Search

As the number of artificial intelligence (AI) applications increases rapidly and more people will be affected by AI’s decisions, there are real needs for novel AI systems that can deliver both accuracy and explanations. To address these needs, this paper proposes a new approach called eXplainable Mapping Analytical Process (XMAP). Different from existing works in explainable AI, XMAP is highly modularised and the interpretability for each step can be easily obtained and visualised. A number of core algorithms are developed in XMAP to capture the distributions and topological structures of data, define contexts that emerged from data, and build effective representations for classification tasks. The experiments show that XMAP can provide useful and interpretable insights across analytical steps. For the binary classification task, its predictive performance is very competitive as compared to advanced machine learning algorithms in the literature. In some large datasets, XMAP can even outperform black-box algorithms without losing its interpretability.

Societal Impact Statement Sorghum is an important cereal crop that provides calories and nutrients for much of the world's population, and it is often grown with low fertiliser input. Optimising the yield, nutritive content and bioavailability of sorghum grain with minimal input is of importance for human nutrition, and arbuscular mycorrhizal (AM) fungi have previously shown potential to assist in this. Across sorghum genetic diversity, AM fungi improved the yield, nutrition and zinc and iron bioavailability of grain in a low phosphorus soil. Thus, food production systems that effectively manage AM fungi may improve consumer outcomes. Summary Sorghum is a C4 cereal crop that is an important source of calories and nutrition across the world, predominantly cultivated and consumed in low- and middle-income countries. Sorghum can be highly colonised by arbuscular mycorrhizal (AM) fungi, and the plant-fungal association can lead to improvements in biomass and nutrient uptake. High-throughput phenotyping allows us to non-destructively interrogate the ‘hidden’ effects of AM fungi on sorghum growth and phenology. Eight genetically diverse sorghum genotypes were grown in a soil amended with 2 or 20 mg P kg−1 and inoculated with an AM fungal culture of Rhizophagus irregularis. High-throughput phenotyping uncovered the ‘hidden’ effects of AM fungi on growth and phenology, while grain biomass, nutrition, Zn and Fe bioavailability and root AM colonisation was determined after destructive harvest. Sorghum plants colonised by AM fungi generally performed better than non-AM control plants, with greater yield, harvest indices, and grain P, Zn and Fe contents. During the early growth stages, AM colonisation led to temporary growth depressions. There were also AM fungal and P fertilisation effects on sorghum time-of-flowering. The sorghum genotype with the highest AM colonisation could barely produce grain when non-inoculated. The two genotypes that failed to mature had very low AM colonisation. Generally, the genetically diverse sorghum genotypes were highly responsive to AM colonisation and produced more grain of greater nutritive quality when colonised, without adverse consequences for micronutrient bioavailability.

Are the biological mechanisms that facilitate perception of external photon stimuli using the sense of sight also responsible for the perception of internal hormone stimuli using the instinctive sense of emotion? Different regions of the body influence one another by communicating on the molecular scale with small electrical ions as well as larger chemical macromolecules such as hormones. For example, the detection of a predator causes hormones to be produced throughout the body, leading to a rapid physical response. To model such a system, we divide biological phenomena into two stages: sensing and communication, where each stage uses electrical ions and various molecules as signals. Designing a biomimetic computer system that can perform such a task is currently a challenge due to the large size of biological macromolecules and the small size of digital electronic components that are suited for electrons. We derive a general molecular communication theory to describe the interaction of molecules on different time and space scales with a thermodynamic model of hormone equilibration based on the Minimization of Helmholtz Free Energy (MFE). Our work paves the way for future cutting-edge AI systems to utilize heterogenous units of information and as a result, more accurately resembles the style of computation performed by biological systems.

Societal Impact Statement Micronutrients such as zinc and iron are critical for human health. For the world's population that relies on cereal products to obtain micronutrients, the bioavailability (absorption of nutrients in the gut) can be hindered by an anti‐nutritional compound, phytate. Phytate accumulation in grain is affected by soil properties including phosphorus availability and arbuscular mycorrhizal (AM) fungi. Here, we investigated the effects of AM fungi and soil phosphorus fertilization on micronutrient bioavailability in durum wheat and found that fertilization greatly decreased the bioavailability of micronutrients, but AM fungi can take up more micronutrients, which can lead to improved bioavailability when the soil is not fertilized. Summary The bioavailability of micronutrients (zinc [Zn] and iron [Fe]) in cereal crops such as durum wheat is critically important for human nutrition. Bioavailability is a product of complex interactions between plant phosphorus (P) uptake and storage in grain (as phytate), and plant micronutrient uptake. The bioavailability of Zn and Fe in cereal grain is affected by soil nutrient concentrations and associations with arbuscular mycorrhizal (AM) fungi, but has been scarcely studied. A geographically diverse collection of 101 durum wheat genotypes was surveyed for grain bioavailability of Zn and Fe. Ten genotypes were then selected and grown with and without AM fungal inoculation and soil P fertilization to understand the effects of manipulating soil P availability and uptake on micronutrient bioavailability. The strongest negative effect on grain micronutrient bioavailability was soil P fertilization, however, it also led to increased grain weight. Crop variety selection had the greatest variation in the P‐fertilized soil, but AM fungal inoculation had a positive effect on bioavailability in one variety in the non‐fertilized soil. In order to grow more nutritious durum wheat crops, variety selection and AM fungal inoculation are important considerations. In general, there is a trade‐off between grain weight (yield) and micronutrient bioavailability in grain that could be addressed through breeding P‐deficiency tolerant varieties.

Societal Impact Statement Arbuscular mycorrhizal fungi (AMF) may contribute to enhanced yield and nutrition of host plants for the purpose of sustainable agriculture. However, the growth response of the host plant to mycorrhizal colonization is generally only measured at harvest, and thus management decisions regarding AMF are made using only a single time point. This study highlights that AMF can provide growth benefits to the host plant over its life. Greater knowledge of how plants respond to AMF over time will improve understanding of how the association functions and ultimately lead to improved management decisions regarding AMF in an agricultural context. Summary Colonization by arbuscular mycorrhizal fungi (AMF) can result in variable responses in the growth and mineral nutrition of host plants, and is highly dependent on soil nutrient condition; limited studies have addressed the effects of AMF on plant growth over time. The aim of this study was to investigate the AMF effects on plant growth over the life of the plant, and interactions with soil phosphorus (P) and zinc (Zn) availability. We used a high‐throughput shoot phenotyping system to examine the temporal growth responses to AMF and soil P and Zn availabilities in the pasture legume Medicago truncatula. Plants were either inoculated with Rhizophagus irregularis or mock‐inoculated, and were examined under two soil P and five soil Zn availability treatments. Plants were then destructively harvested to obtain final biomass and shoot nutrition data. The growth of M. truncatula plants over time responded very differently to AMF depending on the soil P availability. At low P, projected shoot area and absolute growth rate (AGR) became increasingly greater in the mycorrhizal plants over the course of the experiment. At high P, there was a positive growth response to AMF until approximately 40 days after planting, after which the AGR of the non‐mycorrhizal plants increased and the response to AMF became neutral. Zinc availability was highly interactive with P availability, but not with AMF inoculation. This research demonstrates that growth responses to mycorrhizal fungi change over the plant's life, and are highly dependent on soil P availability.

