Search

Picture fuzzy set is an efficient tool for dealing with uncertainty and vagueness, particularly in situations that require assimilation of more dimensions of linguistic assessment such as human voting, feature selection, etc. The correlation coefficient of picture fuzzy sets is a tool to determine the association of two picture fuzzy sets. It has several applications in various disciplines like science, engineering, and management. The prominent applications include decision-making, pattern recognition, clustering analysis, medical diagnosis, etc. In this paper, we introduce a new correlation coefficient for picture fuzzy sets with the justification of its advantages. This correlation coefficient is better than the existing correlation coefficients and other such measures in the picture fuzzy theory because it considers the picture fuzzy set as a whole and also expresses the nature (positive or negative) as well as the extent of association between two PFSs. By performing some comparative analysis based on the computation of correlation degree and linguistic hedges, we establish the effectiveness of the suggested correlation measure over some available correlation measures in a picture fuzzy environment. Further, in the context of pattern recognition, we examine the performance of the proposed correlation measure over some existing picture fuzzy correlation measures. Finally, we apply the suggested picture fuzzy correlation coefficient to a decision-making problem involving the selection of an appropriate COVID-19 mask.

COVID-19 is an infectious disease, which has adversely affected public health and the economy across the world. On account of the highly infectious nature of the disease, rapid automated diagnosis of COVID-19 is urgently needed. A few recent findings suggest that chest X-rays and CT scans can be used by machine learning for the diagnosis of COVID-19. Herein, we employed semi-supervised learning (SSL) approaches to detect COVID-19 cases accurately by analyzing digital chest X-rays and CT scans. On a relatively small COVID-19 radiography dataset, which contains only 219 COVID-19 positive images, 1341 normal and 1345 viral pneumonia images, our algorithm, COVIDCon, which takes advantage of data augmentation, consistency regularization, and multicontrastive learning, attains 97.07% average class prediction accuracy, with 1000 labeled images, which is 7.65% better than the next best SSL method, virtual adversarial training. COVIDCon performs even better on a larger COVID-19 CT Scan dataset that contains 82,767 images. It achieved an excellent accuracy of 99.13%, at 20,000 labels, which is 6.45% better than the next best pseudo-labeling approach. COVIDCon outperforms other state-of-the-art algorithms at every label that we have investigated. These results demonstrate COVIDCon as the benchmark SSL algorithm for potential diagnosis of COVID-19 from chest X-rays and CT-Scans. Furthermore, COVIDCon performs exceptionally well in identifying COVID-19 positive cases from a completely unseen repository with a confirmed COVID-19 case history. COVIDCon, may provide a fast, accurate, and reliable method for screening COVID-19 patients.

When preprocedural images are overlaid on intraprocedural images, interventional procedures benefit in that more structures are revealed in intraprocedural imaging. However, image artifacts, respiratory motion, and challenging scenarios could limit the accuracy of multimodality image registration necessary before image overlay. Ensuring the accuracy of registration during interventional procedures is therefore critically important. The goal of this study was to develop a novel framework that has the ability to assess the quality (i.e., accuracy) of nonrigid multimodality image registration accurately in near real time. We constructed a solution using registration quality metrics that can be computed rapidly and combined to form a single binary assessment of image registration quality as either successful or poor. Based on expert-generated quality metrics as ground truth, we used a supervised learning method to train and test this system on existing clinical data. Using the trained quality classifier, the proposed framework identified successful image registration cases with an accuracy of 81.5%. The current implementation produced the classification result in 5.5 s, fast enough for typical interventional radiology procedures. Using supervised learning, we have shown that the described framework could enable a clinician to obtain confirmation or caution of registration results during clinical procedures.

The process of treating brain cancer depends on the experience and knowledge of the physician, which may be associated with eye errors or may vary from person to person. For this reason, it is important to utilize an automatic tumor detection algorithm to assist radiologists and physicians for brain tumor diagnosis. The aim of the present study is to automatically detect the location of the tumor in a brain MRI image with high accuracy. For this end, in the proposed algorithm, first, the skull is separated from the brain using morphological operators. The image is then segmented by six evolutionary algorithms, i.e., Particle Swarm Optimization (PSO), Artificial Bee Colony (ABC), Genetic Algorithm (GA), Differential Evolution (DE), Harmony Search (HS), and Gray Wolf Optimization (GWO), as well as two other frequently-used techniques in the literature, i.e., K-means and Otsu thresholding algorithms. Afterwards, the tumor area is isolated from the brain using the four features extracted from the main tumor. Evaluation of the segmented area revealed that the PSO has the best performance compared with the other approaches. The segmented results of the PSO are then used as the initial curve for the Active contour to precisely specify the tumor boundaries. The proposed algorithm is applied on fifty images with two different types of tumors. Experimental results on T1-weighted brain MRI images show a better performance of the proposed algorithm compared to other evolutionary algorithms, K-means, and Otsu thresholding methods.

Purpose of Review Currently, there is a large body of research on multi-agent systems addressing their different system theoretic aspects. Aerial swarms as one type of multi-agent robotic systems have recently gained huge interest due to their potential applications. However, aerial robot groups are complex multi-disciplinary systems and usually research works focus on specific system aspects for particular applications. The purpose of this review is to provide an overview of the main motivating applications that drive the majority of research works in this field, and summarize fundamental and common algorithmic components required for their development. Recent Findings Most system demonstrations of current aerial swarms are based on simulations, some have shown experiments using few 10 s of robots in controlled indoor environment, and limited number of works have reported outdoor experiments with small number of autonomous aerial vehicles. This indicates scalability issues of current swarm systems in real world environments. This is mainly due to the limited confidence on the individual robot’s localization, swarm-level relative localization, and the rate of exchanged information between the robots that is required for planning safe coordinated motions. Summary This paper summarizes the main motivating aerial swarm applications and the associated research works. In addition, the main research findings of the core elements of any aerial swarm system, state estimation and mission planning, are also presented. Finally, this paper presents a proposed abstraction of an aerial swarm system architecture that can help developers understand the main required modules of such systems.

