Term Memory Research Articles

A Deep Learning Approach for Detecting Atrial Fibrillation using RR Intervals of ECG

Purpose: Atrial Fibrillation (AF) is one of the most common types of heart arrhythmias observed in clinical practice. AF can be detected using an Electrocardiogram (ECG). ECG signals are time-varying and nonlinear in nature. Hence, it is very difficult for a physician to manually perform accurate and rapid classification of different heart rhythms.
 Materials and Methods: In this paper, we propose a method using Discrete Wavelet Transform (DWT) with db6 as the basis function for denoising ECG signal.
 Results: The denoised ECG is smoothened using the Savitzky- Golay filter. Deep learning methods, such as a combination of Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) (CNN-LSTM) and ResNet18 are used for the accurate classification of ECG signals using Physionet Challenge 2017 database.
 Conclusion: With a 10-fold cross-validation method the model provided overall accuracy of 98.25% with the CNN-LSTM classifier.

Evolution of Natural Language Processing: A Review

Over the years, Natural Language Processing (NLP) has evolved dramatically, moving from early rule based systems to the current era dominated by advanced deep learning models. An overview of the significant turning points and patterns that have influenced the development of NLP is given in this study. In the early days of Natural Language Processing (NLP), rule based methods were the main focus. Linguists would manually create rules to analyze and comprehend human language. Although these systems were somewhat successful, they were unable to handle the complexity and unpredictability of spoken language. A major change was brought about by the introduction of probabilistic models and machine learning techniques with the emergence of statistical approaches. The development of methods like n gram models and hidden Markov models during this time allowed computers to handle linguistic patterns. Large scale linguistic resources like word embeddings and annotated corpora started to appear, which further accelerated the development of NLP. Machine learning algorithms have led to notable advancements in tasks such as machine translation, named entity recognition, and part of speech tagging. NLP has seen a revolution in recent years thanks to deep learning, which uses neural networks to learn intricate language representations. Sequential dependencies in language can now be better understood because of models like Long Short Term Memory Networks (LSTMs) and Recurrent Neural Networks (RNNs). The addition of attention mechanisms, as demonstrated by Transformer and other models, improves the model's ability to manage long range dependencies and perform better on a variety of NLP tasks. In the future, NLP will develop in ways that go beyond performance measurements, exploring interpretability, ethical issues, and the incorporation of multimodal data. As the area develops, it becomes increasingly important to eliminate biases, ensure ethical AI deployment, and improve user centric experiences. This introduction lays the groundwork for an in depth examination of the development of NLP, highlighting significant turning points, difficulties, and potential future directions in this vibrant and quickly developing subject.

SCHeMoS -- Smart Cow Health Monitoring System: An IoT based Cow Hoof Detection and Healthcare Alert System by Using LSTM Network

Human life and existence are intertwined with a few domestic animals. One of the most important animals of this kind is the cow. Cows play a vital role in daily activities. Most of the people in India consume cow’s milk as one of their major nutrients. Monitoring the health of a cow’s everyday life is quite challenging. After infertility and mastitis, lameness is typically ranked as the third most economically significant health issue in dairy herds.Lameness are caused due to genetics, lack in nutrition i.e. a diet deficient in essential nutrients such as biotin, which can lead to hoof problems. Due to geographical environments like cows kept in wet, muddy conditions are more likely to develop hoof problems. This investigation analyses the typical characteristics of cow behavior, and a Smart Cow Health Monitoring System (ScHeMoS) using IoT is proposed to identify the cow’s health through the data obtained from Internet of Things (IoT) sensors, including position, body temperature, stability, acceleration, and animal feed. IoT is combined with Deep learning (DL) technique to monitor and diagnose animal health. We used the Long Short Term Memory (LSTM) network to predict cow lameness by capturing the body temperature and other parameters, which will aid in predicting their illness. The accelerometer values are stored so that it will further help to determine which cow is lame and which is pregnant or regular and could be intimated to the care takers in the farms. We utilised a self collected dataset to perform the investigation. By implementing this system, we achieved 92.45\% accuracy and 0.92 as F1 score.