There is a growing recognition of the role of arbuscular mycorrhizal fungi (AMF) in food security, specifically the potential for AMF to enhance the yield and mineral nutrition-including phosphorus, zinc (Zn), and iron (Fe)-of food crops. However, the bioavailability of Zn and Fe for humans in the grain of cereal crops can be overestimated by failing to consider the abundance of phytic acid (PA). This is because PA can chelate the micronutrients, making them difficult to absorb. In order to understand the effect of an AM fungus and soil Zn concentration on the productivity and nutritional quality of food parts, this study examined the growth and nutritional responses of durum wheat, with and without inoculation with Rhizophagus irregularis, at five soil Zn concentrations. Growth and nutrient responses of the plants to soil Zn amendment was stronger than responses to AMF. However, the protective effect of AMF under soil Zn toxicity conditions was observed as reduced Zn concentration in the mycorrhizal durum wheat grain at Zn50. Here, AMF inoculation increased the concentration of PA in durum wheat grain but had no effect on the concentration of Zn and Fe; this consequently reduced the predicted bioavailability of grain Zn and Fe, which could lead to a decrease in nutritional quality of the grain. This research suggests that in soil with low (available) phosphorus and Zn concentrations, AMF may reduce the food quality of durum wheat because of an increase in PA concentration, and thus, a decrease in the bioavailability of Zn and Fe.

© 1997-2012 IEEE. With a global search mechanism, particle swarm optimization (PSO) has shown promise in feature selection (FS). However, most of the current PSO-based FS methods use a fix-length representation, which is inflexible and limits the performance of PSO for FS. When applying these methods to high-dimensional data, it not only consumes a significant amount of memory but also requires a high computational cost. Overcoming this limitation enables PSO to work on data with much higher dimensionality which has become more and more popular with the advance of data collection technologies. In this paper, we propose the first variable-length PSO representation for FS, enabling particles to have different and shorter lengths, which defines smaller search space and therefore, improves the performance of PSO. By rearranging features in a descending order of their relevance, we facilitate particles with shorter lengths to achieve better classification performance. Furthermore, using the proposed length changing mechanism, PSO can jump out of local optima, further narrow the search space and focus its search on smaller and more fruitful area. These strategies enable PSO to reach better solutions in a shorter time. Results on ten high-dimensional datasets with varying difficulties show that the proposed variable-length PSO can achieve much smaller feature subsets with significantly higher classification performance in much shorter time than the fixed-length PSO methods. The proposed method also outperformed the compared non-PSO FS methods in most cases. © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

© 2019 The Royal Society of New Zealand. Artificial intelligence (AI) emphasises the creation of intelligent machines/systems that function like humans. AI has been applied to many real-world applications. Machine learning is a branch of AI based on the idea that systems can learn from data, identify hidden patterns, and make decisions with little/minimal human intervention. Evolutionary computation is an umbrella of population-based intelligent/learning algorithms inspired by nature, where New Zealand has a good international reputation. This paper provides a review on evolutionary machine learning, i.e. evolutionary computation techniques for major machine learning tasks such as classification, regression and clustering, and emerging topics including combinatorial optimisation, computer vision, deep learning, transfer learning, and ensemble learning. The paper also provides a brief review of evolutionary learning applications, such as supply chain and manufacturing for milk/dairy, wine and seafood industries, which are important to New Zealand. Finally, the paper presents current issues with future perspectives in evolutionary machine learning.This is an Accepted Manuscript of an article published by Taylor & Francis in 'Journal of the Royal Society of New Zealand' on 2019-04-03, available online: https://www.tandfonline.com/10.1080/03036758.2019.1609052.

Recent research has shown that Particle Swarm Optimisation is a promising approach to feature selection. However, applying it on high-dimensional data with thousands to tens of thousands of features is still challenging because of the large search space. While filter approaches are time efficient and scalable for high-dimensional data, they usually obtain lower classification accuracy than wrapper approaches. On the other hand, wrapper methods require a longer running time than filter methods due to the learning algorithm involved in fitness evaluation. This paper proposes a new strategy of combining filter and wrapper approaches in a single evolutionary process in order to achieve smaller feature subsets with better classification performance in a shorter time. A new local search heuristic using symmetric uncertainty is proposed to refine the solutions found by PSO and a new hybrid fitness function is used to better evaluate candidate solutions. The proposed method is examined and compared with three recent PSO based methods on eight high-dimensional problems of varying difficulty. The results show that the new hybrid PSO is more effective and efficient than the other methods.© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Fall events in elderly populations often result in serious injury and may lead to long-term disability and/or death. While many fall detection systems have been developed using wearable sensors to distinguish falls from other daily activities, detection sensitivity and specificity decreases when exposed to more rigorous activities such as running and jumping. This research uses time-frequency analysis of accelerometer-only activity data to develop a strategy for improving fall detection accuracy. In this study, a wireless sensor system (WSS) consisting of a three-axis accelerometer, microprocessor and wireless communications module is used to collect daily activities performed following a script in the laboratory setting. Experiments were conducted on 36 healthy human subjects performing four types of falls (i.e., forward, backward, and left/right sideway falls) as well as normal movements such as standing, walking, stand-to-sit, sit-to-stand, stepping, running and jumping. In total, 1227 different activities were collected and analyzed. The developed algorithm computes the magnitude of three-axis accelerometer data to detect if a critical fall threshold is passed, then analyzes the power spectral density within a critical fall duration window (500 ms) to differentiate fall events from other rigorous activities. Fall events were observed with high energy in the 2&ndash, 3.5 Hz range and distinct from other rigorous activities such as running (3.5&ndash, 5.5 Hz) and jumping (1&ndash, 2 Hz). Preliminary results indicate the power spectral density (PSD)-based algorithm can detect falls with high sensitivity (98.4%) and specificity (98.6%) using lab-based daily activity data. The proposed algorithm has the benefit of improved accuracy over existing time-domain only strategies and multisensor strategies.

This paper aims to produce classifiers that are not only accurate but also interpretable to decision makers. The classifiers are represented in the form of risk scores, i.e. simple linear classifiers where coefficient vectors are sparse and bounded integer vectors which are then optimised by a novel and scalable discrete particle swarm optimisation algorithm. In contrast to past studies which usually use particle swarm optimisation as a pre-processing step, the proposed algorithm incorporates particle swarm optimisation into the classification process. A penalty-based fitness function and a local search heuristic based on symmetric uncertainty are developed to efficiently identify classifiers with high classification performance and a preferred model size or complexity. Experiments with 10 benchmark datasets show that the proposed swarm-based algorithm is a strong candidate to develop effective linear classifiers. Comparisons with other interpretable machine learning algorithms that produce rule-based and tree-based classifiers also demonstrate the competitiveness of the proposed algorithm. Further analyses also confirm the interpretability of the produced classifiers. Finally, the proposed algorithm shows excellent speed-up via parallelisation, which gives it a great advantage when coping with large scale problems.

