Search

Artificial Intelligence is quickly emerging as a technological solution for the agriculture industry to surmount its classical challenges. Artificial Intelligence is facilitating farmers to refine their products and alleviate unfavourable impacts due to the environment. The central concern of this paper is predictive analytics to develop a machine learning model to identify and predict crop yield based on multiple environmental factors. In this paper, a hybrid learner 'RaNN' is proposed that combines the feature sampling and majority voting technique of Random Forest in-combination with the multilayer Feedforward Neural Network to predict the crop yield. Research has also ascertained the essential features responsible for accurate yield prediction. The proposed model works for rice yield prediction, one of the chief grains of India. The region chosen for the work is Punjab, which is among the largest producer states of India for rice. The dataset consists of 15 attributes comprising the weather and agriculture data collected from the Indian Meteorological Department Pune, and Punjab Environment Information System (ENVIS) Center, Government of India. The study has also made a comparative assessment of 'RaNN' with machine learning methods like Multiple Linear Regression, Random Forest, Decision Tree, Boosting Regression, Support Vector Machine Regression, Ensemble Learner, and Artificial Neural Network. Our model RaNN has listed a better prediction accuracy with minimal error among the other techniques providing a 98% correlation between the actual and the predicted yield. Abbreviations: AI – Artificial Intelligence; ANN – Artificial Neural Network; BR – Boosting Regression; Chem Fert – chemical fertilisers; DT – Decision Tree; EL – Ensemble Learner; ENVIS – Punjab Environment Information System; GBM – Stochastic Gradient Boosting Method; GPS – Global Positioning System; HMAX – highest maximum temperature in degrees C; IMD – Indian Meteorological Department; L1 – Lasso regression; L2 – Ridge regression; LMIN – lowest minimum temperature; ML – Machine Learning; MAE – Mean Absolute Error; MEVP – mean evaporation in mm; MLR – Multiple Linear Regression; MMAX – mean maximum temperature in degrees C; MMIN – mean minimum temperature in degrees C; MSSH – Mean sunshine duration in hours; MWS – mean wind speed in km/h; P1 – number of days with precipitation (0.1–0.2 mm); P2 – number of days with precipitation (greater than or equal to 0.3 mm); RaNN – Hybrid RF-ANN model; RMSE – Root Mean Squared Error; $${R^2}$$ R 2 – Coefficient of determination; RD – number of rainy days; RF – Random Forest; SVM Reg – Support Vector Machine Regression; TMRF – total rainfall per month in mm [ABSTRACT FROM AUTHOR]

Fashion image retrieval is one of the important services of e-commerce platforms, and it is also the basis of various fashion-related AI applications. Studies have shown that in a multi-modal environment (images + attribute labels), embedding items into specific attribute spaces can support more fine-grained similarity measures, which is especially suitable for fashion retrieval tasks. In this paper, we propose an attention-based attribute-guided similarity learning network (AttnFashion) for fashion image retrieval. The core of this network is an attribute-guided spatial attention module and an attribute-guided channel attention module, which correspond to the mapping between attributes and image regions, and the mapping between attributes and high-level image semantics, respectively. To make these two modules interact deeply, we design a parallel structure that allows them to share attribute embeddings and guide each other to extract specific features, which also helps to reduce the network parameters of the attention modules. An adaptive feature fusion strategy is proposed to synthesise the features extracted by the two modules. Extensive experiments show that the proposed AttnFashion performs better than current competitive networks in the field of fine-grained attribute-based fashion retrieval. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) has undergone major advances over the past decades, propelled by key innovations in machine learning and the availability of big data and computing power. This paper surveys the historical progress of AI from its origins in logic-based systems like the Logic Theorist to recent deep learning breakthroughs like Bidirectional Encoder Representations from Transformers (BERT), Generative Pretrained Transformer 3 (GPT-3) and Large Language Model Meta AI (LLaMA). The early rule-based systems using handcrafted expertise gave way to statistical learning techniques and neural networks trained on large datasets. Milestones like AlexNet and AlphaGo established deep learning as a dominant AI approach. Transfer learning enabled models pre-trained on diverse corpora to excel at specialised downstream tasks. The scope of AI expanded from niche applications like playing chess to multifaceted capabilities in computer vision, natural language processing and dialogue agents. However, current AI still needs to catch up to human intelligence in aspects like reasoning, creativity, and empathy. Addressing limitations around real-world knowledge, biases, and transparency remains vital for further progress and aligning AI with human values. This survey provides a comprehensive overview of the evolution of AI and documents innovations that shaped its advancement over the past six decades. [ABSTRACT FROM AUTHOR]

The paper introduces partial set-theoretic relations for metasets and investigates their properties. Metaset is a concept of imprecise set designed to represent vague notions in Artificial Intelligence, whose idea stems from Boolean-valued techniques in classical set theory. The basic set relations are extended to functions valued in a Boolean algebra or unit interval. Important classical set theory axioms: extensionality and comprehension are formulated for metasets. The latter enables formal definitions of collections with blurred boundaries by using set-theory formulae. This facilitates representing and reasoning about imprecise data. [ABSTRACT FROM AUTHOR]

