Due to the intermittency and fluctuation of photovoltaic (PV) output power, a high proportion of grid-connected PV power generation systems has a significant impact on power systems. Accurate PV power forecasting can alleviate the uncertainty of the PV power and is of great significance for the stable operation and scheduling of the power systems. Therefore, in this study, a feature rise-dimensional (FRD) two-layer ensemble learning (TLEL) model for short-term PV power deterministic forecasting and probability forecasting is proposed. First， based on the eXtreme Gradient Boosting (XGBoost), Random Forest (RF), CatBoost, and Long-short-term memory (LSTM) models, a TLEL model is constructed utilizing the ensemble learning algorithm. Meanwhile, the FRD method is introduced to construct the FRD-XGBoost-LSTM (R-XGBL), FRD-RF-LSTM(R-RFL), and FRD- CatBoost - LSTM (R-CatBL) models. Subsequently, the above models are combined to construct the FRD-TLEL model for deterministic forecasting, and perform probability interval forecasting based on quantile regression(QR). Finally, the performance of the proposed model is demonstrated with a real-world dataset. By comparing with other models, the proposed model displays better forecasting accuracy for deterministic forecasting and reliable forecasting intervals for probability forecasting, and good generalization ability in the datasets of different seasons and weather types.

In this paper, we identify several relative ordering properties of the modified proportional hazard rate and modified proportional reversed hazard rate models. For this purpose, we use two well-known relative orderings, namely the relative hazard rate ordering and the relative reversed hazard rate ordering. The investigation is to see how a relative ordering between two possible base distributions for the response distributions in these models is preserved when the parameters of the underlying models are changed. We will give some examples to illustrate the results and the conditions under which they are obtained.

In recent years, applying deep learning to solve physics problems has attracted much attention. Data-driven deep learning methods produce operators that can learn solutions to the whole system of partial differential equations. However, the existing methods are only evaluated on simple flow equations (e.g., Burger's equation), and only consider the generalization ability on different initial conditions. In this paper, we construct CFDBench, a benchmark with four classic problems in computational fluid dynamics (CFD): lid-driven cavity flow, laminar boundary layer flow in circular tubes, dam flows through the steps, and periodic Karman vortex street. Each flow problem includes data with various boundary conditions, fluid physical properties, and domain geometries. Compared to existing datasets, the advantages of CFDBench are (1) comprehensive. It contains common physical parameters such as velocity, pressure, and cavity fraction. (2) realistic. It is very suitable for deep learning solutions of fluid mechanics equations. (3) challenging. It has a certain learning difficulty, prompting to find models with strong learning ability. (4) standardized. CFDBench facilitates a comprehensive and fair comparison of different deep learning methods for CFD. We make appropriate modifications to popular deep neural networks to apply them to CFDBench and enable the accommodation of more changing inputs. The evaluation on CFDBench reveals some new shortcomings of existing works and we propose possible directions for solving such problems.

Previous studies to recognize negative emotions (e.g. disgust, fear, sadness) for mental health care have used heavy equipment directly attaching electroencephalogram (EEG) electrodes to the head, making it difficult to use in daily life, and they have proposed binary classification methods to determine whether negative emotion or not. To tackle this problem, we propose a negative emotion recognition system to collect multimodal biosignal data such as five EEG signals in an EEG headset and heart rate, galvanic skin response, and skin temperature in a smart band for classifying multiple negative emotions. It consists of android Internet of Things (IoT) application, an oneM2M-compliant IoT server, and a machine learning server. The android IoT application upload the biosignal data to the IoT server. By using the biosignal data stored in the IoT server, the machine learning server recognizes the negative emotions of disgust, fear, and sadness using a multi-class support vector machine (SVM) model with a radial basis function kernel (RBF). The experimental results showed that the multi-class SVM model achieved 93% accuracy when considering all the multimodal biosignal data. Moreover, when considering only data in the smart band, it could achieve 98% accuracy by optimizing the hyper-parameter of the RBF kernel.

Microsoft has implemented several measures to defend against macro viruses, including the use of Anti-malware Scan Interface (AMSI) and automatic macro blocking. Nevertheless, evidence shows that threat actors have found ways to bypass these mechanisms. As a result, phishing emails continue to apply malicious macros as their essential attack vector. In this paper, we analyze 77 obfuscation features from the attacker’s point of view and extract 46 suspicious keywords in macro. We first combine the above two types of features to train machine learning models on a public dataset. Then, we carry out the same experiment on self-constructed dataset, a collection of newly discovered samples, to see if our proposed method could discover the unseen malicious macros. Experimental results demonstrate that, comparing with the existing researches, our proposed method has a higher detection rate and better consistency. Furthermore, ensemble multi-classifiers with distinct feature selection further improve the detection performance.

RBF networks are used in a variety of real-world applications such as medical data or signal processing problems. The success of these parametric models lies in the successful adaptation of their parameters using efficient computational techniques. In the current work, a method of adjusting the parameters of these networks using Grammatical Evolution is presented. Grammatical Evolution will be used to successfully discover the most promising range of parameter values and then the training of the parameter set will be achieved using a Genetic Algorithm. The new method was applied to a wide range of data fitting and classification problems, and the results were more than promising.

Generative artificial intelligence (AI), in particular large language models such as ChatGPT have reached public consciousness with a wide-ranging discussion of their capabilities and suitability for various professions. Following the printing press and internet, generative AI language models are the third transformative technological invention with truly cross-sectoral impact on knowledge transmission. While the printing press allowed for the transmission of knowledge that is independent of the physical presence of the knowledge holder with publishers acting as gatekeepers, the internet added levels of democratization allowing anyone to publish, along with global immediacy. The development of social media resulted in an increased fragmentation and tribalization of on-line communities on their ways of knowing, resulting in alternative truths propagated in echo chambers. It is against this background that generative AI language models have entered public consciousness. Using strategic foresight methodology, this paper will examine the polemic proposition that the age of generative AI will emerge as an age of public ignorance.

In 1937,German mathematician L.Collatz proposed the following conjeture:for any positive integer,if it is even,divide it by 2,if it is odd,multiply it by 3 and add 1 to get an even number.Continuing with the above rule, the final result will be 1.This paper gives a proof of this conjecture.

We assume that the current mathematical knowledge K is a finite set of statements in the public domain which is time-dependent. This set exists only theoretically. Ignoring K and its subsets, sets exist formally in ZFC theory although their properties can be time-dependent (when they depend on K) or informal. In every branch of mathematics, the set of all knowable truths is the set of all theorems. This set exists independently of K. Algorithms always terminate. We explain the distinction between algorithms whose existence is provable in ZFC and constructively defined algorithms which are currently known. By using this distinction, we obtain non-trivial statements on decidable sets X⊆N that belong to constructive and informal mathematics and refer to the current mathematical knowledge on X. This and the next sentence justify the article title. For any empirical science, we can identify the current knowledge with that science because truths from the empirical sciences are not necessary truths but working models of truth from a particular context. For a set X⊆N whose infiniteness is false or unproven, we define which elements of X are classified as known. No known set X⊆N satisfies Conditions (1)-(4) and is widely known in number theory or naturally defined, where this term has only informal meaning. (1) A known algorithm with no input returns an integer n satisfying card(X)<ω ⇒ X⊆(-∞,n]. (2) A known algorithm for every k∈N decides whether or not k∈X. (3) No known algorithm with no input returns the logical value of the statement card(X)=ω. (4) There are many elements of X and it is conjectured, though so far unproven, that X is infinite. (5) X is naturally defined. The infiniteness of X is false or unproven. X has the simplest definition among known sets Y⊆N with the same set of known elements. We prove that the set X={n∈N: the interval [-1,n] contains more than 29.5+(11!/(3n+1))∙sin(n) primes of the form k!+1} satisfies Conditions (1)-(5) except the requirement that X is naturally defined. 501893∈X. Condition (1) holds with n=501893. card(X∩[0,501893])=159827. X∩[501894,∞)={n∈N: the interval [-1,n] contains at least 30 primes of the form k!+1}. If we add to X some set W satisfying 14≤card(W)≤23, then the following statements hold: X does not satisfy Condition (1), 159827+14≤card(X), the above lower bound is currently the best known, card(X)<ω ⇒ card(X)≤159827+23, the above upper bound is currently the best known, X satisfies Conditions (2)-(5) except the requirement that X is naturally defined. We present a table that shows satisfiable conjunctions of the form #(Condition 1)∧(Condition 2)∧#(Condition 3)∧(Condition 4)∧#(Condition 5), where # denotes the negation ¬ or the absence of any symbol. No set X⊆N will satisfy Conditions (1)-(4) forever, if for every algorithm with no input, at some future day, a computer will be able to execute this algorithm in 1 second or less.

A novel verifiable privacy preservation scheme for outsourcing medical image to cloud through ROI based crypto-watermarking is proposed in the paper. In the proposed scheme, data owner firstly carries out substitution of S-box for the region of interest (ROI) of medical image, and then separates the image into 4 most significant bits (MSBs) plane and 4 least significant bits (LSBs) plane images. Secondly, the hash value of ROI is embedded into the two separated bit plane images using reversible watermarking algorithm. Lastly, some selected hash values are transformed into the initial parameters of chaotic maps, and the two sharing secrets, which are produced through chaos based encryption algorithm, are finally outsourced to two different cloud servers. For authorized users, they can get shares from different cloud servers, and then can losslessly recover the original medical image through a series of decryption operations and extraction of watermarking. Furthermore, the users can verify whether the original image is completely reconstructed or not, they even can locate the tampered parts inside ROI if anyone of the sharing secrets is damaged. Some experiments analyses and comparisons are given to show the security and effectiveness of proposed scheme.

Drone navigation is critical, particularly during the initial and final phases, such as the initial ascension, where pilots may fail due to strong external disturbances that could lead to a crash. In this ongoing work, a drone has been successfully trained to perform an ascent of up to 6 meters with external disturbances simulating wind pushing it up to 24 mph, with the DQN algorithm managing external forces affecting the system. It has been demonstrated that the system can control its height, position, and stability in all three axes (roll, pitch, and yaw) throughout the process. The learning process is carried out in the Gazebo simulator, which emulates interferences, while ROS is used to communicate with the agent.

Abstract:The objects of fine-grained image categories(e.g., bird species) are various subclass under different categories. Because the differences between subclass are very subtle and most of them are concentrated in multiple local areas, the task of fine-grained image recognition is very challenging. At the same time, some fine-grained networks tend to focus on a certain region when judging the target category, resulting in the lack of other auxiliary regional features. To this end, Inception V3 is used as the backbone network, and an enhanced and complementary fine-grained image classification network is designed. While adopting the method of reinforcement learning to obtain more detailed fine grain image features, the complementary network can obtain the complementary discriminant area of the target through the method of attention erasure to increase the network's perception of the overall target. Finally, experiments are conducted on CUB-200-2011, FGVC Aircraft and Stanford dogs three open datasets. The experimental results show that the proposed model has better performance.

X-ray free electron lasers deliver photon pulses that are bright enough to observe diffraction from extremely small crystals, at a time scale outrunning their destruction. As crystals are continuously replaced, this technique is termed serial femtosecond crystallography (SFX). Due to its high pulse repetition rate, the European XFEL enables the collection of rich and extensive data sets, suited to study various scientific problems including ultrafast processes. The enormous data rate, data complexity, and the nature of the pixelized multi-modular area detectors at European XFEL pose severe challenges to users. To streamline the analysis of SFX data, we developed the semi-automated pipeline EXtra-Xwiz around the established CrystFEL program suite, processing diffraction patterns on detector frames into structure factors. Here we present EXtra-Xwiz, and introduce its architecture and use by means of a tutorial. Future plans for its development and expansion are also discussed.