Growing big data has posed a great challenge for machine learning algorithms. To cope with big data, the algorithm has to be both efficient and accurate. Although evolutionary computation has been successfully applied to many complex machine learning tasks, its ability to handle big data is limited. In this paper, we proposed a dynamic self-organising swarm algorithm to learn an effective set of prototypes for big high-dimensional datasets in an unsupervised manner. The novelties of this new algorithm are the energy-based fitness function, the adaptive topological neighbourhood, the growing/shrinking capability, and the efficient learning scheme. Experiments with well-known datasets show that the proposed algorithm can maintain a very compact set of prototypes and achieve competitive predictive performance as compared to other algorithms in the literature. The analyses also show that prototypes generated by the proposed algorithms have a stronger separatability compared to those from other prototype generation algorithms.

Feature space is an important factor influencing the performance of any machine learning algorithm including classification methods. Feature selection aims to remove irrelevant and redundant features that may negatively affect the learning process especially on high-dimensional data, which usually suffers from the curse of dimensionality. Feature ranking is one of the most scalable feature selection approaches to high-dimensional problems, but most of them fail to automatically determine the number of selected features as well as detect redundancy between features. Particle swarm optimisation (PSO) is a population-based algorithm which has shown to be effective in addressing these limitations. However, its performance on high-dimensional data is still limited due to the large search space and high computation cost. This study proposes the first adaptive multi-swarm optimisation (AMSO) method for feature selection that can automatically select a feature subset of high-dimensional data more effectively and efficiently than the compared methods. The subswarms are automatically and dynamically changed based on their performance during the evolutionary process. Experiments on ten high-dimensional datasets of varying difficulties have shown that AMSO is more effective and more efficient than the compared PSO-based and traditional feature selection methods in most cases.

Falls are a major global health problem that may result in long-term health issues, disabilities, and even death (~650,000 fatalities each year). Each year approximately 37.3 million elderly worldwide experience a fall event that is severe enough to require medical attention. This research proposes a system for activity assessment and fall detection intended for in-home applications using the Internet of Things (IoT) for real-time detection of falls events and potentially fall prevention using a low-cost, wearable sensor system. While the proposed system uses an integrated MEMS sensor (i.e. accelerometer, gyroscope) for biomechanical monitoring and event detection, the developed algorithms can also be deployed onto other smart devices. The system communicates periodically with a cloud server system for uploading, archiving, and analyzing sensor data. Data is transferred to the cloud. Once data is received, the cloud server can provide alerts (i.e. automated calls, SMS, EMAIL) to formal and informal caregivers as well as emergency services when falls or other emergencies occur. Additionally, individuals and their caregivers can access and review personalized activity information to assess health, wellness and independence. Preliminary tests using healthy subjects performing Activity Daily Living (ADL) is quite promising, with specificity to detect fall of 100% in about 200 h normal activities in real-world setting. This research will also present practical challenges to deployment of the proposed system in real-world settings including usability, performance, and feedback from end-users.

BackgroundMindfulness training shows promise for improving smoking cessation and lapse recovery, and between-session mobile health messages could enhance treatment engagement and effectiveness. Personalized, in-the-moment text messaging support could be particularly useful for low-income smokers with fewer smoking cessation resources. ObjectiveThis pilot study examined the feasibility of a text messaging program (iQuit Mindfully) as an adjunct to in-person Mindfulness-Based Addiction Treatment (MBAT) for smoking cessation. MethodsA total of 71 participants were randomly assigned to MBAT (n=33) or iQuit Mindfully (n=38; MBAT + between-session text messages); of these, 70% (50/71) were African American, and 61% (43/71) had an annual household income of US $30,000 or less. All participants received 8 weekly therapist-led group counseling sessions, nicotine patches, and self-help materials. Outcomes were feasibility (attrition, engagement, and participants’ ratings), participants’ feedback regarding the text messaging intervention, and smoking cessation (assessed in person). ResultsStrong retention was achieved (76% [54/71] at the end of treatment, and 89% [63/71] at 1-month follow-up). In the iQuit Mindfully group, engagement was high (88% [29/33] indicated reading all or most texts, and 89% [34/38] engaged in interactive texting), and participants provided positive ratings (on a 1-10 scale, average rating for recommending the program to others was 8.4 [SD 2.5]). Participants indicated benefiting from the texts (eg, appreciating encouraging reminders, coping strategies, and social support) and suggested improvements (eg, more personalization). Overall, biochemically confirmed smoking cessation rates were 22% (12/55) at the end of treatment and 19% (12/62) at 1-month follow-up, with no differences between conditions. Living below the poverty level predicted worse cessation outcomes at 1-month follow-up among participants receiving in-person only treatment (P=.03) but not among those receiving iQuit Mindfully. ConclusionsText messaging appears to be a feasible and acceptable modality for supporting mindfulness-based smoking cessation treatment. The availability of 24/7 text messaging might be particularly helpful for low-income smokers who have access to fewer cessation resources and experience significant day-to-day barriers to quitting. Trial RegistrationClinicalTrials.gov NCT03029819; https://clinicaltrials.gov/ct2/show/NCT03029819

A morphological and molecular phylogenetic study of proteocephalid tapeworms of the genus Acanthotaenia von Linstow, 1903, parasites of monitors (Varanidae), was carried out. The type species, A. shipleyi von Linstow, 1903, which was originally described based on an immature specimen from Sri Lanka, is redescribed based on new material from the type host, Varanus salvator, in Sri Lanka, Malaysia, and Vietnam, and its neotype is designated. In addition, Acanthotaenia susanae n. sp. is described from Varanus nebulosus in Vietnam. The new species differs from congeners by the large size of the scolex, width of the rostellum and the number of testes. New molecular data (sequences of lsrDNA and cox1) revealed Acanthotaenia paraphyletic with the inclusion of Australotaenia bunthangi de Chambrier & Scholz, 2012, a parasite of Enhydris enhydris (Ophidia: Homalopsidae) in Cambodia. Molecular data confirm a wide distribution of A. shipleyi (isolates from Malaysia and Vietnam were almost identical) and indicate a strict host specificity (oioxeny) of individual species of the genus. Type specimens of four species made it possible to supplement their morphological descriptions. A survey of all species of Acanthotaenia recognised as valid is presented and the following taxonomic changes are proposed: Acanthotaenia pythonis Wahid, 1968 described from the green python, Morelia viridis, in a zoo, is transferred to Kapsulotaenia as Kapsulotaenia pythonis (Wahid, 1968) n. comb., because it possesses intrauterine eggs grouped in capsules. Acanthotaenia gracilis (Beddard, 1913) from Varanus varius in Australia is considered to be species inquirenda because its original descriptions did not contain sufficient data for adequate circumscription and differentiation from congeners and type material was not available. Generic diagnosis of Acanthotaenia is amended and a key to its seven species is provided.

