Acoustic features extraction for emotion recognition

In the last decade, the efforts of spoken language processing have achieved significant advances, however, the work with emotional recognition has not progressed so far, and can only achieve 50% to 60% in accuracy. This is because a majority of researchers in this field have focused on the synthesis of emotional speech rather than focusing on automating human emotion recognition. Many research groups have focused on how to improve the performance of the classifier they used for emotion recognition, and few work has been done on data pre-processing, such as the extraction and selection of a set of specifying acoustic features instead of using all the possible ones they had in hand. To work with well-selected acoustic features does not mean to delay the whole job, but this will save much time and resources by removing the irrelative information and reducing the high-dimension data calculation. In this paper, we developed an automatic feature selector based on a RF2TREE algorithm and the traditional C4.5 algorithm. RF2TREE applied here helped us to solve the problems that did not have enough data examples. The ensemble learning technique was applied to enlarge the original data set by building a bagged random forest to generate many virtual examples, and then the new data set was used to train a single decision tree, which selects the most efficient features to represent the speech signals for the emotion recognition. Finally, the output of the selector was a set of specifying acoustic features, produced by RF2TREE and a single decision tree.

Road-sign identification using ensemble learning

Ensemble learning that combines the decisions of multiple weak classifiers to from an output, has recently emerged as an effective identification method. This paper presents a road-sign identification system based upon the ensemble learning approach. The system identifies the regions of interest that are extracted from the scene into the road-sign groups that they belong to. A large road-sign image dataset is formed and used to train and test the system. Fifteen groups of road signs are chosen for identification. Five experiments are performed and the results are presented and discussed.

The body keeps the score

American animator Robert Breer has been credited in introducing the first visual bomb to cinema in his loop film Image by Images I (1954), Two abstract animated films by Robert Breer are examined: 69 (1968 5 minutes) and Fuji (1974 10 minutes). Using Merleau-Ponty’s phenomenological perspective, though these films are not representational or photographic in the traditional sense it is argued that they are still able to talk to us about real experiences because ‘the lived perspective, that which we actually perceive, is not a geometric or photographic one.’(Merleau-Ponty, 1964b: 14) 69 provides a metaphor for a system that collapses and Fuji as an articulation of that embodied seeing required for train travel. It is argued that Breer’s work in its explorations of style ahead of content is research into an act of viewing that offers a contemporary simulation of the impact of a traumatic experience on the body. Just as one cannot grab each object in the landscape at the speed of train travel nor can one grab or understand each frame that is presented to the retina of a Robert Breer film. What is required to attain “stillness” is a more dissociated way of looking that allows the images to wash over you. Such a “stillness” may be more about suppression than contemplation and could involve a process of metamorphosis.

Training general practitioners in the assessment of childhood mental health problems

Epidemiological studies have found that most children with mental health problems are not receiving appropriate help. The aim of this study was to assess an approach to train general practitioners (GPs) to detect mental health problems early, engage the families, and assist them in the access of service. Five GPs were given three hours of training on a brief assessment method. Each then interviewed parents whose children they suspected might have a mental health problem. An experienced research clinician then repeated the assessment. This information was fed back to the GP who then assisted the family in obtaining appropriate help. Twenty-nine parents were interviewed in six months. The research clinician and the GPs were in agreement for 90% of the cases for the recognition of mental health problems. GPs’ opinions on the brief assessment method were: easy to use (100%), helpful in obtaining information (100%) and helpful in engaging the parent (100%). The parents were followed up by telephone 3-4 months after the interview. Eighty-eight percent reported that the process was helpful, 67% had received help from services and 67% had improved. We conclude that with brief training, the GPs in this study were able to improve their capacity to provide early intervention for childhood mental health problems.

Integrated model for thermo-mechanical controlled process in rod (or bar) rolling

This study presents an integrated model for computing the thermo-mechanical parameters (cross-sectional shape of workpiece, the pass-by-pass strain and strain rate and the temperature variation during rolling and cooling between inter-stands) and metallurgical parameters (recrystallisation behaviour and austenite grain size—AGS), to assess the potential for developing “Thermo-Mechanical Controlled Process” technology in rod (or bar) rolling, which has been a well-known technical terminology in strip (or plate) rolling since 1970s.