Sign language recognition is essential in hearing-impaired people’s communication. Sign language recognition is an important concern in computer vision and has been developed with rapid progress in image recognition technology. However, sign language recognition using a general monocular camera has problems with occlusion and recognition accuracy in sign language recognition. In this research, we aim to improve accuracy by using a 2-axis bending sensor as an aid in addition to image recognition. We aim to achieve higher recognition accuracy by acquiring hand keypoint information of sign language actions captured by a monocular RGB camera and adding sensor assist. To improve sign language recognition, we need to propose new AI models. In addition, the amount of dataset is small because it uses the original data set of our laboratory. To learn using sensor data and image data, we used MediaPipe, CNN, and BiLSTM to perform sign language recognition. MediaPipe is a method for estimating the skeleton of the hand and face provided by Google. In addition, CNN is a method that can learn spatial information, and BiLSTM can learn time series data. Combining the CNN and BiLSTM methods yields higher recognition accuracy. We will use these techniques to learn hand skeletal information and sensor data. Additionally, the 2-axis Bending sensor glove data support training AI model. Using these methods, we aim to improve the recognition accuracy of sign language recognition by combining sensor data and hand skeleton data. Our method performed better than using skeletal information, achieving 96.5% accuracy in Top-1.

To address the deficiency of existing relation extraction models in effectively extracting relational triplets pertaining to railway traffic knowledge in Tibet, this paper constructs a Tibet Railway Traffic text dataset and provides an enhanced relation extraction model. The proposed model incorporates subject feature enhancement and relational attention mechanisms. It leverages a pre-trained model as the embedding layer to obtain vector representations of text. Subsequently, the subject is extracted and its semantic information is augmented using an LSTM neural network. Furthermore, during object extraction, the multi-head attention mechanism enables the model to prioritize relations associated with the aforementioned features. Finally, objects are extracted based on the subjects and relations. The proposed method has been comprehensively evaluated on multiple datasets, including the Tibet Railway Traffic text dataset and two public datasets. The results on the Tibet dataset achieves an F1-score of 93.3\%, surpassing the baseline model CasRel by 0.8\%, indicating a superior applicability of the proposed model. On the other hand, the model achieves F1-scores of 91.1\% and 92.6\% on two public datasets, NYT and WebNLG, respectively, outperforming the baseline CasRel by 1.5\% and 0.8\%, which highlights the good generalization ability of the proposed model.

Build a special identical equation, use its calculation characters to prove and search for solution of any odd converging to 1 equation through (*3+1)/2^k operation, change the operation to (*3+2^m-1)/2^k, and get a solution for this equation, give a specific example to verify. Thus prove the Collatz Conjecture is true. Furthermore, analysis the sequences produced by iteration calculation during the procedure of searching for solution, build a weight function model, prove it decrease progressively to 0, build a complement weight function model, prove it increase to its convergence state. Build a (*3+2^m-1)/2^k odd tree, prove if odd in (*3+2^m-1)/2^k long huge odd sequence can not converge, the sequence must outstep the boundary of the tree after infinite steps of (*3+2^m-1)/2^k operation.

The technical capabilities of modern Industry 4.0 and Industry 5.0 are rather vast and growing exponentially daily. The present-day Industrial Internet of Things (IIoT) combines manifold underlying technologies that require real-time interconnections and communications among heterogeneous devices. Smart cities are established with sophisticated designs and control for seamless Machine-to-Machine (M2M) communication to optimize resources, costs, performances, and energy distribution. All the sensory devices within a building interact to maintain a sustainable climate for residents and intuitively optimize the energy distribution to optimize energy production. However, it encompasses quite a few challenges for devices that lack compatible and interoperable designs. Conventional solutions are restricted to limited domains or rely on engineers to design and deploy translators for each pair of ontologies. This is a costly process in terms of engineering efforts and computational resources. The issue persists that a new device with a different ontology must be integrated into an existing IoT network. We propose a self-learning model that can determine the taxonomy of devices given their ontology meta-data and structural information. The model finds matches between two distinct ontologies using the Natural Language Processing (NLP) approach for learning linguistic contexts. Then, by visualizing the ontology network as a knowledge graph, it is possible to learn the structure of the meta-data and understand the device's message formulation. Finally, it can align entities of both ontology graphs similar in context and structure. Furthermore, the model performs dynamic M2M translation without requiring extra engineering or hardware efforts.

Requirements Engineering (RE) is an important step in the whole software development lifecycle. The problem in RE is to determine the class of the software requirements as functional and non-functional. Proper and early identification of these requirements is vital for the entire development cycle. On the other hand, manual government of requirement classes is a timewasting task, and it needs intensive effort. Automatic requirement classification techniques through advanced Machine Learning (ML) strategies are started to be developed to address this problem. Basically, software requirements are generated as natural language explanations and therefore requirement classification may be handled as a particular Natural Language Processing (NLP) problem. From ML point of view, classification strategies require dataset to be used in the training/learning phase. For this goal, we generated a unique Turkish dataset having collected the requiremenst from real-world software projects with 4600 samples. Of these requirements, 3000 and 1600 were labeled as functional and non-functional, respectively. The data set has been evaluated using (i) traditional machine learning algorithms, (ii) deep learning algorithms, and (iii) transformer models respectively. As a result BERTurk was found to be the most successful algorithm to discriminate functional and non-functional requirements in terms of 95% f-score metric.

The E-learning system has achieved great development after the pandemic. In this work, we proposed three artificial intelligence-based enhancements to our linguistic interactive E-learning system from different aspects. Compared with the original phonetic transcription exam system, our enhancements include an MFCC+CNN-based disordered speech classification module, a Transformer-based Grapheme-to-Phoneme converter, and a Tacotron2-based IPA-to-Speech speech synthesis system. This work not only provides a better experience for the users of this system but also explores the utilization of artificial intelligence technologies in the E-learning field and linguistic field.

The need to find the global minimum in multi-dimensional functions is a critical problem in many fields of science and technology. Effectively solving this problem requires the creation of initial solution estimates, which are subsequently used by the optimization algorithm to search for the best solution in the solution space. In the context of this article, a novel approach to generating the initial solution distribution is presented which is applied to a genetic optimization algorithm. Using the k-means clustering algorithm, a distribution based on data similarity is created. This helps in generating initial estimates that may be more tailored to the problem. Additionally, the proposed method employs a rejection sampling algorithm to discard samples that do not yield better solution estimates in the optimization process. This allows the algorithm to focus on potentially optimal solutions, thus improving its performance. Finally, the article presents experimental results from the application of this approach to various optimization problems, providing the scientific community with a new method for addressing this significant problem.

One of the most leading causes of death worldwide is Colorectal cancer(CRC). Polyp segmentation is the most important detected measure for preventing CRC. However, there is still a missing rate for diminutive polyps and multiple ones. In order to solve the phenomenon, we propose to introduce auxiliary attention module(AAM) that can enhance the learning of features related to multiple and diminutive polyps by focusing more on the located and detailed information. Meanwhile, we design to decrease missed rate of multiple and diminutive polyps by implementing an area adaptive loss(AAL) which adapts the weight according to the area and the number of polyps. Our proposed novel AAM and AAL concentrates on training with hard examples and localized information. To evaluate the effectiveness and generalization ability of our proposed model, We utilize three different datasets of variable sizes and a cross dataset. Our proposed method achieves the best results on the Kvasir-SEG dataset, the CVC-ClinicDB dataset and the cross dataset, particularly for the Kvasir-Sessile dataset consisting of small,flat and diminutive polyps. Extensive experimental results show that our proposed DoubleAANet surpass the performance of all existing state-of-the-art segmentation methods.

. In this paper, we introduce a series of definitions of generalized affine functions for vector-valued functions. We prove that our generalized affine functions have some similar properties with generalized convex functions. We present examples to show that our generalized affinenesses are different from one another, and also provide an example to show that our definition of presubaffinelikeness is non-trivial; presubaffinelikeness is the weakest generalized affineness introduced in this article. We work with optimization problems that are defined and taking values in linear topological spaces. We devote to the study of constraint qualifications, and derive some optimality conditions as well as a strong duality theorem. Our optimization problems have inequality constraints, equality constrains and abstract constraints; our inequality constraints are generalized convex functions and equality constraints are generalized affine functions.

Social media platforms are not serving only as tools of communication rather they are acting like intricate systems managing our interactions. A major setback to our interactions occur when the flow of information in these networks gets distorted through polarization. It resembles a society where every debate turns into divide. Our research focuses exclusively on quantifying polarization as well as solving this issue head-on. In order to accurately gauge polarization, we’ve developed a new method that takes into consideration majority of its influencing factors. This helps us in correctly quantifying the polarization value of a given network and then by proposing it as an optimization problem we are attempting to maximally decrease polarization while staying within the set budget. We test our method on synthetic and real-world data sets, and find out that polarization is declining, and diversity is increasing. This proves that our recommendation engine has a penchant for finding the ideal connections between the nodes to start a dialogue. Our research presents a successful tactic to quantifying and reducing polarization in social media networks. The results indicate that our novel metric and intervention technique are effective in dismantling echo chambers, thereby promoting diversity in these networks.

Facial emotion detection is a challenging task that deals with emotion recognition. It has applications in various domains, such as behavior analysis, surveillance systems and human-computer interaction (HCI). Numerous studies have been implemented to detect emotions, including classical machine learning algorithms and advanced deep learning algorithms. For the machine learning algorithm, the hand-crafted feature needs to be extracted, which is a tiring task and requires human effort. Whereas in deep learning models, automated feature extraction is employed from samples. Therefore, in this study, we have proposed a novel and efficient deep learning model based on Neural Architecture Search Network utilizing superior artificial networks such as RNN and child networks. We performed the training utilizing the FER 2013 dataset comprising seven classes: happy, angry, neutral, sad, surprise, fear, and disgust. Furthermore, we analyzed the robustness of the proposed model on CK+ datasets and comparing with existing techniques. Due to the implication of reinforcement learning in the network, most representative features are extracted from the sample network. It extracts all key features without losing the key information. Our proposed model is based on one stage classifier and performs efficient classification. Our technique outperformed the existing models attaining an accuracy of 98.14%, recall of 97.57%, and precision of 97.84%.

Accurate and efficient medicinal plant image classification is of utmost importance as these plants produce a wide variety of bioactive compounds that offer therapeutic benefits. With a long history of medicinal plant usage, different parts of plants, such as flowers, leaves, and roots, have been recognized for their medicinal properties and are used for plant identification. However, leaf images are extensively used due to their convenient accessibility and are a major source of information. In recent years, transfer learning and fine-tuning, which use pre-trained deep convolutional networks to extract pertinent features, has emerged as an extremely effective approach for image identification problems. This study is leveraging the power of three component deep convolutional neural networks, namely VGG16, VGG19 and DenseNet201, to derive features from the input images of the medicinal plant dataset, containing leaf images of 30 classes. The models were compared and ensembled to make four hybrid models to enhance the predictive performance by utilizing the averaging and weighted averaging strategies. Quantitative experiments were carried out to evaluate the models on the Mendeley medicinal leaf dataset. The resultant ensemble of VGG19+DensNet201 with fine-tuning showcases enhanced capability in identifying medicinal plant images with an improvement of 7.43% and 5.8% compared with VGG19 and VGG16. Furthermore, VGG19+DensNet201 can outperform its standalone counterparts by achieving an accuracy of 99.12% on the test set. A thorough assessment with metrics such as accuracy, recall, precision, and f1-score firmly establishes the effectiveness of the ensemble strategy.

In this paper, new types of M-fractional wave solutions of mathematical physics model named as truncated M-fractional (1+1)-dimensional non-linear simplified Modified Camassa-Holm model are achieved by applying the modified simplest equation (MSE), Sardar sub-equation and generalized Kudryashov techniques. The gained solutions containing dark, bright, periodic and mixed wave solitons. Effect of fractional order derivative is also discussed. Achieved wave solitons are verified by Mathematica tool. Few of the gained wave solitons are also described through 2-dimensional, 3-dimensional and contour graphs through Mathematica tool. The gained solutions are helpful for the further development of concerned model. Finally, these techniques are simple, fruitful and effective to deal with non-linear FPDEs.