BACKGROUND Mindfulness training shows promise for improving smoking cessation and lapse recovery, and between-session mobile health messages could enhance treatment engagement and effectiveness. Personalized, in-the-moment text messaging support could be particularly useful for low-income smokers with fewer smoking cessation resources. OBJECTIVE This pilot study examined the feasibility of a text messaging program (iQuit Mindfully) as an adjunct to in-person Mindfulness-Based Addiction Treatment (MBAT) for smoking cessation. METHODS A total of 71 participants were randomly assigned to MBAT (n=33) or iQuit Mindfully (n=38; MBAT + between-session text messages); of these, 70% (50/71) were African American, and 61% (43/71) had an annual household income of US $30,000 or less. All participants received 8 weekly therapist-led group counseling sessions, nicotine patches, and self-help materials. Outcomes were feasibility (attrition, engagement, and participants’ ratings), participants’ feedback regarding the text messaging intervention, and smoking cessation (assessed in person). RESULTS Strong retention was achieved (76% [54/71] at the end of treatment, and 89% [63/71] at 1-month follow-up). In the iQuit Mindfully group, engagement was high (88% [29/33] indicated reading all or most texts, and 89% [34/38] engaged in interactive texting), and participants provided positive ratings (on a 1-10 scale, average rating for recommending the program to others was 8.4 [SD 2.5]). Participants indicated benefiting from the texts (eg, appreciating encouraging reminders, coping strategies, and social support) and suggested improvements (eg, more personalization). Overall, biochemically confirmed smoking cessation rates were 22% (12/55) at the end of treatment and 19% (12/62) at 1-month follow-up, with no differences between conditions. Living below the poverty level predicted worse cessation outcomes at 1-month follow-up among participants receiving in-person only treatment (P=.03) but not among those receiving iQuit Mindfully. CONCLUSIONS Text messaging appears to be a feasible and acceptable modality for supporting mindfulness-based smoking cessation treatment. The availability of 24/7 text messaging might be particularly helpful for low-income smokers who have access to fewer cessation resources and experience significant day-to-day barriers to quitting. CLINICALTRIAL ClinicalTrials.gov NCT03029819; https://clinicaltrials.gov/ct2/show/NCT03029819

Feature selection is an essential step in classification tasks with a large number of features, such as in gene expression data. Recent research has shown that particle swarm optimisation PSO is a promising approach to feature selection. However, it also has potential limitation to get stuck into local optima, especially for gene selection problems with a huge search space. Therefore, we developed a PSO algorithm PSO-LSRG with a fast “local search” combined with a gbest resetting mechanism as a way to improve the performance of PSO for feature selection. Furthermore, since many existing PSO-based feature selection approaches on the gene expression data have feature selection bias, i.e. no unseen test data is used, 2 sets of experiments on 10 gene expression datasets were designed: with and without feature selection bias. As compared to standard PSO, PSO with gbest resetting only, and PSO with local search only, PSO-LSRG obtained a substantial dimensionality reduction and a significant improvement on the classification performance in both sets of experiments. PSO-LSRG outperforms the other three algorithms when feature selection bias exists. When there is no feature selection bias, PSO-LSRG selects the smallest number of features in all cases, but the classification performance is slightly worse in a few cases, which may be caused by the overfitting problem. This shows that feature selection bias should be avoided when designing a feature selection algorithm to ensure its generalisation ability on unseen data.

Strongyluris calotis is a heterakid nematode in the large intestine of agamid lizards (Reptilia: Sauria: Agamidae) from the Oriental Region. The standard light microscopic definition of the species counts the "caudal papillae" as 10 pairs on male worms. However, previous work from our group using scanning electron microscopy (SEM) on the heterakid from agamid lizards in Japan, Taiwan, and Singapore revealed that this counting contained a pair of phasmids and that two pairs of postcloacal papillae were completely fused to form a pair of united papillae, thus resulting in "10 pairs." In the present study, we examined S. calotis specimens from the Emma Gray's forest lizard, Calotes emma (Agamidae), living in the plain forest at low altitude, and the Vietnam false bloodsucker, Pseudocalotes brevipes (Agamidae), living in the mountainous forest at high altitude in the northern part of Vietnam. Using SEM, the arrangement of caudal papillae in male worms from an Emma Gray's forest lizard was found to be comparable to classical S. calotis specimens from agamid lizards collected in Japan, Taiwan, and Singapore. However, male worms from Vietnam false bloodsuckers did not have a pair of united papillae but had 10 pairs of independent caudal papillae with a pair of phasmids. Molecular genetic analyses of the ribosomal RNA gene (rDNA) of worms of the classical S. calotis morphotype from Japan and Singapore and two S. calotis morphotypes from Vietnam demonstrated absolutely identical nucleotide sequences of partial 18S rDNA (at least 1764 base pairs (bp)) and 5.8S rDNA (158 bp). However, intraspecific differences were detected in other regions of the rDNA, related to the geographical distribution of hosts regardless of morphotype: 97.8-98.5 % identity (443-446 bp/453 bp) in the internal transcribed spacer (ITS)-1 region, 96.6-98.0 % identity (425-431 bp/440 bp) in the ITS-2 region, and 99.6-99.7 % identity (1149-1151 bp/1154 bp) in the 28S rDNA. Thus, in the future, taxonomic relationships of S. calotis distributed widely in the Oriental Region as well as other nominal Oriental Strongyluris spp., currently six in number, need to be extensively explored based on molecular genetic analyses in addition to intensive morphological characterization.

Classification on high-dimensional data with thousands to tens of thousands of dimensions is a challenging task due to the high dimensionality and the quality of the feature set. The problem can be addressed by using feature selection to choose only informative features or feature construction to create new high-level features. Genetic programming (GP) using a tree-based representation can be used for both feature construction and implicit feature selection. This work presents a comprehensive study to investigate the use of GP for feature construction and selection on high-dimensional classification problems. Different combinations of the constructed and/or selected features are tested and compared on seven high-dimensional gene expression problems, and different classification algorithms are used to evaluate their performance. The results show that the constructed and/or selected feature sets can significantly reduce the dimensionality and maintain or even increase the classification accuracy in most cases. The cases with overfitting occurred are analysed via the distribution of features. Further analysis is also performed to show why the constructed feature can achieve promising classification performance. This is a post-peer-review, pre-copyedit version of an article published in 'Memetic Computing'. The final authenticated version is available online at: https://doi.org/10.1007/s12293-015-0173-y. The following terms of use apply: https://www.springer.com/gp/open-access/publication-policies/aam-terms-of-use.

The formation of arbuscular mycorrhizas (AM) can result in positive, neutral or negative responses in the growth and mineral nutrition of host plants, particularly that of P, Zn and other micronutrients. This study examined the growth and nutritional responses of 15 agriculturally important plant species, including cereals, legumes and vegetables, with and without inoculation with the AM fungus (AMF) Rhizophagus irregularis. Furthermore, we explored whether the responses differed between different functional groups of plants such as monocots and dicots, C3 and C4 plants, and N-fixing and non-N-fixing plants. We found that that mycorrhizal colonisation of roots, plant growth and plant nutrient responses differed between plant species. Among the species analysed, leek (Allium ampeloprasum L. var. porrum) was the most mycorrhiza-responsive, displaying the highest mycorrhizal colonisation and biomass response, and the greatest increases in most mineral nutrients. In other plant species, the concentration of P, Cu, Zn and S were generally enhanced by inoculation with AMF. Furthermore, ionomes differed more greatly between plant species than in response to inoculation with AMF. This research further improves our understanding of the responses of different and diverse plant species to the formation of AM in terms of growth and ionomics under standardised growth conditions. The results of this study may be used in further studies and to inform agricultural practices.