The advantage of this model is that metallurgical and mechanical parameters are obtained simultaneously in a short computation time compared with other models. The model has been applied to a rod mill to predict the exit cross-sectional shape, area and AGS per pass by incorporating the equations for AGS evolution being used in strip rolling. At the finishing train of rod mills, the strain rates reach as high as 1000–3000 s−1 and the inter-pass times are around 10–60 ms.

The results show that the proposed model is an efficient tool for evaluating the effects of process-related parameters on product quality and dimensional tolerance of the products in rod (or bar) rolling. The results of the simulation demonstrated that the equation for AGS evolution being used in strip rolling might have limitations when applied directly to rod rolling at a high strain rate.

High temporal resolution observations of the pulsar microstructure at 102 MHz

We report observations of the microstructure of 7 pulsars at 102 MHz with a time resolution of up to 1 μs. We have detected fine pulse structure with a μs time-scale for all seven pulsars. We observe that interstellar scattering does not broaden the μs time-scale pulsar microstructure, and find structure of a time-scale much shorter than the interstellar scatter broadening. In addition to the previously known structure with time-scale τ_μ of tens of μs, we have detected structures with characteristic time-scale of a few μs, nearly equal to the reciprocal of the analysis bandwidth. This suggests that even shorter micropulses may exist.
Micropulses usually cluster in groups, each of duration tens to hundreds of μs, which may be identified as microstructure observed previously with smaller time resolution.
In addition to the previously known quasi-periodicity of hundreds of milliseconds, we reveal a structures with characteristic period of tens of μs. We observe structures with short quasi-periodicity to have a limited bandwidth. The characteristic period P_μ of these structures in PSR B0950+08 does not have a common value for different frequency regions in the same single pulse.
Scattering was revealed as a train of quasi-periodic micropulses with an exponentially damped envelope. The scatter-broadening and decorrelation bandwidth were measured. We report two time-scales of decorrelation bandwidth of pulsar PSR B0950+08 and propose two branches of Δν_d(ν) dependence.
The dispersion measure of PSR B0950+08 as DM= 2.9686 ± 0.0001 pc cm⁻³ has been determined.

Does elite competition inhibit growth and delay maturation in some gymnasts? quite possibly

Today, elite young gymnasts undertake training programs of progressive volume and intensity from an early age. For example, talented young female gymnasts often commence training at age 5 or 6 and train more than 20 to 30 hours per week year-round throughout childhood and adolescence. Despite the "normal" short stature of top-level gymnasts and the obvious health benefits of physical activity during growth, there is concern that elite level or those gymnasts involved in heavy training regimens may be at risk for adverse effects on growth and maturation. This concern has been the source of much debate in the literature and is complicated by the difficulties in distinguishing between the genetic predisposition to short stature and late or delayed maturation, and the effect of environmental factors such as nutrition and exercise that may influence growth and maturation. The effect of gymnastics training on growth and maturation is often reported as averaged data: an approach that does not identify individual growth patterns. Finding no difference between groups is not proof that there is "in fact" no difference. Accepting the null hypothesis without the appropriate critical review of both the methodological and statistical power to detect differences is a flawed endeavor. We believe there is compelling "circumstantial" evidence to build a case that preparation for advanced gymnastics competition may place some children and youth at risk of reduced growth and delayed maturation.

Chronic intermittent hypoxia and incremental cycling exercise independently depress muscle in vitro maximal Na+-K+-ATPase activity in well-trained athletes

