Increased Training Time Research Articles

DETECTION OF NETWORK INTRUSIONS USING MACHINE LEARNING ALGORITHMS AND FUZZY LOGIC

The study proposed a model of an intrusion detection system based on machine learning using feature selection in large data sets based on ensemble learning methods. Statistical tests and fuzzy rules were used to select the necessary features. When choosing a basic classifier, the behavior of 8 machine learning algorithms was investigated. The proposed system provided a reduction in intrusion detection time (up to 60%) and a high level of attack detection accuracy. The best classification results for all studied datasets were provided by tree-based classifiers: DesignTreeClassifier, ExtraTreeClassifier, RandomForestClassifier. With the appropriate setting, choosing Stacking or Bagging classifier for model training using all data sets provides a small increase in the classification accuracy, but significantly increases the training time (by more than an order of magnitude, depending on the base classifiers or the number of data subsets). As the number of observations in the training dataset increases, the effect of increasing training time becomes more noticeable. The best indicators in terms of learning speed were provided by the VotingClassifier, built on the basis of algorithms with maximum learning speed and sufficient classification accuracy. The training time of the classifier using FuzzyLogic practically does not differ from the training time of the voting classifier (approximately 10-15% more). The influence of the number of features on the training time of the classifiers and the VotingClassifier ensemble depends on the behavior of the base classifiers. For ExtraTreeClassifier, the training time is weakly dependent on the number of features. For DesignTree or KNeibors (and, as a result, for the Voting classifier in general), the training time increases significantly with the increase in the number of features. Reducing the number of features on all datasets affects the estimation accuracy according to the criterion of average reduction of classification errors. As long as the group of features in the training dataset contains the first in the list of features with the greatest influence, the accuracy of the model is at the initial level, but when at least one of the features with a large influence is excluded from the model, the accuracy of the model drops dramatically.

STAR-RISs Assisted NOMA Networks: A Distributed Learning Approach

A novel simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) aided downlink non-orthogonal multiple access (NOMA) communication framework is proposed. Two STAR-RIS protocols are investigated, namely the energy splitting (ES) and the mode switching (MS). However, since the STAR-RIS has a massive number of reconfigurable elements, the passive beamforming problem has enormous action dimensions and extremely high complexity, resulting in an increased training time and performance degradation for the artificial intelligent agent. To resolve this predicament, a partitioning approach is proposed to divide the STAR-RIS into several tiles. A distributed learning approach is conceived for the partitioning and the corresponding tile-based passive beamforming of each STAR-RIS, as well as the power allocation for users to maximize the average throughput achieved by multiple base stations. In particular, the deep reinforcement learning (DRL) agent is employed at each BS, and an access-free federated learning (AFFL) model, which gathers the features of federated learning (FL) and transfer learning (TL) is proposed to accelerate or even exempt the training process for agents. Simulation results indicate that 1) the ES protocol is preferred for being employed in the NOMA networks compared with the MS protocol; 2) the tile-based passive beamforming approach outperforms benchmarks while the STAR-RIS has a large size; 3) the proposed AFFL framework effectively reduces or exempts the training overhead.

Standardizing and Centralizing Datasets for Efficient Training of Agricultural Deep Learning Models.

In recent years, deep learning models have become the standard for agricultural computer vision. Such models are typically fine-tuned to agricultural tasks using model weights that were originally fit to more general, non-agricultural datasets. This lack of agriculture-specific fine-tuning potentially increases training time and resource use, and decreases model performance, leading to an overall decrease in data efficiency. To overcome this limitation, we collect a wide range of existing public datasets for 3 distinct tasks, standardize them, and construct standard training and evaluation pipelines, providing us with a set of benchmarks and pretrained models. We then conduct a number of experiments using methods that are commonly used in deep learning tasks but unexplored in their domain-specific applications for agriculture. Our experiments guide us in developing a number of approaches to improve data efficiency when training agricultural deep learning models, without large-scale modifications to existing pipelines. Our results demonstrate that even slight training modifications, such as using agricultural pretrained model weights, or adopting specific spatial augmentations into data processing pipelines, can considerably boost model performance and result in shorter convergence time, saving training resources. Furthermore, we find that even models trained on low-quality annotations can produce comparable levels of performance to their high-quality equivalents, suggesting that datasets with poor annotations can still be used for training, expanding the pool of currently available datasets. Our methods are broadly applicable throughout agricultural deep learning and present high potential for substantial data efficiency improvements.