Falls are dangerous for the elderly, often leading to disability and death. While many systems have been developed using accelerometers to detect falls from other daily activities, sensitivity and specificity of these systems decrease when exposed to more rigorous activities such as running and jumping. In this paper, we propose a fall detection algorithm which uses time-frequency analyses of accelerometer data to monitor and detect fall events from normal daily activities. For this study, a wireless sensor system (WSS) is placed at the center of the chest to collect real-time data from subjects performing various daily activities including falling onto a cushioned mat. Following an IRB approved protocol, experiments were conducted on 18 healthy human subjects performing four types of falls (i.e. forward, backward, and left/right sideway falls) as well as normal movements such as standing, walking, stand-to-sit, sit-to-stand, stepping, running and jumping. In total, 324 different activities were collected including 108 fall events. The developed algorithm computes magnitude of 3-axis accelerometer data to check if a critical fall threshold is passed, then calculates the power spectral density of this data for a critical fall duration window (500 ms). Fall events were observed with high energy between 2 and 3 Hz that are distinct from other rigorous activities such as running (3.5–5.5 Hz) and jumping (1–2 Hz). Preliminary results indicate the PSD-based algorithm can detect falls with high sensitivity and specificity greater than 90%, respectively.

Feature construction is a pre-processing technique to create new features with better discriminating ability from the original features. Genetic programming (GP) has been shown to be a prominent technique for this task. However, applying GP to high-dimensional data is still challenging due to the large search space. Feature clustering groups similar features into clusters, which can be used for dimensionality reduction by choosing representative features from each cluster to form the feature subset. Feature clustering has been shown promising in feature selection; but has not been investigated in feature construction for classification. This paper presents the first work of utilising feature clustering in this area. We propose a cluster-based GP feature construction method called CGPFC which uses feature clustering to improve the performance of GP for feature construction on high-dimensional data. Results on eight high-dimensional datasets with varying difficulties show that the CGPFC constructed features perform better than the original full feature set and features constructed by the standard GP constructor based on the whole feature set.

The notion of cyberspace became impossible to separate from the notions of cyber threat and cyberattack. Since cyberattacks are getting easier to run, they are also becoming more serious threats from the economic damage perspective. Consequently, we are evident of a continuous adversarial relationship between the attackers trying to mount as powerful as possible attacks and defenders trying to stop the attackers in their goals. To defend against such attacks, defenders have at their disposal a plethora of techniques but they are often falling behind the attackers due to the fact that they need to protect the whole system while the attacker needs to find only a single weakness to exploit. In this paper, we consider one type of a cyberattack – network intrusion – and investigate how to use feature construction via genetic programming in order to improve the intrusion detection accuracy. The obtained results show that feature construction offers improvements in a number of tested scenarios and therefore should be considered as an important step in defense efforts. Such improvements are especially apparent in scenario with the highly unbalanced data, which also represents the most interesting case from the defensive perspective.

Genetic Programming (GP) has shown promise in feature construction where high-level features are formed by combining original features using predefined functions or operators. Multiple feature construction methods have been proposed for high-dimensional data with thousands of features. Results of these methods show that several constructed features can maintain or even improve the discriminating ability of the original feature set. However, some particular features may have better ability than other features to distinguish instances of one class from other classes. Therefore, it may be more difficult to construct a better discriminating feature when combing features that are relevant to different classes. In this study, we propose a new GP-based feature construction method called CDFC that constructs multiple features, each of which focuses on distinguishing one class from other classes. We propose a new representation for class-dependent feature construction and a new fitness function to better evaluate the constructed feature set. Results on eight datasets with varying difficulties showed that the features constructed by CDFC can improve the discriminating ability of thousands of original features in most cases. Results also showed that CFDC is more effective and efficient than the hybrid MGPFC method which was shown to have better performance than standard GP to feature construction.

The myxosporean genus Unicapsula (Multivalvulida: Trilosporidae) is defined as having a spore with three unequal shell valves and polar capsules, of which one is prominent and the two other polar capsules are rudimentary. Genetic characterization of members of the genus, currently 11 nominal species, is, at present, unsatisfactory yet when comparing to the closely related genus Kudoa (Multivalvulida: Kudoidae). In the present study, we characterized long ribosomal RNA gene (rDNA) sequences of three Unicapsula spp., namely Unicapsula pyramidata, Unicapsula seriolae, and a novel myxosporean species, Unicapsula setoensis n. sp., from Asian fishes. Elongated plasmodia of U. pyramidata were found in the trunk muscle of Japanese threadfin breams, Nemipterus japonicus, fished off northern Vietnam in the South China Sea. Semitriangular spores, 5.5-6.4 μm in length and 5.6-9.6 μm in width, consisted of three shell valves with two caudal appendages, 7.2-7.4 μm in length. One prominent polar capsule, 2.0-2.4 μm in diameter, was located in the apical shell valve and two rudimentary polar capsules, 0.4-0.5 μm in diameter, in each caudal shell valve. Elongated plasmodia of U. seriolae were found in the trunk muscle of a greater yellowtail, Seriola dumerili, aquacultured in Japan. Semispherical spores, 5.9-7.4 μm in length and 6.3-7.4 μm in width, also consisted of three shell valves and one prominent polar capsule, 3.4-3.8 μm in diameter, with two rudimentary polar capsules, 0.7-1.0 μm in diameter. Plasmodia of U. setoensis n. sp. were found in the trunk muscle of yellowfin gobies, Acanthogobius flavimanus, fished off Hofu, Yamaguchi Prefecture, in the Inland Sea of Japan. Semispherical spores, 5.6-6.9 μm in diameter, displayed three shell valves and one prominent and two rudimentary polar capsules. The former functional polar capsule was 1.9-2.5 μm in diameter and extruded a 9.4-13.8-μm-long polar filament. Nearly the whole length of the 18S rDNA and more than 2,200 bp of the 28S rDNA of the three Unicapsula spp. were sequenced along with nucleotide sequences of the 5.8S rDNA and internal transcribed spacer-1 and spacer-2 of U. pyramidata and U. setoensis n. sp. Molecular genetic analyses supported the morphological species differentiation of U. pyramidata and U. seriolae, and the distinctness of U. setoensis n. sp. from hitherto known species.

Feature construction and feature selection are common pre-processing techniques to obtain smaller but better discriminating feature sets than the original ones. These two techniques are essential in high-dimensional data with thousands or tens of thousands of features where there may exist many irrelevant and redundant features. Genetic programming (GP) is a powerful technique that has shown promising results in feature construction and feature selection. However, constructing multiple features for high-dimensional data is still challenging due to its large search space. In this paper, we propose a GP-based method that simultaneously performs multiple feature construction and feature selection to automatically transform high-dimensional datasets into much smaller ones. Experiment results on six datasets show that the size of the generated feature set is less than 4% of the original feature set size and it significantly improves the performance of K-Nearest Neighbour, Naive Bayes and Decision Tree algorithms on 15 out of 18 comparisons. Compared with the single feature construction method using GP, the proposed method has better performance on half cases and similar on the other half. Comparisons between the constructed features, the selected features and the combination of both constructed and selected features by the propose method reveal different preferences of the three learning algorithms on these feature sets.

