Resolving cryptic species complexes of major tephritid pests

An FAO/IAEA Co-ordinated Research Project (CRP) on “Resolution of Cryptic Species Complexes of Tephritid Pests to Overcome Constraints to SIT Application and International Trade” was conducted from 2010 to 2015. As captured in the CRP title, the objective was to undertake targeted research into the systematics and diagnostics of taxonomically challenging fruit fly groups of economic importance. The scientific output was the accurate alignment of biological species with taxonomic names; which led to the applied outcome of assisting FAO and IAEA Member States in overcoming technical constraints to the application of the Sterile Insect Technique (SIT) against pest fruit flies and the facilitation of international agricultural trade. Close to 50 researchers from over 20 countries participated in the CRP, using coordinated, multidisciplinary research to address, within an integrative taxonomic framework, cryptic species complexes of major tephritid pests. The following progress was made for the four complexes selected and studied: Anastrepha fraterculus complex – Eight morphotypes and their geographic and ecological distributions in Latin America were defined. The morphotypes can be considered as distinct biological species on the basis of differences in karyotype, sexual incompatibility, post-mating isolation, cuticular hydrocarbon, pheromone, and molecular analyses. Discriminative taxonomic tools using linear and geometric morphometrics of both adult and larval morphology were developed for this complex. Bactrocera dorsalis complex – Based on genetic, cytogenetic, pheromonal, morphometric, and behavioural data, which showed no or only minor variation between the Asian/African pest fruit flies Bactrocera dorsalis, B. papayae, B. philippinensis and B. invadens, the latter three species were synonymized with B. dorsalis. Of the five target pest taxa studied, only B. dorsalis and B. carambolae remain as scientifically valid names. Molecular and pheromone markers are now available to distinguish B. dorsalis from B. carambolae. Ceratitis FAR Complex (C. fasciventris, C. anonae, C. rosa) – Morphology, morphometry, genetic, genomic, pheromone, cuticular hydrocarbon, ecology, behaviour, and developmental physiology data provide evidence for the existence of five different entities within this fruit fly complex from the African region. These are currently recognised as Ceratitis anonae, C. fasciventris (F1 and F2), C. rosa and a new species related to C. rosa (R2). The biological limits within C. fasciventris (i.e. F1 and F2) are not fully resolved. Microsatellites markers and morphological identification tools for the adult males of the five different FAR entities were developed based on male leg structures. Zeugodacus cucurbitae (formerly Bactrocera (Zeugodacus) cucurbitae) – Genetic variability was studied among melon fly populations throughout its geographic range in Africa and the Asia/Pacific region and found to be limited. Cross-mating studies indicated no incompatibility or sexual isolation. Host preference and genetic studies showed no evidence for the existence of host races. It was concluded that the melon fly does not represent a cryptic species complex, neither with regard to geographic distribution nor to host range. Nevertheless, the higher taxonomic classification under which this species had been placed, by the time the CRP was started, was found to be paraphyletic; as a result the subgenus Zeugodacus was elevated to genus level.

A flexible hierarchical approach for facial age estimation based on multiple features

Age estimation from facial images is increasingly receiving attention to solve age-based access control, age-adaptive targeted marketing, amongst other applications. Since even humans can be induced in error due to the complex biological processes involved, finding a robust method remains a research challenge today. In this paper, we propose a new framework for the integration of Active Appearance Models (AAM), Local Binary Patterns (LBP), Gabor wavelets (GW) and Local Phase Quantization (LPQ) in order to obtain a highly discriminative feature representation which is able to model shape, appearance, wrinkles and skin spots. In addition, this paper proposes a novel flexible hierarchical age estimation approach consisting of a multi-class Support Vector Machine (SVM) to classify a subject into an age group followed by a Support Vector Regression (SVR) to estimate a specific age. The errors that may happen in the classification step, caused by the hard boundaries between age classes, are compensated in the specific age estimation by a flexible overlapping of the age ranges. The performance of the proposed approach was evaluated on FG-NET Aging and MORPH Album 2 datasets and a mean absolute error (MAE) of 4.50 and 5.86 years was achieved respectively. The robustness of the proposed approach was also evaluated on a merge of both datasets and a MAE of 5.20 years was achieved. Furthermore, we have also compared the age estimation made by humans with the proposed approach and it has shown that the machine outperforms humans. The proposed approach is competitive with current state-of-the-art and it provides an additional robustness to blur, lighting and expression variance brought about by the local phase features.

Class-specific sparse codes for representing activities

In this paper we investigate the effectiveness of class specific sparse codes in the context of discriminative action classification. The bag-of-words representation is widely used in activity recognition to encode features, and although it yields state-of-the art performance with several feature descriptors it still suffers from large quantization errors and reduces the overall performance. Recently proposed sparse representation methods have been shown to effectively represent features as a linear combination of an over complete dictionary by minimizing the reconstruction error. In contrast to most of the sparse representation methods which focus on Sparse-Reconstruction based Classification (SRC), this paper focuses on a discriminative classification using a SVM by constructing class-specific sparse codes for motion and appearance separately. Experimental results demonstrates that separate motion and appearance specific sparse coefficients provide the most effective and discriminative representation for each class compared to a single class-specific sparse coefficients.

Mining topical relevant patterns for multi-document summarization

Multi-document summarization addressing the problem of information overload has been widely utilized in the various real-world applications. Most of existing approaches adopt term-based representation for documents which limit the performance of multi-document summarization systems. In this paper, we proposed a novel pattern-based topic model (PBTMSum) for the task of the multi-document summarization. PBTMSum combining pattern mining techniques with LDA topic modelling could generate discriminative and semantic rich representations for topics and documents so that the most representative and non-redundant sentences can be selected to form a succinct and informative summary. Extensive experiments are conducted on the data of document understanding conference (DUC) 2007. The results prove the effectiveness and efficiency of our proposed approach.

Automated feature engineering for HTTP tunnel detection

Generating discriminative input features is a key requirement for achieving highly accurate classifiers. The process of generating features from raw data is known as feature engineering and it can take significant manual effort. In this paper we propose automated feature engineering to derive a suite of additional features from a given set of basic features with the aim of both improving classifier accuracy through discriminative features, and to assist data scientists through automation. Our implementation is specific to HTTP computer network traffic. To measure the effectiveness of our proposal, we compare the performance of a supervised machine learning classifier built with automated feature engineering versus one using human-guided features. The classifier addresses a problem in computer network security, namely the detection of HTTP tunnels. We use Bro to process network traffic into base features and then apply automated feature engineering to calculate a larger set of derived features. The derived features are calculated without favour to any base feature and include entropy, length and N-grams for all string features, and counts and averages over time for all numeric features. Feature selection is then used to find the most relevant subset of these features. Testing showed that both classifiers achieved a detection rate above 99.93% at a false positive rate below 0.01%. For our datasets, we conclude that automated feature engineering can provide the advantages of increasing classifier development speed and reducing development technical difficulties through the removal of manual feature engineering. These are achieved while also maintaining classification accuracy.