Divergence-Driven Consistency Training for Semi-Supervised Facial Age Estimation

Facial age estimation has attracted considerable attention owing to its great potential in applications. However, it still falls short of reliable age estimation due to the lack of sufficient training data with accurate age labels. Using conventional semi-supervised methods to exploit unlabeled data appears to be a good solution, but it does not yield sufficient performance gains while significantly increasing training time. Therefore, to tackle these problems, we present a Divergence-driven Consistency Training (DCT) method for enhancing both efficiency and performance in this paper. Following the idea of pseudo-labeling and consistency regularization, we assign pseudo labels predicted by the teacher model to unlabeled samples and then train the student model on labeled and unlabeled samples based on consistency regularization. Based on this, we propose two main promotions. The first is the Efficient Sample Selection (ESS) strategy, which is based on the Divergence Score to select effective samples from massive unlabeled images to reduce the training time and improve efficiency. The second is Identity Consistency (IC) regularization as the additional loss function, which introduces a high dependency of aging traits on a person. Moreover, we propose Local Prediction (LP), which is a plug-and-play component, to capture local semantics. Extensive experiments on multiple age benchmark datasets, including CACD, Morph II, MIVIA, and Chalearn LAP 2015, indicate DCT outperforms the state-of-the-art approaches significantly.

Dendrogram-based Artificial Neural Network modulation classification for dual-hop cooperative relaying communications

This paper contributes to the growing field of Artificial Neural Networks (ANNs) strategies of Automatic Modulation Identification (AMI) for Cognitive Radio (CR). Traditional AMI-based ANN methods suffer from many drawbacks such as overfitting due to ANN architectures with complex layers, low performance caused by falling into local minima, and the increased training time that keeps them from being used in real-time applications.We propose generated Dendrogram to decompose the AMI task into sub-components using the ANN architectures for improved classification accuracy and less training time. In addition, one of the most significant challenges in AMI is identifying the modulation types and orders in cooperative systems due to the combination of several received signals propagating through different unknown channels. We propose dual-hop based on Amplify and Forward protocol (DH-AF) relaying system to generate the dataset used to train and test the proposed model. In addition, DH-AF relaying systems provide better coverage and signal reliability for existing wireless communication systems. We consider that the source communicates with the destination over a direct link (S − D) and indirect link via an intermediate relay (S − R − D) using Distributed Space–Time Block Code (DSTBC). Then we used High Order Cumulants (HOC) and the High Order Moments (HOM) originating from the DSTBC-decoded signal as features, followed by the Dendrogram-based ANN (DANN) classifier. The simulation results confirm that the proposed method outperforms an ordinary ANN and other counterparts while taking less training time.

A multiscale neural network model for the prediction on the equivalent permeability of discrete fracture network

An equivalent permeability approach can upscale the discrete fracture network (DFN) model to an equivalent DFN model and significantly reduce the gas flow simulations in a large-scale fractured gas reservoir. Current equivalent permeability prediction models are only applicable to the reservoir with a simple fracture network. However, an equivalent permeability prediction model has not been available for a reservoir with a multiscale discrete fracture network. This study proposes a multiscale convolutional neural network model (called MsNet) and introduces three mainstream structures with high performance convolutional neural network (CNN) (ResNet-18, VGG-16 and GoogLeNet) to efficiently predict the equivalent permeability of a complex multiscale fracture network. These CNN models use both the images and features of DFN as their input and the equivalent permeability as their output. This MsNet model is validated with the simulation results simulated by Lattice Boltzmann method and compared with the three mainstream CNN structures and an existing permeability prediction model (CNN-4). It is found that this MsNet model innovatively considers the multiscale characteristics of DFN by a multiscale convolution feature fusion and combines the residual connection for further performance enhancement. Both DFN dataset and MsNet model structure affect the model prediction ability. A deeper network structure of MsNet model can enhance its prediction ability, but significantly increases training time. The MsNet-8-4 (a MsNet structure with 8 multiscale connection modules and 4 sub-networks in each module) has the least convergence time and the lowest mean absolute error on the test set. It performs obviously better than other four models on the DFN dataset with higher fracture density. The MsNet model can well accelerate the simulation on the gas flow in a complex discrete fracture network.