Cellular automata are mathematical models that represent systems with complex behavior through simple interactions between their individual elements. These models can be used to study unconventional computational systems and complexity. One notable aspect of cellular automata is their ability to create structures known as gliders, which move in a regular pattern to represent the manipulation of information. This paper introduces the modification of mean-field theory applied to cellular automata, using random perturbations based on the system’s evolution rule. The original aspect of this approach is that the perturbation factor is tailored to the nature of the rule, altering the behavior of the mean-field polynomials. By combining the properties of both the original and perturbed polynomials, it is possible to detect when a cellular automaton is more likely to generate gliders without having to run evolutions of the system.This methodology is a useful approach to finding more examples of cellular automata that exhibit complex behavior. We start by examining elementary cellular automata, then move on to examples of automata that can generate gliders with more states. To illustrate the results of this methodology, we provide evolution examples of the detected automata.

Eight lesions were analyzed using some algorithms of Intelligence Artificial: basal cell carcinoma (BCC), squamous cell carcinoma (SCC), melanoma (MEL), actinic keratosis (AK), benign keratosis (BKL), dermatofibromas (DF), melanocytic nevi (NV), and vascular lesions (VASC). This manuscript presents the possibility of using concatenated signatures (instead of images) obtained from different integral transforms, such as Fourier, Mellin, and Hilbert, to classify skin lesions. Eleven other Artificial Intelligence models were applied so that eight skin lesions could be classified by analyzing the particular signatures of each lesion. The database was randomly divided into 80%–20% for the training and test datasets images, respectively. The metrics that are being reported are accuracy, sensitivity, specificity, and precision. Each case was repeated 30 times to avoid bias, according to the central limit theorem in this work, and the average and ±standard deviation were reported. Although all the results were very satisfactory, the best average mark for the eight lesions analyzed was obtained using the Subspace KNN model, where the metrics for the test were 99.98% accuracy, 99.96% sensitivity, 99.99% specificity, and 99.95% precision.

This study proposes a short- and medium-term electricity consumption prediction algorithm by combining the GRU model suitable for long-term forecasting and the Prophet model suitable for seasonality and event handling. (1) Manufacturing Company B's Electricity consumption data and meteorological data in Naju, Jeollanam-do, South Korea are collected and preprocessed. (2) The preprocessed data proposes the Prophet model in the first step for seasonality and event handling prediction. (3) In the second step, seven multivariate data are experimented with GRU. Specifically, the seven multivariate data consist of six meteorological data and the residuals between the predicted data from the proposed Prophet model in Step 1 and the observed data. These are utilized to predict electricity consumption at 15-minute intervals. (4) Electricity consumption is predicted for short-term (2 days and 7 days) and medium-term (15 days and 30 days) scenarios. The experimental results demonstrate that the proposed method outperforms the conventional Prophet model by more than 23 times and the modified GRU model by more than 2 times in terms of MAPE.

Speech Emotion Recognition (SER) is an interesting and difficult problem to handle. In this paper, we deal with it through the implementation of deep learning networks. We have designed and implemented six different deep learning networks, a Deep Belief Network (DBN), a simple deep neural network (SDNN), a LSTM network (LSTM), a LSTM network with the addition of an attention mechanism (LSTM-ATN), a Convolutional neural network (CNN), and a Convolutional neural network with the addition of an attention mechanism (CNN-ATN), having in mind, apart from solving the SER problem, to test the impact of attention mechanism to the results. Dropout and Batch Normalization techniques are also used to improve the generalization ability (prevention of overfitting) of the models as well as to speed up the training process. The Surrey Audio-Visual Expressed Emotion database (SAVEE), and the Ryerson Audio-Visual Database (RAVDESS) database were used for training and evaluation of our models. The results showed that networks with the addition of the attention mechanism did better than the others. Furthermore, they showed that CNN-ATN was the best among tested networks, achieving an accuracy of 74% for the SAVEE and 77% for the RAVDESS dataset, and exceeded existing state-of-the-art systems for the same datasets.

Given a fuzzy normed space $ \left( X,N \right) $‎, ‎we will introduce the notion of fuzzy near best approximation within a relative distance $ \rho \geq 0 $‎. ‎Some basic properties are characterized and also many examples for illustration are presented‎.

The two main strategies used in this study are the binary representation and the decomposition of a natural number into many compound functions of odd function and even function. The Collatz conjecture regarding odd even numbers in number theory can be examined and discussed using them in this way: The sequence created by the finite iterations of the Collatz function becomes the ultimately periodic sequence if any natural number is the beginning value, proving the conjecture that has been held for 85 years.

The relative position of the orchard robot to the rows of fruit trees is an important parameter for achieving autonomous navigations. The current methods for estimating the position parameters between rows of orchard robots obtain low parameter accuracy, and to address this problem, this paper proposes a machine vision-based method for detecting the relative position of orchard robots and fruit tree rows. Firstly, the fruit tree trunk is identified based on the improved YOLOv4 model; secondly, the camera coordinates of the tree trunk are calculated from the principle of binocular camera triangulation, and the ground projection coordinates of the tree trunk are obtained through coordinate conversion; finally, the midpoints of the projection coordinates of different sides are combined and the navigation path is obtained by linear fitting with the least squares method, and the position parameters of the orchard robot are obtained through calculation. The experimental results show that the average accuracy and average recall of the improved YOLOv4 model for fruit tree trunk detection are 97.05% and 95.42%, respectively, which are 5.92 and 7.91 percentage points higher than those of the original YOLOv4 model. The average errors of heading angle and lateral deviation estimates obtained based on the method in this paper are 0.57° and 0.02 m. The method can accurately calculate heading angle and lateral deviation values at different positions between rows, and can provide a reference for autonomous visual navigation of orchard robots.

In recent years, Neural networks are increasingly deployed in various fields to learn complex patterns and make accurate predictions. However, designing an effective neural network model is a challenging task that requires careful consideration of various factors, including architecture, optimization method, and regularization technique. This paper aims to comprehensively overview the state-of-the-art artificial neural network (ANN) generation and highlight key challenges and opportunities in machine learning applications. It provides a critical analysis of current neural network model design methodologies, focusing on the strengths and weaknesses of different approaches. Also, it explores the use of different learning approaches, including convolutional neural networks (CNN), deep neural networks (DNN), and recurrent neural networks (RNN) in image recognition, natural language processing, and time series analysis. Besides, it discusses the benefits of choosing the ideal values for the different components of ANN, such as the number of Input/output layers, hidden layers number, activation function type, epochs number, and model type selection, which help improve the model performance and generalization. Furthermore, it identifies some common pitfalls and limitations of existing design methodologies, such as overfitting, lack of interpretability, and computational complexity. Finally, it proposes some directions for future research, such as developing more efficient and interpretable neural network architectures, improving the scalability of training algorithms, and exploring the potential of new paradigms, such as Spiking Neural Networks, quantum neural networks, and neuromorphic computing.

We investigate properties of strongly useful topologies, i.e. topologies with respect to which every weakly continuous preorder admits a continuous order-preserving function. In particular, we prove that a topology is strongly useful provided that the topology generated by every family of separable systems is countable. Focusing on normal Hausdorff topologies, whose consideration is fully justified and not restrictive at all, we show that strongly useful topologies are hereditarily separable on closed sets, and we identify a simple condition under which the Lindelöf property holds.

This paper presents a two-stage hierarchical neural network using image classification and object detection algorithms as key building blocks for a system that automatically detects a potential design right infringement. This neural network is trained to return the Top-N original design right records that highly resemble the input image of a counterfeit. Design rights specify the unique aesthetic characteristics of a product. Due to the rapid change of trends, new design rights are continuously generated. This work proposes an Ensemble Neural Network (ENN), an artificial neural network model that aims to deal with a large amount of counterfeit data and design right records that are frequently added and deleted. At first, we performed image classification and objection detection learning per design right using the existing models with a proven track record of high accuracy. The distributed models form the backbone of the ENN and yield intermediate results aggregated at a master neural network. This master neural network is a deep residual network paired with a fully connected network. This ensemble layer is trained to determine the sub-models that return the best result for a given input image of a product. In the final stage, the ENN model multiples the inferred similarity coefficients to the weighted input vectors produced by the individual sub-models to assess the similarity between the test input image and the existing product design rights to see any sign of violation. Given 84 design rights and the sample product images taken meticulously under various conditions, our ENN model achieved average Top-1 and Top-3 accuracies of 98.409% and 99.460%, respectively. Upon introducing new design rights data, a partial update of the inference model was done an order of magnitude faster than the single model. ENN maintained a high level of accuracy as it scaled out to handle more design rights. Therefore, the ENN model is expected to offer practical help to the inspectors in the field, such as the customs at the border that deal with a swarm of products.

Let $(\Omega, \mu)$, $(\Delta, \nu)$ be measure spaces. Let $(\{f_\alpha\}_{\alpha\in \Omega}, \{\tau_\alpha\}_{\alpha\in \Omega})$ and $(\{g_\beta\}_{\beta\in \Delta}, \{\omega_\beta\}_{\beta\in \Delta})$ be unbounded continuous 1-Schauder frames for a Banach space $\mathcal{X}$. Then for every $x \in ( \mathcal{D}(\theta_f) \cap\mathcal{D}(\theta_g))\setminus\{0\}$, we show that \begin{align}\label{UB} \mu(\operatorname{supp}(\theta_f x))\nu(\operatorname{supp}(\theta_g x)) \geq \frac{1}{\left(\displaystyle\sup_{\alpha \in \Omega, \beta \in \Delta}|f_\alpha(\omega_\beta)|\right)\left(\displaystyle\sup_{\alpha \in \Omega , \beta \in \Delta}|g_\beta(\tau_\alpha)|\right)}. \end{align} where \begin{align*} &\theta_f:\mathcal{D}(\theta_f) \ni x \mapsto \theta_fx \in \mathcal{L}^1(\Omega, \mu); \quad \theta_fx: \Omega \ni \alpha \mapsto (\theta_fx) (\alpha):= f_\alpha (x) \in \mathbb{K},\\ &\theta_g: \mathcal{D}(\theta_g) \ni x \mapsto \theta_gx \in \mathcal{L}^1(\Delta, \nu); \quad \theta_gx: \Delta \ni \beta \mapsto (\theta_gx) (\beta):= g_\beta (x) \in \mathbb{K}. \end{align*} We call Inequality (\ref{UB}) as \textbf{Unbounded Donoho-Stark-Elad-Bruckstein-Ricaud-Torr\'{e}sani Uncertainty Principle}. Along with recent \textbf{Functional Continuous Uncertainty Principle} (derived in [arXiv:2308.00312v1 [math.FA], 1 August 2023]), Inequality (\ref{UB}) also improves Ricaud-Torr\'{e}sani uncertainty principle \textit{[IEEE Trans. Inform. Theory, 2013]}. In particular, it improves Elad-Bruckstein uncertainty principle \textit{[IEEE Trans. Inform. Theory, 2002]} and Donoho-Stark uncertainty principle \textit{[SIAM J. Appl. Math., 1989]}.

To avoid loss of information and incorrect ranking, this paper proposes a method for ranking generalized fuzzy numbers, which guarantees both horizontal and vertical values are important parameters affecting the final ranking score. In this method, the normalized height coefficient is introduced to evaluate the influence of the height of fuzzy numbers on the final ranking score. The higher the normalized height coefficient of a fuzzy number is, the higher its ranking. The left area and the right area are presented to calculate the impact of vertical value on the final ranking score. The left area is considered the benefit area. The right area is considered the cost area. The fuzzy number is preferred if the benefit area is larger and the cost area is smaller. The proposed method can be employed to rank both normal and non-normal fuzzy numbers without normalization or height minimization. Numerical examples and comparison with other methods highlight the feasibility and robustness of the proposed method, which can overcome the shortcomings of some existing methods and can support decision-makers to select the best alternative.

