Towards robust automatic affective classification of images using facial expressions for practical applications

Affect is an important feature of multimedia content and conveys valuable information for multimedia indexing and retrieval. Most existing studies for affective content analysis are limited to low-level features or mid-level representations, and are generally criticized for their incapacity to address the gap between low-level features and high-level human affective perception. The facial expressions of subjects in images carry important semantic information that can substantially influence human affective perception, but have been seldom investigated for affective classification of facial images towards practical applications. This paper presents an automatic image emotion detector (IED) for affective classification of practical (or non-laboratory) data using facial expressions, where a lot of “real-world” challenges are present, including pose, illumination, and size variations etc. The proposed method is novel, with its framework designed specifically to overcome these challenges using multi-view versions of face and fiducial point detectors, and a combination of point-based texture and geometry. Performance comparisons of several key parameters of relevant algorithms are conducted to explore the optimum parameters for high accuracy and fast computation speed. A comprehensive set of experiments with existing and new datasets, shows that the method is effective despite pose variations, fast, and appropriate for large-scale data, and as accurate as the method with state-of-the-art performance on laboratory-based data. The proposed method was also applied to affective classification of images from the British Broadcast Corporation (BBC) in a task typical for a practical application providing some valuable insights.

Petrology and textural classification of the Jericho kimberlite, northern Slave Province, Nunavut, Canada

The paper presents data on petrology, bulk rock and mineral compositions, and textural classification of the Middle Jurassic Jericho kimberlite (Slave craton, Canada). The kimberlite was emplaced as three steep-sided pipes in granite that was overlain by limestones and minor soft sediments. The pipes are infilled with hypabyssal and pyroclastic kimberlites and connected to a satellite pipe by a dyke. The Jericho kimberlite is classified as a Group Ia, lacking groundmass tetraferriphlogopite and containing monticellite pseudomorphs. The kimberlite formed, during several consecutive emplacement events of compositionally different batches of kimberlite magma. Core-logging and thin-section observations identified at least two phases of hypabyssal kimberlites and three phases of pyroclastic kimberlites. Hypabyssal kimberlites intruded as a main dyke (HK1) and as late small-volume aphanitic and vesicular dykes. Massive pyroclastic kimberlite (MPK1) predominantly filled the northern and southern lobes of the pipe and formed from magma different from the HK1 magma. The MPK1 magma crystallized Ti-, Fe-, and Cr-rich phlogopite without rims of barian phlogopite, and clinopyroxene and spinel without atoll structures. MPK1 textures, superficially reminiscent of tuffisitic kimberlite, are caused by pervasive contamination by granite xenoliths. The next explosive events filled the central lobe with two varieties of pyroclastic kimberlite: (1) massive and (2) weakly bedded, normally graded pyroclastic kimberlite. The geology of the Jericho pipe differs from the geology of South African or the Prairie kimberlites, but may resemble Lac de Gras pipes, in which deeper erosion removed upper fades of resedimented kimberlites.

Multiple stages classification of Alzheimer’s disease based on structural brain networks using generalized low rank approximations (GLRAM)

To classify each stage for a progressing disease such as Alzheimer’s disease is a key issue for the disease prevention and treatment. In this study, we derived structural brain networks from diffusion-weighted MRI using whole-brain tractography since there is growing interest in relating connectivity measures to clinical, cognitive, and genetic data. Relatively little work has usedmachine learning to make inferences about variations in brain networks in the progression of the Alzheimer’s disease. Here we developed a framework to utilize generalized low rank approximations of matrices (GLRAM) and modified linear discrimination analysis for unsupervised feature learning and classification of connectivity matrices. We apply the methods to brain networks derived from DWI scans of 41 people with Alzheimer’s disease, 73 people with EMCI, 38 people with LMCI, 47 elderly healthy controls and 221 young healthy controls. Our results show that this new framework can significantly improve classification accuracy when combining multiple datasets; this suggests the value of using data beyond the classification task at hand to model variations in brain connectivity.