An evidence-based approach to assessing the effectiveness of training regimen on athlete performance: Youth soccer as a case study.

Athletic performance data are modeled in an effort to better understand the relationship between both hours spent training and a measurement of "commitment" to that training, and improvements in performance. Both increased training time and greater commitment were predicted to produce larger increases in performance improvement, and commitment was predicted to be the more important determinant of improvement. The performance of 108 soccer players (ages 9-18) was quantified over a 10-week training program. Hours spent training ranged from 16 to 90 during the course of the study, while commitment scores ranged from 0.55 to 2.00, based on a scale from 0.00 to 2.40. A model selection approach was used to discriminate among models specifying relationships between training hours and improvement, and commitment and improvement. Despite considerable variability in the data, results provided strong evidence for an increase in performance improvement with both training hours and commitment score. The best models for hours and commitment were directly compared by computing an evidence ratio of 5799, indicating much stronger evidence favoring the model based on commitment. Results of analyses such as these go beyond anecdotal experience in an effort to establish a formal evidentiary basis for athletic training programs.

Deep Learning: Predicting Environments From Short-Time Observations of Postural Balance.

This study introduces a deep learning approach to accurately predict challenging mechanical environments that possibly cause decreasing postural stability. Dual-axis robotic platforms were utilized to simulate various environments and collect center-of-pressure data during narrow and wide stance. A convolutional neural network (CNN) was developed to predict environmental conditions given segmented time-series balance data. Different window sizes were examined to investigate its minimal length for reliable prediction. Effectiveness of the presented CNN was additionally compared with that of conventional machine learning models. Its applicability with low sampled data or more natural stance data was then evaluated. The CNN achieved above 94.5% in the overall prediction accuracy even with 2.5-second length postural sway data, which cannot be achieved by traditional machine learning (ps < 0.05). Increasing data length beyond 2.5 seconds slightly improved the accuracy of CNN but substantially increased training time (60% longer). Importantly, results from averaged normalized confusion matrices revealed that CNN is much more capable of differentiating the mid-level environmental condition. Deep learning could also produce comparable performance in predicting environments even with much lower sampled data or with standing posture changed. CNN removed the burden of feature preparation and accurately predicted environments when dealing with short-length data. It also indicated potentials to real life applications. This study contributes to the advancement of wearable devices and human interactive robots (e.g., exoskeletons and prostheses) by predicting environmental contexts and preventing potential falls.

Derin Öğrenme Modellerinin Doğruluk, Süre ve Boyut Temelli Ödünleşme Değerlendirmesi

Machine Learning and especially deep learning models need to be optimized over three main criteria concurrently, to be operationalized in real-time field applications. These criteria are model’s accuracy, training-testing times and file size. Related work only considers two criteria (e.g. accuracy-time) together. However, it is observed that deep neural networks (DNN) designed to improve model accuracy can increase training time and size, while efforts to reduce model size can lead to lower accuracy. A trade-off needs to be made among these three criteria. In this paper, to demonstrate the effects of different optimization techniques on model performance, we tested ResNet50, ResNet101, VGG16, VGG19, EfficientNet pre-trained models with CIFAR10, CIFAR100 image datasets, which are commonly utilized in the DNN research field. Important performance results obtained over Google Colab Pro and TensorFlow system show that weight quantization is the most successful technique so far in multi-dimensional optimization, while weight clustering and transfer learning techniques remain useful in 2-dimensions. In addition, we designed and tested a new DNN operational score and model-to-model layer transfer method for the first time in literature. We hope that our framework will constitute a multi-dimensional evaluation reference for DNN models before they are operationalized.

