects disappeared after multiple end point adjustment. CONCLUSIONS: In contrast to a recent Dutch study, we could not confirm a short-term effect of UMTS base station-like exposure on well-being. The reported effects on brain functioning were marginal and may have occurred by chance. Peak spatial absorption in brain tissue was considerably smaller than during use of a mobile phone. No conclusions can be drawn regarding short-term effects of cell phone exposure or the effects of long-term base station-like exposure on human health.

The influence of intention on masked priming: A study with semantic classification of words

Unconscious perception is commonly described as a phenomenon that is not under intentional control and relies on automatic processes. We challenge this view by arguing that some automatic processes may indeed be under intentional control, which is implemented in task-sets that define how the task is to be performed. In consequence, those prime attributes that are relevant to the task will be most effective. To investigate this hypothesis, we used a paradigm which has been shown to yield reliable short-lived priming in tasks based on semantic classification of words. This type of study uses fast, well practised classification responses, whereby responses to targets are much less accurate if prime and target belong to a different category than if they belong to the same category. In three experiments, we investigated whether the intention to classify the same words with respect to different semantic categories had a differential effect on priming. The results suggest that this was indeed the case: Priming varied with the task in all experiments. However, although participants reported not seeing the primes, they were able to classify the primes better than chance using the classification task they had used before with the targets. When a lexical task was used for discrimination in experiment 4, masked primes could however not be discriminated. Also, priming was as pronounced when the primes were visible as when they were invisible. The pattern of results suggests that participants had intentional control on prime processing, even if they reported not seeing the primes.

Automatic Food Intake Assessment Using Camera Phones

Obesity is becoming an epidemic phenomenon in most developed countries. The fundamental cause of obesity and overweight is an energy imbalance between calories consumed and calories expended. It is essential to monitor everyday food intake for obesity prevention and management. Existing dietary assessment methods usually require manually recording and recall of food types and portions. Accuracy of the results largely relies on many uncertain factors such as user's memory, food knowledge, and portion estimations. As a result, the accuracy is often compromised. Accurate and convenient dietary assessment methods are still blank and needed in both population and research societies. In this thesis, an automatic food intake assessment method using cameras, inertial measurement units (IMUs) on smart phones was developed to help people foster a healthy life style. With this method, users use their smart phones before and after a meal to capture images or videos around the meal. The smart phone will recognize food items and calculate the volume of the food consumed and provide the results to users. The technical objective is to explore the feasibility of image based food recognition and image based volume estimation. This thesis comprises five publications that address four specific goals of this work: (1) to develop a prototype system with existing methods to review the literature methods, find their drawbacks and explore the feasibility to develop novel methods; (2) based on the prototype system, to investigate new food classification methods to improve the recognition accuracy to a field application level; (3) to design indexing methods for large-scale image database to facilitate the development of new food image recognition and retrieval algorithms; (4) to develop novel convenient and accurate food volume estimation methods using only smart phones with cameras and IMUs. A prototype system was implemented to review existing methods. Image feature detector and descriptor were developed and a nearest neighbor classifier were implemented to classify food items. A reedit card marker method was introduced for metric scale 3D reconstruction and volume calculation. To increase recognition accuracy, novel multi-view food recognition algorithms were developed to recognize regular shape food items. To further increase the accuracy and make the algorithm applicable to arbitrary food items, new food features, new classifiers were designed. The efficiency of the algorithm was increased by means of developing novel image indexing method in large-scale image database. Finally, the volume calculation was enhanced through reducing the marker and introducing IMUs. Sensor fusion technique to combine measurements from cameras and IMUs were explored to infer the metric scale of the 3D model as well as reduce noises from these sensors.

A cognitive analysis of English cognate objects

In this paper, from the perspective of Cognitive Grammar, we consider the question of what kind of verbs can take cognate objects (COs) and what kind of verbs cannot. We investigate the syntactic properties of COs, such as the ability to take modifiers, the passivizability of cognate object constructions (COCs), and the it-pronominalization of COs. It is our contention that a detailed classification of verbs that occur in COCs is required in order to capture the relation between the syntactic properties and the modification of COs. While classifying verbs, we focus on three conceptual factors: the force of energy of the subject, a change of state of the subject, and the objectivity of the cognate noun. The study reveals that these three parameters enable us to capture the difference in the interpretation of COs in relation to modification and syntactic tests.