Athletes commonly attempt to enhance performance by training in normoxia but sleeping in hypoxia [live high and train low (LHTL)]. However, chronic hypoxia reduces muscle Na⁺-K⁺-ATPase content, whereas fatiguing contractions reduce Na⁺-K⁺-ATPase activity, which each may impair performance. We examined whether LHTL and intense exercise would decrease muscle Na⁺-K⁺-ATPase activity and whether these effects would be additive and sufficient to impair performance or plasma K⁺ regulation. Thirteen subjects were randomly assigned to two fitness-matched groups, LHTL (n = 6) or control (Con, n = 7). LHTL slept at simulated moderate altitude (3,000 m, inspired O₂ fraction = 15.48%) for 23 nights and lived and trained by day under normoxic conditions in Canberra (altitude ~600 m). Con lived, trained, and slept in normoxia. A standardized incremental exercise test was conducted before and after LHTL. A vastus lateralis muscle biopsy was taken at rest and after exercise, before and after LHTL or Con, and analyzed for maximal Na⁺-K⁺-ATPase activity [K⁺-stimulated 3-O-methylfluorescein phosphatase (3-O-MFPase)] and Na⁺-K⁺-ATPase content ([³H]ouabain binding sites). 3-O-MFPase activity was decreased by –2.9 ± 2.6% in LHTL (P < 0.05) and was depressed immediately after exercise (P < 0.05) similarly in Con and LHTL (–13.0 ± 3.2 and –11.8 ± 1.5%, respectively). Plasma K⁺ concentration during exercise was unchanged by LHTL; [3H]ouabain binding was unchanged with LHTL or exercise. Peak oxygen consumption was reduced in LHTL (P < 0.05) but not in Con, whereas exercise work was unchanged in either group. Thus LHTL had a minor effect on, and incremental exercise reduced, Na⁺-K⁺-ATPase activity. However, the small LHTL-induced depression of 3-O-MFPase activity was insufficient to adversely affect either K⁺ regulation or total work performed.

No effect of eccentric training on jumper's knee in volleyball plays. During the competitive season : a randomized clinical trial

Background: The effect of surgery on patellar tendinopathy (jumper's knee) is questionable, and conservative treatment protocols have not been properly documented.

Purpose: The aim of this study was to investigate the effect of a newly developed eccentric training program for patellar tendinopathy in volleyball players during the competitive season.

Study Design: Randomized clinical trial.

Methods: Patients were recruited from male and female elite volleyball teams in Norway, and the diagnosis was based on clinical examination alone. Of 51 players diagnosed with patellar tendinopathy, 29 could be included in the study. The training group (n = 13) performed squats on a 25° decline board as a home exercise program (3 × 15 repetitions twice daily) for a 12-week intervention period during the final half of the competitive season. The eccentric (downward) component was done on the affected leg. The control group (n = 16) trained as usual. The primary outcome was a symptom-based questionnaire developed specifically for patellar tendinopathy (Victorian Institute of Sport Assessment score), and patients were followed up before and after the intervention period, as well as after 6 and 30 weeks. All subjects self-recorded training to document their activity level (eccentric training, volleyball training, matches, other training).

Results: There was no change in Victorian Institute of Sport Assessment score during the intervention period in the training (pre, 71.1 ± 11.3; post, 70.2 ± 15.4) or control group (pre, 76.4 ± 12.1; post, 75.4 ± 16.7), nor was there any change during the follow-up period at 6 weeks or 6 months. The training group completed 8.2 ± 4.6 weekly sessions of eccentric training during the intervention period (59% of the recommended volume), and there was no difference between groups in training or competition load.

Conclusion: There was no effect on knee function from a 12-week program with eccentric training among a group of volleyball players with patellar tendinopathy who continued to train and compete during the treatment period. Whether the training would be effective if the patients did not participate in sports activity is not known.

Beyond the Threshold: Life in the New Russia

Amanda Sprang spent nine months, from September of 1995 to May of 1996, studying at Colby College's program in St. Petersburg, Russia. Through contacts made during previous trips to Russia in middle and high school, Amanda was able to quickly rekindle her old friendships and make new ones with many young Russians from different backgrounds. The following work is a collection of twelve essays about life in the New Russia. The essays are framed by a foreword and an epilogue that help place the entire work in a historical context. Although the theme of each essay emerges from a particular incident, within every story Amanda has addressed numerous topics relating to Russian life in today’s changing society. Her first essay, “Art Klinika," takes place in an avant-garde night club in St. Petersburg, and includes a brief yet impressionable, encounter with three young Russian men. “The Birthday Party” recalls a wild evening at the home of her close friend, showing how the Russians greet special occasions. Both the third and fourth essays take place in Moscow, where Amanda returns to visit old friends. These two essays portray the lives of the new economic elite in comparison with the average citizen, as well as show how young Russians face the new challenges that greet them. "Politics Russian Style" recalls a political rally in St. Petersburg, and attempts to shed light on the wacky political world of an infant democracy. Chapters Six through Ten take place away from the western cities of St. Petersburg and Moscow, as Amanda brings us to the cold, mysterious land of Siberia in the dead of winter. She recounts her five day train ride with a retired, high-powered, Communist party official, her experiences in the provincial city of Irkutsk, and a brief trip to a Buddhist monastery and, later, an excursion to Lake Baikal. Back in St. Petersburg, Chapter Eleven gives a humorous account of a ski trip with several Russian friends. Amanda finishes her work with her final chapter, “The Dacha," which describes a weekend spent at a Russian country home with her friend's family.