Qualitative Research on the Training Experiences and Needs of Intensive Care Unit General Nurses Against the Background of Regular Coronavirus Disease 2019 Prevention and Control.

ObjectiveThis study aimed to investigate the training experiences and needs of intensive care unit (ICU) general nurses against a background of regular Coronavirus disease (COVID-19) prevention and control.MethodsUsing the phenomenological method of qualitative research, semi-structured interviews were conducted with 10 ICU nurses. The interview data were analyzed, sorted, summarized, and refined using the content analysis method.ResultsThe following five themes were extracted from the interviews, based on the training experiences of the nurses: 1) broadening their thinking; 2) discovering their personal shortcomings; 3) gaining self-confidence; 4) calmly facing frontline work; 5) experiencing high assessment pressure. The training needs of the nurses could be summarized into the following four themes: 1) increased training time; 2) improving the assessment mechanism; 3) establishing a normal rotating-shift training system; 4) balancing the teaching levels.ConclusionAgainst a background of regular epidemic prevention and control, ICU training for general nurses is of high practical significance and value. Thus, active exploration and research should be conducted to establish perfect training and assessment mechanisms for these nurses. Additionally, training methods that are suitable for clinical needs should be formulated and training systematization and standardization must be promoted.

Brain Decoding Using fMRI Images for Multiple Subjects through Deep Learning.

Substantial information related to human cerebral conditions can be decoded through various noninvasive evaluating techniques like fMRI. Exploration of the neuronal activity of the human brain can divulge the thoughts of a person like what the subject is perceiving, thinking, or visualizing. Furthermore, deep learning techniques can be used to decode the multifaceted patterns of the brain in response to external stimuli. Existing techniques are capable of exploring and classifying the thoughts of the human subject acquired by the fMRI imaging data. fMRI images are the volumetric imaging scans which are highly dimensional as well as require a lot of time for training when fed as an input in the deep learning network. However, the hassle for more efficient learning of highly dimensional high-level features in less training time and accurate interpretation of the brain voxels with less misclassification error is needed. In this research, we propose an improved CNN technique where features will be functionally aligned. The optimal features will be selected after dimensionality reduction. The highly dimensional feature vector will be transformed into low dimensional space for dimensionality reduction through autoadjusted weights and combination of best activation functions. Furthermore, we solve the problem of increased training time by using Swish activation function, making it denser and increasing efficiency of the model in less training time. Finally, the experimental results are evaluated and compared with other classifiers which demonstrated the supremacy of the proposed model in terms of accuracy.

Privacy-Preserving Collaborative Computation for Human Activity Recognition

Human Activity Recognition (HAR) enables computer systems to assist users with their tasks and improve their quality of life in rehabilitation, daily life tracking, fitness, and cognitive disorder therapy. It is a hot topic in the field of machine learning, and HAR is gaining more attention among researchers due to its unique societal and economic advantages. This paper focuses on a collaborative computation scenario where a group of participants will securely and collaboratively train an accurate HAR model. The training process requires collecting a massive number of personal activity features and labels, which raises privacy problems. We decentralize the training process locally to each client in order to ensure the privacy of training data. Furthermore, we use an advanced secure aggregation algorithm to ensure that malicious participants cannot extract private information from the updated parameters even during the aggregation phase. Edge computing nodes have been introduced into our system to address the problem of data generation devices’ insufficient computing power. We replace the traditional central server with smart contract to make the system more robust and secure. We achieve the verifiability of the packaged nodes using the publicly auditability feature of blockchain. According to the experimental data, the accuracy of the HAR model trained by our proposed framework reaches 93.24%, which meets the applicability requirements. The use of secure multiparty computation techniques unavoidably increases training time, and experimental results show that a round of iterations takes 36.4 seconds to execute, which is still acceptable.