A novel industrial process situation awareness model based on multi‐time scale dynamic feature fusion with applications to float glass manufacturing

AbstractModern industrial manufacturing processes often focus on the changes of performance indicators and the evolution of operation conditions. However, the dynamics of variables are vague within processes and even more difficult to be characterised across different processes. The time‐series dynamic characteristics of the different scales among variables, processes, and production cycles develop and transfer with changes in parameters, equipment, and processes. It is difficult to accurately show the quality index and operating condition trend at the same time. To solve these problems, a situation awareness (SA) framework integrating multi‐time scale dynamic features for manufacturing processes is proposed. First, data are condensed and reconstructed through the denoising long short term memory autoencoder to reveal the time series dynamic characteristics to get neighbourhood features which contain features among neighbourhood samples. Second, the neighbourhood features divided into window blocks are fused into the stage features by statistical analysis. Finally, a multi‐scale isometric convolution network is designed to extract the local and global features, which can effectively show the development of dynamic features on a long time scale, and profoundly describe the influence of full cycle features on variables and operating conditions. The proposed model is verified on the real data set of a float glass manufacturing process, and the SA model can well predict the future trend of long time series.

Using explainable artificial intelligence (XAI) methods to understand the nonlinear relationship between the Three Gorges Dam and downstream flood

Study RegionIn the Yangtze River basin of China. Study focusThe emerging Explainable Artificial Intelligence (XAI) methods provide us an opportunity to understand the nonlinear relationship that the Deep Learning(DL) model learned inside. The construction of the Three Gorges Dam (TGD) has successfully minimized the likelihood of flooding in the Yangtze River basin. The XAI methods can help us to know the nonlinear relationship behind it. We apply the Long Short Term Memory (LSTM) network, in conjunction with two XAI methods, SHapley Additive exPlanation (SHAP) and Expected Gradient (EG), to do our work.In our DL model, we use YiChang (YC) station runoff,Precipitation (Pre) and vapour pressure deficit (VPD) data from the middle and lower river basin as input, while the output of the model generates runoff data at the DaTong (DT) station, XAI methods enable us to calculate the significance of each input feature is for generating the output feature in a DL model. In this study, we examine the difference in importance scores between the Before Three Gorges Dam (BTGD) period and the After Three Gorges Dam (ATGD) period. New Hydrological Insights for the RegionIn the BTGD period, YC runoff was the primary contributor to flooding at the DT station. However, in the ATGD period, the largest contribution to flooding in the middle and lower Yangtze River basin has shifted from YC runoff to the the middle and lower reaches of precipitation. Our results suggest that the XAI can show the nonlinear relationship between the TGD and downstream flood clearly and the TGD can effectively mitigate flooding in the middle and lower river basins by regulating runoff from the upper river basin. The work shows the potential of XAI to explain the nonlinear relationship in the hydrology field.

Interpretable intelligent fault diagnosis strategy for fixed-wing UAV elevator fault diagnosis based on improved cross entropy loss

