Exploiting petri-net structure for activity classification and user instruction within an industrial setting

Phish Phactors: Offensive and Defensive Strategies

In the traditional two-stream convolutional neural network, RGB image and optical flow image are trained separately and then simply fused, which results in the lack of fine-grained interaction between static image and dynamic clue, making the important clue of timing information unable to play its full role in the task of video action recognition. We propose a spatial-temporal co-attention network, which allows the attention of spatial features and temporal features to guide each other and collect basic information from the two features. The network utilizes the attention mechanism to estimate the commonality between static images and temporal information by focusing on their shared common semantics. Our experiments verify the effectiveness of the spatial-temporal co- attention network in combining spatial information and temporal information, and obtain better performance on three public standard datasets.

This paper proposes the utilization of large language models as recommendation systems for museum visitors. Since the aforementioned models lack the notion of context, they cannot work with temporal information that is often present in recommendations for cultural environments (e.g., special exhibitions or events). In this respect, the current work aims to enhance the capabilities of large language models through a fine-tuning process that incorporates contextual information and user instructions. The resulting models are expected to be capable of providing personalized recommendations that are aligned with user preferences and desires. More specifically, Generative Pre-trained Transformer 4, a knowledge-based large language model is fine-tuned and turned into a context-aware recommendation system, adapting its suggestions based on user input and specific contextual factors such as location, time of visit, and other relevant parameters. The effectiveness of the proposed approach is evaluated through certain user studies, which ensure an improved user experience and engagement within the museum environment.

Accurate rainfall intensity nowcasting has many applications such as flash flood defense and sewer management. Conventional computational intelligence tools do not take into account temporal information, and the series of rainfall is treated as continuous time series. Unfortunately, rainfall intensity is not a continuous time series as it has different dry periods in between raining seasons. Hence, conventional computational intelligence tools sometimes are not able to offer acceptable accuracy. An ensemble constitutes of classification, regression and reward models is proposed. The classification model identifies rain or no rain episodes, whereas the regression model predicts the rainfall intensity. The error of the regression model is then predicted by the reward regression model. Through that, the spatial information is captured by the classification model, and the temporal information is captured by the regression and reward models. Preliminary experimental results are encouraging.

The developmental process of embryos follows a monotonic order. An embryo can progressively cleave from one cell to multiple cells and finally transform to morula and blastocyst. For time-lapse videos of embryos, most existing developmental stage classification methods conduct per-frame predictions using an image frame at each time step. However, classification using only images suffers from overlapping between cells and imbalance between stages. Temporal information can be valuable in addressing this problem by capturing movements between neighboring frames. In this work, we propose a two-stream model for developmental stage classification. Unlike previous methods, our two-stream model accepts both temporal and image information. We develop a linear-chain conditional random field (CRF) on top of neural network features extracted from the temporal and image streams to make use of both modalities. The linear-chain CRF formulation enables tractable training of global sequential models over multiple frames while also making it possible to inject monotonic development order constraints into the learning process explicitly. We demonstrate our algorithm on two time-lapse embryo video datasets: i) mouse and ii) human embryo datasets. Our method achieves 98.1% and 80.6% for mouse and human embryo stage classification, respectively. Our approach will enable more pro-found clinical and biological studies and suggests a new direction for developmental stage classification by utilizing temporal information.

Mobile fitness applications provide the opportunity to show users real-time feedback on their current fitness activity. For such applications, it is essential to accurately track the user's current fitness activity using available mobile sensors, such as inertial measurement units (IMUs). Convolutional neural networks (CNNs) have been shown to produce strong results in different time series classification tasks, including the recognition of daily living activities. However, fitness activities can present unique challenges to the human activity recognition task (HAR), including greater similarity between individual activities and fewer available data for model training. In this paper, we evaluate the applicability of CNNs to the fitness activity recognition task (FAR) using IMU data and determine the impact of input data size and sensor count on performance. For this purpose, we adapted three existing CNN architectures to the FAR task and designed a fourth CNN variant, which we call the scaling fully convolutional network (Scaling-FCN). We designed a preprocessing pipeline and recorded a running exercise data set with 20 participants, in which we evaluated the respective recognition performances of the four networks, comparing them with three traditional machine learning (ML) methods commonly used in HAR. Although CNN architectures achieve at least 94% test accuracy in all scenarios, two traditional ML architectures surpass them in the default scenario, with support vector machines (SVMs) achieving 99.00 ± 0.34% test accuracy. The removal of all sensors except one foot sensor reduced the performance of traditional ML architectures but improved the performance of CNN architectures on our data set, with our Scaling-FCN reaching the highest accuracy of 99.86 ± 0.11% on the test set. Our results suggest that CNNs are generally well suited for fitness activity recognition, and noticeable performance improvements can be achieved if sensors are dropped selectively, although traditional ML architectures can still compete with or even surpass CNNs when favorable input data are utilized.