BiInNet: Bilateral Inversion Network for Real-Time Velocity Analysis

Most previous studies focus on using complex deep neural networks to learn diverse features of massive synthetic data. In more realistic situations with a limited number of data pairs, complex networks not only have higher computational complexity, increasing training time and reducing inference speed, but also tend to over-fit a small amount of training data, thus having weak generalization capability. To address the aforementioned problem, we propose a lightweight architecture for real-time velocity inversion in realistic situations, the bilateral inversion network (BiInNet). BiInNet uses lightweight ResNet18, ShuffleNetV2, and modified MobileNetV2 as backbones, taking into account the inversion accuracy and inference speed. To reduce the redundant information in common shot gathers and focus on graphical property features which are strongly correlated with velocity, the intermediate results of velocity analysis, semblances, and interval velocity models are prepared as data pairs. Numerical experiments show that BiInNet can infer interval velocity models in real-time, with frames per second (FPS) up to 76.90 when ResNet18 is used as the backbone. Moreover, BiInNet achieves the best inversion accuracy on more realistic fold models, fault models, salt models, and noisy dataset (NFOMD) when adopting ShuffleNetV2 as the backbone, which illustrates that BiInNet can be applied to velocity inversion tasks of different geological structures and is robust to noise. Adopting transfer learning to fine-tune pretrained model, BiInNet is effectively applicable to velocity reversal models and field data, which further demonstrates the reliability of the proposed method and provides a practical velocity inversion scheme when the field data pairs are insufficient.

Deep Neural Networks-Based Weight Approximation and Computation Reuse for 2-D Image Classification

Deep Neural Networks (DNNs) are computationally and memory intensive, which present a big challenge for hardware, especially for resource-constrained devices such as Internet-of-Things (IoT) nodes. This paper introduces a new method to improve DNNs performance by fusing approximate computing with data reuse techniques for image recognition applications. First, starting from the pre-trained network, then the DNNs weights are approximated based on the linear and quadratic approximation methods during the retraining phase to reduce the DNN model size and number of arithmetic operations. Then, the DNNs weights are replaced with the linear/quadratic coefficients to execute the inference so that different DNNs weights can be computed using the same coefficients. That leads to a repetition of the weights, which enables the reuse of the DNN sub-computations (computational reuse) and leverages the same data (data reuse) to reduce DNNs computations memory accesses, and improve energy efficiency, albeit at the cost of increased training time. Complete analysis for MNIST, Fashion MNIST, CIFAR 10, CIFAR 100, and tiny ImageNet datasets is presented for image recognition, where different DNN models are used, including LeNet, ResNet, AlexNet, and VGG16. Our results show that the linear approximation achieves <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1211.3\times $ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$21.8\times $ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$700\times $ </tex-math></inline-formula> , and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$19.3\times $ </tex-math></inline-formula> on LeNet-5 MNIST, LeNet Fashion MNIST, VGG16 and ResNet-20. respectively, with small accuracy loss. Compared to the state-of-the-art Row Stationary (RS) method, the proposed architecture saved 54% of the total number of adders and multipliers needed. Overall, the proposed approach is suitable for IoT edge devices as it reduces computing complexity, memory size, and memory access with a small impact on accuracy.

