A Smartphone-based Plant Disease Detection and Treatment Recommendation System using Machine Learning Techniques

Plant diseases cause major crop production losses worldwide, and a lot of significant research effort has been directed toward making plant disease identification and treatment procedures more effective. It would be of great benefit to farmers to be able to utilize the current technology in order to leverage the challenges facing agricultural production and hence improve crop production and operation profitability. In this work, we designed and implemented a user-friendly smartphone-based plant disease detection and treatment recommendation system using machine learning (ML) techniques. CNN was used for feature extraction while the ANN and KNN were used to classify the plant diseases; a content-based filtering recommendation algorithm was used to suggest relevant treatments for the detected plant diseases after classification. The result of the implementation shows that the system correctly detected and recommended treatment for plant diseases

AI-based Analysis on Relationship between Genes and Personality

AI can be applied in various ways to the measurement of personality in psychology. Measuring the impact of a single gene on personality can be handled by AI technologies, at least technically, i.e., using supervised learning models of machine learning. The ABO blood type is a relatively easy biological marker to examine; therefore, people in many countries know their type, and its impact on the relationship with personality has been the subject of a large amount of research. In this study, we selected the ABO blood type as the target gene, examined its association with personality, and cross-checked the results with previous works. Two scales were used to measure personality: a) blood type personality traits extracted from previous studies, and b) the TIPI-J, a simplified version of the Big Five personality test. In the former, the AI was able to predict the respondents’ blood types with a higher probability than chance, while in the latter, the accuracy was within the range of chance. These obtained results were also discussed.

Algorithm for the set of similarity criteria formation for a physical process in the class of homogeneous functions

The efficiency of application of linear programming methods to problems of the theory of similarity and dimensions is shown. A general algorithm for formation of the set of similarity criteria for a physical process in the class of homogeneous functions is proposed. The set of systems of linear algebraic equations is created using the combinatorial method and chain diagrams. Basic and free variables and their corresponding variants of dimensionless sets of independent arguments, which are taken as the main similarity criteria, are distinguished. The set of derived similarity criteria is found using the basic criteria and the Cayley table.

The Interesting and Complete Artificial Intelligence (ICAI) – Version 1

A new field titled “The Interesting and Complete Artificial Intelligence (ICAI)” is invented in this work. In this article, we define this new ICAI field. Four new ICAI algorithms are designed in this work. This paper titled “The Interesting and Complete Artificial Intelligence (ICAI) – Version 1” is just the starting point of this new field. We request Research Scientists across the globe to work in this new direction of Artificial Intelligence and publish their work with titles such as “The Interesting and Complete Artificial Intelligence (ICAI) – Version 1.1”, “The Interesting and Complete Artificial Intelligence (ICAI) – Version 2” or “The Interesting and Complete Artificial Intelligence (ICAI) – Final Version”.

Nearly Reversible ECG Steganography based on Polar Coordinate System with Digital Replacement Technique

In this paper, we present a nearly reversible data hiding for electrocardiogram (ECG) hosts. Based on the polar coordinate system domain, medical diagnosis and personal data can be embedded in an ECG signal by the simple digital replacement technique. Simulations revealed that the restored ECG with near lossless quality can be obtained by the proposed method at receiver site. In addition, the perceived quality of the marked ECG is very good with a high payload size. Moreover, the resultant signal-to-noise ratio (SNR), peak SNR, and payload of the proposed method outperforms those of existing techniques. Since the computation cost is low, the proposed method can be used in portable biometrics or ECG measuring instruments.

ASER: Arabic Speech Emotion Recognition Employing Wav2vec2.0 and HuBERT Based on BAVED Dataset

Recently, there have been tremendous research outcomes in the fields of speech recognition and natural language processing. This is due to the well-developed multilayers deep learning paradigms such as wav2vec2.0, Wav2vecU, WavBERT, and HuBERT that provide better representation learning and high information capturing. Such paradigms run on hundreds of unlabeled data, then fine-tuned on a small dataset for specific tasks. This paper introduces a deep learning constructed emotional recognition model for Arabic speech dialogues. The developed model employs the state of the art audio representations include wav2vec2.0 and HuBERT. The experiment and performance outcomes of our model overcome the previous known results.

