Search

We present a deep learning (DL) network-based approach for detecting and semantically segmenting two specific types of tuberculosis (TB) lesions in chest X-ray (CXR) images. In the proposed method, we use a basic U-Net model and its enhanced versions to detect, classify, and segment TB lesions in CXR images. The model architectures used in this study are U-Net, Attention U-Net, U-Net++, Attention U-Net++, and pyramid spatial pooling (PSP) Attention U-Net++, which are optimized and compared based on the test results of each model to find the best parameters. Finally, we use four ensemble approaches which combine the top five models to further improve lesion classification and segmentation results. In the training stage, we use data augmentation and preprocessing methods to increase the number and strength of lesion features in CXR images, respectively. Our dataset consists of 110 training, 14 validation, and 98 test images. The experimental results show that the proposed ensemble model achieves a maximum mean intersection-over-union ( MIoU ) of 0.70, a mean precision rate of 0.88, a mean recall rate of 0.75, a mean F1-score of 0.81, and an accuracy of 1.0, which are all better than those of only using a single-network model. The proposed method can be used by clinicians as a diagnostic tool assisting in the examination of TB lesions in CXR images.

The objective of this paper is to present a novel design of intelligent neuro-supervised networks (INSNs) in order to study the dynamics of a mathematical model for Parkinson's disease illness (PDI), governed with three differential classes to represent the rhythms of brain electrical activity measurements at different locations in the cerebral cortex. The proposed INSNs are constructed by exploiting the knacks of multilayer structure neural networks back-propagated with the Levenberg-Marquardt (LM) and Bayesian regularization (BR) optimization approaches. The reference data for the grids of input and the target samples of INSNs were formulated with a reliable numerical solver via the Adams method for sundry scenarios of PDI models by way of variation of sensor locations in order to measure the impact of the rhythms of brain electrical activity. The designed INSNs for both backpropagation procedures were implemented on created datasets segmented arbitrarily into training, testing, and validation samples by optimization of mean squared error based fitness function. Comparison of outcomes on the basis of exhaustive simulations of proposed INSNs via both LM and BR methodologies was conducted with reference solutions of PDI models by means of learning curves on MSE, adaptive control parameters of algorithms, absolute error, histogram error plots, and regression index. The outcomes endorse the efficacy of both INSNs solvers for different scenarios in PDI models, but the accuracy of the BR-based method is relatively superior, albeit at the cost of slightly more computations.

The ongoing fast-paced technology trend has brought forth ceaseless transformation. In this regard, cloud computing has long proven to be the paramount deliverer of services such as computing power, software, networking, storage, and databases on a pay-per-use basis. The cloud is a big proponent of the internet of things (IoT), furnishing the computation and storage requisite to address internet-of-things applications. With the proliferating IoT devices triggering a continual data upsurge, the cloud-IoT interaction encounters latency, bandwidth, and connectivity restraints. The inclusion of the decentralized and distributed fog computing layer amidst the cloud and IoT layer extends the cloud's processing, storage, and networking services close to end users. This hierarchical edge-fog-cloud model distributes computation and intelligence, yielding optimal solutions while tackling constraints like massive data volume, latency, delay, and security vulnerability. The healthcare domain, warranting time-critical functionalities, can reap benefits from the cloud-fog-IoT interplay. This research paper propounded a fog-assisted smart healthcare system to diagnose heart or cardiovascular disease. It combined a fuzzy inference system (FIS) with the recurrent neural network model's variant of the gated recurrent unit (GRU) for pre-processing and predictive analytics tasks. The proposed system showcases substantially improved performance results, with classification accuracy at 99.125%. With major processing of healthcare data analytics happening at the fog layer, it is observed that the proposed work reveals optimized results concerning delays in terms of latency, response time, and jitter, compared to the cloud. Deep learning models are adept at handling sophisticated tasks, particularly predictive analytics. Time-critical healthcare applications reap benefits from deep learning's exclusive potential to furnish near-perfect results, coupled with the merits of the decentralized fog model, as revealed by the experimental results.

