A Novel CCA-NMF Whitening Method for Practical Machine Learning Based Underwater Direction of Arrival Estimation

Underwater direction of arrival(DOA)estimation has always been a very challenging theoretical and practical problem.Due to the serious non-stationary,non-linear,and non-Gaussian characteristics,machine learning based DOA estimation methods trained on simulated Gaussian noised array data cannot be directly applied to actual underwater DOA estimation tasks.In order to deal with this problem,environmental data with no target echoes can be employed to analyze the non-Gaussian components.Then,the obtained information about non-Gaussian components can be used to whiten the array data.Based on these considerations,a novel practical sonar array whitening method was proposed.Specifically,based on a weak assumption that the non-Gaussian components in adjacent patches with and without target echoes are almost the same,canonical cor-relation analysis(CCA)and non-negative matrix factorization(NMF)techniques are employed for whitening the array data.With the whitened array data,machine learning based DOA estimation models trained on simulated Gaussian noised datasets can be used to perform underwater DOA estimation tasks.Experimental results illustrated that,using actual underwater datasets for testing with known machine learning based DOA estimation models,accurate and robust DOA estimation performance can be achieved by using the proposed whitening method in different underwater con-ditions.

A Machine Learning-Based Web Application for Heart Disease Prediction

This work leveraged predictive modeling techniques in machine learning (ML) to predict heart disease using a dataset sourced from the Center for Disease Control and Prevention in the US. The dataset was preprocessed and used to train five machine learning models: random forest, support vector machine, logistic regression, extreme gradient boosting and light gradient boosting. The goal was to use the best performing model to develop a web application capable of reliably predicting heart disease based on user-provided data. The extreme gradient boosting classifier provided the most reliable results with precision, recall and F1-score of 97%, 72%, and 83% respectively for Class 0 (no heart disease) and 21% (precision), 81% (recall) and 34% (F1-score) for Class 1 (heart disease). The model was further deployed as a web application.

Fault Identification and Health Monitoring of Gas Turbine Engines Using Hybrid Machine Learning-based Strategies

Ahealth monitoring scheme is developed in this work by using hybrid machine learning strategies to iden-tify the fault severity and assess the health status of the aircraft gas turbine engine that is subject to component degrada-tions that are caused by fouling and erosion.The proposed hybrid framework involves integrating both supervised recur-rent neural networks and unsupervised self-organizing maps methodologies,where the former is developed to extract ef-fective features that can be associated with the engine health condition and the latter is constructed for fault severity modeling and tracking of each considered degradation mode.Advantages of our proposed methodology are that it ac-complishes fault identification and health monitoring objectives by only discovering inherent health information that are available in the system I/O data at each operating point.The effectiveness of our approach is validated and justified with engine data under various degradation modes in compressors and turbines.

UCAV situation assessment method based on C-LSHADE-Means and SAE-LVQ

The unmanned combat aerial vehicle(UCAV)is a research hot issue in the world,and the situation assessment is an important part of it.To overcome shortcomings of the existing situation assessment methods,such as low accuracy and strong dependence on prior knowledge,a datadriven situation assessment method is proposed.The clustering and classification are combined,the former is used to mine situational knowledge,and the latter is used to realize rapid assessment.Angle evaluation factor and distance evaluation factor are proposed to transform multi-dimensional air combat information into two-dimensional features.A convolution success-history based adaptive differential evolution with linear population size reduc-tion-means(C-LSHADE-Means)algorithm is proposed.The convolutional pooling layer is used to compress the size of data and preserve the distribution characteristics.The LSHADE algorithm is used to initialize the center of the mean clustering,which over-comes the defect of initialization sensitivity.Comparing experi-ment with the seven clustering algorithms is done on the UCI data set,through four clustering indexes,and it proves that the method proposed in this paper has better clustering performance.A situation assessment model based on stacked autoen-coder and learning vector quantization(SAE-LVQ)network is constructed,and it uses SAE to reconstruct air combat data fea-tures,and uses the self-competition layer of the LVQ to achieve efficient classification.Compared with the five kinds of assess-ments models,the SAE-LVQ model has the highest accuracy.Finally,three kinds of confrontation processes from air combat maneuvering instrumentation(ACMI)are selected,and the model in this paper is used for situation assessment.The assessment results are in line with the actual situation.

Personalized movie recommendation method based on ensemble learning

Aiming at the personalized movie recommendation problem,a recommendation algorithm in-tegrating manifold learning and ensemble learning is studied.In this work,manifold learning is used to reduce the dimension of data so that both time and space complexities of the model are mitigated.Meanwhile,gradient boosting decision tree(GBDT)is used to train the target user profile prediction model.Based on the recommendation results,Bayesian optimization algorithm is applied to optimize the recommendation model,which can effectively improve the prediction accuracy.The experimental results show that the proposed algorithm can improve the accuracy of movie recommendation.