Unhealthy landscapes: policy recommendations on land use change and infectious disease emergence

Anthropogenic land use changes drive a range of infectious disease outbreaks and emergence events and modify the transmission of endemic infections. These drivers include agricultural encroachment, deforestation, road construction, dam building, irrigation, wetland modification, mining, the concentration or expansion of urban environments, coastal zone degradation, and other activities. These changes in turn cause a cascade of factors that exacerbate infectious disease emergence, such as forest fragmentation, disease introduction, pollution, poverty, and human migration. The Working Group on Land Use Change and Disease Emergence grew out of a special colloquium that convened international experts in infectious diseases, ecology, and environmental health to assess the current state of knowledge and to develop recommendations for addressing these environmental health challenges. The group established a systems model approach and priority lists of infectious diseases affected by ecologic degradation. Policy-relevant levels of the model include specific health risk factors, landscape or habitat change, and institutional (economic and behavioral) levels. The group recommended creating Centers of Excellence in Ecology and Health Research and Training, based at regional universities and/or research institutes with close links to the surrounding communities. The centers' objectives would be 3-fold: a) to provide information to local communities about the links between environmental change and public health ; b) to facilitate fully interdisciplinary research from a variety of natural, social, and health sciences and train professionals who can conduct interdisciplinary research ; and c) to engage in science-based communication and assessment for policy making toward sustainable health and ecosystems.

Machine learning and small robot navigation

Developing successful navigation and mapping strategies is an essential part of autonomous robot research. However, hardware limitations often make for inaccurate systems. This project serves to investigate efficient alternatives to mapping an environment, by first creating a mobile robot, and then applying machine learning to the robot and controlling systems to increase the robustness of the robot system. My mapping system consists of a semi-autonomous robot drone in communication with a stationary Linux computer system. There are learning systems running on both the robot and the more powerful Linux system. The first stage of this project was devoted to designing and building an inexpensive robot. Utilizing my prior experience from independent studies in robotics, I designed a small mobile robot that was well suited for simple navigation and mapping research. When the major components of the robot base were designed, I began to implement my design. This involved physically constructing the base of the robot, as well as researching and acquiring components such as sensors. Implementing the more complex sensors became a time-consuming task, involving much research and assistance from a variety of sources. A concurrent stage of the project involved researching and experimenting with different types of machine learning systems. I finally settled on using neural networks as the machine learning system to incorporate into my project. Neural nets can be thought of as a structure of interconnected nodes, through which information filters. The type of neural net that I chose to use is a type that requires a known set of data that serves to train the net to produce the desired output. Neural nets are particularly well suited for use with robotic systems as they can handle cases that lie at the extreme edges of the training set, such as may be produced by "noisy" sensor data. Through experimenting with available neural net code, I became familiar with the code and its function, and modified it to be more generic and reusable for multiple applications of neural nets.

Traffic safety education and health promoting school : a metropolitan and rural pilot study

Traffic Safety Education (TSE) is an important part of a school's program; however, it competes with many other components of schooling such as literacy, numeracy and a number of health areas. Hence TSE provision in Victorian schools has been somewhat fragmented and haphazard in its delivery. This small pilot study involved two metropolitan and two rural schools which attempted to link TSE into mainstream school activities through the new Victorian Essential Learning Standards (VELS) utilising the internationally accepted Health Promoting Schools (HPS) framework.
The findings of the pilot study showed that though schools face many demands, understanding and ownership of TSE is possible when administrative support, professional development and adequate planning time are made available. The report outlines several key recommendations to improve the delivery of Traffic Safety Education in Victorian schools.