Several advances in computing facilities were made due to the advancement of science and technology, including the implementation of automation in multi-specialty hospitals. This research aims to develop an efficient deep-learning-based brain-tumor (BT) detection scheme to detect the tumor in FLAIR- and T2-modality magnetic-resonance-imaging (MRI) slices. MRI slices of the axial-plane brain are used to test and verify the scheme. The reliability of the developed scheme is also verified through clinically collected MRI slices. In the proposed scheme, the following stages are involved: (i) pre-processing the raw MRI image, (ii) deep-feature extraction using pretrained schemes, (iii) watershed-algorithm-based BT segmentation and mining the shape features, (iv) feature optimization using the elephant-herding algorithm (EHA), and (v) binary classification and verification using three-fold cross-validation. Using (a) individual features, (b) dual deep features, and (c) integrated features, the BT-classification task is accomplished in this study. Each experiment is conducted separately on the chosen BRATS and TCIA benchmark MRI slices. This research indicates that the integrated feature-based scheme helps to achieve a classification accuracy of 99.6667% when a support-vector-machine (SVM) classifier is considered. Further, the performance of this scheme is verified using noise-attacked MRI slices, and better classification results are achieved.

Brain tumor diagnosis has been a lengthy process, and automation of a process such as brain tumor segmentation speeds up the timeline. U-Nets have been a commonly used solution for semantic segmentation, and it uses a downsampling-upsampling approach to segment tumors. U-Nets rely on residual connections to pass information during upsampling; however, an upsampling block only receives information from one downsampling block. This restricts the context and scope of an upsampling block. In this paper, we propose SPP-U-Net where the residual connections are replaced with a combination of Spatial Pyramid Pooling (SPP) and Attention blocks. Here, SPP provides information from various downsampling blocks, which will increase the scope of reconstruction while attention provides the necessary context by incorporating local characteristics with their corresponding global dependencies. Existing literature uses heavy approaches such as the usage of nested and dense skip connections and transformers. These approaches increase the training parameters within the model which therefore increase the training time and complexity of the model. The proposed approach on the other hand attains comparable results to existing literature without changing the number of trainable parameters over larger dimensions such as 160 × 192 × 192. All in all, the proposed model scores an average dice score of 0.883 and a Hausdorff distance of 7.84 on Brats 2021 cross validation., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Vijay, Guhan, Srinivasan, Vincent and Chang.)

Introduction: Cancer happening rates in humankind are gradually rising due to a variety of reasons, and sensible detection and management are essential to decrease the disease rates. The kidney is one of the vital organs in human physiology, and cancer in the kidney is a medical emergency and needs accurate diagnosis and well-organized management., Methods: The proposed work aims to develop a framework to classify renal computed tomography (CT) images into healthy/cancer classes using pre-trained deep-learning schemes. To improve the detection accuracy, this work suggests a threshold filter-based pre-processing scheme, which helps in removing the artefact in the CT slices to achieve better detection. The various stages of this scheme involve: (i) Image collection, resizing, and artefact removal, (ii) Deep features extraction, (iii) Feature reduction and fusion, and (iv) Binary classification using five-fold cross-validation., Results and Discussion: This experimental investigation is executed separately for: (i) CT slices with the artefact and (ii) CT slices without the artefact. As a result of the experimental outcome of this study, the K-Nearest Neighbor (KNN) classifier is able to achieve 100% detection accuracy by using the pre-processed CT slices. Therefore, this scheme can be considered for the purpose of examining clinical grade renal CT images, as it is clinically significant., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Rajinikanth, Vincent, Srinivasan, Ananth Prabhu and Chang.)