The current popular machine learning-based fault diagnosis methods make it difficult to explain the diagnostic results, leading to low user trust in such diagnostic techniques. In this regard, this paper explores the study of the interpretability of intelligent fault diagnosis algorithms using the elevator of a fixed-wing unmanned aerial vehicle (UAV) as a diagnostic object. The Transformer model combines excellent modeling capability and efficient sequence data processing, is chosen to mine fault signal features to guarantee accurate diagnosis. Among the proposed interpretable fault diagnosis models, the local interpretable model-agnostic explanations (LIME) model is used to provide explicit interpretability for the decision-making process of the diagnosis model. In addition, a loss function called RDCE (reinforced diagnostic cross-entropy) Loss is designed to minimize the negative impact of different sample sizes for different fault types on the diagnostic performance. This loss function is designed to weigh the various types of faults to speed up the convergence of the model and improve the diagnostic accuracy. By comparing the proposed diagnostic strategy with other commonly used machine learning models, including long short term memory and recurrent neural network (RNN), the average diagnostic accuracy of the proposed diagnostic strategy is 99.97%, significantly better than that of the comparison algorithms. At the same time, this paper provides an in-depth interpretable analysis of the diagnostic process of the Transformer. The diagnostic process of the Transformer model gives the reasons for the diagnostic results from the point of view of the kind of features processed by the model. Based on this, the diagnostic model is simplified. After streamlining the number of features from 40 to 24 according to their importance, the diagnostic accuracy of the model is improved by 0.26%, and the diagnostic efficiency is improved. In addition, the proposed diagnostic strategy also shows significant advantages in terms of noise robustness.

Biological aging of two innate behaviors of Drosophila melanogaster: Escape climbing versus courtship learning and memory.

Motor and cognitive aging can severely affect life quality of elderly people and burden health care systems. In search for diagnostic behavioral biomarkers, it has been suggested that walking speed can predict forms of cognitive decline, but in humans, it remains challenging to separate the effects of biological aging and lifestyle. We examined a possible association of motor and cognitive decline in Drosophila, a genetic model organism of healthy aging. Long term courtship memory is present in young male flies but absent already during mid life (4-8 weeks). By contrast, courtship learning index and short term memory (STM) are surprisingly robust and remain stable through mid (4-8 weeks) and healthy late life (>8 weeks), until courtship performance collapses suddenly at ~4.5 days prior to death. By contrast, climbing speed declines gradually during late life (>8 weeks). The collapse of courtship performance and short term memory close to the end of life occur later and progress with a different time course than the gradual late life decline in climbing speed. Thus, during healthy aging in male Drosophila, climbing and courtship motor behaviors decline differentially. Moreover, cognitive and motor performances decline at different time courses. Differential behavioral decline during aging may indicate different underlying causes, or alternatively, a common cause but different thresholds for defects in different behaviors.

A novel attention-based long short term memory and fully connected neutral network approach for production energy consumption prediction under complex working conditions

Continuously growing demands due to the predictable faults or abnormal events of the flexible production line are becoming a challenge to easily cause the energy waste, which needs to accurately predict the real-time energy consumption of the actual production process. By reviewing the related works about prediction model approach and energy consumption analysis in the actual production application, it is necessary to overcome two main challenges: optimal prediction selection and internal relation mining of energy consumption under different equipment working conditions. To deal with the existing challenges, the paper proposes a novel attention-based Long and Short-Term Memory (LSTM) approach to predict energy consumption with temporal series under various equipment working conditions. This method offers forecasting support to form a complete prediction framework for the automatic Miniature Circuit Breaker (MCB) production line, which can be used to predict the specific working condition based on attention-based LSTM approach. By comparing various prediction approaches for energy consumption under the working condition prediction with various equipment of different production line, the Fully Connected Neutral (FCN) network approach can achieve a high accuracy and effectiveness based on MAE, R2 and MSE evaluations.

Intelligent Differentiation Framework for Lewy Body Dementia and Alzheimer’s disease using Adaptive Multi-Cascaded ResNet–Autoencoder–LSTM Network