A FULLY BAYESIAN GRADIENT-FREE SUPERVISED DIMENSION REDUCTION METHOD USING GAUSSIAN PROCESSES

Modern day engineering problems are ubiquitously characterized by sophisticated computer codes that map parameters or inputs to an underlying physical process. In other situations, experimental setups are used to model the physical process in a laboratory, ensuring high precision while being costly in materials and logistics. In both scenarios, only limited amount of data can be generated by querying the expensive information source at a finite number of inputs or designs. This problem is compounded further in the presence of a high-dimensional input space. State-of-the-art parameter space dimension reduction methods, such as active subspace, aim to identify a subspace of the original input space that is sufficient to explain the output response. These methods are restricted by their reliance on gradient evaluations or copious data, making them inadequate to expensive problems without direct access to gradients. The proposed methodology is gradient-free and fully Bayesian, as it quantifies uncertainty in both the low-dimensional subspace and the surrogate model parameters. This enables a full quantification of epistemic uncertainty and robustness to limited data availability. It is validated on multiple datasets from engineering and science and compared to two other state-of-the-art methods based on four aspects: a) recovery of the active subspace, b) deterministic prediction accuracy, c) probabilistic prediction accuracy, and d) training time. The comparison shows that the proposed method improves the active subspace recovery and predictive accuracy, in both the deterministic and probabilistic sense, when only few model observations are available for training, at the cost of increased training time.

Exploration on Automatic Management of GIS Using TL-CNN and IoT

The research aims to effectively monitor the state of complex industrial equipment in real time, diagnose the internal Partial Discharge (PD) pattern of Gas Insulated Metal Enclosed Switchgear (GIS), implement effective health management, and change the traditional model optimization route of increasing training time in exchange for performance improvement. This paper studies the complex equipment-oriented Health Management System (HMS) based on Internet of Things (IoT) technology and Transfer Learning. Firstly, the principles of Transfer Learning and Deep Learning (DL) technology are introduced. Secondly, the requirements of GIS internal status recognition and management are studied. Furthermore, a GIS-oriented HMS based on Transfer Learning-optimized Convolutional Neural Networks (CNN) is proposed, and the training dataset is constructed. Finally, the proposed model is tested. The results show that the complex equipment-oriented HMS based on IoT technology, CNN, and Transfer Learning can detect the internal status of GIS in real time. Compared with the traditional DL algorithm and expert system, the proposed model has a shorter training time of only 16min, faster convergence speed, high testing recognition rate, and over 96% recognition rate. Compared with other mainstream algorithms, it has higher identification, the storage parameter volume is 408, and the storage space is 12.8MB. Moreover, the proposed Transfer Learning-optimized CNN model can accurately detect the status of GIS, identify abnormal statuses, and help prolong the service life of GIS. The proposed complex equipment-oriented HMS contributes to the intelligent manufacturing industry and provides a new direction for applying emerging Computer Technology in the intelligent industry.

Depression Detection on COVID 19 Tweets Using Chimp Optimization Algorithm

The Covid-19 outbreak has an unprecedented effects on people's daily lives throughout the world, causing immense stress amongst individuals owing to enhanced psychological disorders like depression, stress, and anxiety. Researchers have used social media data to detect behaviour changes in individuals with depression, postpartum changes and stress detection since it reveals critical aspects of mental and emotional diseases. Considerable efforts have been made to examine the psychological health of people which have limited performance in accuracy and demand increased training time. To conquer such issues, this paper proposes an efficient depression detection framework named Improved Chimp Optimization Algorithm based Convolution Neural Network–Long Short Term Memory and Natural Language Processing for Covid-19 Twitter data. In the proposed method, the tweets are pre-processed, user's frequent tweet identification, and hash tag identification has been done. The processed tweets are then clustered through cluster head selection using Swap-Displacement-Reversion-Bull based Optimization Algorithm and cluster formation using the Bregman distance-based K-Means algorithm. Then, the psycholinguistic features are extracted from the clustered data and inputted to the Improved Chimp Optimization Algorithm-based-Convolution Neural Network-Long Short Term Memory network for depression classification. Preliminary results show that the proposed method provides greater performance with 97.7% efficiency and outperforms the existing methodologies.