Current surveillance systems frequently use fixed-angle cameras and record a feed from those cameras. There are several disadvantages to such systems, including a low resolution for far away objects, a limited frame range and wasted disk space. This paper presents a novel algorithm for automatically detecting, tracking and zooming in on active targets. The object tracking system is connected to a camera that has a 360° horizontal and 90° vertical movement range. The combination of tracking, movement identification and zoom means that the system is able to effectively improve the resolution of small or distant objects. The object detection system allows for the disk space to be conserved as the system ceases recording when no valid targets are detected. Using an adaptive object segmentation algorithm, it is possible to detect the shape of moving objects efficiently. When processing multiple targets, each target is assigned a color and is treated separately. The tracking algorithm is able to adapt to targets moving at different speeds and is able to control the camera according to a predictive formula to prevent the loss of image quality due to camera trail. In the test environment, the zoom can sufficiently lock onto the head of a moving human; however, simultaneous tracking and zooming occasionally results in a failure to track. If this system is deployed with a facial recognition algorithm, the recognition accuracy can be effectively improved.

Underwater image processing has been shown to exhibit significant potential for exploring underwater environments. It has been applied to a wide variety of fields, such as underwater terrain scanning and autonomous underwater vehicles (AUVs)-driven applications, such as image-based underwater object detection. However, underwater images often suffer from degeneration due to attenuation, color distortion, and noise from artificial lighting sources as well as the effects of possibly low-end optical imaging devices. Thus, object detection performance would be degraded accordingly. To tackle this problem, in this article, a lightweight deep underwater object detection network is proposed. The key is to present a deep model for jointly learning color conversion and object detection for underwater images. The image color conversion module aims at transforming color images to the corresponding grayscale images to solve the problem of underwater color absorption to enhance the object detection performance with lower computational complexity. The presented experimental results with our implementation on the Raspberry pi platform have justified the effectiveness of the proposed lightweight jointly learning model for underwater object detection compared with the state-of-the-art approaches.

Convolutional Neural Network (CNN) has been employed in classifying the COVID cases from the lungs' CT-Scan with promising quantifying metrics. However, SARS COVID-19 has been mutated, and we have many versions of the virus B.1.1.7, B.1.135, and P.1, hence there is a need for a more robust architecture that will classify the COVID positive patients from COVID negative patients with less training. We have developed a neural network based on the number of channels present in the images. The CNN architecture is developed in accordance with the number of the channels present in the dataset and are extracting the features separately from the channels present in the CT-Scan dataset. In the tower architecture, the first tower is dedicated for only the first channel present in the image; the second CNN tower is dedicated to the first and second channel feature maps, and finally the third channel takes account of all the feature maps from all three channels. We have used two datasets viz. one from Tongji Hospital, Wuhan, China and another SARS-CoV-2 dataset to train and evaluate our CNN architecture. The proposed model brought about an average accuracy of 99.4%, F1 score 0.988, and AUC 0.99., (© 2022. The Author(s).)

Reinforcement learning (RL) with both exploration and exploit abilities is applied to games to demonstrate that it can surpass human performance. This paper mainly applies Deep Q-Network (DQN), which combines reinforcement learning and deep learning to the real-time action response of NS-SHAFT game with Cheat Engine as the API of game information autonomously. Based on a personal computer, we build an experimental learning environment that automatically captures the NS-SHAFT's frame, which is provided to DQN to decide the action of moving left, moving right, or stay in same location, survey different parameters: such as the sample frequency, different reward function, and batch size, etc. The experiment found that the relevant parameter settings have a certain degree of influence on the DQN learning effect. Moreover, we use Cheat Engine as the API of NS-SHAFT game information to locate the relevant values in the NS-SHAFT game, and then read the relevant values to achieve the operation of the overall experimental platform and the calculation of Reward. Accordingly, we successfully establish an instant learning environment and instant game training for the NS-SHAFT game.

