Automated Room Occupancy Prediction Using Fuzzy-Rough Set Theory-Based Supervised Learning

BACKGROUNDTraditional methods of developing predictive models in inflammatory bowel diseases (IBD) rely on using statistical regression approaches to deriving clinical scores such as the Crohn's disease (CD) activity index. However, traditional approaches are unable to take advantage of more complex data structures such as repeated measurements. Deep learning methods have the potential ability to automatically find and learn complex, hidden relationships between predictive markers and outcomes, but their application to clinical prediction in CD and IBD has not been explored previously.AIMTo determine and compare the utility of deep learning with conventional algorithms in predicting response to anti-tumor necrosis factor (anti-TNF) therapy in CD.METHODSThis was a retrospective single-center cohort study of all CD patients who commenced anti-TNF therapy (either adalimumab or infliximab) from January 1, 2010 to December 31, 2015. Remission was defined as a C-reactive protein (CRP) < 5 mg/L at 12 mo after anti-TNF commencement. Three supervised learning algorithms were compared: (1) A conventional statistical learning algorithm using multivariable logistic regression on baseline data only; (2) A deep learning algorithm using a feed-forward artificial neural network on baseline data only; and (3) A deep learning algorithm using a recurrent neural network on repeated data. Predictive performance was assessed using area under the receiver operator characteristic curve (AUC) after 10× repeated 5-fold cross-validation.RESULTSA total of 146 patients were included (median age 36 years, 48% male). Concomitant therapy at anti-TNF commencement included thiopurines (68%), methotrexate (18%), corticosteroids (44%) and aminosalicylates (33%). After 12 mo, 64% had CRP < 5 mg/L. The conventional learning algorithm selected the following baseline variables for the predictive model: Complex disease behavior, albumin, monocytes, lymphocytes, mean corpuscular hemoglobin concentration and gamma-glutamyl transferase, and had a cross-validated AUC of 0.659, 95% confidence interval (CI): 0.562-0.756. A feed-forward artificial neural network using only baseline data demonstrated an AUC of 0.710 (95%CI: 0.622-0.799; P = 0.25 vs conventional). A recurrent neural network using repeated biomarker measurements demonstrated significantly higher AUC compared to the conventional algorithm (0.754, 95%CI: 0.674-0.834; P = 0.036).CONCLUSIONDeep learning methods are feasible and have the potential for stronger predictive performance compared to conventional model building methods when applied to predicting remission after anti-TNF therapy in CD.

The increasing popularity of smart wearable devices can be attributed to progress in research towards human activity recognition. With the use of tiny sensing units, the different human activities of day-to-day life can be identified with a high accuracy. However, as a fitness tracking product, smart wearables are not always accurate in determining actual physical motion details. For example, recognizing walk activity may not always be possible when the monitoring device is held in hand, or kept in pockets. For precise recognition of walk activity, movement of legs needs to be monitored. However, the movement of legs while walking must be distinguished from simple leg swing activities. The present work designs an IMU based sensing system that can prevent false identification of a mimicked walk or leg swing in sitting posture as a real walk activity, using conventional and convolutional deep learning algorithms. The system shows remarkable capability of identifying an actual walk from a mimicked walk activity using CNN 95% of the time.

Augmenting a deep-learning algorithm with canal inspection knowledge for reliable water leak detection from multispectral satellite images

A new perspective on dealing with the noise sensitive problem of repetitive control algorithms is given in the paper. It is firstly shown that, in continuous-time domain, what the conventional repetitive learning algorithm does is equivalent to adapting all the values of the periodic uncertainties over one period. Such an endeavor means very high bandwidth of the learning algorithm as an infinite number of parameters need to be adapted, which puts a great demand on microprocessor memory in implementing the algorithms. At the same time, such a formulation also makes the algorithm very sensitive to noise as it treats the values of the periodic uncertainties over the same period totally independent from each other, just like a random noise. Based on this new perspective on the noise sensitive problem of repetitive algorithm, a simple remedy is provided for the recently proposed adaptive robust repetitive control (ARRC) design by recognizing the physical dependence of the values of the periodic uncertainties over the same period and using certain known basis functions to capture these physical dependence. By doing so, only the amplitudes of these known basis functions need to be adapted on-line. The net results are that, not only the number of the parameters to be adapted is reduced drastically, but also the noise sensitive problem of the conventional learning algorithm is overcome. The precision motion control of a linear motor drive system is used as an application example. The comparative experimental results demonstrate that, with the new adaptive robust repetitive control design, not only the noise sensitive problem of repetitive learning is completely eliminated, but also a much improved tracking performance is achieved due to the built-in extrapolation capability of the basis functions used.