Application of Cognitive Engineering Principles to the Redesign of a Dichotomous Identification Key for Parasitology

Dichotomous identification keys are used throughout biology for identification of plants, insects, and parasites. However, correct use of identification keys can be difficult as they are not usually intended for novice users who may not be familiar with the terminology used or with the morphology of the organism being identified. Therefore, we applied cognitive engineering principles to redesign a parasitology identification key for the Internet. We addressed issues of visual clutter and spatial distance by displaying a single question couplet at a time and by switching to the appropriate next couplet after the user made a choice. Our analysis of the original paper-based key versus the Web-based approach found that of 26 applicable cognitive engineering principles, the paper key did not meet 4 (15%) and partially met 11 (42%). In contrast, the redesigned key met 100% of 32 applicable cognitive engineering principles.

Taxonomy development and knowledge representation of nurses' personal cognitive artifacts.

Nurses prepare knowledge representations, or summaries of patient clinical data, each shift. These knowledge representations serve multiple purposes, including support of working memory, workload organization and prioritization, critical thinking, and reflection. This summary is integral to internal knowledge representations, working memory, and decision-making. Study of this nurse knowledge representation resulted in development of a taxonomy of knowledge representations necessary to nursing practice.This paper describes the methods used to elicit the knowledge representations and structures necessary for the work of clinical nurses, described the development of a taxonomy of this knowledge representation, and discusses translation of this methodology to the cognitive artifacts of other disciplines. Understanding the development and purpose of practitioner's knowledge representations provides important direction to informaticists seeking to create information technology alternatives. The outcome of this paper is to suggest a process template for transition of cognitive artifacts to an information system.

BrainCheck - a very brief tool to detect incipient cognitive decline: optimized case-finding combining patient- and informant-based data.

INTRODUCTION Optimal identification of subtle cognitive impairment in the primary care setting requires a very brief tool combining (a) patients' subjective impairments, (b) cognitive testing, and (c) information from informants. The present study developed a new, very quick and easily administered case-finding tool combining these assessments ('BrainCheck') and tested the feasibility and validity of this instrument in two independent studies. METHODS We developed a case-finding tool comprised of patient-directed (a) questions about memory and depression and (b) clock drawing, and (c) the informant-directed 7-item version of the Informant Questionnaire on Cognitive Decline in the Elderly (IQCODE). Feasibility study: 52 general practitioners rated the feasibility and acceptance of the patient-directed tool. Validation study: An independent group of 288 Memory Clinic patients (mean ± SD age = 76.6 ± 7.9, education = 12.0 ± 2.6; 53.8% female) with diagnoses of mild cognitive impairment (n = 80), probable Alzheimer's disease (n = 185), or major depression (n = 23) and 126 demographically matched, cognitively healthy volunteer participants (age = 75.2 ± 8.8, education = 12.5 ± 2.7; 40% female) partook. All patient and healthy control participants were administered the patient-directed tool, and informants of 113 patient and 70 healthy control participants completed the very short IQCODE. RESULTS Feasibility study: General practitioners rated the patient-directed tool as highly feasible and acceptable. Validation study: A Classification and Regression Tree analysis generated an algorithm to categorize patient-directed data which resulted in a correct classification rate (CCR) of 81.2% (sensitivity = 83.0%, specificity = 79.4%). Critically, the CCR of the combined patient- and informant-directed instruments (BrainCheck) reached nearly 90% (that is 89.4%; sensitivity = 97.4%, specificity = 81.6%). CONCLUSION A new and very brief instrument for general practitioners, 'BrainCheck', combined three sources of information deemed critical for effective case-finding (that is, patients' subject impairments, cognitive testing, informant information) and resulted in a nearly 90% CCR. Thus, it provides a very efficient and valid tool to aid general practitioners in deciding whether patients with suspected cognitive impairments should be further evaluated or not ('watchful waiting').