Learning deficits occurs prior to memory retrieval impairment in female Senescence Accelerated Mouse (SAMP8)

AbstractBackgroundThe most regularly used mouse models of Alzheimer's disease in drug development include APP/PS1, 3xTg, and 5xFAD mice. This is a limitation as all these mice represent familial AD. Given sporadic AD accounts for the majority of the AD cases in human, there is an unmet need to validate potential rodent models to better represent sporadic AD. SAMP8 is a naturally‐occurring mouse line that displays many characteristics identified in Alzheimer’s disease (AD) patients, such as learning and memory deficits, and accumulation of beta‐amyloid. In people with preclinical AD, deficits in learning manifest faster than decline in memory retrieval. It is unclear if SAMP8 mice also exhibit this feature, and therefore the current study aims to determine if this feature can be observed in SAMP8, to support the use of SAMP8 as a mouse model of sporadic AD for drug development.MethodThe cognitive function of SAMP8 mice and their age‐matched non‐AD control SAMR1 mice (at various ages) were assessed using Y maze spatial memory test, with 3‐10 min training duration and 1.5‐3 h interval between training and testing session.ResultAt 3‐4 months old, SAMP8 but not SAMR1 failed to differentiate the novel arm from familiar arm in a standard Y maze test (3 min training, 3 h interval). When training time was increased to 10 min, SAMP8 passed the test, while increased training time did not affect the performance of SAMR1 mice. These data indicated that longer training time is required by SAMP8 than SAMR1 to achieve the expected performance, suggesting the presence of learning deficits in SAMP8. Interestingly, at 6‐7 months old, though both SAMP8 and SAMR1 received 10‐min training, only SAMR1 passed the test. The performance of SAMP8 mice was successfully improved by shortening the interval between training and testing (from 3 h to 1.5 hr). These data indicate a deteriorated memory retention capability and a possible impairment in memory retrieval in SAMP8.ConclusionOverall, this study has provided supportive evidence that learning deficits occurs prior to memory retrieval impairment in SAMP8, and the use of SAMP8 as mouse model for AD.

Autonomous Vehicle Path Planning using Q-Learning

Path planning is vital in autonomous vehicle technology, from robots to self-driving cars and driverless trucks, it is impossible to navigate without a proper path planning algorithm, various algorithms exist Q-learning being one of them. Q-learning is used extensively in discrete applications as it is effective in finding solutions to these problems. This research investigates the possibility of using Q-learning for solving the local path planning problem with obstacle avoidance. Q-learning is split into two phases, the first being the training phase, and the second being the application phase. During training, Q-learning requires exponentially increasing training time based on the system’s state space. However, when Q-learning is applied it becomes as simple as a lookup table which allows it to run on even the simplest microcontrollers. Two simulations are conducted with varying environments. One to showcase the ability to learn the optimal path, the other to showcase the ability for learning navigation in variable environments. The first simulation was run on a static environment with one obstacle, with enough training episodes, Q-learning could solve the path planning problem with minimal movement steps. The second simulation focuses on a randomized environment, obstacles and the agent’s starting position are randomly chosen at the start of every episode. During testing, Q-learning was able to find a path to the target when a path did exist, as It was possible in certain configurations for the vehicle to be stuck in between obstacles with no feasible path or solution.

Comparison of Standard and Pretrained CNN Models for Potato, Cotton, Bean and Banana Disease Detection

Plant diseases lead to a significant decrease in product efficiency and economic losses for producers. However, early detection of plant diseases plays an important role in preventing these losses. Today, Convolutional Neural Network (CNN) models are widely used for image processing in many fields such as face recognition, climate, health, and agriculture. But in these models, the weights of the layers are randomly initialized during training, which increases training time and decreases performance. With the method known as Transfer Learning in the literature, CNN models are trained on large databases such as ImageNet. Then, pretrained CNN models are created using the weights obtained in this training. Thus, training time decreases while performance improves. In this study, standard and pretrained versions of popular CNN models DarkNet-19, GoogleNet, Inception-v3, Resnet-18, and ShuffleNet have been used for automatic classification of diseases from leaf images of potato, cotton, bean, and banana. In the experimental study, the classification performances of all these standard and pretrained CNN models are presented comparatively. Experimental results have shown that the performance of CNN models is significantly improved by transfer learning, even in a small number of epochs.