An unsupervised competitive learning algorithm based on the classical -means clustering algorithm is proposed. The proposed learning algorithm called the centroid neural network (CNN) estimates centroids of the related cluster groups in training date. This paper also explains algorithmic relationships among the CNN and some of the conventional unsupervised competitive learning algorithms including Kohonen's self-organizing map (SOM) and Kosko's differential competitive learning (DCL) algorithm. The CNN algorithm requires neither a predetermined schedule for learning coefficient nor a total number of iterations for clustering. The simulation results on clustering problems and image compression problems show that CNN converges much faster than conventional algorithms with compatible clustering quality while other algorithms may give unstable results depending on the initial values of the learning coefficient and the total number of iterations.

Computer-aided breast cancer detection and classification in mammography: A comprehensive review

There is an increasing need for artificial intelligence in the field of medical related learning frameworks which is capable of efficiently handling the multimodal data which is under resource constrained situations. Conventional machine learning and deep learning algorithms are usually depending on the large labelled dataset and limited environment with less applicability for real world applications. The adoption of the Artificial intelligence in the field of healthcare is the need for the learning and effective handling of the multimodal healthcare data. Traditional machine learning and deep learning algorithms depends on the large-scale datasets with label, limiting the usage of the current clinical environment. This will limit the applicability of the real-world clinical environments by the data lackness and variance in the domain. In this work, Large Language Models are used with deep metric learning framework for multimodal medical journal classification. In this work, Large Language Model is implemented using deep metric learning framework for the multimodal dataset. The multimodal dataset comprises of text, table and images from online repository. The data manually downloaded from the PubMed website is used in this work. The proposed LLM guide framework outperformed all other models trained by various benchmark datasets.

In our daily life, heart-related diseases are the most dangerous diseases in the world, some of them can be cured even though it is time taking, but others have high-risk factors that make them difficult to treat. Considering these risk factors, there is a chance that a patient can die. This is the main criterion to focus on this disease because of death rate is high. As a team, we mainly focused on four diseases that have recorded increased deaths: Heart disease, Depression, Kidney disease, and Lung Cancer. Based on this, we have surveyed the disorders to predict them at the earliest, making them easy to cure. From this survey, we learned that a high number of deaths are recorded due to heart-related issues, which 17.9 million people globally each year. It is known that diagnosis of heart disease is quite challenging, but that doesn't mean that person is on the verge of their life. There are effective ways in which a person can be gone through an automated prediction of their heart condition. Machine and deep learning algorithms are practical and efficient in producing the most accurate results. These algorithms are helpful in many ways and different fields, mainly in the medical domain, for predicting diseases based on symptoms.

The advancement of autonomous driving technology is becoming increasingly vital in the modern technological landscape, where it promises notable enhancements in safety, efficiency, traffic management, and energy use. Despite these benefits, conventional deep reinforcement learning algorithms often struggle to effectively navigate complex driving environments. To tackle this challenge, we propose a novel network called DynamicNoise, which was designed to significantly boost the algorithmic performance by introducing noise into the deep Q-network (DQN) and double deep Q-network (DDQN). Drawing inspiration from the NoiseNet architecture, DynamicNoise uses stochastic perturbations to improve the exploration capabilities of these models, thus leading to more robust learning outcomes. Our experiments demonstrated a 57.25% improvement in the navigation effectiveness within a 2D experimental setting. Moreover, by integrating noise into the action selection and fully connected layers of the soft actor–critic (SAC) model in the more complex 3D CARLA simulation environment, our approach achieved an 18.9% performance gain, which substantially surpassed the traditional methods. These results confirmed that the DynamicNoise network significantly enhanced the performance of autonomous driving systems across various simulated environments, regardless of their dimensionality and complexity, by improving their exploration capabilities rather than just their efficiency.

Conventional rule learning algorithms aim at finding a set of simple rules, where each rule covers as many examples as possible. In this paper, we argue that the rules found in this way may not be the optimal explanations for each of the examples they cover. Instead, we propose an efficient algorithm that aims at finding the best rule covering each training example in a greedy optimization consisting of one specialization and one generalization loop. These locally optimal rules are collected and then filtered for a final rule set, which is much larger than the sets learned by conventional rule learning algorithms. A new example is classified by selecting the best among the rules that cover this example. In our experiments on small to very large datasets, the approach’s average classification accuracy is higher than that of state-of-the-art rule learning algorithms. Moreover, the algorithm is highly efficient and can inherently be processed in parallel without affecting the learned rule set and so the classification accuracy. We thus believe that it closes an important gap for large-scale classification rule induction.