Do Students Not Care about Extra Credit Opportunities? Investigating Student Perceptions of Extra Credit Value vs. Effort

Giving “extra credit” work to students has been a controversial and hotly debated pedagogical issue for the last 20 years (Blood et al. 1993; Groves 2000; Muztaba Fuad and Jones 2012; Norcross et al. 1989; Weimer 2011). Previous work has focused on the faculty perspective discussing benefits and drawbacks associated with extra credit work (e.g. Hill et al. 1993; Norcross et al. 1989). Other scholars have investigated the use and effects of pop quizzes and other extra credit assignments on students’ final grades (Thorne 2000; Oley 1993). Some authors have criticized that the empirical exploration of understanding students’ motivational and performance efforts remains scarce and “rarely appears in the literature” (Mays and Bower 2005, p. 1). Besides a gap of empirical work it further appears that most existing studies stem from Psychology or Information Science. Yet it is surprising that, even though the topic of extra credit is considered a common practice in marketing education (Ackerman and Kiesler 2007), there is a wide gap within the marketing education literature. For example, a quick search in the Journal of Marketing Education for the keyword “extra credit” shows only 25 search results; yet none of those papers address motivational or performance effects of extra credit. A further search in Marketing Education Review yielded no results at all. To the authors’ knowledge, the topic has only been addressed once by Ackerman and Kiesler in the 2007 MEA Proceedings who conclude that for “such a common part of the marketing education curriculum, we know surprisingly little about its impact on students” (p. 123).

Combining HPLC-DAD and ICP-MS data for improved analysis of complex samples: Classification of the root samples from Cortex moutan

A combined data matrix consisting of high performance liquid chromatography–diode array detector (HPLC–DAD) and inductively coupled plasma-mass spectrometry (ICP-MS) measurements of samples from the plant roots of the Cortex moutan (CM), produced much better classification and prediction results in comparison with those obtained from either of the individual data sets. The HPLC peaks (organic components) of the CM samples, and the ICP-MS measurements (trace metal elements) were investigated with the use of principal component analysis (PCA) and the linear discriminant analysis (LDA) methods of data analysis; essentially, qualitative results suggested that discrimination of the CM samples from three different provinces was possible with the combined matrix producing best results. Another three methods, K-nearest neighbor (KNN), back-propagation artificial neural network (BP-ANN) and least squares support vector machines (LS-SVM) were applied for the classification and prediction of the samples. Again, the combined data matrix analyzed by the KNN method produced best results (100% correct; prediction set data). Additionally, multiple linear regression (MLR) was utilized to explore any relationship between the organic constituents and the metal elements of the CM samples; the extracted linear regression equations showed that the essential metals as well as some metallic pollutants were related to the organic compounds on the basis of their concentrations

Combined NIR/MIR analysis: A novel method for the classification of complex substances such as Illicium verum Hook. F. and its adulterants

A novel combined near- and mid-infrared (NIR and MIR) spectroscopic method has been researched and developed for the analysis of complex substances such as the Traditional Chinese Medicine (TCM), Illicium verum Hook. F. (IVHF), and its noxious adulterant, Iuicium lanceolatum A.C. Smith (ILACS). Three types of spectral matrix were submitted for classification with the use of the linear discriminant analysis (LDA) method. The data were pretreated with either the successive projections algorithm (SPA) or the discrete wavelet transform (DWT) method. The SPA method performed somewhat better, principally because it required less spectral features for its pretreatment model. Thus, NIR or MIR matrix as well as the combined NIR/MIR one, were pretreated by the SPA method, and then analysed by LDA. This approach enabled the prediction and classification of the IVHF, ILACS and mixed samples. The MIR spectral data produced somewhat better classification rates than the NIR data. However, the best results were obtained from the combined NIR/MIR data matrix with 95–100% correct classifications for calibration, validation and prediction. Principal component analysis (PCA) of the three types of spectral data supported the results obtained with the LDA classification method.

Acoustic classification of Australian anurans using syllable features

Acoustic classification of anurans (frogs) has received increasing attention for its promising application in biological and environment studies. In this study, a novel feature extraction method for frog call classification is presented based on the analysis of spectrograms. The frog calls are first automatically segmented into syllables. Then, spectral peak tracks are extracted to separate desired signal (frog calls) from background noise. The spectral peak tracks are used to extract various syllable features, including: syllable duration, dominant frequency, oscillation rate, frequency modulation, and energy modulation. Finally, a k-nearest neighbor classifier is used for classifying frog calls based on the results of principal component analysis. The experiment results show that syllable features can achieve an average classification accuracy of 90.5% which outperforms Mel-frequency cepstral coefficients features (79.0%).