Multi Multi-Task Learning with Dynamic Splitting for Open Open-Set Wireless Signal Recognition

Open-set recognition(OSR)is a realistic problem in wireless signal recogni-tion,which means that during the inference phase there may appear unknown classes not seen in the training phase.The method of intra-class splitting(ICS)that splits samples of known classes to imitate unknown classes has achieved great performance.However,this approach relies too much on the predefined splitting ratio and may face huge performance degradation in new environment.In this paper,we train a multi-task learning(MTL)net-work based on the characteristics of wireless signals to improve the performance in new scenes.Besides,we provide a dynamic method to decide the splitting ratio per class to get more precise outer samples.To be specific,we make perturbations to the sample from the center of one class toward its adversarial direction and the change point of confidence scores during this process is used as the splitting threshold.We conduct several experi-ments on one wireless signal dataset collected at 2.4 GHz ISM band by LimeSDR and one open modulation recognition dataset,and the analytical results demonstrate the effective-ness of the proposed method.

CREATION OF OPTIMAL MOVEMENT STRATEGY OF PLURAL MOVING OB-JECTS BY GA

The topographic information of a closed world is expressed as a graph. The plural mov- ingobjects which go and back in it according to a single moving strategy are supposed.The moving strategy is expressed by numerical values as a decision table. Coding is performed with this table as chromosomes, and this is optimized by using genetic algorithm. These environments were realized on a computer, and the simulation was carried out. As the result, the learning of the method to act so that moving objects do not obstruct mutually was recognized, and it was confirmed that these methods are effective for optimizing moving strategy.

GeoAI Technologies and Their Application Areas in Urban Planning and Development: Concepts, Opportunities and Challenges in Smart City (Kuwait, Study Case)

Artificial intelligence has significantly altered many job workflows, hence expanding earlier notions of limitations, outcomes, size, and prices. GeoAI is a multidisciplinary field that encompasses computer science, engineering, statistics, and spatial science. Because this subject focuses on real-world issues, it has a significant impact on society and the economy. A broad context incorporating fundamental questions of theory, epistemology, and the scientific method is used to bring artificial intelligence (Al) and geography together. This connection has the potential to have far-reaching implications for the geographic study. GeoAI, or the combination of geography with artificial intelligence, offers unique solutions to a variety of smart city issues. This paper provides an overview of GeoAI technology, including the definition of GeoAI and the differences between GeoAI and traditional AI. Key steps to successful geographic data analysis include integrating AI with GIS and using GeoAI tools and technologies. Also shown are key areas of applications and models in GeoAI, likewise challenges to adopt GeoAI methods and technology as well as benefits. This article also included a case study on the use of GeoAI in Kuwait, as well as a number of recommendations.

Ensemble Attention Guided Multi-SEANet Trained with Curriculum Learning for Noninvasive Prediction of Gleason Grade Groups from MRI

The Gleason grade group(GG)is an important basis for assessing the malignancy of prostate can-cer,but it requires invasive biopsy to obtain pathology.To noninvasively evaluate GG,an automatic prediction method is proposed based on multi-scale convolutional neural network of the ensemble attention module trained with curriculum learning.First,a lesion-attention map based on the image of the region of interest is proposed in combination with the bottleneck attention module to make the network more focus on the lesion area.Second,the feature pyramid network is combined to make the network better learn the multi-scale information of the lesion area.Finally,in the network training,a curriculum based on the consistency gap between the visual evaluation and the pathological grade is proposed,which further improves the prediction performance of the network.Ex-perimental results show that the proposed method is better than the traditional network model in predicting GG performance.The quadratic weighted Kappa is 0.4711 and the positive predictive value for predicting clinically significant cancer is 0.9369.

Active transfer learning of matching query results across multiple sources

Entity resolution （ER） is the problem of identi- fying and grouping different manifestations of the same real world object. Algorithmic approaches have been developed where most tasks offer superior performance under super- vised learning. However, the prohibitive cost of labeling training data is still a huge obstacle for detecting duplicate query records from online sources. Furthermore, the unique combinations of noisy data with missing elements make ER tasks more challenging. To address this, transfer learning has been adopted to adaptively share learned common structures of similarity scoring problems between multiple sources. Al- though such techniques reduce the labeling cost so that it is linear with respect to the number of sources, its random sam- piing strategy is not successful enough to handle the ordinary sample imbalance problem. In this paper, we present a novel multi-source active transfer learning framework to jointly select fewer data instances from all sources to train classi- fiers with constant precision/recall. The intuition behind our approach is to actively label the most informative samples while adaptively transferring collective knowledge between sources. In this way, the classifiers that are learned can be both label-economical and flexible even for imbalanced or quality diverse sources. We compare our method with the state-of-the-art approaches on real-word datasets. Our exper- imental results demonstrate that our active transfer learning algorithm can achieve impressive performance with far fewerlabeled samples for record matching with numerous and var- ied sources.