Purpose of Review With the rapid growth and development of robotic technology, its implementation in medical fields has also been significantly increasing, with the transition from the period of mainly using surgical robots to the era with combinations of multiple types of robots. Therefore, this paper introduces the newest robotic systems and technology applied in operating rooms as well as their architectures for integration. Recent Findings Besides surgical robots, other types of robotic devices and machines such as diagnostic and treatment devices with robotic operating tables, robotic microscopes, and assistant robots for surgeons emerge one after another, improving the quality of surgery from different aspects. With the increasing number and type of robots, their integration platforms are also proposed and being spread. Summary This review paper presents state-of-the-art robot-related technology in the operating room. Robotic platforms and robot components which appeared in the last decade are described. In addition, system architectures for the integration of robots as well as other devices in operating rooms are also introduced and compared.

Delimited control is a powerful mechanism for programming language extension which has been recently proposed for Prolog (and implemented in SWI-Prolog). By manipulating the control flow of a program from inside the language, it enables the implementation of powerful features, such as tabling, without modifying the internals of the Prolog engine. However, its current formulation is inadequate: it does not capture Prolog's unique non-deterministic nature which allows multiple ways to satisfy a goal. This paper fully embraces Prolog's non-determinism with a novel interface for disjunctive delimited control, which gives the programmer not only control over the sequential (conjunctive) control flow, but also over the non-deterministic control flow. We provide a meta-interpreter that conservatively extends Prolog with delimited control and show that it enables a range of typical Prolog features and extensions, now at the library level: findall, cut, branch-and-bound optimisation, probabilistic programming, . . . This paper is under consideration for publication in Theory and Practice of Logic Programming (TPLP)., Comment: Other version of paper is available at: arXiv:2108.02972. This paper is under consideration for publication in Theory and Practice of Logic Programming (TPLP)

The paper considers the task of natural language text generation, particularly the task of question generation based on the given text. Recent research in the area of text generation shows that better quality is achieved using the autoregressive generative models trained on language modeling tasks. However, such models do not use the metainformation of the text structure. In the paper, this approach is applied to Russian language texts. The architecture of the intelligent question generation system is described in detail.

The detection of roads from satellite images is among the most important topics for planning and development for cities, which replaces manual methods, but they turn out to be a complex task due to the complexity of the objects. This paper discusses issues related to the detection and segmentation of roads in very high-resolution aerial images. In order to resolve these issues, we propose in this paper the use, deployment, and validation of deep learning strategies, in particular, the U-net architecture based on deep convolutional neural networks for extracting roads from remote sensing images. Data augmentation techniques and preprocessing were applied to improve accuracy. We use in our processing for road segmentation the Massachusetts Road Dataset, which is publicly available. The results obtained showed excellent performance in terms of recall, precision, accuracy, and F1 score, and they are very close to the ground truth; it outperforms all other models presented, with a high accuracy of 97.7%.

Over the past years, the application of electronic nose devices has been investigated as an important tool for monitoring meat quality. Unfortunately, the standard of meat can easily degrade if not handled properly and become a significant hazard if consumed. Hence, the food safety system is extremely important to ensure the standard of consumable food. This paper represents, enhancements on meat quality monitoring accuracy using different classifiers: Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Network (ANN), and Decision Tree (DT), focusing on four-class classification. Unlike other research, this paper targets a new problem which is the prediction of meat remaining lifetime, using RF, SVM, ANN, and DT regressors. The dataset used here consists of readings from 9 gas sensors plus a humidity and temperature sensor. The system was trained using 67% of the dataset and was tested using the remaining 33%. The results show a maximum accuracy rate of 99.29% for classification and predicted the remaining lifetime with 0.99 R2 and 9.14 RMSE.

Early classification of coronavirus disease (COVID-19) has a vital role in controlling the rapid spread of this disease and saving patients’ lives. The fast spread of COVID-19 increased the diagnostic encumbrance of radiologists. Computed tomography (CT) imaging is an effective tool to detect COVID-19 but requires a radiology expert and takes a large time. The machine learning (ML) based models are considered as one of the important ways to analyze the CT images to detect the COVID-19 cases. Therefore, this paper has been focused on finding a suitable machine learning algorithm that can automatically analyze CT images to extract and detect COVID-19 pneumonia features with higher accuracy. This research used classifiers as the Artificial Neural Network (ANN), Support Vector Machine (SVM), Decision tree (DT) to classify CT images into COVID-19 and NonCOVID-19. This paper also designed an Adaptive Neuro-Fuzzy Inference System (ANFIS) based model to achieve a fast and accurate diagnosis of Covid-19. The CT exams of other lung diseases were included in the dataset to improve the model performance. So, the NonCOVID-19 results of the proposed models include the other lung diseases. Confusion matrices and ROC analyses of the proposed models are analyzed using 5-fold cross-validation. During the study and testing of several proposed models, the experimental results showed that the performance of the ANFIS proposed model achieved the best performance with an accuracy of 98.63% and 0.02 s testing time. In the main purpose of this study is to shed light on the ML-based COVID-19 detection models for researchers working with ML techniques and help avoid proven failures, especially for small imprecise datasets.