Weak contact metric structures on a smooth manifold, introduced by V. Rovenski and R. Wolak in 2022, have provided new insight into the theory of classical structures. In this paper, we define new structures of this kind (called weak nearly Sasakian and weak nearly cosymplectic and nearly K\"{a}hlerian structures) and study their geometry. We introduce weak nearly K\"{a}hlerian manifolds (generalizing nearly K\"{a}hlerian manifolds) and characterize weak nearly Sasakian and weak nearly cosymplectic hypersurfaces in such Riemannian manifolds.

This article obtains data through questionnaire survey, and then uses the Multiple Indicators Multiple Causes (MIMIC) Model to establish the Taoyuan City’s quality of life quantifying framework in a city-level community context. Statistical test results show that the reliability of overall model is high and is suitable for policy analysis. There are thirteen variables in the structural model that significantly affect the quality of life as well as eleven indicators in the measurement model that can significantly measure the quality of life. Then, half of the observations are substituted back to calculate the quality of life. Via ArcGis operation, it finds that the quality of life of Longtan District is the best as well as Dayuan District is the worst one. LISA cluster of quality of life illustrates hot spots areas are distributed in Longtan, Daxi, and Pingzhen Districts.

Autism Spectrum Disorder (ASD) is a neuro developmental condition that impacts social interac-tion, communication, and behavior. It is called a spectrum because its symptoms and degrees of severity can vary greatly from one person to the next. Differentiations in brain structure and function have been observed between autistic and typically developing brains. Various aspects of brain function, including information processing, sensory perception, and the capacity to interpret and respond to social cues, may be affected by these differences. The signs and symptoms of ASD are readily apparent to parents in the first few years of their child’s life. The symptoms of ASD, it is said, first appear in early childhood and continue into maturity. Brain MRI analysis utilizing deep learning methods show encouraging findings in the study of ASD. In this study, we look at how well a customized VGG16 architecture compares models that have already been trained. Inception v3, ResNet50, DenseNet121, and MobileNet are used to identify and analyze ASD problems in a brain MRI dataset from people with ASD. The proposed methods have been vali-dated on the unlabeled ABIDE 1 dataset that is freely available to the public. After the unlabeled data has been clustered, five different Deep Learning (DL) methods are used and compared. The results are compared to those of other studies that have already been conducted.

In this paper, we analyze the convergence of a finite difference method with the implicit forward time central space (FTCS) scheme for solving the three-dimensional advection-diffusion-reaction equation (ADRE). It is proved that the method is unconditionally convergent. We apply the scheme to obtain numerical solutions for the transport of pollutants in street tunnel problems with various reaction coefficients and various rates of change of concentrations of sources or sinks of pollution.

Vehicle re-identification research under surveillance cameras has yielded impressive results. However, the challenge of Unmanned Aerial Vehicle (UAV)-based vehicle re-identification (ReID) presents a high degree of flexibility, mainly due to complicated shooting angles, occlusions, low discrimination of top-down features, and significant changes in vehicle scales. To address this, we propose a novel Dual Mixing Attention Network (DMANet) to extract discriminative features robust to variations in viewpoint. Specifically, we first present a plug-and-play Dual Mixing Attention Module (DMAM) to capture pixel-level pairwise relationships and channel dependencies, where DMAM is composed of Spatial Mixing Attention (SMA) and Channel Mixing Attention (CMA). First, the original feature is divided according to the dimensions of spatial and channel to obtain multiple subspaces. Then, a learnable weight is applied to capture the dependencies between local features in the mixture space. Finally, the features extracted from all subspaces are aggregated to promote their comprehensive feature interaction. Moreover, the DMAM can be readily inserted into backbone networks at any depth to improve vehicle discrimination. The experiments show that the proposed structure gains a better performance compared with the representative methods in the UAV-based vehicle ReID task. Our code and models will be publicly released.

This research highlights the importance of error-correcting codes in ensuring secure and efficient data transmission over noisy channels. It discusses the application of Convolutional codes and the Viterbi algorithm for error detecting and correcting in applications where the data rate is high and the error probability is relatively low. This research extends beyond previous studies by conducting a comparative analysis of Convolutional codes, the Viterbi algorithm, and alternative coding methods utilized in satellite communication systems, by evaluating their effectiveness and efficiency relative to other coding approaches like BCH, LDPC, and turbo codes. The evaluation encompasses key performance metrics including error correction capabilities, computational complexity, and robustness against various error types. Additionally, practical implementation factors such as power consumption, computational requirements, and compatibility with existing hardware are considered. The analysis sheds light on the advantages and disadvantages of each coding method, offering insights into why convolutional codes and the Viterbi algorithm are particularly suitable for GPS systems.

Due to a shortage of funding and other market challenges, Small and Medium-sized Enterprises (SMEs) have a tough time adopting new technologies. Numerous technological obstacles nega-tively impact the long-term commercial achievement of SMEs. The deployment of Industry 4.0 might resolve several technological challenges. A sustainable city is a difficult structure whose economical, societal, and ecological components interact and compete with one another. There is a dearth of actual methodologies for measuring interaction. The objective of Industry 4.0 is to obtain a better degree of performance effectiveness and profitability, and greater automation. Conse-quently, the purpose of the research is to determine the influence of Industry 4.0 in fostering economic efficiency in small and medium enterprises' sustainability. A Sustainable City using Multi-Criteria Decision Making (SC-MCDM) system is designed in this research to test and achieve sustainable developmental goals. This paper then gives a technique for calculating the interaction between various standards, such as static interactions and dynamical pattern resemblance, as well as the weight variables of every indication generated by the connection. Furthermore, the ap-plication of the suggested technique is proved by assessing the sustainable development goals of twelve Chinese cities within the Triple Bottom Line (TBL) paradigm. From a geographic-temporal viewpoint, spatial variations in city sustainability reveal regional inequalities in sustainability. Indicator scores suggest that the lack of research spending, falling financing in stationary assets, shortage of financial development, and inadequate shared transit are the most significant limiting factors for most communities. Furthermore, the growth of tertiary industries, the improvement of energy performance, the expansion of green areas, and the reduction of pollution emissions are the key driving forces for enhancing sustainability. Compared to other methodologies, Multi-Criteria Decision Making (MCDM) considers the interplay between conditions, which is an excellent way to assess the sustainability of a city. The experimental findings show the impact of MCDM and sustainability to achieve sustainable development goals.

Fish feeding behavior analysis plays a critical role in aquaculture, marine fisheries, and ecological monitoring. At present, the accuracy of current fish feeding behavior analysis is easily affected by the environment, and the hypoxia state in water and high temperature have a huge impact on behavior. In addition, the poor stability, and the speed is affected by the calculation amount of the model, so it cannot be applied to aquaculture ponds. In order to solve the above problems, we propose an improved RepVGG-based method for fish feeding behavior analysis to identify nine behavioral states of fish populations, including hypoxia, hot, and normal states of none, medium, and strong feeding. Firstly, our method adds the identity and residual branches to the block of the VGG network, focusing on the acceleration operation to ensure accuracy. At the same time, the Efficient Channel Attention (ECA) module is added to reduce dimensionality to balance speed and accuracy. To evaluate the effectiveness of the method, it is validated on a constructed fish feeding behavior dataset and compared with a Convolutional Neural Network (CNN) including AlexNet, VGG16, ResNet34, MobileNet V3, and RepVGG. The experimental results show that after 15 epochs of training, the average precision of proposed method reached 97%. Compared with the basic classification algorithm, our method can increase by at least 3% while the inference speed exceeds 85 Frames Per Second (FPS). This study can be integrated into the aquaculture vision system to guide users to plan feeding strategies, and provide new ideas and methods for water quality monitoring.

Our natural language approach concerns syntactic analysis using a dedicated Javascript library - wink-nlp - and semantic analysis based on Prolog programming language, facilitated by another Javascript library - tau-prolog - that allows defining logical programs, declaring rules and checking for goals inside Javascript language. Firstly, our program splits the original text into sentences, than into tokens and identifies each part of the sentence, dynamically maps entities into Prolog rules, then check the spelling accordingly to the Definite Clause Grammar (DCG) by querying the pre-defined program for initial goals (the sentence itself). Basically, we let the parser infer its own rules from the syntactic point of view, then check the grammar from a semantic perspective against the DCG inside the same work flow or pipeline of steps.The provided article combine the usage of wink-nlp and tau-prolog packages for natural language processing (NLP) and understanding (NLU), demonstrates the need of a supplementary logic layer based on beta reductions and provide a method to convert lambda abstractions into arrow Javascript functions.

Data Extraction is a technique is called as clustering which is used to retrieve data either from the files or data bases or both. This paper focuses on the performance evaluation parameters of the clustering algorithms based on different parameters or conditions or constraints and parameters which are used to perform the clustering process to get the clusters on the data sets. Therefore best clusters are retrieved when best parameters or conditions or constraints or preferences which are applied on the data sources for the clustering process. These parameters or conditions or constraints are opted by the user called as user preferences.

In this research a neccessary and sufficient condition for the proof of the Binary Goldbach conjecture is established. It is established that the square of all natural numbers greater or equal to 2 have an additive partition equal to the sum of the square of a natural number greater or equal to zero and a Goldbach partition semiprime. All Goldbach partition semiprimes are odd except 4. This finding is in itself proof all composite even numbers have at least Goldbach partition. The result of the proof of the Binary Goldbach conjecture is used to prove the Andrica and Legendre conjectures. The Riemann hypothesis is examined and sources of non trivial zeroes outside the critical strip are discussed. An example example of a non-trivial zero outside the critical strip is given

Static and dynamic analysis of website security risks is generally used for website security meas-urements. The website security measurements method recently proposed includes similarity hash-based website security risk analysis and machine learning-based website security risk anal-ysis. In this study, a method that can be performed through information disclosed on the Internet was proposed to measure the risk of a website. DNS information, IP information, and website history information are required to measure the risk of a website. In addition, global traffic rank-ing, malicious code distribution history, and HTTP access status can be checked in the website history information. In this study, information related to the security risk of websites in a total of 2,000 domains was collected and analyzed in 1,000 normal and malicious domains. Through the experiment results, 11 open information collection items were selected to measure the security risk of the website. This study presented the possibility of using public information collection to measure website security risk.

Deep sky observation is a fascinating activity, but it requires favourable conditions in order to be fully appreciated. Complex equipment, light pollution around urban areas, lack of contextual information often prevents newcomers from making the most of their observations, restricting the field to a niche expert audience. In this paper, we show how combining the usage of smart telescopes with eXplainable Artificial Intelligence makes the practice of astronomy even more accessible and educative, and how it has been applied during outreach sessions In Luxembourg Greater Region.

The flour milling industry, a vital component of global food production, is undergoing a transformative phase driven by the integration of smart devices and advanced technologies. This transition promises improved efficiency, quality, and sustainability in flour production. Accurate estimation of protein, moisture and ash content in wheat grains and flour is of paramount importance due to their direct impact on product quality and compliance with industry standards. This paper explores the application of Near-Infrared (NIR) spectroscopy as a non-destructive, efficient, and cost-effective method for measuring the aforementioned essential parameters in wheat and flour, by investigating the effectiveness of a low-cost handle NIR spectrometer. Furthermore, a novel approach using Fuzzy Cognitive Maps (FCMs) is proposed to estimate protein, moisture and ash content in grain seeds and flour, marking the first known application of FCMs in this context. Our study includes an experimental setup that assesses different types of wheat seeds and flour samples and evaluates three NIR pre-processing techniques to enhance parameter estimation accuracy. The results indicate that low-cost NIR equipment can contribute to the estimation of the under-study parameters.