In recent years, most of the patients with dementia have acquired healthcare systems within the primary care system and they also have some challenging psychiatric and medical issues. Here, dementia-based symptoms are not identified in the primary care center, because they are affected by various factors like psychological symptoms, clinically relevant behavior, numerous psychotropic medications, and multiple chronic medical conditions. To enhance the healthcare-related applications, the primary healthcare system with additional resources like coordination with interdisciplinary dementia specialists, feasible diagnosis, and screening process need to be improved. Therefore, the differentiation between Alzheimer’s Disease (AD) and Lewy Body Dementia (LBD) has been acquired to provide the best clinical support to the patients. In this research work, the deep structure depending on AD and LBD systems has been implemented with the help of an adaptive algorithm to provide promising outcomes over dementia detection. Initially, the input images are collected from online sources. Thus, the collected images are forwarded to the newly designed Multi-Cascaded Deep Learning (MSDL), where the ResNet, Autoencoder, and weighted Long-Short Term Memory (LSTM) networks are serially cascaded to provide effective classification results. Then, the fully connected layer of ResNet is given to the Autoencoder structure. Here, the output from the encoder phase is optimized by using the Adaptive Water Wave Cuttlefish Optimization (AWWCO), which is derived from the Water Wave Optimization (WWO) and Cuttlefish Algorithm (CA), and the resultant selected output is fed to the weight-optimized LSTM network. Further, the parameters in the MSDL network are optimized by using the same AWWCO algorithm. Finally, the performance comparison over different heuristic algorithms and conventional dementia detection approaches is done for the validation of the overall effectiveness of the suggested model in terms of various estimation measures.

A maximal overlap discrete wavelet packet transform coupled with an LSTM deep learning model for improving multilevel groundwater level forecasts

Developing precise groundwater level (GWL) forecast models is essential for the optimal usage of limited groundwater resources and sustainable planning and management of water resources. In this study, an improved forecasting accuracy for up to 3 weeks ahead of GWLs in Bangladesh was achieved by employing a coupled Long Short Term Memory (LSTM) network-based deep learning algorithm and Maximal Overlap Discrete Wavelet Packet Transform (MODWPT) data preprocessing. The coupled LSTM-MODWPT model’s performance was compared with that of the LSTM model. For both standalone LSTM and LSTM-MODWPT models, the Random Forest feature selection approach was employed to select the ideal inputs from the candidate GWL lags. In the LSTM-MODWPT model, input GWL time series were decomposed using MODWPT. The ‘Fejér-Korovkin’ mother wavelet with a filter length of 18 was used to obtain a collection of scaling coefficients and wavelets for every single input time series. Model performance was assessed using five performance indices: Root Mean Squared Error; Scatter Index; Maximum Absolute Error; Median Absolute Deviation; and an a-20 index. The LSTM-MODWPT model outperformed standalone LSTM models for all time horizons in GWL forecasting. The percentage improvements in the forecasting accuracies were 36.28%, 32.97%, and 30.77%, respectively, for 1-, 2-, and 3-weeks ahead forecasts at the observation well GT3330001. Accordingly, the coupled LSTM-MODWPT model could potentially be used to enhance multiscale GWL forecasts. This research demonstrates that the coupled LSTM-MODWPT model could generate more precise GWL forecasts at the Bangladesh study site, with potential applications in other geographic locations globally.

HUBUNGAN KUALITAS TIDUR DENGAN MEMORI JANGKA PENDEK (SHORT-TERM MEMORY) PADA PELAJAR KELAS XII SMA KRISTEN BASIC BATAM

Background: : Sleep is defined as a subconscious state where a person can still be awakened by providing sensory stimulation or other stimuli. Sleep is also a form or way to relieve one's physical or mental fatigue. Sleep quality can affect brain function in concentrating and recalling knowledge storage or also called memory. Methods: The method used is Observational Analytics. The sample in this research isThere are 57 class XII students at Batam Basic Christian High School in 2023. Sampling used total sampling technique. Data collection techniques use observation and questionnaires. The data analysis technique uses Chi-Square Test. Results: There is a relationship between sleep quality and short-term memory where the results obtained are good sleep quality, there are 78.3% of respondents who have high short-term memory, 21.7% have medium short-term memory, and 0% who have low short term memory. Of respondents with poor sleep quality, 20% had high short-term memory, 36% had medium short-term memory, and 44% had low short-term memory. Conclusion: It can be concluded that there issignificant relationship between sleep quality and short-term memory in class XII students of Batam Basic Christian High School in 2023 with a p-value = 0.000.