Feature selection and discretisation have shown their effectiveness for data preprocessing especially for high-dimensional data with many irrelevant features. While feature selection selects only relevant features, feature discretisation finds a discrete representation of data that contains enough information but ignoring some minor fluctuation. These techniques are usually applied in two stages, discretisation and then selection since many feature selection methods work only on discrete features. Most commonly used discretisation methods are univariate in which each feature is discretised independently; therefore, the feature selection stage may not work efficiently since information showing feature interaction is not considered in the discretisation process. In this study, we propose a new method called PSO-DFS using bare-bone particle swarm optimisation (BBPSO) for discretisation and feature selection in a single stage. The results on ten high-dimensional datasets show that PSO-DFS obtains a substantial dimensionality reduction for all datasets. The classification performance is significantly improved or at least maintained on nine out of ten datasets by using the transformed “small” data obtained from PSO-DFS. Compared to applying the two-stage approach which uses PSO for feature selection on the discretised data, PSO-DFS achieves better performance on six datasets, and similar performance on three datasets with a much smaller number of features selected.

Boltzmann headstone S = k B Log W turns out to be the Rosette stone for Greek physics translation optical display of the microwave sensing hieroglyphics. The LHS is the molecular entropy S measuring the degree of uniformity scattering off the sensing cross sections. The RHS is the inverse relationship (equation) predicting the Planck radiation spectral distribution parameterized by the Kelvin temperature T. Use is made of the conservation energy law of the heat capacity of Reservoir (RV) change T Δ S = -ΔE equals to the internal energy change of black box (bb) subsystem. Moreover, an irreversible thermodynamics Δ S > 0 for collision mixing toward totally larger uniformity of heat death, asserted by Boltzmann, that derived the so-called Maxwell-Boltzmann canonical probability. Given the zero boundary condition black box, Planck solved a discrete standing wave eigenstates (equation). Together with the canonical partition function (equation) an average ensemble average of all possible internal energy yielded the celebrated Planck radiation spectral (equation) where the density of states (equation). In summary, given the multispectral sensing data (equation), we applied Lagrange Constraint Neural Network (LCNN) to solve the Blind Sources Separation (BSS) for a set of equivalent bb target temperatures. From the measurements of specific value, slopes and shapes we can fit a set of Kelvin temperatures T’s for each bb targets. As a result, we could apply the analytical continuation for each entropy sources along the temperature-unique Planck spectral curves always toward the RGB color temperature display for any sensing probing frequency.

In this paper, we discuss a framework for bridging the gap between security and medical Large Data Analysis (LDA) with functional- biomarkers. Unsupervised Learning for individual e-IQ & IQ relying on memory eliciting (i.e. scent, grandmother images) and IQ baseline profiles could further enhance the ability to uniquely identify and properly diagnose individuals. Sub-threshold changes in a common/probable biomedical biomarker (disorders) means that an individual remains healthy, while a martingale would require further investigation and more measurements taken to determine credibility. Empirical measurements of human actions can discover anomalies hidden in data, which point to biomarkers revealed through stimulus response. We review the approach for forming a single-user baseline having 1-d devices and a scale-invariant representation for N users each (i) having N*d(i) total devices. Such a fractal representation of human-centric data provides self-similar levels information and relationships which are useful for diagnosis and identification causality anywhere from a mental disorder to a DNA match. Biomarkers from biomedical devices offer a robust way to collect data. Biometrics could be envisioned as enhanced and personalized biomedical devices (e.g. typing fist), but used for security. As long as the devices have a shared context origin, useful information can be found by coupling the sensors. In the case of the electroencephalogram (EEG), known patterns have emerged in low frequency Delta Theta Alpha Beta-Gamma (DTAB-G) waves when an individual views a familiar picture in the visual cortex which is shown on EEGs as a sharp peak. Using brainwaves as a functional biomarker for security can lead the industry to create more secure sessions by allowing not only passwords but also visual stimuli and/or keystrokes coupled with EEG to capture and stay informed about real time user e-IQ/IQ data changes. This holistic Computer Science (CS) Knowledge Discovery in Databases, Data Mining (KDD, DM) approach seeks to merge the fields having a shared data origin - biomarkers revealed through stimulus response.

A new cosmocercid nematode species, Cosmocercoides tonkinensis n. sp., is described from the scale-bellied tree lizard (Acanthosaura lepidogaster) in the northern and central parts of Vietnam. The new species is characterized by medium-sized male worms (4.2-5.1 mm in length and 0.34-0.37 mm in width) relative to known members of the genus, with lateral alae, two sharply pointed spicules of equal length (0.22-0.26 mm in length), a gubernaculum (0.113-0.122 mm in length), 16 or 17 pairs of caudal rosettes, and the presence of somatic papillae. Female worms are slightly larger than male worms (5.3-5.5 mm in length and 0.32-0.42 mm in width), with the vulva situated at 3/5 from the anterior end, and elliptical embryonated eggs, 0.064- 0.084 mm long by 0.040-0.048 mm wide. From 19 recorded species of the genus, the morphology of C. tonkinensis n. sp. is closest to C. multipapillata, C. bufonis, and C. pulcher reported from toads and frogs in East Asia. The present new species is differentiated from them by the number of caudal rosettes, tail length relative to body length, presence of somatic papillae and lateral alae, and embryonated eggs. Furthermore, after C. variabilis in North America and C. sauria in Brazil, this new species is only the third species to be recorded from a reptilian host. The 18S ribosomal RNA gene (rDNA) of the new species is almost identical to that of C. dukae infecting land snails and slugs in North America. Between the present new species and C. pulcher from a toad (Bufo japonicus) in Japan, remarkably fewer nucleotide changes were noticed in the 18S to 28S rDNA including the internal transcribed spacer regions. The molecular phylogenetic position of the genus Cosmocercoides is briefly discussed.

Purpose The purpose of this study was to evaluate homecare nurses' knowledge of wound assessment using digital images and case studies. Design A descriptive design was used. Subjects and setting Subjects were a convenience sample of 33 registered nurses from a Washington, DC, metropolitan-based home health agency. Methods Participants were asked to complete a demographic data sheet and a wound assessment checklist, while viewing projected digital images of 10 different wounds. A case study accompanied each image and provided wound assessment data that could not be visualized. Frequencies were calculated to determine the percentage of homecare nurses who were accurate in their assessment. Results The most common error in staging was a lack of recognition of wounds that were not stageable. The majority of the homecare nurses were able to accurately identify wound bed and periwound characteristics; the greatest variability was found in the ratings for wound bed color. Conclusions Despite the difficulty of interpreting digital images of wounds, the study findings support the value of using them to evaluate nurses' knowledge of the visual aspects of wound assessment as a basis for educational programs.