Due to the inclusion of both the principles and divination methods, the study of Yijing (Yijing) becomes more complex. The complex data types, diverse semantic relationships, and unclear influencing mechanisms in Yijing pose challenges to its scientific research. Knowledge graph, as an advanced way of organizing knowledge, can provide technical support in exploring the hidden connections and knowledge structure within text resources. This paper proposes a method of constructing a Yijing knowledge graph based on Neo4j. By analyzing the concepts, entities, and various related relationships in Yijing, the method discusses the basic architecture, data model, and implementation steps of constructing the Yijing knowledge graph. It also extracts, integrates, and structures the Yijing knowledge, allowing for inquiries, associations, and reasoning about the knowledge and its various elements. By adopting a top-down approach, the paper reconstructs the fundamental knowledge system of the Yijing, including yin-yang, the five elements, generation and restriction, 64 hexagrams, and six lines(yao). It establishes a knowledge graph pattern layer and a data layer that encompass concepts, attributes, and relationships. With the technical support of the Neo4j platform, the visualization and retrieval of Yijing knowledge are realized, providing new ideas and methods for studying the mechanisms of the Yijing. The proposed method of constructing a Yijing knowledge graph can be expanded to other types of ancient scripture knowledge graph research and can be applied to the field of digital humanities, promoting in-depth cross-disciplinary research and integration.

Purpose To alleviate the data imbalance problem caused by subjective and objective reasons, scholars have developed different data preprocessing algorithms, among which undersampling algorithms are widely used because of their fast and efficient performance. However, when the number of samples of some categories in a multi-classification dataset is too small to be processed by sampling, or the number of minority class samples is only 1 to 2, the traditional undersampling algorithms will be weakened. Methods This study selects 9 multi-classification time series datasets with extremely few samples as the objects, fully considers the characteristics of time series data, and uses a three-stage algorithm to alleviate the data imbalance problem. Stage one: Random oversampling with disturbance items increases the number of sample points; Stage two: On this basis, SMOTE (Synthetic Minority Oversampling Technique) oversampling; Stage three: Using dynamic time warping distance to calculate the distance between sample points, identify the sample points of Tomek Links at the boundary, and clean up the boundary noise.Results This study proposes a new sampling algorithm. In the 9 multi-classification time series datasets with extremely few samples, the new sampling algorithm is compared with four classic undersampling algorithms, ENN (Edited Nearest Neighbours), NCR (Neighborhood Cleaning Rule), OSS (One Side Selection) and RENN (Repeated Edited Nearest Neighbours), based on macro accuracy, recall rate and F1-score evaluation indicators. The results show that: In the 9 datasets selected, the dataset with the most categories and the least number of minority class samples, FiftyWords, the accuracy of the new sampling algorithm is 0.7156, far beyond ENN, RENN, OSS and NCR; its recall rate is also better than the four undersampling algorithms used for comparison, at 0.7261; its F1-score is increased by 200.71%, 188.74%, 155.29% and 85.61%, respectively, relative to ENN, RENN, OSS, and NCR; In the other 8 datasets, this new sampling algorithm also shows good indicator scores.Conclusion The new algorithm proposed in this study can effectively alleviate the data imbalance problem of multi-classification time series datasets with many categories and few minority class samples, and at the same time clean up the boundary noise data between classes.

We consider a stochastic production planning problem with regime switching. There are k≥1 regimes corresponding to different economic cycles. The problem is to minimize the production costs and analyze the problem by the value function approach. Our main contribution is to show that the optimal production is characterized by an exact solution of an elliptic system of partial differential equations. A verification result is given for the determined solution.

Smart grid capabilities have grown significantly in recent years. The smart grid provides advanced real-time handling of faults, advanced automatic control for efficient electricity transmission, monitoring and collection of the electrical system's capacity, and communication for information sharing. Unfortunately, its exposure to public networks makes it increasingly vulnerable to privacy breaches, vulnerabilities, and cyber-attacks. Cyber security threats and vulnerabilities in smart grid networks have become a primary concern that needs to be addressed before deploying a smart grid. Furthermore, the wide range of protocols increases the attack surface of a smart grid. This study focuses on the vulnerability of Modbus, which is regarded as one of the most prevalent protocols in smart grid communication networks. This paper presents preliminary findings of analyzing cyber-attacks against the Modbus protocol using a virtual testbed to investigate its effects on the smart grid network protocol. The concept incorporates an emulated Modbus/TCP network environment built from open-source software components that imitate fundamental industrial control features of the smart grid. Finally, we analyze the cycle of a cyber-attack leading through Reconnaissance to a DoS attack on the Modbus/TCP protocol and propose improvements to the test bed for protocol attack detection and mitigation.

In recent years, graph neural networks (GNNs) have become a promising method for analyzing data structured in graph format. By considering connections between entities in a graph, GNNs are able to extract valuable insights. One notable variation of GNN is the graph attention network (GAT), which employs the attention mechanism and has demonstrated promising performance in various applications. However, its ability to incorporate feature information from nodes beyond the immediate neighborhood is limited, leading to degraded performance on heterophilic data. To address this limitation, this thesis proposes a novel attention-based model, namely the Directional Graph Attention Network (DGAT). This model combines the feature-based attention with the global directional information extracted from the graph topology, as inspired by the Directional Graph Network (DGN). A new class of Laplacian matrices is proposed and an existing theoretical result on DGN is extended. This extension bridges a gap in the literature. The experimental results presented in the thesis, based on nine real-world benchmarks and ten synthetic data sets, demonstrate the superiority of the proposed DGAT model compared to the GAT baseline model. Particularly on heterophilic data sets, DGAT showed a notable average increase of approximately 35% in node classification tasks across all heterophilic real-world data sets. In addition, DGAT outperforms GAT by an average margin of around 51% in all ten synthetic data sets with various levels of heterophily

This paper presents a novel approach for individual design perception modeling using the YUKI-trained Fuzzy Inference System. The study focuses on understanding how individuals perceive design based on personality traits, particularly openness to experience. The proposed YUKI algorithm optimizes the FCM clustering algorithm, enhancing its ability to handle uncertain and imprecise data. The YUKI-trained FIS generates several Sugeno-type FIS models to predict design perception, to minimize the Root Mean Squared Error between the model prediction and the actual design perception of participants. The results demonstrate that the YUKI-trained FIS offers more accurate predictions compared to the traditional FCM-trained FIS, and the RMSE values for individual design perceptions fall within a satisfactory range of 0.84 to 1.32. The YUKI-trained FIS proves effective in clustering individuals based on their level of openness, providing insights into how personality traits influence design perception.

Abstract: The two-dimensional Fuzzy Transform was applied in image compression. The quality of the image compressed with this methodis better than that obtained using methods based on fuzzy relation equations and comparable with that of the JPEG method, with better compression execution times. In this paper we propose a variation of the method based on the two-dimensional Fuzzy Transform of image compression, in which the image is first partitioned into blocks and then each block is compressed with the higher compression rate. The advantage of this method consistsinto a greater compression of the image, guaranteeing a high quality of the reconstructed image.The results show that our method is better than the Fuzzy Transform method improving also the quality of the reconstructed image.

We prove that a diffeological space is diffeomorphic to the categorical join of any generating family of plots.

In this paper, we continue the research cycle on the properties of convolutional neural network-based image recognition systems and ways to improve noise immunity and robustness [1]. Currently, a popular research area related to artificial neural networks is adversarial attacks. The effect of adversarial attacks on the image is not highly perceptible to the human eye, also it drastically reduces the neural network accuracy. Image perception by a machine is highly dependent on the propagation of high frequency distortions throughout the network. At the same time, a human efficiently ignores high-frequency distortions, perceiving the shape of objects as a whole. The approach proposed in this paper can improve the image recognition accuracy in the presence of high-frequency distortions, in particular, caused by adversarial attacks. The proposed technique makes it possible to measure up the logic of artificial neural network to that of a human, for whom high-frequency distortions are not decisive in object recognition.

this paper we present approaches for generating random numbers along with potential applications. Rather than trying to provide extensive coverage of several techniques or algorithms that have appeared in the scientific literature, we focus on some representative approaches presenting their workings and properties in detail. Our goal is to delineate their strengths and weaknesses as well as their potential application domains so as the reader can judge what would be the best approach for the application in hand, possibly a combination of the available approaches. For instance, a physical source of randomness can be used for the initial seed, then suitable preprocessing can enhance its randomness and then the output of the preprocessing can feed different types of generators, e.g. a linear congruential generator, a cryptographically secure one and one based on the combination of one way hash functions and shared key cryptoalgorithms in various modes of operation. Then, if desired, the outputs of the different generators can be combined giving the final random sequence. Moreover, we present a set of practical randomness tests which can be applied on the outputs of random number generators in order to assess their randomness characteristics. In order to demonstrate the importance of unpredictable random sequences, we present an application of cryptographically secure generators in domains where unpredictability is one of the major requirements, i.e. eLotteries and cryptographic key generation.

In view of the problem that the hot and cold loads of mushroom houses are affected by multiple factors such as environment, mushrooms, and equipment, which are difficult to accurately model, this paper proposes a short-term load prediction method based on empirical wavelet transform (EWT) and mixed autoregressive integrated moving average (ARIMA) and convolutional bi-directional short- and long-term attention mechanism (CNN-BiLSTM-Attention). The method first uses the Boruta algorithm to filter the input characteristics, and then uses the EWT method to decompose the mushroom house load data into 4 modal components. Then the Lempel-Ziv method is introduced to divide the modal components into two categories of high and low frequencies, and the CNN-BiLSTM-Attention and ARIMA prediction models are constructed separately. Finally, the two types of prediction results are superimposed and reconstructed to obtain the final load prediction value. The test results show that the Boruta algorithm can effectively filter out the characteristics of key influencing factors. Compared with the Spearman and Pearson correlation coefficient methods, the mean absolute error (MAE) of the prediction results is reduced by 14.72% and 3.75%, respectively; compared with the ensemble empirical mode decomposition (EEMD) method, the EWT method can increase the decomposition and reconstruction error by 103 orders of magnitude, which can effectively improve the prediction accuracy of the model; compared with the individual neural network model, the prediction effect of the model proposed in this paper has obvious advantages, and the MAE, root mean square error (RMSE) and mean absolute percentage error (MAPE) of the prediction results are reduced respectively. 31.06%, 26.52% and 39.27%.

Based on the definition of double fuzzy relations, two types of new rough set models are constructed, which are multi-granulation double fuzzy rough sets called optimistic and pessimistic multi-granulation double fuzzy rough sets, and some of their properties were studied. In addition, we study the relationship between optimistic and pessimistic multi-granulation double fuzzy rough sets and double fuzzy rough sets.

In this paper, we study properties of formal concepts from an order-theoretic perspective. We first establish a natural correspondence between formal contexts and preorders as well as their induced posets. Then, based on the poset induced from a formal context, we provide characterization for join-irreducible or meet-irreducible elements of finite concept lattices. In addition, we introduce the notion of rough conceptual approximations based on topological closure and interior operators. In contrast with the conventional definition of equivalence class of an object used in Pawlakian approximation spaces, we instead utilize the extent of an object concept. We show that rough conceptual approximations are equivalent to approximation operators in the generalized approximation space associated with the preorder corresponding to a formal context. We also illustrate these theoretical results with examples and discuss their potential applications.

