Novelty Detection System Research Articles

Enabling Seamless Connectivity: Networking Innovations in Wireless Sensor Networks for Industrial Application.

The wide-ranging applications of the Internet of Things (IoT) show that it has the potential to revolutionise industry, improve daily life, and overcome global challenges. This study aims to evaluate the performance scalability of mature industrial wireless sensor networks (IWSNs). A new classification approach for IoT in the industrial sector is proposed based on multiple factors and we introduce the integration of 6LoWPAN (IPv6 over low-power wireless personal area networks), message queuing telemetry transport for sensor networks (MQTT-SN), and ContikiMAC protocols for sensor nodes in an industrial IoT system to improve energy-efficient connectivity. The Contiki COOJA WSN simulator was applied to model and simulate the performance of the protocols in two static and moving scenarios and evaluate the proposed novelty detection system (NDS) for network intrusions in order to identify certain events in real time for realistic dataset analysis. The simulation results show that our method is an essential measure in determining the number of transmissions required to achieve a certain reliability target in an IWSNs. Despite the growing demand for low-power operation, deterministic communication, and end-to-end reliability, our methodology of an innovative sensor design using selective surface activation induced by laser (SSAIL) technology was developed and deployed in the FTMC premises to demonstrate its long-term functionality and reliability. The proposed framework was experimentally validated and tested through simulations to demonstrate the applicability and suitability of the proposed approach. The energy efficiency in the optimised WSN was increased by 50%, battery life was extended by 350%, duplicated packets were reduced by 80%, data collisions were reduced by 80%, and it was shown that the proposed methodology and tools could be used effectively in the development of telemetry node networks in new industrial projects in order to detect events and breaches in IoT networks accurately. The energy consumption of the developed sensor nodes was measured. Overall, this study performed a comprehensive assessment of the challenges of industrial processes, such as the reliability and stability of telemetry channels, the energy efficiency of autonomous nodes, and the minimisation of duplicate information transmission in IWSNs.

A system reliability approach to real-time unsupervised structural health monitoring without prior information

Unsupervised techniques have gained much attention in the last decade as the most practical real-time structural health monitoring (SHM) approach. However, there are still obstacles to robust real-time health monitoring among the proposed unsupervised methods in the literature. These barriers include loss of information from dimensionality reduction, case-dependency of feature extraction steps, lack of dynamic-class novelty detection approaches, and detection results’ sensitivity to user-defined detection parameters. This study introduces an unsupervised real-time SHM method, addressing the above four obstacles simultaneously. Furthermore, the proposed technique requires no prior information from structures before going online as a step towards having a general SHM technique. No prior information is common for newly detected novelties, preventing the establishment of detection baselines. Without the baselines, dynamic-class novelty detection cannot take place. Hence, while solving the dynamic-class novelty detection hindrance with Generative Adversarial Networks (GAN), the framework can be adjusted to be prior-information-free. Online generations of data objects with GAN from the incoming data stream is the key feature that addresses the obstacles above. A mixture of low- and high-dimensional features are used to train multi-ensembles of GAN and one-class joint Gaussian distribution models (1-CG). A novelty detection system of limit-state functions based on GAN and 1-CG models’ detection scores is constructed. The Resistance of the limit-state functions is tuned to user-defined detection parameters with the GAN-generated data objects through reliability analysis. The tuning makes the detection results robust to the user-defined detection parameters. The proposed novelty detection framework is applied to two standard SHM datasets to illustrate its generalizability: Yellow Frame and Z24 Bridge. All different damage categories are identified with low sensitivity to the initial choice of detection window length by employing the proposed dynamic and static baseline approaches with few or no false alarms.

Fusion of Novelty Detectors Using Deep and Local Invariant Visual Features for Inspection Task