3D Intervertebral Disc Localization and Segmentation from MR Images by Data-Driven Regression and Classification

In this paper we propose a new fully-automatic method for localizing and segmenting 3D intervertebral discs from MR images, where the two problems are solved in a unified data-driven regression and classification framework. We estimate the output (image displacements for localization, or fg/bg labels for segmentation) of image points by exploiting both training data and geometric constraints simultaneously. The problem is formulated in a unified objective function which is then solved globally and efficiently. We validate our method on MR images of 25 patients. Taking manually labeled data as the ground truth, our method achieves a mean localization error of 1.3 mm, a mean Dice metric of 87%, and a mean surface distance of 1.3 mm. Our method can be applied to other localization and segmentation tasks.

Fully automatic segmentation of AP pelvis X-rays via random forest regression with efficient feature selection and hierarchical sparse shape composition

In clinical practice, traditional X-ray radiography is widely used, and knowledge of landmarks and contours in anteroposterior (AP) pelvis X-rays is invaluable for computer aided diagnosis, hip surgery planning and image-guided interventions. This paper presents a fully automatic approach for landmark detection and shape segmentation of both pelvis and femur in conventional AP X-ray images. Our approach is based on the framework of landmark detection via Random Forest (RF) regression and shape regularization via hierarchical sparse shape composition. We propose a visual feature FL-HoG (Flexible- Level Histogram of Oriented Gradients) and a feature selection algorithm based on trace radio optimization to improve the robustness and the efficacy of RF-based landmark detection. The landmark detection result is then used in a hierarchical sparse shape composition framework for shape regularization. Finally, the extracted shape contour is fine-tuned by a post-processing step based on low level image features. The experimental results demonstrate that our feature selection algorithm reduces the feature dimension in a factor of 40 and improves both training and test efficiency. Further experiments conducted on 436 clinical AP pelvis X-rays show that our approach achieves an average point-to-curve error around 1.2 mm for femur and 1.9 mm for pelvis.

Implicit threat, self-regulatory resources, and cognitive performance

The color red has been considered to indicate threat in achievement contexts. Recent studies have used brief confrontations with red — either as the color or as the word red — to prime for implicit threat, and have found a related impairment of cognitive performance. In another line of research, it has been shown that initial self-regulatory efforts cause diminished investment of self-regulatory resources afterwards, leading to a relative shift from a controlled to an automatic mode of information processing. We assume that activation of implicit threat via the color or the word red impairs cognitive performance more strongly during automatic compared to controlled processing of information. To test this hypothesis, we manipulated undergraduates’ (n = 78) momentary processing mode (automatic vs. controlled) by an initial task that required either high or low self-regulatory effort. Afterwards, participants were briefly confronted with red or gray stimuli and were then asked to complete a standardized intelligence measure. As expected, confrontation with red, as opposed to gray, impaired intellectual performance when participants were in an automatic processing mode. In contrast, no color effect emerged when participants were in a relatively controlled processing mode. In a second study, we replicated this finding in a sample of secondary school students (n = 130), using the black-printed word red or gray to experimentally manipulate implicit threat. Among others, the present findings may help to explain occasional difficulties in replicating findings of priming research.

Descriptive/Inferential Cognitive Processes and Evaluative Cognitive Processes: Relationships Among Each Other and with Emotional Distress

We aimed to delineate key constructs from two forms of cognitive-behavioral therapy: cognitive therapy and rational-emotive behavior therapy. Furthermore, we aimed to investigate the interrelations among each other and with emotional distress. The key constructs of the underlying theories of these therapies (i.e., descriptive/inferential beliefs, evaluative beliefs) are often treated together as distorted cognitions and included as such in various scales. We used a cross-sectional design. Seventy-four undergraduate students (mean age = 24.68) completed measures of automatic thoughts and emotional distress. Three therapists trained in cognitive-behavioral therapy divided automatic thoughts into descriptive/inferential beliefs and evaluative beliefs by consensus. Correlation and mediation analyses were performed. These constructs showed medium to high associations to each other and to distress. The relationship between descriptive/inferential beliefs and distress was mediated by evaluative beliefs. Descriptive and inferential cognitions may not produce emotions without first being appraised in terms of personal relevance.