This paper investigates how agents learn and perform efficient strategies by trying different actions in asymmetric confrontation setting. Firstly, we use Gomoku as an example to analyse the causes and impacts of asymmetric confrontation: the first mover gains higher power than the second mover. We find that the first mover learns how to attack quickly while it is difficult for the second mover to learn how to defend since it cannot win the first mover and always receives negative rewards. As such, the game is stuck at a deadlock in which the first mover cannot make further advances to learn how to defend, and the second mover learns nothing. Secondly, we propose an ancillary mechanism (AM) to add two principles to the agent's actions to overcome this difficulty. AM is a guidance for the agents to reduce the learning difficulty and to improve their behavioural quality. To the best of our knowledge, this is the first study to define asymmetric confrontation in reinforcement learning and propose approaches to tackle such problems. In the numerical tests, we first conduct a simple human vs AI experiment to calibrate the learning process in asymmetric confrontation. Then, an experiment of 15*15 Gomoku game by letting two agents (with AM and without AM) compete is applied to check the potential of AM. Results show that adding AM can make both the first and the second movers become stronger in almost the same amount of calculation. [ABSTRACT FROM AUTHOR]

Automated planning is a prominent Artificial Intelligence (AI) challenge that has been extensively studied for decades, which has led to the development of powerful domain-independent planning systems. The performance of domain-independent planning systems are strongly affected by the structure of the search space, that is dependent on the application domain and on its encoding. This paper proposes and investigates a novel way of combining machine learning and heuristic search to improve domain-independent planning. On the learning side, we use learning to predict the plan cost of a good solution for a given instance. On the planning side, we propose a bound-sensitive heuristic function that exploits such a prediction in a state-space planner. Our function combines the input prediction (derived inductively) with some pieces of information gathered during search (derived deductively). As the prediction can sometimes be grossly inaccurate, the function also provides means to recognise when the provided information is actually misguiding the search. Our experimental analysis demonstrates the usefulness of the proposed approach in a standard heuristic best-first search schema. [ABSTRACT FROM AUTHOR]

Humans are affected by some diseases due to ageing, which raises the necessity of effective healthcare operation schemes. Such techniques are necessary to provide efficiently and cost-effectively service to patients at the proper time. The huge knowledge required to process the HC application is obtained from the developed HC technologies. Research has recently shown that artificial intelligence (AI) can facilitate extraordinary performance for various HC applications. However, recently different metaheuristic-based optimisation algorithms have been developed to improve AI-based HC techniques’ performance. Therefore, this review discusses different HC models that leverage the benefits of metaheuristic algorithms to achieve better performance. The major goal of this review is to support the researchers seeking a better reference to develop secure and smarter metaheuristic-based HC models. These models are efficient in reducing system complexity by improving efficiency. But in the future, many openings are available to meet such requirements efficient techniques that satisfy all the existing challenges. This developed review has surveyed and summarised different challenges and future directions to understand the available challenges. This research reviews various journal publications based on the metaheuristic approach.es from the recent papers available in standard journals from 2015 to 2021. [ABSTRACT FROM AUTHOR]

Currently, there is no effective cure for SARS-COVID-19 diseases. The identification of novel therapeutic targets and drug-like compounds is required for the development of anti-COVID-19 drugs. Virtual screening is currently the most significant component for identifying drug-like molecules from large datasets for drug design and development. However, there are no effective easily available and user-friendly applications for virtual screening of drug leads against SARS-COV-2. Therefore, we have developed a user-friendly web-app named 'AIDrugApp' for the virtual screening of inhibitor molecules against SARS-CoV-2. AIDrugApp is a novel open-access, deep learning AI-based inhibitory activity prediction and data statistics visualisation platform. Users can predict the inhibitory activities (Active/Inactive) and pIC-50 values of new compounds against SARS-CoV-2 replicase polyprotein, 3CLpro and human angiotensin-converting enzymes. It is also useful for virtual screening of chemical features of molecules towards SARS-COVID-19 clinical trial bioactivities. This paper presents the development and architecture of AIDrugApp. We also present two case studies where large sets of molecules were screened using the 'Bioactivity Prediction' module of our app. Screened molecules were analysed further for validation by molecular docking and ADME analysis to identify the potential drug candidates. [ABSTRACT FROM AUTHOR]

Coronavirus disease (COVID-19) pandemic has intensively damaged human socio-economic lives and the growth of countries around the world. Many efforts have been made in the direction of artificial intelligence (AI) techniques to detect the corona at an early stage and take necessary precautions to stop it from spreading or recovery from the infection. However, the situation and solutions are still challenging. In this paper, we proposed various technological aspects, solutions using a supervised/unsupervised manner and continuous health monitoring with physiological parameters. Finally, the performance of COVID-19 detection with Gaussian mixture model-universal background model (GMM-UBM) technique using the voice signal has been demonstrated. The developed system achieves the COVID-19 detection performance in terms of areas under receiver operating characteristic (ROC) curves in the range 60–67%. Moreover, the various lessons learned from the current COVID-19 crisis are presented for future directions. [ABSTRACT FROM AUTHOR]