Image Colorization is the problem of defining colors for grayscale images. Deep neural networks proved a great success in different fields recently. Therefore, it is used to solve the image colorization problem; moreover, it proved to be a very good choice. In literature, few review papers addressed the colorization problem. Most of them classified the research papers according to one or two criteria as input image type, a number of colored output images, colorization methodology, techniques or networks used in colorization, and network paths. This review classifies the papers according to these criteria intagrally and with a relatively large number of papers. Besides, the review displays the commonly used datasets and measures of comparison. It is found that deep learning is a widely used solution methodology to the problem. Unifying the comparison measures and data sets might help show the advances of the new models.

Diabetic retinopathy (DR) is a diabetes complication that damages the retina. This type of medical condition affects up to 80% of patients with diabetes for 10 or more years. The expertise and equipment required are often lacking in areas where diabetic retinopathy detection is most needed. Most of the work in the field of diabetic retinopathy has been based on disease detection or manual extraction of features. Thus, this research aims at automatic diagnosis of the disease in its different stages using deep learning neural network approach. This paper presents the design and implementation of Graphic Processing Unit (hereby GPU) accelerated deep convolutional neural networks to automatically diagnose and thereby classify high-resolution retinal images into five stages of the disease based on its severity. The accuracy of the single model convolutional neural networks presented in this paper is 71.65% from VGG-16.

Prostate cancer (PCa) treatment strategies and optimal diagnostic are constantly changing. The goal of the pathologists is to analyze the whole slide images (WSIs) and distinguish a malignant from a benign tumor. The pathologists must have long-term experience in the detection of biomarkers of a particular disease. Medical imaging is primarily considered as one of the most significant sources to derive information regarding the biomarkers. Therefore, to assist the pathologists and clinicians, we developed Artificial intelligence (AI) based computer-aided detection (CAD) system. This paper presents an AI technique, the dual-channel parallel convolution neural network (DCPCNN) for fine-grained detection and classification. The histological grades of PCa considered for this study are benign, grade 3, grade 4, and grade 5. Therefore, the proposed AI model aims to perform multiclass classification using multiple patterns of images extracted from WSIs of a prostate biopsy. Moreover, stain normalization was performed to standardize the intensity and contrast level of the image. DCPCNN consists of two CNNs whose convolution layer outputs are concatenated for the final classification. The overall accuracy of multiclass classification achieved by DCPCNN is 98.4% indicates that the proposed model predicted the images almost perfectly accurately. Also, the research findings, limitations of the existing method, and future scope have been described distinctly in this paper.

Recently, Machine learning models gaining more popularity and can be considered as a significant investment and valuable assets for companies. These models can be used in a wide variety of tasks and in different fields of medicine, automation and robotics in factories, FinTech for banking and financial sectors as well as in modern e-commerce and marketing platforms. If these machine learning models are not well protected by intellectual property (IP), competitor can copy and steal these models and they can tweak these models to avoid detection with very little time and efforts and claiming these models as their own products. There are special considerations should be highlighted to properly draft and publish successful machine learning model patent. This paper aims to highlight the best practices of drafting patents of newly innovative machine learning models. Special focuses on the possible directions of these innovations where machine learning models can be considered as the modern solutions that need to be protected as valuable investments. This paper focused on the increased recent importance of artificial intelligence-related inventions and attempting to clarify doubts about AI-patents. The definition and understanding of functional claiming is critical step toward successful AI-patents. These efforts help researchers and developers to overcome the challenges of ambiguity of AI-patents as these patents totally different in aspects than traditional hardware circuitry patents for example. Therefore, with these guidance of the best practices the building blocks functions can be easily identified for innovative methods that can AI patentable.

An increasing volume of malicious spam calls has ushered an urgent need for a system that can automatically detect them. A robust spam call detection system must identify and block spam calls with high accuracy. Unlike current techniques that use crowd sourcing and are prone to phone number spoofing, this paper proposes a novel deep learning-based approach to classify phone calls, as spam or ham, based on the generated call transcript. This paper proposes a means of classification using embedded features with a 2-Path Hybrid Model (2PHM), comprising of a Long Short Term Memory Network (LSTM) and a Sentence Similarity Network. The 2PHM uses the transcript generated from the call by converting it into feature vectors, embedded in a high dimensional latent space, using the Universal Sentence Encoder embedding technique. Both paths of the hybrid model generate results that are weighed in an 85:15 ratio to finally generate a classification. The proposed system has been tested against Machine Learning models like Naive Bayes, K-Nearest Neighbors, Random Forests and Support Vector Machines and performs better than them, with an overall classification accuracy of 93% and a latency of 3 s.

In this paper the issue of the latency of the cognitive assistant system, which functions on the basis of the stylometry, is considered. The conducted research allows concluding that the system latency can be decreased by means of the text sample size adaptation. The first approach to this is to correlate the text samples with the data source types and the methods of the text feature vector forming. Besides, the users’ feedbacks on the cognitive assistant functioning quality can be involved into the text sample size determination. In this paper, the new method of text sample size adaptation is proposed and discussed. It includes two approaches: the first one is the ontologycal analysis based on the data source type attribute, and the second one is the cognitive analysis of the users’ feedbacks. The mixture of these approaches allows to decrease the text sample size and so to decrease the time needed for the text feature vector forming.