A predictive energy management strategy for plug-in hybrid electric vehicles using real-time traffic based reference SOC planning

The fuel economy of plug-in hybrid electric vehicles (PHEVs) is strongly affected by the battery state of charge (SOC) depletion pattern. This paper proposes and studies a real-time traffic-based SOC reference planning method. The method uses a dataset to collect and capture real traffic information and then enriches the dataset using a data augmentation method developed in this paper. The augmented dataset is optimized by dynamic programing (DP) algorithm to obtain the optimal reference SOC for model training. The traffic information and optimal reference SOC are processed and used to train a long-short term memory (LSTM) neural network, which is used for online reference SOC planning. Finally, a predictive energy management (PEM) strategy is adopted to follow the SOC reference by optimizing instantaneous power allocation with the predicted velocities. Simulation results show that the proposed method outperforms the linear reference SOC planning method in both smooth and congested traffic scenarios.

Deep Learning Model for Tamil Part-of-Speech Tagging

Abstract Part-of-Speech (POS) tagging is one of the popular Natural Language Processing (NLP) tasks. It is also considered to be a preliminary task for other NLP applications such as speech recognition, machine translation, and sentiment analysis. A few works have been published on POS tagging for the Tamil language. However, the performance of the POS tagger with unknown words is not explored in the literature. The appearance of unknown words is a frequently occurring problem in POS tagging and makes it a challenging task. In this paper, we propose a deep learning-based POS tagger for Tamil using Bi-directional Long Short Term Memory (BLSTM). The performance of the POS tagger was evaluated using known and unknown words. The POS tagger with regular word-level embeddings produces 99.83 and 92.46% accuracies for all known and 63.21% unknown words. It clearly shows that the accuracy decreases when the number of unknown words increases. To improve the performance of the POS tagger with unknown words, the proposed BLSTM model that uses word-level, character-level and pre-trained word embeddings. Test results of this model show a 2.57% improvement for 63.21% of unknown words, with an accuracy of 95.03%.

Explainability in AI-based behavioral malware detection systems

Nowadays, our security and privacy are strongly threatened by malware programs which aim to steal our confidential data and make our systems out of service, among other things. While traditional signature-based malware detection methods or statistical analysis have proven to be ineffective and time-consuming, recently data-driven Artificial Intelligence (AI) techniques, i.e. Machine Learning (ML) and Deep Learning (DL) approaches, have been successfully applied leveraging the behavior of malware in terms of API calls, and achieving promising performances. However, their black-box behavior leads to a lack of explainability thus preventing their application in real world scenarios. In light of this, eXplainable Artificial Intelligence (XAI) methodologies and tools can be effectively embedded within an AI-based malware detection process in order to make more understandable the produced results. In this paper, we propose a XAI framework for behavioral malware detection problems and evaluate the usefulness of four XAI methods (SHAP, LIME, LRP and Attention mechanism) on three datasets with different size, sequence length and number of classes, by which we could evaluate the strengths and weaknesses – from effectiveness and efficiency point of views – of recurrent deep architectures (i.e. Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) models), and their applicability in the modern Cyber Security (CS) scenarios.

The intellectual disability risk gene Kdm5b regulates long term memory consolidation in the hippocampus.