In astronomy, neural networks are often trained on simulation data with the prospect of being used on telescope observations. Unfortunately, training a model on simulation data and then applying it to instrument data leads to a substantial and potentially even detrimental decrease in model accuracy on the new target data set. Simulated and instrument data represent different data domains, and for an algorithm to work in both, domain-invariant learning is necessary. Here, we employ domain adaptation techniques – Maximum Mean Discrepancy as an additional transfer loss and Domain Adversarial Neural Networks – and demonstrate their viability to extract domain-invariant features within the astronomical context of classifying merging and non-merging galaxies. Additionally, we explore the use of Fisher loss and entropy minimization to enforce better in-domain class discriminability. We show that the addition of each domain adaptation technique improves the performance of a classifier when compared to conventional deep learning algorithms. We demonstrate this on two examples: between two Illustris-1 simulated data sets of distant merging galaxies, and between Illustris-1 simulated data of nearby merging galaxies and observed data from the Sloan Digital Sky Survey. The use of domain adaptation techniques in our experiments leads to an increase of target domain classification accuracy of up to ${\sim }20{{\ \rm per\ cent}}$. With further development, these techniques will allow astronomers to successfully implement neural network models trained on simulation data to efficiently detect and study astrophysical objects in current and future large-scale astronomical surveys.

In this paper, a hybrid supervised learning algorithm for neural network was proposed. The problem of local minimum learning usually occurred in the real application of neural network is tried to be solved or reduced. In order to improve the efficiency and stability of conventional error back-propagation learning algorithm, a hybrid learning method combining the linear multi-regression and backpropagation techniques was developed. To demonstrate the superiority of the method we developed, one example was simulated. The conventional BP learning method was also performed as the comparison with the new method proposed. From the results shown, the conventional BP method easily makes neural model plunge into the local minima. On the contrary, the new method we proposed not only has a fast learning, but also has a better learning efficiency.

Cerebellar model articulation controller (CMAC) is a useful neural network learning technique. It was developed two decades ago but yet lacks adequate learning algorithm especially when it is used in a hybrid-type controller. Part I of this work was devoted to introduce a new CMAC adaptive learning algorithm. Part II will be directed to experimental application of new learning algorithm of a CMAC based hybrid-type real time controller. The proposed controller is applied for the trajectory tracking of a piezoelectric actuated tool post. It has been proven that the piezoelectric actuated tool post has hysteretic behavior. Extensive experiments have been carried out on the experimental setup to evaluate the proposed adaptive learning algorithm of CMAC. Only few experiments and their results are being presented. In these experiments, the performance of the piezoelectric actuated tool post has been examined and evaluated using different types of control algorithms and applying external load disturbance. The control performance of the proposed controller is compared with those of conventional controllers (PI controller and the conventional CMAC based controller). The experimental results showed that performance of the hybrid-type controller using the proposed learning algorithm is stable and more effective than that of the conventional controllers. Testing and comparing the learning ability of the proposed learning algorithm with that of the conventional CMAC learning algorithm indicated the effectiveness of the learning ability of the proposed algorithm. Finally, the response using the proposed hybrid-type controller is slightly better than using the conventional PI controller under the effect of external load disturbance.

Human activity recognition using mobile sensors is becoming increasingly important. Scaling up from individuals to groups, that is, Group Activity Recognition (GAR), has attracted significant attention recently. This paper investigates energy consumption for GAR and proposes a novel distributed middleware called GroupSense for mobile GAR. We implemented and tested GroupSense, which incorporates a protocol for the exchange of information required for GAR. We also investigated the battery drain of continuous activity recognition in a range of simple GAR scenarios. We then conclude with lessons learnt for GAR.

Misfiring in multi-cylinder is caused due to abnormal combustion of the engine. Cylinders produce less power if engine misfires. Engine misfires generate unburned hydrocarbons and increase the load on the catalytic converter. The job of the catalytic converter is to convert harmful pollutants into less harmful emissions before they ever leave the vehicle exhaust system. If the misfire rate is excessive, the catalytic converter can overheat and be damaged. Hence engine misfire becomes a severe issue and should be detected in early stages. During misfire and at normal combustion, every cylinder has its own unique vibration spectrum this will be a very useful phenomenon for misfire detection. In this work, vibration signals are recorded using a piezoelectric accelerometer for normal combustion as well as combustion with a misfire for each cylinder. The obtained vibration signals are used for training and testing of conventional machine learning algorithm as well as the deep learning algorithm. Support Vector Machine (SVM) with statistical feature extraction as conventional machine learning algorithm and Convolutional Neural Network (CNN) as deep learning algorithm are used for misfire detection in multi-cylinder. In this paper, the evaluation parameters of classifiers such as overall accuracy, precision, recall etc. are compared. Deep learning algorithm i.e. CNN without feature Extraction was found to be performing better for multiclass misfire detection compared to CNN with feature extraction and SVM.