Brand identity plays a vital role in business success. With the strong development of the market economy and scientific and technologiccal revolution, there are many new brands introduced to the market. So, how can customers identify that brand belongs to what industry or that logo is true or false? Therefore, the enterprises should have good strategy to enhance their competitiveness, especially in the recognizing brand. Logo of the enterprise can be used as suitable objects in computer vision applications for recognizing brands and providing associated services such as logo-based commercial research, and brand trend analysis. In this paper, we will present an overview of the brand and the importance of brand recognition. Then, the paper discusses the brand determination by using different approaches, thereby showing the pros and cons of these methods. Finally, we propose strategies to improve the competitiveness for enterprises in brand recognition based on machine learning model. The results show that our method increased the performance in brand recognition with large input size; conduce to help businesses maintain; and expand and improve trust for customers. It can also contribute to prevent unfair competition, and enhance the enterprise’s position in the domestic and international market.

Due to the complexity of the domestic road environment, the real-time detection and anti-collision warning of various categories of objects on the road are the key points to be solved. The safety assistant driving system based on machine vision is a good solution to avoid danger. Through the use of deep learning algorithm, it can detect the driving, pedestrians, non-motor vehicles and other real-time and anti-collision warning in the road environment. At the same time, it can detect whether drivers have bad driving behaviors such as fatigue driving, driving distraction and timely warning, so as to ensure the safety of the driving environment. This paper mainly studies the auxiliary driving safety early warning system based on the Internet of vehicles. According to the deep learning algorithm, this paper studies the target detection algorithm and collision early warning, analyzes and compares the principles of the related algorithms in machine vision ranging, and completes the camera calibration and the camera parameter acquisition required by visual distance measurement, through stereo matching and depth map mapping, target recognition and range detection are completed. In order to study the accuracy of the relative distance detection estimation algorithm of the camera, this paper selects 6 sample pictures in the special data training center of the road, and uses the distance detection and estimation algorithm to carry out the distance detection experiment, and calculates the distance of the detected object. The experimental results show that the accuracy of distance detection decreases with the increase of distance, the relationship between them is negative.

With the development of science and technology, translation softwares have been developed faster and faster to assist people with translation. All sorts of translation softwares are emerging quickly and people can get a lot of help from using translation softwares when studying and working. It is a good complementary English translation software based on the translation corpus and to find countermeasures of the existed problems. This paper tests the data and software by using particle group improvement algorithms. The experimental results show that the accuracy of English translation software using the corpus and particle group improvement algorithm will be greatly improved. The purpose of this paper is to study the current situation of the construction of English software.

As a rapid, accurate, convenient, and non-destructive agricultural product analysis technology, NIR analysis technology has been widely used in agricultural product quality testing and raw material source identification. It is generally considered to be a non-destructive that is expected to further replace traditional agricultural chemical analysis detection technology. At present, the identification of citrus soil origin identification and crop quality monitoring technology based on near-infrared spectroscopy analysis is still relatively complicated, time-consuming, labor-consuming, and not accurate enough, and its completeness, systemicity and functionality are still not practical. The rapid identification of the origin of citrus and the effective quality supervision and inspection technology system play a very important role in promoting the healthy development of the citrus industry in our country. Based on this, this paper proposes a NIR-origin spectrum identification model based on a deep limit machine learning machine to further improve the accuracy of NIR-origin spectrum identification. First, we have a general understanding of the NIR origin spectrum identification to be studied in this article. To pave the way for the experimental part, and then propose an algorithm based on the depth limit machine (DELM) according to related technical issues, and verify it experimentally. The experimental results show that the DELM classification accuracy proposed in this paper reaches 0.932. The accuracy is better than the other two algorithms, but the PCA+machine Learning method is similar to the DELM effect, but the calculation is more complicated, requiring multiple steps such as dimensionality reduction+classifier construction, and DELM directly inputs the spectral information through depth the network and ELM are effectively integrated to construct an end-to-end feature extraction+deep classification model, which is more direct and efficient. In addition, compared with ELM, DELM can learn high-level and more abstract spectral feature expression more effectively, so it has a higher recognition rate.

With the continuous progress of science and technology, people get information on the Internet more and more quickly, the way is more and more convenient. People are more willing to use mobile devices, computers and other electronic products than to obtain information from paper books, newspapers and other channels. While using these electronic products, there will be many behaviors of storing or spreading bad information. Traditional OCR technology can be widely used in the detection and recognition of ordinary single background level text detection and recognition, but for the natural scene pictures with a certain Angle of the text detection and recognition effect is not good. With the development of deep learning technology, text detection and text recognition are mostly completed by deep learning architecture. In this paper, the popular EAST algorithm and CRNN algorithm are combined to detect and identify the text information in the natural scene.

In recent years, deep algorithms and big data and other technical means have risen rapidly, and the application of artificial intelligence has become the future development trend of various industries. In the news industry, AI is involved in all aspects of news gathering, content production, distribution and consumer consumption. This paper mainly studies the cutting-edge application and development trend of artificial intelligence in the field of new media in the era of AI. In this paper, the news media industry takes advantage of the application advantage of artificial intelligence and puts forward a news recommendation algorithm based on neural network. In this paper, the collaborative filtering method is used to recommend news by using cyclic neural network (RNN). However, in the face of the problem that the RNN network structure is repeated and difficult to recommend in parallel in collaborative filtering, this paper applies Slices Neural Network (SRNN) to the collaborative filtering recommendation system to improve the training and operating efficiency of the system.