The calibration of three-dimensional (3D) coordinates in augmented reality (AR) systems is a complex activity. It involves the recognition of environmental characteristics and technology that models the 3D space of the device, determining its position and orientation. In the industrial environment, it is common for AR applications to cover large spaces, making it difficult to maintain attributes such as precision and accuracy. The set of sensors and mapping algorithms available in HoloLens stimulate the development of virtual reality (VR) applications, in particular localization techniques. This study proposes calibration models of the 3D coordinates of the HoloLens for indoor industrial environments. The performance of tests in a relevant environment provides data necessary to evaluate the performance of the proposed models in terms of precision and accuracy in determining point coordinates in the study environment. The results show improvements in determining the axes that define the 3D space, with a direct influence on the position of the points observed in the experiment

The introduction of autonomous technologies in cities—such as driverless cars, ground robots, and drones—promises to transform urban services and interactions. As a newly emergent, intuitive, and promising technology, eye-gaze-based mobile robot teleoperation (referred to as Tele-gaze in this context) has recently been applied to human–mobile robot interaction for various activities in cities, such as in the use of assistive technologies to improve the autonomy and well-being of people with limited mobility. More recently, we have begun to witness a shift that takes advantage of automation assistance to improve human performance using Tele-gaze. However, there is a knowledge gap with regard to how various levels of automation assistance, when combined with interaction modalities, can affect human operators and their collaboration with non-human agents. More specifically, we need to identify the factors that can influence the Tele-gaze-based systems and their effects on the human–robot collaboration. In this paper, a novel Tele-gaze system supported by four interactive modalities is proposed. The eye-gaze control is supported by increasing levels of automation assistance from the mobile robot side, with two basic mechanisms (eye-imitation camera and user-will trigger mechanisms) present in all four modalities—Modality 1: without any automation assistance; Modality 2: with a collision-avoidance mechanism; Modality 3: with a collision-avoidance mechanism and pathway middle mechanism; and Modality 4: with a collision-avoidance mechanism and a guideline-following mechanism. Four sets of experiments with an indoor navigation task were conducted with the four interactive modalities. Each set was tested by our 12 participants using one of the four modalities. We analyzed and discussed the experiments’ outcomes from both (1) the mobile robot side and (2) the human operator side. Early findings indicated that automation assistance and human capacity can not only reinforce one another but also constrain one another. We suggest that adopting the right balance, with the appropriate level of automation assistance, is key to enhancing the Tele-gaze-based interactions without compromising human dominance, user experience, and the flexibility of the system capacity.

This article introduces a novel approach, termed the Asymmetric Probabilistic Tsetlin (APT) Machine, which incorporates the Stochastic Point Location (SPL) algorithm with the Asymmetric Steps technique into the Tsetlin Machine (TM). APT introduces stochasticity into the state transitions of Tsetlin Automata (TA) by leveraging the SPL algorithm, thereby enhancing pattern recognition capabilities. To enhance random search processes, we introduced a decaying normal distribution into the procedure. Meanwhile, the Asymmetric Steps approach biases state transition probabilities towards specific input patterns, further elevating operational efficiency. The efficacy of the proposed approach is assessed across diverse benchmark datasets for classification tasks. The performance of APT is compared with traditional machine learning algorithms and other Tsetlin Machine models, including the Asymmetric Tsetlin (AT) Machine, characterized by deterministic rules for Asymmetric transitions, and the Classical Tsetlin (CT) Machine, employing deterministic rules for symmetric transitions. Strikingly, the introduced APT methodology demonstrates highly competitive outcomes compared to established machine learning methods. Notably, both APT and AT exhibit state-of-the-art performance, surpassing the Classical Tsetlin Machine, emphasizing the efficacy of asymmetric models for achieving superior outcomes. Remarkably, APT exhibits even better performance than AT, particularly in handling complex datasets.

Matrix-variate Gaussian type or Wishart type distributions in the real domain are widely used in the literature. When the exponential trace has an arbitrary power and when a factor involving a determinant enters into the model or a matrix-variate gamma type or Wishart type model with exponential trace having an arbitrary power, is extremely difficult to handle. Evaluation of the normalizing constant in such a model is the most important part because when studying the properties of such a model, the method used in the evaluation of the normalizing constant will be the relevant steps in all the computations involved. One such model with a factor involving a trace and the exponential trace having an arbitrary power, in the real domain, is known in the literature as Kotz' model. No explicit evaluation of the normalizing constant in the model involving trace with an exponent and determinant with an exponent entering into the model and at the same time the exponential trace having an arbitrary exponent seems to be available in the literature. The normalizing constant widely used in the literature and interpreted as the normalizing constant in the general model and refers to as a Kotz' model does not seem to be correct. Corresponding model in the complex domain, with the correct normalizing constant, does not seem to be available in the literature. One of the main contributions in this paper is the matrix-variate distributions in the complex domain belonging to Gaussian type, gamma type, type-1 and type-2 beta type when the exponential trace has an arbitrary power. All these models are believed to be new. A second main contribution is the explicit evaluation of the the normalizing constants, in the real and complex domains especially in the complex domain, in a matrix-variate model involving a determinant and a trace as multiplicative factors and at the same time the exponential trace having an arbitrary power. Another main contribution is the introduction of matrix-variate models with exponential trace having an arbitrary exponent, in the categories of type-1 beta, type-2 beta and gamma distributions or in the family of Mathai's pathway models [1], both in the real and complex domains. Another new contribution is the logistic-based extensions of models in the real and complex domains with exponential trace having an arbitrary exponent and connecting to extended zeta functions introduced by this author recently. Some properties of such models are indicated but not derived in detail in order to limit the size of the paper. The techniques and steps used at various stages in this paper will be highly useful for people working in multivariate statistical analysis as well as people applying such models in engineering problems, communication theory, quantum physics and related areas, apart from statistical applications.

The primary purpose of this article is to deduce specific order estimates for the \textit{Mertens Function} $M(n)$, which facilitates us to analyze the location of zeros of the \textit{Riemann Zeta function} $\zeta(s)$. The paper also provides a brief overview about the notion of the \textit{Mertens Function} $M(n)$ and \textit{Redheffer Matrices} $\mathbb{A}_{n}$. In addition to learning about various \textit{spectral properties} of $ \mathbb{A}_{n}$, we shall also deduce the relation between these two, which, eventually would lead us to establish a necessary and sufficient condition for the \textit{Riemann Hypothesis} to hold true, as justified by \textit{Redheffer} himself. We shall also observe several numerical evidence as well as theoretical justification behind the falsity of the famous \textit{Mertens Hypothesis}, along with how researchers over the years have approached towards deriving an estimate of the smallest possible natural number $n$ for which the first such violation of the theorem occurs, utilizing numerous conjectures annotating about the order of $M(n)$. Readers who are highly motivated in pursuing research in any of the topics relevent to the contents of this paper will surely find the \texttt{References} section to be extremely resourceful.

The unsupervised domain-adaptive vehicle reidentification approach aims to transfer knowledge from a labeled source domain to an unlabeled target domain, however there are knowledge differences between the target domain and the source domain. To reduce domain differences, existing unsupervised domain-adaptive rerecognition methods generally require access to the source domain data to assist in re-training the target domain model. But for security reasons, in many cases, data between different domains cannot communicate. To this end, this paper proposes an unsupervised domain-adaptive vehicle re-identification method based on source-free knowledge transfer. First, by constructing a passive domain knowledge migration module, the target domain is consistent with the source domain model output to train a generator to generate the "source-like samples". Then, it can effectively reduce the model knowledge difference and improve the model generalization performance. According to the experiment and testing of VeRi776 and VehicleID, two mainstream public data sets in this field, the rank-k and mAP indexes obtained are both improved, and are suitable for object re-recognition tasks without source data.

The main object of this work is to establish the existence and uniqueness of a solution to the 3D Navier-Stokes (NS) system for an incompressible fluid with viscosity. The nonlinearity of the NS system, as well as the need to estimate velocity and pressure for every value of the viscosity parameter [1] make them challenging to solve. In this regard, in the present work, we study the Navier-Stokes system, which describe the flow of a viscous incompressible fluid and the solution was obtained for velocity and pressure in an analytical form. In addition, the found pressure distribution law, which is described by a Poisson type equation and plays a fundamental role in the theory of Navier-Stokes systems in constructing analytic smooth (conditionally smooth) solutions.

A topic of growing interest in urban remote sensing is the automated extraction of geometrical building information for 3D city modeling. Roof geometry information is useful for applications such as urban planning, solar potential estimation and telecommunication installation planning, and wind flow simulations for pollutant diffusion analysis. Recent research has proven that the advance in remote sensing technologies and deep learning methods offer the prospects of deriving the roof structure information accurately and efficiently. In this study, we propose a Vectorized Roof Extractor- method based on Fully Convolutional Networks (FCNs) and advanced polygonization method to extract roof structure from aerial imagery and a normalized Digital Surface Models (nDSM) in a regularized vector format. The roof structure consists of building outlines, external edges of the building roof, inner rooflines, internal intersections of the main roof planes. The methodology is comprised of segmentation, vectorization and post-processing for outer rooflines, external edges of the building roof, and inner rooflines, and internal intersections of the main roof planes. For the comparison, we adapt the Frame field Learning (FFL) method originally designed to extract building polygons [1]. Our experiments are conducted on a custom data set derived for the city of Enschede, The Netherlands, using aerial imagery, nDSM and manually digitized training polygons. The results show that the proposed Vectorized Roof Extractor outperformed adapted FFL on PoLiS distance with values of 3.5 m and 1.2 m for outlines and inner rooflines, respectively. Furthermore, the model surpassed the adapted FFL on PoLiS-thresholded F-score for outlines and inner rooflines, with 0.31 and 0.57, respectively. The Vectorized Roof Extractor produced adequate visual results, with straighter walls and fewer missed inner roofline detections. It can predict buildings with common walls thanks to skeleton graph computation. To summarize, the proposed method is suitable for urban applications and has the potential to be improved further.

This article develops duality principles and numerical results for a large class of non-convex variational models. The main results are based on fundamental tools of convex analysis, duality theory and calculus of variations. More specifically the approach is established for a class of non-convex functionals similar as those found in some models in phase transition. Finally, in the last section we present a concerning numerical example and the respective software.

A problem involving the government's inspection of coins in Lower Slobbovia is discussed in the \emph{American Mathematical Monthly}. It is desirable to classify and correct counterfeit coins by utilizing the fewest possible measures. However, previous article only proves the existence of the solution, which does not give a practical solution to the problem. This note provides effective methods to achieve the identification of coiners using dirac delta function and singularity function. Moreover, unit-order construction of continuum mappings and discretization of unique basis vectors with semi-expansion are established in S-base space.

Using traditional methods based on detection rules written by human security experts, there is a significant challenge in accurately detecting many network threats that are increasingly becoming sophisticated. In order to deal with the limitation of the traditional methods, network threat detection techniques utilizing artificial intelligence technologies such as machine learning are being extensively studied. Research has also been conducted on analyzing various string patterns in network packet payloads through natural language processing techniques to detect attack intent. However, due to the nature of packet payloads containing binary data as well as text data, a new approach is needed that goes beyond typical natural language processing techniques. In this paper, we study a token extraction method optimized for payloads using n-gram and byte pair encoding techniques. Furthermore, we generate embedding vectors that can understand the context of the packet payload using algorithms such as Word2Vec and FastText. We also compute the embedding of various header data associated with packets, such as IP addresses and ports. Given the combination of these features, we ensemble a text 1D-CNN and a multi-head attention network in a novel fashion. We validated the effectiveness of our classification technique with the CICIDS2017 open dataset and over half a million data collected by The Education Cyber Security Center (ECSC) currently operating in South Korea. The proposed model showed remarkable progress compared to previous studies, demonstrating a highly accurate classification performance with an F1-Score of 0.998. Our model can also preprocess and classify 150,000 network threats per minute to help security agents in the field divert their time to analyzing more complex attack patterns.

Domain-specific systems-on-chip (DSSoCs) aim to narrow the gap between general-purpose processors and application-specific designs. CPU clusters enable programmability, while hardware accelerators tailored to the target domain minimize task execution times and power consumption. Traditional operating system (OS) schedulers can diminish the potential of DSSoCs as their execution times can be orders of magnitude larger than the task execution time. To address this problem, we propose a dynamic adaptive scheduling (DAS) framework that combines the advantages of a fast, low-overhead scheduler and a sophisticated, high-performance scheduler with a larger overhead. We present a novel runtime classifier that chooses the better scheduler type as a function of the system workload, leading to improved system performance and energy-delay product (EDP). Experiments with five real-world streaming applications indicate that DAS consistently outperforms fast, low-overhead, and slow, sophisticated schedulers. DAS achieves a 1.29x speedup and 45% lower EDP than the sophisticated scheduler under low data rates and a 1.28x speedup and 37% lower EDP than the fast scheduler when the workload complexity increases. Furthermore, we demonstrate that the superior performance of the DAS framework also applies to hardware platforms, with up to a 48% and 52% reduction in execution time and EDP, respectively.