In this study, a novel framework using multiple novelty detection filters is developed to learn a model of the normality of a robot’s visual perception, which is called multichannel novelty detection. Subsequently, the acquired model was used to highlight dissimilar perceptions when the robot explored an environment. The main purpose of fusing multiple novelty filters is that each novelty filter performs well in detecting specific types of novelties; therefore, a new framework is proposed that demonstrates a new way to combine multiple different purposed novelty detection filters together in order to yield an overall more robust novelty status on the visual features. To develop a multichannel novelty detection system, expectation- and appearance-based novelty detection models were used in this study. To become experts in detecting different types of novelty using these models, different features from the input image were extracted as inputs for the models. The expectation-based novelty detection model uses the MobileNetV2 deep network to extract the deep features of the input image, which is subsequently used to learn a sequential and temporal model of normality to detect novelty. By contrast, the appearance-based novelty detection model uses speeded up robust features (SURF), which provide more region-focused features within the input image, to identify whether a specific region of the image is novel. The proposed multichannel novelty detection system is a completely online and real-time approach that is very important for mobile robotics applications. The proposed framework was tested in three novel environments, and it was reported that the proposed multichannel novelty detection system performs better than expectation-based and appearance-based novelty filters separately. Statistically, in the three novel environments, the Matthews correlation coefficients are reported to be 0.94, 0.97, and 0.93, and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> scores are reported to be 0.95, 0.97, and 0.93, respectively, which proves that and can be concluded as almost perfect statistically.

Novelty detection for metabolic dynamics established on breast cancer tissue using 2D NMR TOCSY spectra

Most metabolic profiling approaches focus only on identifying pre-known metabolites on NMR TOCSY spectrum using configured parameters. However, there is a lack of tasks dealing with automating the detection of new metabolites that might appear during the dynamic evolution of biological cells. Novelty detection is a category of machine learning that is used to identify data that emerge during the test phase and were not considered during the training phase. We propose a novelty detection system for detecting novel metabolites in the 2D NMR TOCSY spectrum of a breast cancer-tissue sample. We build one- and multi-class recognition systems using different classifiers such as, Kernel Null Foley-Sammon Transform, Kernel Density Estimation, and Support Vector Data Description. The training models were constructed based on different sizes of training data and are used in the novelty detection procedure. Multiple evaluation measures were applied to test the performance of the novelty detection methods. Depending on the training data size, all classifiers were able to achieve 0% false positive rates and total misclassification error in addition to 100% true positive rates. The median total time for the novelty detection process varies between 1.5 and 20 seconds, depending on the classifier and the amount of training data. The results of our novel metabolic profiling method demonstrate its suitability, robustness and speed in automated metabolic research.

CNN‐based novelty detection for terrestrial and extra‐terrestrial autonomous exploration

Novelty detection is concerned with detecting features that do not belong to any known class or are not well represented by existing models. Ergo, in autonomous navigation novelty detection determines whether an input camera frame contains certain entities of high interest which do not correspond to a known category. One of the key requirements for the future space exploration missions is the reduction of the information to be transferred back to Earth. Thus, novelty detection techniques have been developed to select the subset of acquired images with significant measurements that justify utilisation of the limited bandwidth from the available information link. Such methods are based on the identification of salient regions, which are then evaluated against a set of trained classifiers. We explore a novelty detection approach, based on the reasoning properties of Neural Networks, which follow the same guidelines while also being trainable in an end-to-end manner. This characteristic allows for the intertwined optimisation of the individual components leading to a closer estimation of a global solution. Our experiments reveal that the proposed novelty detection system achieves better performance, as compared to hand-crafted techniques, when the learning and testing examples refer to similar environments.

Experiments in online expectation-based novelty-detection using 3D shape and colour perceptions for mobile robot inspection

Novelty detection is a very useful function for detecting abnormal data in any application. An expectation-based novelty-detection approach has been introduced that learns the dynamic relationship model among normal data in order to predict the next expected data. Most novelty-detection systems use an offline approach with a fixed structure, a system type that has limitations when the data count in the environment is unknown. A new expectation-based novelty-detection system features an online recurrent neural network approach that learns the data by inserting new nodes or deleting unused nodes from its structure. Generally, to detect novelties, a global novelty threshold is defined to filter out all input data as novel whenever the prediction error of the network exceeds the threshold. However, because a neural network cannot learn to predict all classes of input data perfectly, using a global novelty threshold leads to the misclassification of the insufficiently learned normal data as novel. To overcome this problem, the novelty-detection system has been improved to learn local novelty thresholds alongside its learning to predict expectations. The proposed algorithm is applied to an online novelty detection using colour and depth data obtained from a Kinect sensor on a mobile robot. The performance of the expected novelty detector and its limitations during experiments are analysed and shown. Furthermore, colour and depth data as inputs into the novelty filter are separately analysed and their contributions on the overall novelty detection highlighted. In conclusion, the performance of the novelty filter could further be improved by applying a better feature-selection technique to extract more interesting features from high-dimensional input data.