A catastrophic epidemic of Severe Acute Respiratory Syndrome-Coronavirus, commonly recognised as COVID-19, introduced a worldwide vulnerability to human community. All nations around the world are making enormous effort to tackle the outbreak towards this deadly virus through various aspects such as technology, economy, relevant data, protective gear, lives-risk medications and all other instruments. The artificial intelligence-based researchers apply knowledge, experience and skill set on national level data to create computational and statistical models for investigating such a pandemic condition. In order to make a contribution to this worldwide human community, this paper recommends using machine-learning and deep-learning models to understand its daily accelerating actions together with predicting the future reachability of COVID-19 across nations by using the real-time information from the Johns Hopkins dashboard. In this work, a novel Exponential Smoothing Long-Short-Term Memory Networks Model (ESLSTM) learning model is proposed to predict the virus spread in the near future. The results are evaluated using RMSE and R-Squared values. [ABSTRACT FROM AUTHOR]

The work presents a concept of an implementation of an explainable artificial intelligence (XAI) using effective models of third-generation neurons. The article discusses a concept of building a neural network based on spiking neurons modelled on ladder nervous systems. A distinction is made between voltage signals encoding information in a network and current signals which contain the correlation between information in the network and pattern features. Analyzes feature a neuron model based on the cusp catastrophe theory eliminating network sensitivity to problems of synapse plasticity, weight mismatch and coupling of neurons based on electric models. The paper presents applications of a spiking neural network for reporting the state of water quality while generating justifications. The article contains results of an analysis of confusion of justifications with ACC = 1 for a set of 10,000 patterns. It also discusses the speed of pattern analysis in the simulated network. [ABSTRACT FROM AUTHOR]

Research on machine deep learning with fuzzy neural network (FNN) is one hot topic in the Artificial Intelligent (AI) domain. In order to support the application of the IoT (Internet of Things) and make use of these image data to get perfect image reasonably and efficiently, it is necessary to fuse these sensed data, therefore the multiple-sensors' image aggregation becomes a key technology. In this paper, novel FNN-based machine deep learning approach for image aggregation in application of the IoT is proposed. When this approach is done, dynamic learning from eigenvalue transition example can improve traditional learning approach based on static eigenvalue of example. And the neural network is used to be demonstrated its unique superiority of image understanding. FNN-based machine deep learning approach can learn from dynamic eigenvalues, the change of data can be learned and the varieties of the eigenvalue can be understood and remembered. The relative experiments have shown the designed approach for image aggregation is fast and effective, and it can be adapted for the many image applications of the IoT. [ABSTRACT FROM AUTHOR]

Recent advancements in the field of Artificial Intelligence (AI) have provided an opportunity to create autonomous devices, robots, and machines characterised particularly with the ability to make decisions and perform tasks without human mediation. One of these devices, Unmanned Aerial Vehicles (UAVs) or drones are widely used to perform tasks like surveillance, search and rescue, object detection and target tracking, and many more. Efficient real-time object detection in aerial videos is an urgent need, especially with the increasing use of UAV in various fields. The sensitivity in performing said tasks demands that drones must be efficient and reliable. This paper presents our research progress in the development of applications for the identification and detection of person using the convolutional neural networks (CNN) YOLO-v2 based on the camera of drone. The position and state of the person are determined with deep-learning-based computer vision. The person detection results show that YOLO-v2 detects and classifies object with a high level of accuracy. For real-time tracking, the tracking algorithm responds faster than conventionally used approaches, efficiently tracking the detected person without losing it from sight. [ABSTRACT FROM AUTHOR]

In the object recognition task, due to changes in size, colour, illumination, position, viewing angle, and environmental background, great uncertainty is caused. The invariant recognition capability required to adapt to such diverse uncertainties has also become one of the most challenging goals of artificial intelligence, as only biometric systems can do this. The approach to dealing with uncertainty in the field of pattern recognition is nothing more than training with a large number of samples and powerful machine learning algorithms, and finally generating a classifier. Among them, knowledge representation has not only been ignored, but has even been considered redundant. But research from cognitive psychology and experimental psychology suggests that humans do not use such a huge mechanism. In contrast, we use more similar methods of symbolic artificial intelligence, such as representation, induction, reasoning, interpretation, and constraint propagation, to deal with uncertainty in object recognition. In this paper, the skeleton tree is used as the basic means to form the formal representation of the topological features and geometric features of the object, and based on the generalisation framework, the knowledge extraction of a small number of similar representations is used to form a generalised explicit representation of the knowledge about the object category. This generalised form representation can cope with uncertainties such as size, colour, shape, etc., and is significantly superior to current mainstream machine learning methods in terms of explainability and computational cost. [ABSTRACT FROM AUTHOR]