There is a growing interest in context-aware recommendation systems (CARS) due to their ability to enable novelty, dynamism and serendipity in resulting recommendations. The incorporation of different user-contextual parameters is important in CARS. However, the problem of identifying the most optimal subset of user-contextual parameters that add real value to resulting recommendations from CARS remain unresolved. This paper investigates an approach to characterise user-contextual parameters and identify the optimal subset of parameters that enables best results from CARS algorithms. In this paper, two data sets were collected from different people in Africa, each data set had 21 classified user-contexts and corresponding likes. An association rule mining (apriori) algorithm was used to generate rules from the user profiles (user contextual-parameters) from both data sets, to identify user-contextual parameters which are strongly associated with certain user preferences. Five(5)[Hobbies, Mood, Family setup, Religion and Gender] user-contextual parameters out of the 21 were identified as the optimal subset of parameters for the domain and the data sets in this study. This optimal subset was found promising in helping CARS as the parameters which can estimate best the preferences of the users and hence led to best recommendations. This paper contributes a new method of identifying the optimal subset of user-contextual parameters in any domain, which enables CARS lgorithms to produce the most appropriate recommendations for each user.

Swarm Intelligence (SI) is a biological phenomenon that enables social species to reach group decisions by converging as real-time systems. Studied in fish schools, bird flocks, and bee swarms, SI has been shown to greatly amplify group intelligence. Artificial Swarm Intelligence (ASI) is recently developed method that enables networked human groups, moderated by real-time swarming algorithms to achieve similar benefits. While ASI can significantly boost the accuracy of group forecasts, estimation, and decisions, the process can be brittle if a large majority supports an inaccurate view, even if their average confidence is low. Thus, a major focus of ASI research has been to increase resilience to low-confidence majorities. This paper introduces a new structure called a hyperswarm that enables a confident minority to more easily sway an unsure majority, enabling convergence on solutions that would otherwise be inaccessible. The approach involves dividing a population P into a set of overlapping subgroups (H1, H2 … HP) such that each member is only exposed to the real-time behaviors of their subgroup. And because each subgroup overlaps multiple other subgroups, interactions can quickly propagate across the full population. In this paper we simulate hyperswarm dynamics, showing that a confident minority can sway a less confident majority in real time, even when more than 65% of the participants initially harbor the majority view, so long as the minority has higher confidence. In addition, we derive theoretical guidelines to predict hyperswarm success based on population size, subgroup size, and confidence differential.

Machine Learning (ML) and Artificial Intelligence (AI), in general, are based on search algorithms. In this paper, we use paradoxically the same search techniques again to look for the general theory of machine learning itself. In other words, we search for a unifying machine learning theory. For this purpose, we turn out for a help to the general theory of computation, called $-calculus, that is based on meta-search and super-turing/hypercomputational models. We hope that in such a way, we can unify machine learning and this should be useful in the development of new methods, algorithms, embedded devices and computer programs in the future. Firstly, we overview main machine learning areas as our training examples, and by applying our background knowledge we hand pick-up a hypothetical reasonable theory of ML. Next, we justify that this is a good generalization of ML. The open research question remains whether by applying various ML techniques we can induce automatically the optimal ML theory from the hypothesis space of possible theories. Thus, hopefully, the follow-up paper would be titled “In search of the optimal machine learning theory”.

This paper addresses the balancing of a haptic device by using a set of springs. The proposed haptic device is based on a purely translational parallel manipulator. Given the specific application as haptic device, it is necessary to eliminate or minimize the effect of gravity for achieving a suitable positioning and force feedback. Given the peculiarities of this haptic device, this paper reports the design, construction and preliminary testing of a simple and low-cost balancing solution based on an external set of springs. Simulation results and preliminary tests are reported for showing the engineering feasibility and effectiveness of the proposed solution.

Ship type identification in a maritime context can be critical to the authorities to control the activities being carried out. Although Automatic Identification Systems (AIS) has been mandatory for certain vessels if a vessel does not have them voluntarily or not, it can lead to a whole set of problems, so the use of tracking alternatives such as radar is fully complementary. However, radars provide positions, but not what they are detecting. Having systems capable of adding categorical information to radar detections of vessels makes it possible to increase control of the activities being carried out, improve safety in maritime traffic, and optimize on-site inspection resources on the part of the authorities. This paper addresses the binary classification problem (fishing ships versus all other vessels) using unbalanced data from real vessel trajectories. It is performed from a Deep Learning (DL) approach comparing two of the main trends, Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM). In this paper it is proposed the weighted Cross-Entropy (WCE) methodology and compared with classical data balancing strategies. Both networks show high performance when applying WCE compared to the classical machine learning approaches and classical balancing techniques. This work is shown to be a novel approach to the international problem of identifying fishing ships without contexts.