Summary Chloroquine-resistant Plasmodium vivax has not yet occurred in Vietnam. The efficacy of artemisinin forP.vivaxwasnotestablished.Weconductedadouble-blindrandomizedstudyinvolving240inpatientswithP. vivax malaria who received artemisinin (40 mg/kg over 3 days) plus placebo chloroquine (Art) orchloroquine(25 mg/kgover3 days)plusplaceboartemisinin(Chl).Patientswerefollowedupwithweeklyblood smears for 28 days. In each group 113 cases were analysed. All patients recovered rapidly. Themedian (range) parasite clearance time of regimen Art was 24 h (8–72) and of Chl 24 h (8–64; P ¼ 0.3).Parasitesreappearedintwocasesineachgrouponday14,ineightcasesineachgroup(7%)onday16andin 25 (23%) and 18 (16%) cases, respectively, at the end of 4-week follow-up (P ¼ 0.3). The populationparasite clearance curve followed a mono-exponential decline. The parasite reduction ratio per 48 hreproduction cycle was 2.3 · 10 4 for both regimens. We conclude that artemisinin and chloroquine areequallyeffectiveinthetreatmentofP.vivaxinfectionsinVietnam.Reappearanceofparasitesbeforeday16(7%) suggests the emergence of chloroquine resistance. Three days of artemisinin monotherapy does notprevent recrudescence.keywords Plasmodium vivax, artemisinin, chloroquine, Vietnam, drug-resistance, recrudescencecorrespondence P. J. de Vries, Division of Infectious Diseases, Tropical Medicine and AIDS, AcademicMedical Center, F4-217, Meibergdreef 9, 1105 AZ Amsterdam, The Netherlands.Tel: (+)31 (0)20 5664380; Fax: (+)31 (0)20 6972286; E-mail: p.j.devries@amc.uva.nlIntroductionIn South-east Asia morbidity attributable to Plasmodiumvivax prevails while P. falciparum gradually comes undercontrol by applying artemisinin drugs with other controlmeasures such as insecticide-treated bed nets (Phan et al.1999; Nosten et al. 2000). This trend was also observed inBinh Thuan, a mountainous province in the south ofVietnam (unpublished information, Binh Thuan ProvincialMalaria Station).Chloroquineisthefirst-linedrugfortreatmentofP.vivaxin most areas of the world (World Health Organization1997), although artemisinin and derivatives are also used invarious regimens and they appear to be effective (Nguyenet al. 1993). It was not yet known whether chloroquine-resistantP.vivaxisprevalentinVietnam.Artemisinindrugsare very active against P. vivax but the efficacy has not beenfirmly established. Therefore, this study aimed to establishand compare the efficacy of artemisinin and chloroquine inthe treatment of blood stage infections of P. vivax inVietnam. Based on our own experience in pharmacody-namicmodellingofthetimecourseofP.falciparum,a3-dayregimen of artemisinin should be effective. Longer regimenswere considered to conflict with good patient compliance.MethodsPatient selection and treatmentFrom September 1997 to January 2000, subjects aged15 years or older with a microscopically confirmed P. vivax(asexual stage) infection, presenting at eight primary health

Trends in telehealth technologies have promoted a unique collaboration between nursing and biomedical engineering faculty in a training program at the Catholic University of America. The goalof the program is to prepare future nurses and biomedical engineers to collaborate in providing improved health care services for the elderly living at home. Nursing faculty provide graduate biomedical engineering students with information on nursing assessment, clinical foundations, and care of the elderly as a knowledge base to improve their designs of technology for this population. In return, undergraduate nursing students are given the opportunity to obtain a hands-on experience with new and emerging telehealth technologies in home care and to expand their therapeutic communication skills.

Since the Brain Order Disorder (BOD) group reported on a high density Electroencephalogram (EEG) to capture the neuronal information using EEG to wirelessly interface with a Smartphone [1,2], a larger BOD group has been assembled, including the Obama BRAIN program, CUA Brain Computer Interface Lab and the UCSD Swartz Computational Neuroscience Center. We can implement the pair-electrodes correlation functions in order to operate in a real time daily environment, which is of the computation complexity of O(N3) for N=102~3 known as functional f-EEG. The daily monitoring requires two areas of focus. Area #(1) to quantify the neuronal information flow under arbitrary daily stimuli-response sources. Approach to #1: (i) We have asserted that the sources contained in the EEG signals may be discovered by an unsupervised learning neural network called blind sources separation (BSS) of independent entropy components, based on the irreversible Boltzmann cellular thermodynamics(ΔS < 0), where the entropy is a degree of uniformity. What is the entropy? Loosely speaking, sand on the beach is more uniform at a higher entropy value than the rocks composing a mountain – the internal binding energy tells the paleontologists the existence of information. To a politician, landside voting results has only the winning information but more entropy, while a non-uniform voting distribution record has more information. For the human’s effortless brain at constant temperature, we can solve the minimum of Helmholtz free energy (H = E − TS) by computing BSS, and then their pairwise-entropy source correlation function. (i) Although the entropy itself is not the information per se, but the concurrence of the entropy sources is the information flow as a functional-EEG, sketched in this 2nd BOD report. Area #(2) applying EEG bio-feedback will improve collective decision making (TBD). Approach to #2: We introduce a novel performance quality metrics, in terms of the throughput rate of faster (Δt) & more accurate (ΔA) decision making, which applies to individual, as well as team brain dynamics. Following Nobel Laureate Daniel Kahnmen’s novel “Thinking fast and slow”, through the brainwave biofeedback we can first identify an individual’s “anchored cognitive bias sources”. This is done in order to remove the biases by means of individually tailored pre-processing. Then the training effectiveness can be maximized by the collective product Δt * ΔA. For Area #1, we compute a spatiotemporally windowed EEG in vitro average using adaptive time-window sampling. The sampling rate depends on the type of neuronal responses, which is what we seek. The averaged traditional EEG measurements and are further improved by BSS decomposition into finer stimulus-response source mixing matrix [A] having finer & faster spatial grids with rapid temporal updates. Then, the functional EEG is the second order co-variance matrix defined as the electrode-pair fluctuation correlation function C(s~, s~’) of independent thermodynamic source components. (1) We define a 1-D Space filling curve as a spiral curve without origin. This pattern is historically known as the Peano-Hilbert arc length a. By taking the most significant bits of the Cartesian product a≡ O(x * y * z), it represents the arc length in the numerical size with values that map the 3-D neighborhood proximity into a 1-D neighborhood arc length representation. (2) 1-D Fourier coefficients spectrum have no spurious high frequency contents, which typically arise in lexicographical (zig-zag scanning) discontinuity [Hsu & Szu, “Peano-Hilbert curve,” SPIE 2014]. A simple Fourier spectrum histogram fits nicely with the Compressive Sensing CRDT Mathematics. (3) Stationary power spectral density is a reasonable approximation of EEG responses in striate layers in resonance feedback loops capable of producing a 100, 000 neuronal collective Impulse Response Function (IRF). The striate brain layer architecture represents an ensemble