Detecting static and dynamic novelties using dynamic neural network

This paper presents a dynamic neural network based novelty filter where a mobile robot explored in an environment and built a dynamic model of the robot normal sensory-motor values perceived from the environment. Afterwards, the acquired model of normality was used on the robot to predict expected values of the sensory-motor inputs during the patrolling. Novelties could be detected if the prediction error between model-predicted values and real observed values exceeded a certain novelty threshold. Because of high uncertainty while robot interactions with the environment, the network-prediction errors along the robot route were not normally distributed to define only one novelty threshold. Therefore region-specific novelty thresholds were estimated by the proposed novelty detection system. As a result, the robot is capable of selecting a local novelty threshold depending on where the robot currently occupied.To evaluate the proposed system, a set of real-world robotic experiments were carried out. Experimental results showed that the novelty filter was able to highlight unusual static and dynamic objects in the environment. Furthermore, the filter also produced reliable local novelty thresholds while the robot patrolled in the noisy environment.

Damage detection in aluminum and composite elements using neural networks for Lamb waves signal processing

Abstract One of the important factors in the structural health monitoring systems is the amount of data that need to be analysed in real time. This study investigated the use of artificially deteriorated signals of Lamb waves in training the novelty detection (ND) system for the early damage detection. In this system Auto-associative Neural Networks were trained using principal components calculated on the basis of experimentally measured signals. The specimens studied relate to two different materials commonly used in the aerospace industry, i.e. aluminium and glass fibre reinforced polymer. Lamb waves measured in these specimens are a good example that the ND algorithm works correctly in case of simple as well as complex signals. Furthermore, it was found that the designed ND system remained sensitive and robust even when it used raw signals with a relatively low sampling rate, on a fairly narrow time window and even noised signals.

Multilevel Cortical Processing of Somatosensory Novelty: A Magnetoencephalography Study.

Using magnetoencephalography (MEG), this study investigates the spatio-temporal dynamics of the multilevel cortical processing of somatosensory change detection. Neuromagnetic signals of 16 healthy adult subjects (7 females and 9 males, mean age 29 ± 3 years) were recorded using whole-scalp-covering MEG while they underwent an oddball paradigm based on simple standard (right index fingertip tactile stimulation) and deviant (simultaneous right index fingertip and middle phalanx tactile stimulation) stimuli gathered into sequences to create and then deviate from stimulus patterns at multiple (local vs. global) levels of complexity. Five healthy adult subjects (3 females and 2 males, mean age 31, 6 ± 2 years) also underwent a similar oddball paradigm in which standard and deviant stimuli were flipped. Local deviations led to a somatosensory mismatch response peaking at 55–130 ms post-stimulus onset with a cortical generator located at the contralateral secondary somatosensory (cSII) cortex. The mismatch response was independent of the deviant stimuli physical characteristics. Global deviants led to a P300 response with cortical sources located bilaterally at temporo-parietal junction (TPJ) and supplementary motor area (SMA). The posterior parietal cortex (PPC) and the SMA were found to generate a contingent magnetic variation (CMV) attributed to top-down expectations. Amplitude of mismatch responses were modulated by top-down expectations and correlated with both the magnitude of the CMV and the P300 amplitude at the right TPJ. These results provide novel empirical evidence for a unified sensory novelty detection system in the human brain by linking detection of salient sensory stimuli in personal and extra-personal spaces to a common framework of multilevel cortical processing.

Comparison and Analysis of Two Approaches to Find Novel Documents out of Several Documents

Novelty detection system is used to extract documents with new or novel information from list of documents. Without looking for lot of redundant information, we can get useful information in a limited time. Cosine similarity and Language modeling are the two emerging techniques of information retrieval in today’s scenario. The current study performs the analysis and comparison between these two models. Keywords Cosine similarity, Information retrieval, Language modeling, Novelty detection, Smoothing

Application of the Elastic Waves and Neural Networks as a Tool of Damage Detection and Health Monitoring in Aircraft's Structures