Detection of COVID-19 by using patient’s blood platelets using an artificial neural network to perform large-scale automated testing. The deep learning model uses the CBC test results to detect the virus with an accuracy of 89.26%, which achieve higher accuracy than the widely used RT-PCR test. The model has achieved accuracy with only a thousand rows, which assures that the model can achieve better results with more data. The objective of the paper is to provide an automated and accurate method to detect COVID-19 using machine learning to apply it in large-scale testing, to help in containing the virus and prevent the spread of the virus. The scope of the paper is on the detection methodology using the blood platelets values extracted from the complete blood cycle (CBC) testing and discussing the future possibilities of improving the automated prevention method. The paper uses a dataset provided by Hospital Israelita Albert Einstein in Brazil, which has over 50 features of different tests as Influenza A, Influenza B, Uria, etc.…, many of these features had missing values or wasn’t relevant to the existence of the virus in the body;therefore, the feature selection led to filtering the 17 blood features. The K-Nearest Neighbour (KNN) Imputation imputed the missing values in the 17 filtered values. The analysis & visualization of the blood features concluded that the complete blood cycle test values highly correlated with each other, and there is a change occurs due to the presence of the virus is clear, especially to Eosinophils and Leukocytes, at which they represent the white blood cells forming the immune system that reacts against any virus or bacteria attracting the human body. The paper has applied five different machine learning algorithms: logistic regression, support vector machine (SVM), random forest, K neighbours and decision tree. Meanwhile, in the second approach, used an artificial neural network with intensive use of network optimization and hyperparameter tuning to achieve the highest accuracy possible. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Detection of abnormality in Musculoskel et al. radiographs often requires the involvement of a radiologist but the recent advancement in deep learning technique helped us to detect abnormality in musculoskeletal radiographs. In this paper, each model’s performance is evaluated on unseen Mura-dataset. A novel method has been developed based on CNN architectures (DenseNet169, Vgg16 and ResNet50) by training it with MURA dataset and performed hyperparameter optimization for all the 3 models. Showing how Deep Convolution Neural Networks could be extended to medical images. DenseNet169 showed the highest accuracy. In this paper, found that model (Densenet169) achieved training accuracy of 87.88% and validation accuracy of 79.20%. In case of training loss and validation loss, the model achieved 0.3304 and 0.4887 respectively.

Wireless networks are the foundation of modern communication. This also leads to network data hijacking and network attacks. Despite the fact that different databases and methods exist to combat this, the network intrusion problem is still on the rise. To address this, the proposed research work introduces a faster and better Intrusion Detection System trained on the AWID data-set with faster learning and better accuracy. A unique supervised studying device has been evolved to categorise the community wi-fi as malicious or benign. To discover the wi-fi version by considering the detection wi-fi rate, a combination of supervised gaining knowledge of a set of rules and feature choice technique are used. Through this it is observed that, Artificial Neural Network (ANN) is primarily based on the machine studying with wrapper characteristic selection that outperform support vector machine (SVM) technique even as classifying community traffic. To assess the performance, NSL-KDD dataset with feature wrapping is used to categorise community traffic data with the use of SVM and ANN supervised machine gaining knowledge technique. Comparative studies suggests that, the proposed model is faster and more efficient than different existing fashions to recognize the intrusion detection rate. This paper aims to categorize the threats to Institute of electrical and Electronics Engineers (IEEE) 802.11n well known protocol and classify the contemporary answers and countermeasures to them. In addition, this paper proposes a more accurate, and faster widespread intrusion detection system as a proposed solution for IEEE 802.11 threats.

Self driving cars are picking up pace and thus serves as a challenging research domain. One of the most crucial functions in an autonomous vehicle is accurately detecting and recognising the traffic signs. Traffic sign detection is a crucial task in traffic sign recognition systems. Deep neural networks are proven powerful in traffic sign classification. As traffic sign violation leads to law and order disruption, posing a threat to human life, there is a need for robust algorithms with efficient actuation to perform the delegated task. Thus, this paper proposes a robust algorithm which addresses challenges like haze, fog, unclear images due to improper condition of roads to efficiently detect and recognize traffic signs using Image manipulation, Optical Character Recognition (OCR) algorithm and You Only Look Once (YOLOv3) detection algorithm. The proposed algorithm in this paper for hazy images that aids in ADAS applications has an accuracy of 87.29%. This contributes to the emerging research domains of autonomous vehicles and self-driving cars.

Background. Online platforms have now fully emerged as a platform to share their views on various subjects and issues with various viewers. Purpose. Though we have different ways of expressing ourselves, the most common is text. The dataset has texts, selected_text, punctuations, emoticons, etc. Methods. The paper targets to analyze sentiments from Twitter posts. We use the approach to train our model for detecting sentiment from tweets. Some interesting novelties in this paper are (i) including a hybrid approach for analyzing the sentiment of the tweets, (ii) introducing Jaccard similarity, and (iii) aiming to find which neural network (RNN or CNN) algorithm works better with our dataset. Results. With overall analysis, Bi-Directional LSTM performs better out of the three, and hence, the accuracy of the hybrid model enhances, indirectly. Conclusion. Finally, a concluding scope in which RNN and our hybrid approach perform better and are approximately 4–5% improved than the past models. The future implications related to the work are also given to improve the quality of the model.

The paper deals with the issues of automatic assessment of the quality of glass rods in the production process. Traditionally, quality control at glass enterprises is carried out visually by a process control operator. The high speed of modern technological processes leads to errors in quality assessment. To improve the quality of glass rods, an automatic control system based on machine vision methods is required. Such a system should automatically recognize defects in digital images that continuously come during the production process. The main task of image processing in the quality control system is the automatic search and recognition of defects. The proposed solution to this problem includes two stages. At the first stage, a set of features (descriptors) is formed, which are necessary for the classification of defects. The paper describes the presentation of features based on the use of statistical methods of segmentation of textured images. For the formation of descriptors, the information contained in the histograms of the first and second orders was used. A grayscale difference matrix was also used. The procedure for validating and classifying defects was carried out using a deep learning neural network. The description of the network and the algorithm for its training are given. In order to assess the effectiveness of the automatic defect recognition system, tests were carried out. The results of these tests showed that the use of a neural network and the proposed representation of features provides good discrimination for the analysis and classification of glass rod defects.

This paper presents an open-sourced MATLAB simulation and analysis platform dedicated to legged climbing robots. This simulator enables the design of any limbed robotic system as an articulated multi-body with a floating base and simulates it walking and climbing in an arbitrary environment. The main variable environmental parameters are inclination, gravity, and ground stiffness, and any point cloud can be installed as the terrain map. Furthermore, the simulator employs a rigid body dynamics engine. This paper first describes the simulator structure, and the computational flow and next presents the representative simulation examples where quadrupedal robots assumed gripping on the wall or climbing on the steep slope.