Brain-computer interfaces (BCIs) are well-known instances of how technology can convert a user's brain activity taken from non-invasive electroencephalography (EEG) into computer commands for the purpose of computer-assisted communication and interaction. However, not all users are attaining the accuracy required to use a BCI consistently, despite advancements in technology. Accordingly, previous research suggests that human factors could be responsible for the variance in BCI performance among users. Therefore, the user's internal mental states and traits including motivation, affect or cognition, personality traits, or the user's satisfaction, beliefs or trust in the technology have been investigated. Going a step further, this manuscript aims to discuss which human factors could be potential superordinate factors that influence BCI performance, implicitly, explicitly as well as inter- and intraindividually. Based on the results of previous studies that used comparable protocols to examine the motivational, affective, cognitive state or personality traits of healthy and vulnerable EEG-BCI users within and across well-investigated BCIs (P300-BCIs or SMR-BCIs, respectively), it is proposed that the self-relevance of tasks and stimuli and the user's self-concept provide a huge potential for BCI applications. As potential key human factors self-relevance and the user's self-concept (self-referential knowledge and beliefs about one's self) guide information processing and modulate the user's motivation, attention, or feelings of ownership, agency, and autonomy. Changes in the self-relevance of tasks and stimuli as well as self-referential processing related to one's self (self-concept) trigger changes in neurophysiological activity in specific brain networks relevant to BCI. Accordingly, concrete examples will be provided to discuss how past and future research could incorporate self-relevance and the user's self-concept in the BCI setting - including paradigms, user instructions, and training sessions.

Here we propose a new machine learning algorithm for classification of human activities by means of accelerometer and gyroscope signals. Based on a novel hierarchical system of logistic regression classifiers and a relatively small set of features extracted from the filtered signals, the proposed algorithm outperformed previous work on the DaLiAc (Daily Life Activity) and mHealth datasets. The algorithm also represents a significant improvement in terms of computational costs and requires no feature selection and hyper-parameter tuning. The algorithm still showed a robust performance with only two (ankle and wrist) out of the four devices (chest, wrist, hip and ankle) placed on the body (96.8% vs. 97.3% mean accuracy for the DaLiAc dataset). The present work shows that low-complexity models can compete with heavy, inefficient models in classification of advanced activities when designed with a careful upstream inspection of the data.

User Interface (UI) testing has become a common practice for quality assurance of industrial mobile applications (in short as apps). While many automated tools have been developed, they often do not satisfy two major industrial requirements that make a tool desirable in industrial settings: high applicability across platforms (e.g., Android, iOS, AliOS, and Harmony OS) and high capability to handle apps with non-standard UI elements (whose internal structures cannot be acquired using platform APIs). Toward addressing these industrial requirements, automated visual testing emerges to take only device screenshots as input in order to support automated test generation. In this paper, we report our experiences of developing and deploying VTest, our industrial visual testing framework to assure high quality of Taobao, a highly popular industrial app with about one billion monthly active users. VTest includes carefully designed techniques and infrastructure support, outperforming Monkey (which has been popularly deployed in industry and shown to perform superiorly or similarly compared to state-of-the-art tools) with 87.6% more activity coverage. VTEST has been deployed both internally in Alibaba and externally in the Software Green Alliance to provide testing services for top smart-phone vendors and app vendors in China. We summarize five major lessons learned from developing and deploying VTEST.

Early prediction of sugarcane genotypes susceptible and resistant to Diatraea saccharalis using spectroscopies and classification techniques.