There exist a large group of structures like e.g. aircraft, which operational safety requires periodical inspections or even continuous monitoring of its health. Sometimes the structures are equipped with Structural Health Monitoring systems which usually utilizes the phenomena of elastic waves propagation in solids. The analysis of elastic waves signals consists in general of quantitative and qualitative description of theirs changes (e.g. attenuation, distortion, reflection) caused by a damage appearance and growth. Since the reflections and dispersion effects may produce pretty complex signals, therefore the determination of parameters suitable for damage detection requires the application of advance signal processing techniques. For this purpose an approach of novelty detection and damage evaluation based on soft computing methods (for example - Neural Networks) was proposed in this paper. Two levels of the damage identification problem were realized: novelty detection and damage assessment. The system accuracy and reliability were verified during laboratory tests. It was proved that the system can be used for the analysis of simple as well as complex signals. One of the important factors in the structural health monitoring systems is the amount of data that need to be analysed in real time. This study investigated the use of artificially deteriorated signals of elastic waves in training the novelty detection (ND) system. In this system auto-associative neural networks were trained using the principal components calculated on the basis of experimentally measured signals. It was found that the designed ND system remained sensitive and robust even when it uses raw signals with a relatively low sampling rate, on a fairly narrow time window and even noisy signals.

Mismatch negativity to acoustical illusion of beat: How and where the change detection takes place?

In case of binaural presentation of two tones with slightly different frequencies the structures of brainstem can no longer follow the interaural time differences (ITD) resulting in an illusionary perception of beat corresponding to frequency difference between the two prime tones. Hence, the beat-frequency does not exist in the prime tones presented to either ear. This study used binaural beats to explore the nature of acoustic deviance detection in humans by means of magnetoencephalography (MEG). Recent research suggests that the auditory change detection is a multistage process. To test this, we employed 26Hz-binaural beats in a classical oddball paradigm. However, the prime tones (250Hz and 276Hz) were switched between the ears in the case of the deviant-beat. Consequently, when the deviant is presented, the cochleae and auditory nerves receive a “new afferent”, although the standards and the deviants are heard identical (26Hz-beats). This allowed us to explore the contribution of auditory periphery to change detection process, and furthermore, to evaluate its influence on beats-related auditory steady-state responses (ASSRs). LORETA-source current density estimates of the evoked fields in a typical mismatch negativity time-window (MMN) and the subsequent difference-ASSRs were determined and compared. The results revealed an MMN generated by a complex neural network including the right parietal lobe and the left middle frontal gyrus. Furthermore, difference-ASSR was generated in the paracentral gyrus. Additionally, psychophysical measures showed no perceptual difference between the standard- and deviant-beats when isolated by noise. These results suggest that the auditory periphery has an important contribution to novelty detection already at sub-cortical level. Overall, the present findings support the notion of hierarchically organized acoustic novelty detection system.

A One-Class SVM Based Tool for Machine Learning Novelty Detection in HVAC Chiller Systems

Faulty operations of Heating, Ventilation and Air Conditioning (HVAC) chiller systems can lead to discomfort for the occupants, energy wastage, unreliability and shorter equipment life. Such faults need to be detected early to prevent further escalation and energy losses. Commonly, data regarding unforeseen phenomena and abnormalities are rare or are not available at the moment for HVAC installations: for this reason in this paper an unsupervised One-Class SVM classifier employed as a novelty detection system to identify unknown status and possible faults is presented. The approach, that exploits Principal Component Analysis to accent novelties w.r.t. normal operations variability, has been tested on a HVAC literature dataset.

Auditory deviance detection revisited: Evidence for a hierarchical novelty system

The fast detection of novel or deviant stimuli is a striking property of the auditory processing which reflects basic organizational principles of the auditory system and at the same time is of high practical significance. In human electrophysiology, deviance detection has been related to the occurrence of the mismatch negativity (MMN) — a component of the event-related potential (ERP) evoked 100 to 250ms after the occurrence of a rare irregular sound. Recently, it has been shown in animal studies that a considerable portion of neurons in the auditory pathway exhibits a property called stimulus-specific adaptation enabling them to encode inter-sound relationships and to discharge at higher rates to rare changes in the acoustic stimulation. These neural responses have been linked to the deviant-evoked potential measured at the human scalp, but such responses occur at lower levels anatomically (e.g. the primary auditory cortex as well as the inferior colliculi) and are elicited earlier (20–30ms after sound onset) in comparison to MMN. Further, they are not considerable enough in size to be interpreted as a direct neural correlate of the MMN. We review here a series of recent findings that provides a first step toward filling this gap between animal and human recordings by showing that comparably early modulations due to a sound's deviancy can be observed in humans, particularly in the middle-latency portion of the ERP within the first 50ms after sound onset. The existence of those early indices of deviance detection preceding the well-studied MMN component strongly supports the idea that the encoding of regularities and the detection of violations is a basic principle of human auditory processing acting on multiple levels. This sustains the notion of a hierarchically organized novelty and deviance detection system in the human auditory system.