IMAGE RESTOR ATION UNDER CAUCHY NOISE WITH SPA RSE REPR ESENTATION PRIOR AND TOTAL GENER ALIZED VA RIATION

This article introduces a novel variational model for restoring images degraded by Cauchy noise and/or blurring.The model integrates a nonconvex data-fidelity term with two regularization terms,a sparse representation prior over dictionary learning and total generalized variation(TGV)regularization.The sparse representation prior exploiting patch information enables the preservation of fine features and textural patterns,while adequately denoising in homogeneous regions and contributing natural visual quality.TGV regularization further assists in effectively denoising in smooth regions while retaining edges.By adopting the penalty method and an alternating minimization approach,we present an efficient iterative algorithm to solve the proposed model.Numerical results establish the superiority of the proposed model over other existing models in regard to visual quality and certain image quality assessments.

Understanding taxi drivers＇ routing choices from spatial and social traces

Most of our learning comes from other people or from our own experience. For instance, when a taxi driver is seeking passengers on an unknown road in a large city, what should the driver do？ Alternatives include cruising around the road or waiting for a time period at the roadside in the hopes of finding a passenger or just leaving for another road enroute to a destination he knows （e.g., hotel taxi rank）？ This is an interesting problem that arises everyday in cities all over the world. There could be different answers to the question poised above, but one fundamental problem is how the driver learns about the likelihood of finding passengers on a road that is new to him （as he has not picked up or dropped off passengers there before）. Our observation from large scale taxi driver trace data is that a driver not only learns from his own experience but through interactions with other drivers. In this paper, we first formally define this problem as socialized information learning （SIL）, second we propose a framework including a series of models to study how a taxi driver gathers and learns information in an uncertain environment through the use of his social network. Finally, the large scale real life data and empirical experiments confirm that our models are much more effective, efficient and scalable that prior work on this problem.

Active improvement of hierarchical object features under budget constraints

When we think of an object in a supervised learn- ing setting, we usually perceive it as a collection of fixed at- tribute values. Although this setting may be suited well for many classification tasks, we propose a new object repre- sentation and therewith a new challenge in data mining; an object is no longer described by one set of attributes but is represented in a hierarchy of attribute sets in different levels of quality. Obtaining a more detailed representation of an ob- ject comes with a cost. This raises the interesting question of which objects we want to enhance under a given budget and cost model. This new setting is very useful whenever re- sources like computing power, memory or time are limited. We propose a new active adaptive algorithm （AAA） to im- prove objects in an iterative fashion. We demonstrate how to create a hierarchical object representation and prove the ef- fectiveness of our new selection algorithm on these datasets.

Integrating Appreciative Inquiry （AI） into architectural pedagogy： An assessment experiment of three retrofitted buildings in the city of Glasgow

Recently there has been a growing trend to encourage learning outside the classrooms, socalled ＇universities without walls.＇ To this end, mechanisms for learning beyond the boundaries of classroom settings can provide enhanced and challenging learning opportunities. This paper introduces Appreciative Inquiry （AI） as a mechanism that integrates various forms of inquiry into learning. AI is operationalized as a Walking Tour assessment project which was introduced as part of the class Cultural end Beheviourel Fectors in Architecture and Urbanism delivered at the Department of Architecture, University of Strathclyde - Glasgow where thirty-two Master of Architecture students were enrolled. The Walking Tour assessment involved the exploration of 6 factors that delineate key design characteristics in three retrofitted buildings in Glasgow： Theatre Royal, Reid Building, and The Lighthouse. Working in groups, students assessed factors that included context, massing, interface, wayfinding, socio-spatial, and comfort. Findings reveal that students were able to focus on critical issues that go beyond those adopted in traditional teaching practices while accentuating the value of introducing AI and utilizing the built environment as an educational medium. Conclusions are drawn to emphasize the need for structured learning experiences that enable making judgments about building qualities while effectively interrogating various characteristics.

Probabilistic models of vision and max-margin methods

It is attractive to formulate problems in computer vision and related fields in term of probabilis- tic estimation where the probability models are defined over graphs, such as grammars. The graphical struc- tures, and the state variables defined over them, give a rich knowledge representation which can describe the complex structures of objects and images. The proba- bility distributions defined over the graphs capture the statistical variability of these structures. These proba- bility models can be learnt from training data with lim- ited amounts of supervision. But learning these models suffers from the difficulty of evaluating the normaliza- tion constant, or partition function, of the probability distributions which can be extremely computationally demanding. This paper shows that by placing bounds on the normalization constant we can obtain compu- rationally tractable approximations. Surprisingly, for certain choices of loss functions, we obtain many of the standard max-margin criteria used in support vector machines （SVMs） and hence we reduce the learning to standard machine learning methods. We show that many machine learning methods can be obtained in this way as approximations to probabilistic methods including multi-class max-margin, ordinal regression, max-margin Markov networks and parsers, multiple- instance learning, and latent SVM. We illustrate this work by computer vision applications including image labeling, object detection and localization, and motion estimation. We speculate that rained by using better bounds better results can be ob- and approximations.