The histone lysine demethylase KDM5B is implicated in recessive intellectual disability disorders and heterozygous, protein truncating variants in KDM5B are associated with reduced cognitive function in the population. The KDM5 family of lysine demethylases has developmental and homeostatic functions in the brain, some of which appear to be independent of lysine demethylase activity. To determine the functions of KDM5B in hippocampus-dependent learning and memory, we first studied male and female mice homozygous for a Kdm5b ΔARID allele that lacks demethylase activity. Kdm5b ΔARID/ΔARID mice exhibited hyperactivity and long-term memory deficits in hippocampus-dependent learning tasks. The expression of immediate early, activity-dependent genes was downregulated in these mice and hyperactivated upon learning stimulus compared to wildtype mice. A number of other learning-associated genes was also significantly dysregulated in the Kdm5b ΔARID/ΔARID hippocampus. Next, we knocked down Kdm5b specifically in the adult, wildtype mouse hippocampus with shRNA. Kdm5b knockdown resulted in spontaneous seizures, hyperactivity and hippocampus-dependent long-term memory and long-term potentiation deficits. These findings identify KDM5B as a critical regulator of gene expression and synaptic plasticity in the adult hippocampus and suggest that at least some of the cognitive phenotypes associated with KDM5B gene variants are caused by direct effects on memory consolidation mechanisms.Significance statement The histone lysine demethylase KDM5B has been implicated in cognitive performance and intellectual disability conditions in the human population. In the present manuscript we show that mice expressing a demethylase-deficient KDM5B and mice with a specific knockdown of KDM5B in the adult hippocampus exhibit hippocampus-dependent learning and memory phenotypes. Molecular analyses suggest a key role for KDM5B in regulating the dynamic expression of activity-regulated genes during memory consolidation. Deficits in LTP are present in mice with KDM5B knockdown. Together, these findings provide the first evidence for a direct function for KDM5B in memory consolidation in the hippocampus.

Masked Statement Classification in Conversational Text

Sarcasm can be really tricky for computer programs that analyze text to understand people’s feelings and opinions. This is because sarcasm involves saying something with the opposite meaning of what you actually feel, often to make fun of a situation. When computers analyze text, they focus on the words used rather than the intended meaning, which can lead to mistakes in how the text is categorized. Sarcasm also creates problems when trying to figure out the author’s true emotions in tasks like sentiment analysis. So, there is a need of a way to identify sarcasm in text and correct the sentiment it conveys. Recent studies have employed deep learning and machine learning methods to identify sarcasm. Deep learning is quite powerful, but traditional machine learning methods are still widely used and can work as well if trained properly. This study aims to compare different algorithms like Long Short Term Memory (LSTM), K-Nearest Neighbors (KNN), Computational Neural Network(CNN), and Artificial Neural Network(ANN) etc to see how well they work in sarcasm detection. The survey examined several systems and algorithms for detecting sarcasm, as well as any faults or drawbacks associated with these approaches. It also discusses various important challenges and future directions for sarcasm detection research in order to provide useful insights in this field

Human motion activity recognition and pattern analysis using compressed deep neural networks

ABSTRACT This work presents an on-device machine learning model with the ability to identify different mobility gestures called human activity recognition (HAR), which includes running, walking, squatting, jumping, and others. The data is collected through an Arduino Nano 33 BLE Sense board with a sampling rate of 119 Hz, which is embedded with an Inertial Measurement Unit (IMU) sensor. The same board is used as a microcontroller to identify human gestures by developing an end-to-end edge computing application. A deep neural network model is trained and then compressed for deployment on the board to create a self-contained, embedded device capable of identifying the type of gesture performed. Three deep learning models, namely Multi-Layer Perceptron (MLP), Convolutional Neural Network – Long Short Term Memory (CNN-LSTM) & CNN-Gated Recurrent Unit (CNN-GRU), are evaluated in the identification of the mobility gestures. The observed accuracy of the models is 96%, 97.1% and 97.8%, respectively, MLP, CNN-LSTM & CNN-GRU across the different gesture categories. The study shows the utility of embedded devices with deep neural network-based models, which can provide low cost, minimal power usage, and meet data privacy requirements in HAR.