Acoustic features for multi-level classification of Australian frogs

Over past few decades, frog species have been experiencing dramatic decline around the world. The reason for this decline includes habitat loss, invasive species, climate change and so on. To better know the status of frog species, classifying frogs has become increasingly important. In this study, acoustic features are investigated for multi-level classification of Australian frogs: family, genus and species, including three families, eleven genera and eighty five species which are collected from Queensland, Australia. For each frog species, six instances are selected from which ten acoustic features are calculated. Then, the multicollinearity between ten features are studied for selecting non-correlated features for subsequent analysis. A decision tree (DT) classifier is used to visually and explicitly determine which acoustic features are relatively important for classifying family, which for genus, and which for species. Finally, a weighted support vector machines (SVMs) classifier is used for the multi- level classification with three most important acoustic features respectively. Our experiment results indicate that using different acoustic feature sets can successfully classify frogs at different levels and the average classification accuracy can be up to 85.6%, 86.1% and 56.2% for family, genus and species respectively.

A Classification of Homogeneous Operators in the Cowen-Douglas Class

A complete list of homogeneous operators in the Cowen-Douglas class B-n(D) is given. This classification is obtained from an explicit realization of all the homogeneous Hermitian holomorphic vector bundles on the unit disc under the action of the universal covering group of the bi-holomorphic automorphism group of the unit disc.

Comparison of decision tree, support vector machines, and Bayesian network approaches for classification of falls in Parkinson’s disease

Being able to accurately predict the risk of falling is crucial in patients with Parkinson’s dis- ease (PD). This is due to the unfavorable effect of falls, which can lower the quality of life as well as directly impact on survival. Three methods considered for predicting falls are decision trees (DT), Bayesian networks (BN), and support vector machines (SVM). Data on a 1-year prospective study conducted at IHBI, Australia, for 51 people with PD are used. Data processing are conducted using rpart and e1071 packages in R for DT and SVM, con- secutively; and Bayes Server 5.5 for the BN. The results show that BN and SVM produce consistently higher accuracy over the 12 months evaluation time points (average sensitivity and specificity > 92%) than DT (average sensitivity 88%, average specificity 72%). DT is prone to imbalanced data so needs to adjust for the misclassification cost. However, DT provides a straightforward, interpretable result and thus is appealing for helping to identify important items related to falls and to generate fallers’ profiles.

Automatic ICD-10 classification of cancers from free-text death certificates

Objective Death certificates provide an invaluable source for cancer mortality statistics; however, this value can only be realised if accurate, quantitative data can be extracted from certificates – an aim hampered by both the volume and variable nature of certificates written in natural language. This paper proposes an automatic classification system for identifying cancer related causes of death from death certificates. Methods Detailed features, including terms, n-grams and SNOMED CT concepts were extracted from a collection of 447,336 death certificates. These features were used to train Support Vector Machine classifiers (one classifier for each cancer type). The classifiers were deployed in a cascaded architecture: the first level identified the presence of cancer (i.e., binary cancer/nocancer) and the second level identified the type of cancer (according to the ICD-10 classification system). A held-out test set was used to evaluate the effectiveness of the classifiers according to precision, recall and F-measure. In addition, detailed feature analysis was performed to reveal the characteristics of a successful cancer classification model. Results The system was highly effective at identifying cancer as the underlying cause of death (F-measure 0.94). The system was also effective at determining the type of cancer for common cancers (F-measure 0.7). Rare cancers, for which there was little training data, were difficult to classify accurately (F-measure 0.12). Factors influencing performance were the amount of training data and certain ambiguous cancers (e.g., those in the stomach region). The feature analysis revealed a combination of features were important for cancer type classification, with SNOMED CT concept and oncology specific morphology features proving the most valuable. Conclusion The system proposed in this study provides automatic identification and characterisation of cancers from large collections of free-text death certificates. This allows organisations such as Cancer Registries to monitor and report on cancer mortality in a timely and accurate manner. In addition, the methods and findings are generally applicable beyond cancer classification and to other sources of medical text besides death certificates.