Systems capable of real-time monitoring have several potential health-related applications, particularly for individuals who desire to age in place as well as those living with acute health conditions. An electrical response exists near the scalp from ionic transmission within neurons (brain cells) and may be measured noninvasively by electroencephalography (EEG). Use of EEG for detecting convulsive1, 2 and nonconvulsive3 epilepsy is well developed and documented in the literature with sensitivities between 80 and 90%. Real-time EEG monitoring during sleep may provide valuable information on alterations in sleep patterns, which has been shown to be effective in detecting and predicting anxiety, depression, and early dementia in the elderly.4, 5 Anxiety and depression in turn have been directly correlated to numerous deleterious chronic health conditions such as cardiovascular disease, stroke, sleep disorders, and diabetes. Having a mechanism to detect and predict onset of anxiety and depression would be a powerful out-of-clinic tool. A potential application for at-home EEGmonitoring is assessment of head injuries and post-concussion syndrome. As these conditions affect the alertness of individuals, there is evidence that head injuries affect the alpha wave patterns of the EEG in the range of 8–12Hz.6 While many previous studies have shown the potential for EEG to detect and assess cognitive impairments, most have been conducted under controlled research conditions in the clinic. Extension of these findings to the home requires further investigation as environmental conditions are likely to affect the EEG data collected. Wang and colleagues7 showed the efficacy of an untethered, wireless brain-machine interface system using 20 dry electrodes embedded into a head cap. This wireless ‘functional’ EEG Figure 1. (a) User-friendly smartphone interface to the functional electroencephalography (f-EEG) head mount. (b) 1D Peano-Hilberttype space-filling curve replaces the 3D layout of the electrodes. (c) High-density wired conventional EEG is replaced by a wireless hat. (d) Right-hemisphere brain f-EEG response stimulated by the visual input for a left eye dominator: before (left) and after compressive sensing (middle), as well as the difference errors (right). (e) Singlet electrode-averaged EEG (left) vs. pair-electrode fluctuation f-EEG (right) reflecting the subject’s intention to point a computer screen cursor to the left as opposed to the right: 121 electrodes (1 node to 82 points), 250Hz (averaged over 1/16 second).

Feature selection is a process of selecting a subset of relevant features from a large number of original features to achieve similar or better classification performance and improve the computation efficiency. As an important data pre-processing technique, research into feature selection has been carried out over the past four decades. Determining an optimal feature subset is a complicated problem. Due to the limitations of conventional methods, evolutionary computation EC has been proposed to solve feature selection problems. Particle swarm optimisation PSO is an EC technique which recently has caught much interest from researchers in the field. This paper presents a review of PSO for feature selection in classification. After describing the background of feature selection and PSO, recent work involving PSO for feature selection is reviewed. Current issues and challenges are also presented for future research.

Rudimentarybrain machine interfacehas existed for the gaming industry. Here, we propose a wireless, real-time, and smartphone-based electroencephalogram (EEG) system for homecare applications. The system uses high-density dry electrodes and compressive sensing strategies to overcome conflicting requirements between spatial electrode density, temporal resolution, and spatiotemporal throughput rate.Spatial sparsenessis addressed by close proximity between active electrodes and desired source locations and using an adaptive selection ofNactive among10Npassive electrodes to formm-organized random linear combinations of readouts,m≪N≪10N.Temporal sparsenessis addressed via parallel frame differences in hardware. During the design phase, we took tethered laboratory EEG dataset and applied fuzzy logic to compute (a) spatiotemporal average of larger magnitude EEG data centers in 0.3 second intervals and (b) inside brainwave sources by Independent Component Analysis blind deconvolution without knowing the impulse response function. Our main contributions are the fidelity of quality wireless EEG data compared to original tethered data and the speed of compressive image recovery. We have compared our recovery of ill-posed inverse data against results using Block Sparse Code. Future work includes development of strategies to filter unwanted artifact from high-density EEGs (i.e., facial muscle-related events and wireless environmental electromagnetic interferences).

We applied Compressive Sensing to design an affordable, convenient Brain Machine Interface (BMI) measuring the high spatial density, and real-time process of Electroencephalogram (EEG) brainwaves by a Smartphone. It is useful for therapeutic and mental health monitoring, learning disability biofeedback, handicap interfaces, and war gami ng. Its spec is adequate for a biomedical laboratory, without the cables hanging over the head and tethered to a fixed computer terminal. Our improved the intrinsic signal to noise ratio (SNR) by using the non-uniform placement of the measuring electrodes to create the proximity of measurement to the source effect . We computing a spatiotemporal average the larger magnitude of EEG data centers in 0.3 second taking on tethered laboratory data , using fuzzy logic, and computing the inside brainwave sources, by Independent Component Analysis (ICA) . Consequently, we can overlay them together by non-uniform electrode distribution enhancing the signal noise ratio and therefore the degree of sparseness by threshold. We overcame the conflicting requirements between a high spatial electrode density and precise temporal resolution (beyond Event Related Potential (ERP) P300 brainwave at 0.3 sec), and Smartphone wireless bottleneck of spatiotemporal throughput rate. Our main contribution in this paper is the quality and the speed of iterative compressed image recovery algorithm based on a Block Sparse Code (Baranuick et al , IEEE/IT 2008) . As a result, we achieved real-time wireless dynamic measurement of EEG brainwaves, matching well with traditionally tethered high density EEG.

The objective of this research is to canvas the landscape of existing standards and guidelines relating to electronic personal health records (PHRs). Here, we propose a consensus standard for PHRs consisting of 14 data components, 11 of which should be essential for all PHRs and 3 additional recommended data components, as well as 4 key features. Through a survey of existing commercially PHR vendors, we observe a low level of adoption of existing standards.

Health care spending in the U.S. over the past decade has dramatically increased over the past decade and is expected to rise to 20% of GDP in the United States by the end of the decade. In 2010, the U.S. Congress approved the Health Care Reform Act with a critical component of this legislation being the adoption of health information technologies (i.e. EMRs, EHRs, PHRs, etc.) aimed at transforming the health care system. Consumer-driven health care models are seen as essential to control the escalating costs of health care. The objective of this research is to canvas the landscape of existing standards and guidelines relating to electronic personal health records (PHRs) and to evaluate the level of adoption of these standards and guidelines amongst current vendors. Through this effort, we propose a consensus standard for PHRs consisting of 14 data components, 11 of which should be essential for all PHRs and 3 additional recommended data components. Through a survey of existing PHR vendors, we observe a low level of adoption of existing standards in commercially available PHR products and note a wide variation (36-73%) of inclusion of critical and desired data components. Further, we propose 4 key features and services based upon a review of the existing literature to facilitate consumer adoption and to improve usefulness of PHRs. By proposing a consensus standard for PHR data components and features, we seek to provide clarity to developers and vendors of HIT products to facilitate product development, interoperability, and integration and data exchange with existing EMR/EHR products

Background: This study aims to estimate the age-specific risks of clinical dengue attack (i.e., the risk of symptomatic dengue among the total number of dengue virus (DENV) infections) during primary and secondary infections. Methods: We analyzed two pieces of epidemiological information in Binh Thuan province, southern Vietnam, i.e., age-specific seroprevalence and a community-wide longitudinal study of clinical dengue attack. The latter data set stratified febrile patients with DENV infection by age as well as infection parity. A simple modeling approach was employed to estimate the age-specific risks of clinical dengue attack during primary and secondary infections. Results: Using the seroprevalence data, the force of infection was estimated to be 11.7% (95% confidence intervals (CI): 10.8-12.7) per year. Median age (and the 25-75 percentiles) of dengue fever patients during primary and secondary infections were 12 (9-20) and 20 (14-31) years, respectively. The estimated age-specific risk of clinical dengue increases as a function of age for both primary and secondary infections; the estimated proportion of symptomatic patients among the total number of infected individuals was estimated to be, link_to_subscribed_fulltext