The Feasibility of Two Handheld Spectrometers for Meat Speciation Combined with Chemometric Methods and Its Application for Halal Certification

Handheld visible-near-infrared (Vis-NIR) and near-infrared (NIR) spectroscopy can be cost-effective, rapid, non-destructive and transportable techniques for identifying meat species and may be valuable for enforcement authorities, retail and consumers. In this study, a handheld Vis-NIR (400–1000 nm) and a handheld NIR (900–1700 nm) spectrometer were applied to discriminate halal meat species from pork (halal certification), as well as speciation of intact and ground lamb, beef, chicken and pork (160 meat samples). Several types of class modeling multivariate approaches were applied. The presented one-class classification (OCC) approach, especially with the Vis-NIR sensor (95–100% correct classification rate), was found to be suitable for the application of halal from non-halal meat-species discrimination. In a discriminant approach, using the Vis-NIR data and support vector machine (SVM) classification, the four meat species tested could be classified with accuracies of 93.4% and 94.7% for ground and intact meat, respectively, while with partial least-squares discriminant analysis (PLS-DA), classification accuracies were 87.4% (ground) and 88.6% (intact). Using the NIR sensor, total accuracies of the SVM models were 88.2% and 81.5% for ground and intact meats, respectively, and PLS-DA classification accuracies were 88.3% (ground) and 80% (intact). We conclude that the Vis-NIR sensor was most successful in the halal certification (OCC approaches) and speciation (discriminant approaches) for both intact and ground meat using SVM.

Learning to sense from events via semantic variational autoencoder

In this paper, we introduce the concept of learning to sense, which aims to emulate a complex characteristic of human reasoning: the ability to monitor and understand a set of interdependent events for decision-making processes. Event datasets are composed of textual data and spatio-temporal features that determine where and when a given phenomenon occurred. In learning to sense, related events are mapped closely to each other in a semantic vector space, thereby identifying that they contain similar contextual meaning. However, learning a semantic vector space that satisfies both textual similarities and spatio-temporal constraints is a crucial challenge for event analysis and sensing. This paper investigates a Semantic Variational Autoencoder (SVAE) to fine-tune pre-trained embeddings according to both textual and spatio-temporal events of the class of interest. Experiments involving more than one hundred sensors show that our SVAE outperforms a competitive one-class classification baseline. Moreover, our proposal provides desirable learning requirements to sense scenarios, such as visualization of the sensor decision function and heat maps with the sensor’s geographic impact.

Triple-VAE: A Triple Variational Autoencoder to Represent Events in One-Class Event Detection

Events are phenomena that occur at a specific time and place. Its detection can bring benefits to society since it is possible to extract knowledge from these events. Event detection is a multimodal task since these events have textual, geographical, and temporal components. Most multimodal research in the literature uses the concatenation of the components to represent the events. These approaches use multi-class or binary learning to detect events of interest which intensifies the user's labeling effort, in which the user should label event classes even if there is no interest in detecting them. In this paper, we present the Triple-VAE approach that learns a unified representation from textual, spatial, and density modalities through a variational autoencoder, one of the state-ofthe-art in representation learning. Our proposed Triple-VAE obtains suitable event representations for one-class classification, where users provide labels only for events of interest, thereby reducing the labeling effort. We carried out an experimental evaluation with ten real-world event datasets, four multimodal representation methods, and five evaluation metrics. Triple-VAE outperforms and presents a statistically significant difference considering the other three representation methods in all datasets. Therefore, Triple-VAE proved to be promising to represent the events in the one-class event detection scenario.

NFAD: fixing anomaly detection using normalizing flows

Anomaly detection is a challenging task that frequently arises in practically all areas of industry and science, from fraud detection and data quality monitoring to finding rare cases of diseases and searching for new physics. Most of the conventional approaches to anomaly detection, such as one-class SVM and Robust Auto-Encoder, are one-class classification methods, i.e., focus on separating normal data from the rest of the space. Such methods are based on the assumption of separability of normal and anomalous classes, and subsequently do not take into account any available samples of anomalies. Nonetheless, in practical settings, some anomalous samples are often available; however, usually in amounts far lower than required for a balanced classification task, and the separability assumption might not always hold. This leads to an important task—incorporating known anomalous samples into training procedures of anomaly detection models. In this work, we propose a novel model-agnostic training procedure to address this task. We reformulate one-class classification as a binary classification problem with normal data being distinguished from pseudo-anomalous samples. The pseudo-anomalous samples are drawn from low-density regions of a normalizing flow model by feeding tails of the latent distribution into the model. Such an approach allows to easily include known anomalies into the training process of an arbitrary classifier. We demonstrate that our approach shows comparable performance on one-class problems, and, most importantly, achieves comparable or superior results on tasks with variable amounts of known anomalies.

Learning to Classify DWDM Optical Channels from Tiny and Imbalanced Data

Applying machine learning algorithms for assessing the transmission quality in optical networks is associated with substantial challenges. Datasets that could provide training instances tend to be small and heavily imbalanced. This requires applying imbalanced compensation techniques when using binary classification algorithms, but it also makes one-class classification, learning only from instances of the majority class, a noteworthy alternative. This work examines the utility of both these approaches using a real dataset from a Dense Wavelength Division Multiplexing network operator, gathered through the network control plane. The dataset is indeed of a very small size and contains very few examples of `bad” paths that do not deliver the required level of transmission quality. Two binary classification algorithms, random forest and extreme gradient boosting, are used in combination with two imbalance handling methods, instance weighting and synthetic minority class instance generation. Their predictive performance is compared with that of four one-class classification algorithms: One-class SVM, one-class naive Bayes classifier, isolation forest, and maximum entropy modeling. The one-class approach turns out to be clearly superior, particularly with respect to the level of classification precision, making it possible to obtain more practically useful models.

One-Class Classification Using lp-Norm Multiple Kernel Fisher Null-Space

The paper addresses the one-class classification (OCC) problem and advocates a one-class multiple kernel learning (MKL) approach for this purpose. To this aim, based on the Fisher null-space one-class classification principle, we present a multiple kernel learning algorithm where an $\ell_p$-norm constraint ($p\geq1$) on kernel weights is considered. We cast the proposed one-class MKL task as a min-max saddle point Lagrangian optimisation problem and propose an efficient method to solve it. An extension of the proposed one-class MKL approach is also considered where several related one-class MKL tasks are learned concurrently by constraining them to share common kernel weights. <br>An extensive assessment of the proposed method on a range of data sets from different application domains confirms its merits against the baseline and several other algorithms.<br>