Direct measurement of inner prosthesis loading during activities of daily living: Proposal for classification of functional outcome

Background The purpose of this presentation is to outline the relevance of the categorization of the load regime data to assess the functional output and usage of the prosthesis of lower limb amputees. The objectives are • To highlight the need for categorisation of activities of daily living • To present a categorization of load regime applied on residuum, • To present some descriptors of the four types of activity that could be detected, • To provide an example the results for a case. Methods The load applied on the osseointegrated fixation of one transfemoral amputee was recorded using a portable kinetic system for 5 hours. The load applied on the residuum was divided in four types of activities corresponding to inactivity, stationary loading, localized locomotion and directional locomotion as detailed in previously publications. Results The periods of directional locomotion, localized locomotion, and stationary loading occurred 44%, 34%, and 22% of recording time and each accounted for 51%, 38%, and 12% of the duration of the periods of activity, respectively. The absolute maximum force during directional locomotion, localized locomotion, and stationary loading was 19%, 15%, and 8% of the body weight on the anteroposterior axis, 20%, 19%, and 12% on the mediolateral axis, and 121%, 106%, and 99% on the long axis. A total of 2,783 gait cycles were recorded. Discussion Approximately 10% more gait cycles and 50% more of the total impulse than conventional analyses were identified. The proposed categorization and apparatus have the potential to complement conventional instruments, particularly for difficult cases.

Isohydric and anisohydric characterisation of vegetable crops. The classification of vegetables by their physiological responses to water stress

Research on the physiological response of crop plants to drying soils and subsequent water stress has grouped plant behaviours as isohydric and anisohydric. Drying soil conditions, and hence declining soil and root water potentials, cause chemical signals—the most studied being abscisic acid (ABA)—and hydraulic signals to be transmitted to the leaf via xylem pathways. Researchers have attempted to allocate crops as isohydric or anisohydric. However, different cultivars within crops, and even the same cultivars grown in different environments/climates, can exhibit both response types. Nevertheless, understanding which behaviours predominate in which crops and circumstances may be beneficial. This paper describes different physiological water stress responses, attempts to classify vegetable crops according to reported water stress responses, and also discusses implications for irrigation decision-making.

Molecular classification of familial colorectal and endometrial carcinoma

Hereditary nonpolyposis colorectal cancer (HNPCC) is the most common known clearly hereditary cause of colorectal and endometrial cancer (CRC and EC). Dominantly inherited mutations in one of the known mismatch repair (MMR) genes predispose to HNPCC. Defective MMR leads to an accumulation of mutations especially in repeat tracts, presenting microsatellite instability. HNPCC is clinically a very heterogeneous disease. The age at onset varies and the target tissue may vary. In addition, families that fulfill the diagnostic criteria for HNPCC but fail to show any predisposing mutation in MMR genes exist. Our aim was to evaluate the genetic background of familial CRC and EC. We performed comprehensive molecular and DNA copy number analyses of CRCs fulfilling the diagnostic criteria for HNPCC. We studied the role of five pathways (MMR, Wnt, p53, CIN, PI3K/AKT) and divided the tumors into two groups, one with MMR gene germline mutations and the other without. We observed that MMR proficient familial CRC consist of two molecularly distinct groups that differ from MMR deficient tumors. Group A shows paucity of common molecular and chromosomal alterations characteristic of colorectal carcinogenesis. Group B shows molecular features similar to classical microsatellite stable tumors with gross chromosomal alterations. Our finding of a unique tumor profile in group A suggests the involvement of novel predisposing genes and pathways in colorectal cancer cohorts not linked to MMR gene defects. We investigated the genetic background of familial ECs. Among 22 families with clustering of EC, two (9%) were due to MMR gene germline mutations. The remaining familial site-specific ECs are largely comparable with HNPCC associated ECs, the main difference between these groups being MMR proficiency vs. deficiency. We studied the role of PI3K/AKT pathway in familial ECs as well and observed that PIK3CA amplifications are characteristic of familial site-specific EC without MMR gene germline mutations. Most of the high-level amplifications occurred in tumors with stable microsatellites, suggesting that these tumors are more likely associated with chromosomal rather than microsatellite instability and MMR defect. The existence of site-specific endometrial carcinoma as a separate entity remains equivocal until predisposing genes are identified. It is possible that no single highly penetrant gene for this proposed syndrome exists, it may, for example be due to a combination of multiple low penetrance genes. Despite advances in deciphering the molecular genetic background of HNPCC, it is poorly understood why certain organs are more susceptible than others to cancer development. We found that important determinants of the HNPCC tumor spectrum are, in addition to different predisposing germline mutations, organ specific target genes and different instability profiles, loss of heterozygosity at MLH1 locus, and MLH1 promoter methylation. This study provided more precise molecular classification of families with CRC and EC. Our observations on familial CRC and EC are likely to have broader significance that extends to sporadic CRC and EC as well.