Various Optical Character Recognition (OCR) methods, especially, machine learning models, work towards the solution of recognizing patterns in intelligent ways from data that is originally not available in digital format. These patterns are converted into data that a machine can recognize (by the proper algorithm) and can further manipulate for various manipulations. The basic characteristics of the implementation presented here are based on a balance between the complexity of the algorithm applied and the highest precision that can be obtained. In this paper, we attempt to recognize precise patterns from a set of handwritten characters without making the implementation intractably complex. Specifically, in the context of the Urdu language spoken and written by more than a hundred million people around the world, very little exploration has been carried out. This paper proposes the application of an established machine learning model, namely, using the Support Vector Machine (SVM) algorithm; and investigates the efficiency of its application for recognizing handwritten characters of the Urdu language, a subject that has never been investigated before.

Facial Expression recognition (FER) is a vital field of artificial intelligence and computer vision owing to its remarkable academic potential. Recognition of facial expression has many implicit applications, and it has attracted much attention of researchers during the last decade. The relation between the facial features to each human emotion is the main focus of the investigation. By training a neural network with such features, one can realize a system that can provide analytical data on human behaviors. This paper proposes a facial expression recognition system architecture based on a deep convolutional neural network. In the course, various neural networks are studied and compared on their facial expression recognition, and one can find that the CNN deep learning method can be one of the best options to take. The paper includes human facial emotion detection procedures that include three significant steps: face recognition; characteristic feature extraction; emotion classification. A set of experiments is performed to evaluate the proposed system’s performance, and the recognition accuracy is measured in terms of the facial emotion recognition challenge (FERC-2013) and Japanese female facial expression (JAFFE) dataset.

Many dynamic ensemble selection (DES) methods are known in the literature. A previously-developed by the authors, method consists in building a randomized classifier which is treated as a model of the base classifier. The model is equivalent to the base classifier in a certain probabilistic sense. Next, the probability of correct classification of randomized classifier is taken as the competence of the evaluated classifier. In this paper, a novel randomized model of base classifier is developed. In the proposed method, the random operation of the model results from a random selection of the learning set from the family of learning sets of a fixed size. The paper presents the mathematical foundations of this approach and shows how, for a practical application when learning and validation sets are given, one can determine the measure of competence and build a MC system with the DES scheme. The DES scheme with the proposed model of competence was experimentally evaluated on the collection of 67 benchmark datasets and compared in terms of eight quality criteria with two ensemble classifiers which use the previously-proposed concepts of randomized model. The proposed approach achieved the lowest ranks for almost all investigated quality criteria.

The paper deals with the issue of hate speech and radicalization. Oftentimes, they are spread by means of social media. Twitter lets one express their views in a relatively anonymous way; however, it seems to be a simple, yet effective tool for disseminating offensive or radical contents, too. The paper proposes an effective solution which applies machine learning for detecting signs of radicalization and hate speech in Twitter posts. The authors decided to use the Polish language, which due to the level of its complexity is known to pose a challenge for automated sentiment analysis. The authors also needed to create their own dataset of posts containing hate speech, as prior to the experiment, there existed no such datasets in the language. In the paper, the underlying technologies are first presented, then the course of experiment is described and the final conclusions are given thereafter.

Only 4% of household waste generated in Africa is recycled. Current research uses machine learning models in cloud-based solutions to classify waste. However, in countries with limited internet access, there is a need to increase user engagement in classifying waste using an on-device approach. Developing a machine learning model for a mobile device with limited size and speed is a challenge. This research proposes an on-device deep learning framework to encourage the recycling of household waste. The proposed framework combines an optimal deep learning image classification model and gamification elements. A combination of multiple waste datasets named WasteNet consisting of 33,520 images is used to train the deep learning image classification model using seven classes of recyclable waste namely e-waste, garbage, glass, metal, organic, paper and plastic. Data augmentation and transfer learning techniques are applied to train five models on a mobile device namely, MobileNetV2, VGG19, DenseNet201, ResNet152V2 and InceptionResNetV2. Results of the five models are presented in this paper based on accuracy, loss, latency and size. This research shows promise for InceptionResNetV2, MobileNetV2 and DenseNet201in encouraging householders to engage in recycling waste using gamification on a mobile device.

Advanced driver-assistance systems (ADAS) play a significant role in reducing traffic fatalities and vehicular accidents. Among the many ADAS technologies is the blind spot alert monitor alerts you of a vehicle or an obstruction before you change lanes. This paper investigates extending the monitoring concept to detect if a car emerging from the blind spot is attempting to cut into your lane. In that respect, we would perceive the direction of the infringing vehicle. There are various means of sensing such a situation, including radar, lidar, camera, and sonar. We focus on using lidar and deep learning for this purpose in this paper. In particular, we present the experiments carried out to verify the concept, including details of the equipment, experimental data, and MATLAB Deep Learning for detection.