Peptide profiles generated using SELDI/MALDI time of flight mass spectrometry provide a promising source of patient-specific information with high potential impact on the early detection and classification of cancer and other diseases. The new profiling technology comes, however, with numerous challenges and concerns. Particularly important are concerns of reproducibility of classification results and their significance. In this work we describe a computational validation framework, called PACE (Permutation-Achieved Classification Error), that lets us assess, for a given classification model, the significance of the Achieved Classification Error (ACE) on the profile data. The framework compares the performance statistic of the classifier on true data samples and checks if these are consistent with the behavior of the classifier on the same data with randomly reassigned class labels. A statistically significant ACE increases our belief that a discriminative signal was found in the data. The advantage of PACE analysis is that it can be easily combined with any classification model and is relatively easy to interpret. PACE analysis does not protect researchers against confounding in the experimental design, or other sources of systematic or random error. We use PACE analysis to assess significance of classification results we have achieved on a number of published data sets. The results show that many of these datasets indeed possess a signal that leads to a statistically significant ACE.

The availability and expansion of social media has made it difficult to distinguish between fake and real news. Information falsification has exponentially increased as a result of how simple it is to spread information through sharing. Social media dependability is also under jeopardy due to the extensive dissemination of false information. Therefore, it has become a research problem to automatically validate information, specifically source, content, and publisher, to identify it as true or false. Despite its limitations, machine learning (ML) has been crucial in the categorization of information. Previous studies suggested three-step methods for categorising false information on social media. In the first step of the process, the data set is subjected to a number of pre-processing processes in order to transform unstructured data sets into structured data sets. The unknowable properties of fake news and the features are extracted by the Lexicon Model in the second stage. In the third stage of this research project, a feature selection method by WOA (Whale Optimization Algorithm) for weight value to tune the classification part. Finally, a Hybrid Classification model that is hybrid with a fuzzy based Convolutional Neural Network and kernel based support vector machine is constructed in order to identify the data pertaining to bogus news. However using single classifier for fake news detection produces the insufficient accuracy. To overcome this issue in this work introduced an improved model for fake news classification. To turn unstructured data sets into structured data sets, a variety of pre-processing operations are used on the data set in the initial phase of the procedure. The unknowable properties of fake news and the features are extracted by the Lexicon Model in the second stage. In the third stage of this research project, a feature selection method by COA (Coati Optimization Algorithm) for weight value to tune the classification part. Finally, an ensemble of RNN (Recurrent Neural Networks), VGG-16 and ResNet50.A classification model was developed to recognise bogus news information. Evaluate each fake news analysis' performance in terms of accuracy, precision, recall, and F1 score. The suggested model, out of all the methodologies taken into consideration in this study, provides the highest outcomes, according to experimental findings

A vegetation classification model, which takes account of not only spectral information of data but also spatial and temporal information, is proposed for high spatial resolution multispectral scanner data such as Landsat/TM (thematic mapper) images. For this purpose, Markov random field model (MRF) is introduced for spectral, spatial and temporal information of data. The MRF exploits spatial class dependencies between neighboring pixels in any image and temporal class dependencies between temporal sequences. By integrating spectral, spatial, and temporal information in the classification model, it is expected to improve classification accuracy. The performance of the proposed model is investigated by using actual Landsat/TM temporal images. The experimental results shows that the classification accuracy of proposed model is about 5.09% higher than Maximum Likelihood Method that used as reference model. From this experiment, we can conclude that the proposed model is useful for classification of Landsat/TM images.

SummaryMobile phones are equipped with a rich set of sensors, such as accelerometers, magnetometers, gyroscopes, photometers, orientation sensors, and gravity sensors. These sensors can be used for human activity recognition in the ubiquitous computing domain. Most of reported studies consider acceleration signals that are collected from a known fixed device location and orientation. This paper describes how more accurate results of basic activity recognition can be achieved with transformed accelerometer data. Based on the rotation matrix (Euler Angle Conversion) derived from the orientation angles of gyroscopes and orientation sensors, we transform input signals into a reference coordinate system. The advantage of the transformation is that it allows activity classification and recognition to be carried out independent of the orientation of sensors. We consider five user activities: staying, walking, running, ascending stairs, and descending stairs, with a phone being placed in the subject's hand, or in pants pocket, or in a handbag. The results show that an overall orientation independent accuracy of 84.77% is achieved, which is a improvement of 17.26% over those classifications without input transformation. Copyright © 2014 John Wiley & Sons, Ltd.

Breaking News