Wireless sensor networks (WSN) are widely used in various fields such as military, industrial and transportation for real-time monitoring, sensing and data collection of different environments or objects. However, the development of WSN is hindered by several limitations, including energy, storage space, computing power and data transmission rate. Among these, the availability of power energy plays a crucial role as it directly determines the lifespan of WSN. To extend the life cycle of WSN, two key approaches are power supply improvement and energy conservation. Therefor, we proposed an energy harvesting system and a low energy consumption mechanism for WSN. Firstly, we delved into the energy harvesting technology of WSN, explored the utilization of solar energy and mechanical vibration energy to ensure a continuous and dependable power supply to the sensor nodes, and analyzed the voltage output characteristics of bistable piezoelectric cantilever. Secondly, we proposed a neighbor discovery mechanism that utilizes a separation beacon, is based on reply to ACK, and can facilitate the identification of neighboring nodes. This mechanism operates at a certain duty cycle ratio, significantly reduces idle listening time and results in substantial energy savings. In comparison to the Disco and U-connect protocols, our proposed mechanism achieves a remarkable reduction of 66.67% and 75% in the worst discovery delay, respectively. Furthermore, we introduced a data fusion mechanism based on integer wavelet transform. This mechanism effectively eliminates data redundancy caused by spatio-temporal correlation, results in a data compression rate of 5.42. Additionally, it significantly reduces energy consumption associated with data transmission by the nodes.

Agriculture is one of the indispensable fields for the survival of mankind. Potatoes also have a significant role in the field of agriculture. The quality and quantity of potatoes are significantly impacted by several diseases, such as early blight and late blight, and manual interpretation of these leaf diseases is time-consuming and inconvenient. Fortunately, leaf appearance is used to detect diseases in potato plants. Productivity will considerably rise if the infections are detected early. Different types of image processing methods and machine learning methods are used for early recognition of those diseases from leaf images so that the product losses are decreased significantly. For the incredible and marvelous performance of CNN, it is the most popular deep learning method that is used immensely for the recognition of leaf diseases from images. Several pretrained deep learning models, such as VGG16, ResNet50, InceptionV3, MobileNetV2, Xception, and a deep learning model developed using CNN, are employed for potato leaf disease classification and recognition on the same dataset. The transfer learning technique is applied to the pretrained model and the data augmentation technique is applied to the Proposed CNN model for potato disease classification from leaf samples. Compared to pretrained models, the proposed CNN model offers the lowest loss and highest accuracy for potato leaf disease detection while using fewer parameters and layers. It achieves the best performance with a test accuracy of 99.33% compared to other Pretrained models used in the diagnosis of potato leaf disease.

UAV (Unmanned aerial vehicle) communication offers the possibility to establish the new net-works. To overcome the PE (pointing error) and beam misalignment of millimeter-wave massive MIMO (Multiple-in multiple-out)/FSO (Free Space Optical) caused by UAV jitter, a Tensor-train decomposition based hybrid beamforming for millimeter-wave massive MIMO/FSO in UAV with RIS (Reconfigurable Intelligence Surface) networks is investigated to improve the system spectral efficiency. Firstly, the high-dimensional channels of the RIS-assisted millimeter-wave massive MIMO/FSO in UAV are represented as the low-dimensional channels by Tensor-train decomposition. Secondly, the FSO PE caused by UAV jitter can be effectively solved by BIGRU (Bidirectional Gated Recurrent Unit)-attention neural network model. The fast-fading channels and Doppler shifts are estimated by the FCTPM (Fast Circulant Tensor Power Method) based on the Tensor-train decomposition. Finally, the RIS phase shift matrix is optimized by the SVD (Singular Value Decomposition). The Hybrid beamforming and RIS phase shift matrix are esti-mated by the low-complexity PE-AltMin (Phase Extraction Alternating Minimization) method to solve the beam misalignment. Simulation experiments demonstrate that the proposed method has higher spectrum utilization than other methods.

In this paper, we present an innovative technique that improves the convergence order of iterative schemes that do not require the evaluation of Jacobian matrices. Using this procedure, we achieve a remarkable increase in the order of convergence, raising it from p to p + 3 units, which results in a remarkable improvement in the overall performance. We have conducted comprehensive numerical tests in various scenarios to validate the theoretical results, showing the efficiency and effectiveness of the new Jacobian-free schemes.

In light of advancing technology, the conventional clock network architecture has become inadequate for addressing the intricacies inherent in modern System-on-Chip (SoC) designs. While clock mesh topology offers resilience against On-Chip Variation (OCV) fluctuations, it still necessitates manual intervention. Therefore, substantial scope exists for methodological enhancements and the refinement of rapid analytical techniques. This paper introduces a novel clock mesh synthesis approach, underpinned by dynamic programming algorithms, that guarantees latency constraints. Our experimental findings demonstrate that our algorithm achieves an additional 26.6% reduction in power consumption compared to the baseline methodology. Furthermore, it substantially reduces runtime by an average of 78.0% when contrasted with traditional simulation methods. These results highlight the potential of our methodology for enhancing the efficiency and power management of clock mesh.

This article introduces a new fractional approach to the concept of information dimension of complex networks, based on a (q,q′)-entropy proposed in the literature. The q parameter measures how far is the number of subsystems (for a given size ε) from the mean number of overall sizes. The q′ (interaction index) measures when the interactions between subsystems are greater (q′&gt;1), lesser (q′&lt;1) or equal to the interactions into these subsystems. The computations of the proposed information dimension are carried out on several real-world and synthetic complex networks. The results from the proposed information dimension are compared with those from the information dimension based on the Shannon entropy.

People often make mistakes, so we try to automate every aspect of our lives. Sports is no exception. While just over a decade ago humans were analyzing games, today this is being done by artificial intelligence. Due to rapid development over the past decade, neural networks are now faster, more accurate, and in some areas even better than their human counterparts. In this paper, we present an algorithm that can detect player statistics during an NBA broadcast. It also helps users better understand the game and the use of augmented reality. The algorithm detects players on the court, tracks their movements, and assigns them to their respective teams. Using homography estimation, we transform the players’ positions from a three-dimensional space in the video to a two-dimensional space on the playing field plane. We define a new algorithm that predicts the players’ actions and their statistics. The results show that the proposed method can effectively identify the players, their respective teams, and their positions. It can also analyze their actions with high accuracy.

The efficient recognition and classification of personal protective equipment are essential for en-suring the safety of personnel in complex industrial settings. Using the existing methods, manually performing macro-level classification and identification of personnel in intricate spheres is tedious, time-consuming, and inefficient. The availability of several artificial intelligence models in recent times presents a new paradigm shift in object classification and tracking in complex settings. In this study, several compact and efficient deep learning model architectures are explored, and a new efficient model is constructed by fusing the learning capabilities of the individual, efficient models for better object feature learning and optimal inferencing. The new model construct follows the contributory learning theory whereby each fussed model brings its learned features, which are then combined to obtain a more accurate and rapid model using normalized quantization-aware learning. During the investigation, a separable convolutional driven model was constructed as a base model, and then the various efficient architectures combined for the rapid identification and classification of the various hardhat classes used in complex industrial settings. A remarkable rapid classification and accuracy were recorded with the new resultant model.

The Physics-Informed Neural Networks (PINNs) improve the efficiency of data utilization by combining physical principles with neural network algorithms and ensure that the predictions are consistent and stable with the physical laws. PINNs opens up a new approach to address inverse problems in fluid mechanics. Based on the single-relaxation-time lattice Boltzmann method (SRT-LBM) with the Bhatnagar-Gross-Krook (BGK) collision operator, the PINN-SRT-LBM model is proposed in this paper for solving the inverse problem in fluid mechanics. The PINN-SRT-LBM model consists of three components. The first component involves a deep neural network that predicts the equilibrium control equations in different discrete velocity directions within SRT-LBM. The second component employs another deep neural network to predict non-equilibrium control equations, enabling inference of the fluid's non-equilibrium characteristics. The third component, a physics informed function translates the outputs of the first two networks into physical infor-mation. By minimizing the residuals of the physical partial differential equations (PDEs), the physics informed function infers relevant macroscopic quantities of the flow. The model evolves two sub-models applicable to different dimensions, named PINN-SRT-LBM-I and PINN-SRT-LBM-II models according to the construction of the physical informed function. The innovation of this work is the introduction of SRT-LBM and discrete velocity models as physical drivers into the neural network through the interpretation function. Therefore, PINN-SRT-LBM allows the neural network to handle inverse problems of various dimensions and focus on problem-specific solving. Experimental results confirm the accurate prediction of flow infor-mation at different Reynolds numbers within the computational domain. Relying on the PINN-SRT-LBM models, inverse problems in fluid mechanics can be solved efficiently.

Convolution, recurrent and attention-based deep learning techniques have produced the most recent state-of-the-art results in multiple sensor-based human activity recognition (HAR) datasets. However, these techniques have high computing costs, restricting their use in low-powered devices. Different methods have been employed to increase the efficiency of these techniques; however, this often results in worse performance. Recently, pure MLP architectures have demonstrated competitive performance in vision-based tasks with lower computation costs than other deep-learning techniques. The MLP-Mixer is a pioneering pure MLP architecture that produces competitive results with state-of-the-art models in computer vision tasks. This paper shows the viability of the MLP-Mixer in sensor-based HAR. Furthermore, experiments are performed to gain insight into the Mixer modules essential for HAR, and a visual analysis of the Mixer’s weights is provided, validating the Mixer’s learning capabilities. As a result, the Mixer achieves an F1 score of 97%, 84.2%, 91.2% and 90% on the PAMAP2, Daphnet Gait, Opportunity Gestures and Opportunity Locomotion datasets, respectively, outperforming state-of-the-art models in all datasets except Opportunity Gestures.

The smart grid system, an improvised form of the traditional grid, is considered a critical cyber-physical system. Due to its complex combination of smart and legacy technologies, this technology is characterized by a wide range of features such as full duplex communication, advanced metering infrastructure, remote monitoring, and control. However, despite this system’s substantial environmental and socio-economic impact on modern life, it poses severe security vulnerabilities due to its integration and interconnected and interdependent cyber-physical components. Based on the rapid development of cyber-physical systems (CPS), academics and industries have investigated relevant techniques to enhance and strengthen the security measures of the SG system. The intrusion detection system is a countermeasure, a powerful safeguard against various cyber-attacks and threats. The contribution of the IDSs to the SG paradigm is examined in this study. A comprehensive review has been presented in this study, highlighting different techniques, basic ideas, and analyses. Besides discussing the contemporary pertinent research studies, the shortcomings of the existing IDS for the SG system are also identified with a recommendation for future research direction.

This study explores the potential of data science software solutions like Customer Relationship Management Software (CRM) for increasing the revenue generation of businesses. We focused on those businesses in Accommodation and Food Service sector across the European Union (EU). The investigation is contextualized within the rising trend of data-driven decision making, examining the potential correlation between data science application and business revenue. Employing a comprehensive evaluation of Eurostat datasets from 2014 to 2021, we used both univariate and multivariate analyses, we assessed e-commerce sales data across countries, focusing on the usage of big data and CRM tools. Big data utilization showed a clear, positive relationship with enhanced e-commerce sales. However, CRM tools exhibited a dualistic impact: while their use in marketing showed no significant effect on sales, their application in non-marketing functions had a negative correlation. These findings underscore the potential role of CRM and data science solutions in enhancing business performance in the EU's Accommodation and Food Service industry.