Stress-Nets- A Novel LSTM Ensembled Single Feed Forward Layers for Stress Classification with EEG Signals

Mental instability and emotional imbalance   of the individual can be reflected in the form of stress which results  in an inappropriate work ethics.  There are various methods for the Stress creation. Moreover , several bio-signal sources such as Electroencephalograph(EEG), Electrocardiography(ECG) and Electromyography(EMG) are considered to be the important catalyst for developing the stress detection systems(SDS). Recently, machine and deep learning algorithms has gained more popularity in designing the SDS using the bio-signals. Further, EEG based SDS with ML and DL algorithms plays an important role for its high classification accuracy and performance. However, these EEG based SDS  systems needs the better lime light of improvisation in terms of  performance and computational overhead to deal with multiple datasets.  In this context, this manuscript proposes new  Long Short term Memory recurrent units(LSTM) for extracting temporal features while enhanced extreme learning machines are employed for better classification with less computational complexity. The different data sources are used to collect the EEG signals in which the collected  signals are preprocessed for evaluating the proposed model. Additionally, the experiments are performed by DEAP  and Kaggle datasets as well as performance parameters and  compared by conventional  Fused  Support vector machines (F-SVM),BI-Long Short Term Memory(BILSTM), Random Forest(RF) and  Deep Convolutional Neural network(DCNN).  Results shows which proposed EEG based SDS has better performance than other conventional  ones  of high accuracy in stress detection and for diagnosing classify the stress-levels .

Behavior classification and spatiotemporal analysis of grazing sheep using deep learning

Monitoring multiple behavioral patterns and grazing trajectories of individual sheep can provide valuable information for various aspects of livestock production. The emergence of low-cost miniature sensors, coupled with the continuous advancement of deep learning technologies, has ushered in a new generation of intelligent solutions for precision livestock farming. This study aims to explore the deployment methods of motion sensors, selection of data collection frequencies, and choice of deep learning algorithms to provide accurate classification of multiple behaviors in grazing sheep. Based on this, in conjunction with the acquired location information, the goal is to comprehend the spatiotemporal distribution of grazing sheep behaviors. Devices capable of collecting Inertial Measurement Unit (IMU) and location data were attached to the jaw, neck, and hind leg of sheep. Four datasets were created using IMU data with a frequency of 20 Hz and a 5 s time window from different positions (neck, neck & leg, jaw, jaw & leg). Two deep learning models, Convolutional Neural Network (CNN) - Long Short Term Memory (LSTM) and Temporal Convolutional Network (TCN)-Transformer, were employed to classify six grazing sheep behaviors: walking, standing, grazing, lying, standing-ruminating, and lying-ruminating. The results indicate that by fusing data from the neck- and leg-mounted devices and utilizing the CNN-LSTM model, the accuracy reached the highest at 99.3 %. Furthermore, a comparison was made regarding the behavior classification accuracy of this fused data at different IMU data frequencies (20, 10, 5, and 1 Hz). It was found that even when the data frequency was reduced to 1 Hz, the classification accuracy for the six sheep behaviors still exceeded 96 %. Additionally, the trained model with the highest accuracy was applied to monitoring grazing sheep behavior under two different management procedures. Further analysis of the time budgets of sheep behavior revealed differences in the durations of behaviors under different management procedures. For extensively grazing sheep, location information was also monitored and combined with behavior classification results to generate the spatiotemporal distribution of sheep behavior. The technologies presented are important for gaining further insights into the health status of grazing livestock and grassland, thereby enhancing grazing management practices by informing grazing choices and optimizing grassland utilization.

Privacy-protecting predictive cache method based on blockchain and machine learning in Internet of vehicles

To solve the privacy leakage problem faced by Internet of Vehicles (IoV) users when enjoying location-based services (LBS), a privacy-protecting predictive cache method based on blockchain and machine learning (BML-PPPCM) is proposed. First, a Bi-directional Long-Short Term Memory (Bi-LSTM) model is used to predict query requests over a future period based on historical request information. The predicted results are recommended to neighbors and broadcast to requestors. Then, deep Q-learning (DQN) is utilized to determine the optimal cache decision. Finally, a trust mechanism is introduced to calculate trust values, and blockchain is used to store transaction data and trust data, preventing malicious tampering by attackers. The simulation results show that BML-PPPCM has a higher cache hit ratio than other similar schemes and performs well in privacy protection and suppression of malicious and incentive denial of service providers.