Self-Driving Vehicles Using End to End Deep Imitation Learning

Autonomous Driving is one of the difficult problems faced the automotive applications. Nowadays, it is restricted due to the presence of some laws that prevent cars from being fully autonomous for the fear of accidents occurrence. Researchers try to improve the accuracy and safety of their models with the aim of having a strong push against these restricted Laws. Autonomous driving is a sought-after solution which isn’t easily solved by classical approaches. Deep Learning is considered as a strong Artificial Intelligence paradigm which can teach machines how to behave in difficult situations. It proved its success in many differ domains, but it still has sometime in the automotive applications. The presented work will use the end-to-end deep machine learning field in order to reach to our goal of having Full Autonomous Driving Vehicle that can behave correctly in different scenarios. CARLA simulator will be used to learn and test the deep neural networks. Results will show not only performance on CARLA’s simulator as an end-to-end solution for autonomous driving, but also how the same approach can be used on one of the most popular real datasets of automotive that includes camera images with the corresponding driver’s control action.

Analytical modeling of the binary dynamic circuit motion

The binary dynamic circuit, which can be a design scheme for a number of technical systems is considered in the paper. The dynamic circuit is characterized by the kinetic energy of the translational motion of two masses, the potential energy of these masses’ elastic interaction and the dissipative function of energy dissipation during their motion. The free motion of a binary dynamic circuit is found according to a given initial phase state. A mathematical model of the binary dynamic circuit motion in the canonical form and the corresponding characteristic equation of the fourth degree are compiled. Analytical modeling of the binary dynamic circuit is carried out on the basis of the proposed particular solution of the complete algebraic equation of the fourth degree. A homogeneous dynamic circuit is considered and the reduced coefficients of elasticity and damping are introduced. The dependence of the reduced coefficients of elasticity and damping is established, which provides the required class of solutions to the characteristic equation. An ordered form of the analytical representation of a dynamic process is proposed in symmetric determinants, which is distinguished by the conservatism of notation with respect to the roots of the characteristic equation and phase coordinates.

Handwritten Signature Biometric Data Analysis for Personality Prediction System Using Machine Learning Techniques

Handwritten signature has been considered as one of the most widely accepted behavioral personal trait in Biometric security system; and It contains various dynamic and innate behavioral traits like shapes and patterns which can certainly find a person’s soft characteristics like age, gender, Personality, handedness and many more. Person’s signature or handwriting determines the state of the person’s mind or personality characteristics at the time of writing. This paper provides a personality prediction system of different characteristics determining the personality of a person based on offline handwritten signature Images. Experiments are carried out using supervised learning techniques. Results shows a significant recognition rate and validates the effectiveness against the state-of-art techniques in comparison to similar works.

The Efficiency of Aggregation Methods in Ensemble Filter Feature Selection Models

Ensemble feature selection is recommended as it proves to produce a more stable subset of features and a better classification accuracy when compared to the individual feature selection methods. In this approach, the output of feature selection methods, called base selectors, are combined using some aggregation methods. For filter feature selection methods, a list aggregation method is needed to aggregate output ranked lists into a single list, and since many list aggregation methods have been proposed the decision on which method to use to build the optimum ensemble model is a de facto question. In this paper, we investigate the efficiency of four aggregation methods, namely; Min, Median, Arithmetic Mean, and Geometric Mean. The performance of aggregation methods is evaluated using five datasets from different scientific fields with a variant number of instances and features. Besides, the classifies used in the evaluation are selected from three different classes, Trees, Rules, and Bayes. The experimental results show that 11 out of the 15 best performance results are corresponding to ensemble models. And out of the 11 best performance ensemble models, the most efficient aggregation methods are Median (5/11), followed by Arithmetic Mean (3/11) and Min (3/11). Also, results show that as the number of features increased, the efficient aggregation method changes from Min to Median to Arithmetic Mean. This may suggest that for a very high number of features the efficient aggregation method is the Arithmetic Mean. And generally, there is no aggregation method that is the best for all cases.