Integrating systems acquired from third parties and legacies has become of great necessity in companies. This is mainly due to the need to exchange information between entities, such as banks, suppliers, customers, allies, etc. Therefore, it is essential to guarantee the integrity of the data and keep the integration up to date with the changes that can occur. Furthermore, reducing the transaction risk and avoiding losing information is necessary. Implementing this complex task involving technological and business challenges requires appropriate architecture implementation. This article presents an architecture named Dynamic Canonical Data Model through agnostic messages. The contribution involves treating the low link in integrating software units, also called the integration of loosely coupled software units. In particular, it focuses on internal data and external data integration. The proposal reduces their integration, maintenance time, and cost, maximizing their scalability and promoting reuse. To illustrate their components, a case study undertaken at the Mexican Logistics Company Paquetexpress is presented. The company has evaluated different enterprise application integration systems over 26 years to achieve a standardized integration. The article describes an architecture designed and implemented for this delivery company in a real-world case. The implementation’s source code was registered in the National Registry of Copyrights of Mexico.

Slime Mould Algorithm (SMA) is a new swarm intelligence algorithm inspired by the oscillatory behavior of slime molds during foraging. Numerous researchers have widely applied SMA and its variants in various domains and proved its value by the experiments in literatures. In this paper a comprehensive survey on SMA is introduced, which is based on 130 articles visa Google-scholar between 2022 and July, 2023. Firstly, the theory of SMA is described. Secondly the improved SMA variants are provided and categorized according to the approach that they are applied with. Finally, it also discusses the main applications domains of SMA such as engineering optimization, energy optimization, machine learning, network, scheduling optimization, image segmentation and etc. This review presents some research suggestion for researcher who is interested in this algorithm.

Due to the success of artificial intelligence (AI) applications in the medical field over the past decade, concerns about the explainability of these systems have increased. The reliability requirements of black-box led algorithms for making decisions affecting patients pose a challenge even beyond their accuracy. Recent advances in AI increasingly underscore the need to incorporate explainability into these systems. While most traditional AI methods and expert systems are inherently interpretable, recent literature has focused primarily on explainability techniques for more complex models such as deep learning. This scoping review analyzes the existing literature on explainability and interpretability of AI methods in the medical and clinical field, providing an overview of past and current research trends, and limitations that might impede the development of Explainable Artificial Intelligence (XAI) in medicine, challenges, and possible research directions. In addition, this review discusses possible alternatives for leveraging medical knowledge to improve interpretability in clinical settings, while taking into account the needs of users.

In recent years, Vehicular Ad-hoc Networks (VANETs) have become a popular subject of research due to their ability to enhance safety and improve travel comfort. However, VANETs relies on wireless technology for safety messaging exchange, jamming detection and recovery strategies. This dependence on receiving these metrics can lead to security threats that are either unique to VANETs or observed in ad-hoc networks, resulting in significant challenges in Dedicated Short-Range Communication (DSRC). To address these challenges, this paper proposes a novel recovery strategy for detecting jammers in Dedicated Short-Range Communication (DSRC) within VANETs. The proposed model contains algorithms that can detect deceptive jammers and switch the Safety Application to a fail-safe mode. Additionally, the paper introduces a recovery strategy to facilitate faster transitioning of the Safety Applications from fail-safe mode to an operational mode, thereby minimizing the impact of jamming. This recovery strategy dynamically adjusts message rates in situations where communication anomalies, such as jamming, are detected. The experimental results indicate that this recovery strategy helps Safety Applications transition to be more efficient and reliable compared to earlier operational models in the literature.

Log collection and storage is a crucial process for enterprises around the globe. Log analysis helps identify potential security breaches and, in some cases, is required by law for compliance. However, enterprises often delegate these responsibilities to third-party Cloud Service Providers (CSPs), where the logs are collected and processed for anomaly detection and stored in a data warehouse for archiving. Prevalent schemes rely on plain (unencrypted) data for anomaly detection. More often, these logs can reveal sensitive information about an organization or the customers of that organization. Hence, it is best to keep it encrypted at all times. This paper presents "SigML++," an extension of work done in "SigML." We utilize Fully Homomorphic Encryption (FHE) with the Cheon-Kim-Kim-Song (CKKS) scheme for supervised log anomaly detection on encrypted data. We use an Artificial Neural Network (ANN) based probabilistic polynomial approximations using a Perceptron with linear activation. We probabilistically approximate the Sigmoid activation function (σ(x)) in the encrypted domain for the intervals [−10,10] and [−50,50]. Experiments show better approximations for Logistic Regression (LR) and Support Vector Machine (SVM) for low-order polynomials.

Over the years, network analysis became a promising strategy to analyze complex system, i.e. systems composed by a large number of interacting elements. In particular, multilayer networks have emerged as a powerful framework for modelling and analysing complex systems with multiple types of interactions. Network analysis can be applied to pharmacogenomics to gain insights into the interactions between genes, drugs, and diseases. By integrating network analysis techniques with pharmacogenomic data, the goal consists to uncover complex relationships and identify key genes to use in pathway enrichment analysis to figure out biological pathways involved in drug response and adverse reactions. In this study, we model omics, diseases and drugs data together through the multilayer network representation. Then, we mined the multilayer network with a community detection algorithm by obtaining top communities. After that, we used the identified list of genes from the communities to perform pathway enrichment analysis (PEA) to figure out the biological function affected form the selected genes. The results show that the genes forming the top community have the multiple roles through different pathways.

This work uses a new approach to investigate the Riemann hypothesis, drawing conclusions about its trueness. It is based on the more general method presented in a very recent publication, by the same author, showing in detail how to ap- proach that very well-known and interesting problem. This is achieved by means of the theory of dynamical systems (Poincaré index associated to equilibria of 2-dimensional systems) and the study of the zeros of the Dirichlet eta function, defined by a Dirichlet series. By using the well-known fact that the zeros of the eta function would include all zeros of the Riemann zeta function in the (open) critical strip, excluded the critical line, (0,1/2) ∪ (1/2,1) × (−∞,∞), the development proceeds using only the eta function. In addition, the open and simply connected region (1/2,1) × (0,∞) is used along the text, taking into account the symmetries of zeros of the functions under analysis in the critical strip. The basic line of proof is to find the mathematical expression for the Poincaré index of the vector field associated to the eta function, assuming the existence of a zero of the eta function outside the critical line (in (1/2,1) × (0,∞)), and investigating the resulting unfoldings. Eventually, an inconsistency occurs and the proof ends by contradiction.

COVID-19 transmission models have conferred great value in informing public health understanding, planning, and response. However, the pandemic also demonstrated the infeasibility of basing public health decision-making on transmission models with pre-set assumptions. No matter how favourably evidenced when built, a model with fixed assumptions is challenged by numerous factors that are difficult to predict. Ongoing planning associated with rolling back and re-instituting measures, initiating surge planning, and issuing public health advisories can benefit from approaches that allow state estimates for transmission models to be continuously updated in light of unfolding time series. A model being continuously regrounded by empirical data in this way can provide a consistent, integrated depiction of the evolving underlying epidemiology and acute care demand, offer the ability to project forward such a depiction in a fashion suitable for triggering the deployment of acute care surge capacity or public health measures, support quantative evaluation of tradeoffs associated with prospective interventions in light of the latest estimates of the underlying epidemiology. We describe here the design, implementation and multi-year daily use for public health and clinical support decision-making of a particle filtered COVID-19 compartmental model, which served Canadian federal and provincial governments via regular reporting starting in June 2020. The use of the Bayesian Sequential Monte Carlo algorithm of Particle Filtering allows the model to be re-grounded daily and adapt to new trends within daily incoming data – including test volumes and positivity rates, endogenous and travel-related cases, hospital census and admissions flows, daily counts dose-specific vaccinations administered, measured concentration of SARS-CoV-2 in wastewater, and mortality. Important model outputs include estimates (via sampling) of the count of undiagnosed infectives, the count of individuals at different stages of the natural history of frankly and pauci-symptomatic infection, the current force of infection, effective reproductive number, and current and cumulative infection prevalence. Following a brief description of model design, we describe how the machine learning algorithm of particle filtering is used to continually reground estimates of dynamic model state, support probabilistic model projection of epidemiology and health system capacity utilization and service demand and probabilistically evaluate trade-offs between potential intervention scenarios. We further note aspects of model use in practice as an effective reporting tool in a manner that is parameterized by jurisdiction, including support of a scripting pipeline that permits a fully automated reporting pipeline other than security-restricted new data retrieval, including automated model deployment, data validity checks, and automatic post-scenario scripting and reporting. As demonstrated by this multi-year deployment of Bayesian machine learning algorithm of particle filtering to provide industrial-strength reporting to inform public health decision making across Canada, such methods offer strong support for evidence-based public health decision making informed by ever-current articulated transmission models whose probabilistic state and parameter estimates are continually regrounded by diverse data streams.

Deployments of real-world object-detection systems often experience a degradation in performance over time due to concept drift. Systems that leverage thermal cameras are especially susceptible because the respective thermal signatures of objects and their surroundings are highly sensitive to environmental changes. In this study, a conditioning method is investigated. The method aims to guide the training loop of thermal object detection systems by leveraging an auxiliary branch to predict the weather, while directly or indirectly conditioning the baseline detection system. Leveraging such an approach to train detection networks does not necessarily improve the performance of native architectures, however, it can be observed that conditioned networks manage to extract a signal from thermal images that guides the network to detect objects that baseline models miss. As the extracted signal appears to be quite noisy and very challenging to regress accurately, further work is needed to identify an ideal optimization vector.

(1) Background: The social robot interaction design is critical in determining acceptance and user experience. However, few studies have systematically discussed the current focus and future research directions of social robot interaction design from a bibliometric perspective. Therefore, in order to identify the latest research progress and evolution trajectory of research hotspots in social robot interaction design over the last decade. (2) Methods: based on 2416 papers related to social robot interaction design collected in the Web of Science (WOS) database, a comprehensive review was conducted by using bibliometrics to draw a knowledge map using VOSviewer and CiteSpace in an integrated manner. (3) Conclusions: The current research hotspots of social robot interaction design mainly focus on #1the study of human-robot relationships in social robot, #2Research on the Emotional Design of Social Robot, #3research on social robot for children's psychotherapy, #4research on companion robot for elderly rehabilitation, and #5research on educational social robot. The reference co-citation identifies the classic literature that forms the basis of the current research, which provides theoretical guidance and methods for the current research. Finally, we discuss several future research directions and challenges in this field.

Hate Speech Detection in Arabic presents a multifaceted challenge due to the broad and diverse linguistic terrain. With its multiple dialects and rich cultural subtleties, Arabic requires particular measures to address hate speech online successfully. To address this issue, academics and developers have used natural language processing (NLP) methods and machine learning algorithms adapted to the complexities of Arabic text. However, many proposed methods were hampered by a lack of a comprehensive dataset/corpus of Arabic hate speech. In this research, we propose a novel multi-class public Arabic dataset comprised of 403,688 annotated tweets categorized as extremely positive, positive, neutral, or negative based on the presence of hate speech. Using our developed dataset, we additionally characterize the performance of multiple machine learning models for Hate speech identification in Arabic Jordanian dialect tweets. Specifically, the Word2Vec, TF-IDF, and AraBert text representation models have been applied to produce word vectors. With the help of these models, we can provide classification models with vectors representing text. After that, seven Machine learning classifiers have been evaluated: Support Vector Machine (SVM), Logistic Regression (LR), Naive Bays (NB), Random Forest (RF), AdaBoost (Ada), XGBoost (XGB), and CatBoost (CatB). In light of this, the experimental evaluation revealed that, in this challenging and unstructured setting, our gathered and annotated datasets were rather efficient and generated encouraging assessment outcomes. This will enable academics to delve further into this crucial field of study.