D2S: Document-to-sentence framework for novelty detection

Novelty detection aims at identifying novel information from an incoming stream of documents. In this paper, we propose a new framework for document-level novelty detection using document-to-sentence (D2S) annotations and discuss the applicability of this method. D2S first segments a document into sentences, determines the novelty of each sentence, then computes the document-level novelty score based on a fixed threshold. Experimental results on APWSJ data show that D2S outperforms standard document-level novelty detection in terms of redundancy-precision (RP) and redundancy-recall (RR). We applied D2S on the document-level data from the TREC 2004 and TREC 2003 Novelty Track and find that D2S is useful in detecting novel information in data with a high percentage of novel documents. However, D2S shows a strong capability to detect redundant information regardless of the percentage of novel documents. D2S has been successfully integrated in a real-world novelty detection system.

Multilingual novelty detection

Novelty detection aims at reducing redundant information from a chronologically ordered list of documents or sentences. Other studies of novelty detection have been conducted on the English language, but few papers have addressed the problem of multilingual novelty detection. Likewise, research in multilingual information retrieval have rarely been applied to novelty detection. This paper attempts to bridge the two disciplines by first describing the preprocessing steps for English, Malay and Chinese, then applying document and sentence-level novelty detection for the three languages on APWSJ and TREC 2004 Novelty Track data. Experiments on sentence-level novelty detection show similar results for all three languages, which indicates that our algorithm is suitable for multilingual novelty detection at the sentence level. However, results for document-level novelty detection show a disparity across the different languages, with English and Malay outperforming Chinese. After applying sentence-level novelty detection to detect novel documents, we observe substantial improvements on all three languages. This demonstrates that segmenting documents into sentences improves document-level novelty detection in multiple languages, and has practical benefits for a real-time multilingual novelty detection system.

Geometrical Kernel Machine for Prediction and Novelty Detection of Disruptive Events in TOKAMAK Machines

This paper presents a recently introduced Kernel Machine, called Geometrical Kernel Machine, used to predict disruptive events in nuclear fusion reactors. The algorithm proposed to construct the Kernel Machine is able to automatically determine both the number of neurons and the synaptic weights of a Multilayer Perceptron neural network with a single hidden layer. It has been demonstrated that the resulting network is able to classify any finite set of patterns defined in a real domain. The prediction problem has been here modeled as a two classes classification problem. The geometrical interpretation of the network equations allows us both to develop the disruption predictor and to manage the so called ageing of the kernel machine. In fact, using the same kernel machine, a novelty detection system has been integrated in the predictor, increasing the overall system performance, and the reliability of the predictor.

The design of enhanced online condition monitoring systems for turning processes

The increasing requirements of high quality and low cost of products have created an urgent need to implement new technologies in current automated manufacturing environments. Condition monitoring systems of manufacturing processes have been recognised in recent years as one of the essential technologies that provide the competitive advantage in many manufacturing environments. This paper aims to developing an effective sensor fusion model for turning processes for the detection of tool wear. Multi-sensors combined with a novelty detection algorithm are used to detect tool wear and provide diagnostic and prognostic information. A novel approach using dynamic threshold is utilised to improve the accuracy of the novelty detection system. The results found indicate that the suggested approach provides a responsive and effective solution in monitoring tool wear in turning.

Differential involvement of amygdala and hippocampus in responding to novel objects and contexts

Different medial temporal lobe structures are involved in memory for different types of novel cues and novel relationships among familiar cues. We measured the behavior of rats with amygdala or hippocampal damage, when confronted with novelty in an incidental learning paradigm. We examined both direct and indirect measures of memory. Following habituation to an environment, proximal objects or distal cues were manipulated in several ways. We found that rats with hippocampal damage exhibited a deficit on direct measures of memory, but performed normally on all indirect measures. Rats with amygdala damage exhibited a deficit on a direct measure, and performed normally on an indirect measure, of memory for proximal object identity. Thus, the hippocampus may be necessary for success on direct measures of memory for distal cues and proximal objects and the relationships among them. Likewise, the amygdala may be necessary for success on some direct measures of memory, such as memory for aspects of proximal object identity. Neither the amygdala nor the hippocampus functions as a generalized novelty detection system. To the extent that we tap implicit and explicit knowledge using this paradigm, we suggest that in the rat, the amygdala and hippocampal systems are necessary for at least some types of explicit knowledge.