Roads make a huge contribution to the economy of a territory. As a platform for transportation, roads are widely used by every countries in the world. Potholes in road are one of the major concerns in the transportation infrastructure. A lot of research works have been proposed using Computer Vision to detect potholes that include wide range of image processing and object detection algorithms. There is a need for potholes detection with adequate accuracy and speed, and that can be implemented with ease and low setup cost. In this paper, we have developed efficient deep learning Convolution Neural Networks (CNNs) to detect potholes in real-time with adequate accuracy. This paper compares the performance of YOLOv5 Large (Y\(_{l}\)), YOLOv5 Medium (Y\(_{m}\)) and YOLOv5 Small (Y\(_{s}\)) with ResNet101 backbone and Faster R-CNN with ResNet50 (FPN), VGG16 and MobileNetV2 backbone. The experiments results show that YOLOv5s is more applicable for real-time potholes detection because of its speed. It is able to detect potholes in high as well as low resolution images in 0.009s. With the use of Inverse Perspective Mapping with YOLOv5 to estimate area, we concluded that the detection can still be done in real time with area estimation.

Swarm Robotics is an emerging field of adapting the phenomenon of natural swarms to robotics and a study of robots to mimic natural swarms, like ants and birds, to form a scalable, flexible, and robust system. These robots show self-organization, autonomy, cooperation, and coordination amongst themselves. Additionally, their cost and design complexity factor must be as low as possible to reach systems similar to natural swarms. Further, the communication amongst the robots can either be direct (robot-to-robot) or indirect (robot-to-environment) and without any central entity to control them. Swarm robotics has a wide range of application fields, from simple household tasks to military missions. This paper reviews the swarm robotics approaches from its history to its future based on 217 references. It highlights the prominent pioneers of swarm robotics and enlights the initial swarm robotics methods. The presence of swarm robotics is shown based on simulators, projects, and real-life applications. For the future, this paper presents visions and ideas of swarm robotics.

Fine-tuning the pre-trained language model is the current mainstream method of text classification. Take the fine-tuning BERT model as an example, this kind of approach has three main problems: the first one is that the training of massive parameters will cause high training costs The second is that the model is very easy to over-fit in trainable samples, resulting in low transferability. Third, the fine-tuning model is not good at long text classification task. In this paper, we take the sentiment classification task as an example and use the classification accuracy as a metric. We compared two methods to problem one: using a compressed language model (decreased 0.1%) and using entirely frozen weight (reduced by 4%). For the second problem, in the case of using fixed weights (reduced by 4%), Convolutional Networks (CNN) and Capsule Networks (CAP) are used to extract n-gram features and clustering features so that the classification accuracy is improved (increased by 0.5% and decreased by 0.2% respectively). The corpus transfer test shows that CAP’s accuracy is greater than the fine-tuning model (increased by 0.6%). Meanwhile, this article proposes a method to process the long text classification task by expanding position embedding to support long text input (increased by 1.1%). Finally, this paper compares the training speed and parameter scale of different models under the combination of different strategies, and uses the F1 value, precision rate, recall rate and accuracy to measure each model.

Setting a question paper is an integral activity of a teaching-learning process, it is more so in formal education systems such as schools, colleges and Universities. At times, it becomes a tricky and annoying act for the tutor to divert oneself from main stream teaching and spend time thinking about setting a question paper on the intended topic. This paper presents an Artificial Intelligence powered, web enabled, personalized service application for the educators to automatically set up a question paper on the selected topic/syllabus. The application allows the setter to choose the type of the questions, type of headers, number of allotted marks etc. and in a click of a button the question paper is displayed in the desired format. The application silently scrapes the relevant web content in the background and creates a database of questions with topics, weights, and levels of difficulty. The application also allows the user to enter the questions manually and integrates them into the database. The application has an answer database module to couple the correct answers with the questions. The AI component of the application works on text mining and content classification. It also assists in suggesting questions on the supplied text content. The application allows the user to have a simple login and explore the QPSetter for the personal usage. This application is useful for all levels of tutors who want to automatically set the question papers. It helps in preserving, confidentiality, integrity of the question papers along with helping in a quick time question paper setting.

Extracting information of musical attributes such as harmony and key modulation from the symbolic music text is a critical process in Music Information Retrieval (MIR) systems. This research paper presents a new approach to automatically detect key modulations in a musical piece considered in its symbolic musical level. The method does not entail any preset rules respect to the musical grammar. The Markov process is used in order to identify the relations between the sounds and their movement within the harmonic structure. The information theory is used to define the tonality (or key) when sounds are changed by means of accidentals (sharp, flat or natural). The method has been tested on tonal polyphonic compositions and gave encouraging results, with an accuracy ranging between 82% and 91% on the base of the historical period of the analyzed music composition. Future improvements of the method are discussed briefly at the end of the paper.

This paper proposes a standard way to represent sparse tensors. A broad theoretical framework for tensor data scattering methods used in various deep learning frameworks is established. This paper presents a theorem that is very important for performance analysis and accelerator optimization for implementing data scattering. The theorem shows how the impossibility of slicing happens in tenser data scattering. A sparsity measuring formula is provided, which can effectively indicate the storage efficiency of sparse tensor and the possibility of parallelly using it. The source code, including CUDA code, is provided in a related open-source project.

The paper presents a new approach to recognize small parts from high-resolution 4K images grabbed by the embedded camera with trained convolutional network models. The main principle is a combination of standard machine vision techniques (OpenCV library) to identify blobs in the high-resolution image and parse to a suitable set of regions of interest, which are later recognized by trained convolutional neural network model (Tensorflow framework). The convolutional neural network model with single-shot detection was selected to identify the position of the object. 3D virtual models of parts with autogenerated orientations are used for simpler input data generation. Two embedded devices were selected for use in the experimental system. The first is NVidia Xavier dev board with 4K camera and integrated APU and the second is Raspberry PI 4 with external APU Intel Neural Compute Stick 2. The last part of the paper shows the implementation of the presented principle to the virtual device (HTC Vive Pro) for assisted assembly tasks to train and check workers during the teaching process.