Multimodal medical image fusion is a current technique applied in the applications related to medical field to combine images from the same modality or different modalities to improve the visual content of the image to perform further operations like image segmentation. Biomedical research and medical image analysis highly demand medical image fusion to perform higher level of medical analysis. Multimodal medical fusion assists medical practitioners to visualize the internal organs and tissues. Multimodal medical fusion of brain image helps to medical practitioners to simultaneously visualize hard portion like skull and soft portion like tissue. Brain tumor segmentation can be accurately performed by utilizing the image obtained after multimodal medical image fusion. The area of the tumor can be accurately located with the information obtained from both Positron Emission Tomography and Magnetic Resonance Image in a single fused image. This approach increases the accuracy in diagnosing the tumor and reduces the time consumed in diagnosing and locating the tumor. The functional information of the brain is available in the Positron Emission Tomography while the anatomy of the brain tissue is available in the Magnetic Resonance Image. Thus, the spatial characteristics and functional information can be obtained from a single image using a robust multimodal medical image fusion model. The proposed approach uses a generative adversarial network to fuse Positron Emission Tomography and Magnetic Resonance Image into a single image. The results obtained from the proposed approach can be used for further medical analysis to locate the tumor and plan for further surgical procedures. The performance of the GAN based model is evaluated using two metrics, namely, structural similarity index and mutual information. The proposed approach achieved a structural similarity index of 0.8551 and a mutual information of 2.8059., Competing Interests: The authors declare that they have no conflicts of interest to report regarding the present study., (Copyright © 2022 R. Nandhini Abirami et al.)

Understanding the reason for an infant's cry is the most difficult thing for parents. There might be various reasons behind the baby's cry. It may be due to hunger, pain, sleep, or diaper-related problems. The key concept behind identifying the reason behind the infant's cry is mainly based on the varying patterns of the crying audio. The audio file comprises many features, which are highly important in classifying the results. It is important to convert the audio signals into the required spectrograms. In this article, we are trying to find efficient solutions to the problem of predicting the reason behind an infant's cry. In this article, we have used the Mel-frequency cepstral coefficients algorithm to generate the spectrograms and analyzed the varying feature vectors. We then came up with two approaches to obtain the experimental results. In the first approach, we used the Convolution Neural network (CNN) variants like VGG16 and YOLOv4 to classify the infant cry signals. In the second approach, a multistage heterogeneous stacking ensemble model was used for infant cry classification. Its major advantage was the inclusion of various advanced boosting algorithms at various levels. The proposed multistage heterogeneous stacking ensemble model had the edge over the other neural network models, especially in terms of overall performance and computing power. Finally, after many comparisons, the proposed model revealed the virtuoso performance and a mean classification accuracy of up to 93.7%., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Joshi, Srinivasan, Vincent, Rajinikanth and Chang.)

The unbounded increase in network traffic and user data has made it difficult for network intrusion detection systems to be abreast and perform well. Intrusion Systems are crucial in e-healthcare since the patients' medical records should be kept highly secure, confidential, and accurate. Any change in the actual patient data can lead to errors in the diagnosis and treatment. Most of the existing artificial intelligence-based systems are trained on outdated intrusion detection repositories, which can produce more false positives and require retraining the algorithm from scratch to support new attacks. These processes also make it challenging to secure patient records in medical systems as the intrusion detection mechanisms can become frequently obsolete. This paper proposes a hybrid framework using Deep Learning named "ImmuneNet" to recognize the latest intrusion attacks and defend healthcare data. The proposed framework uses multiple feature engineering processes, oversampling methods to improve class balance, and hyper-parameter optimization techniques to achieve high accuracy and performance. The architecture contains <1 million parameters, making it lightweight, fast, and IoT-friendly, suitable for deploying the IDS on medical devices and healthcare systems. The performance of ImmuneNet was benchmarked against several other machine learning algorithms on the Canadian Institute for Cybersecurity's Intrusion Detection System 2017, 2018, and Bell DNS 2021 datasets which contain extensive real-time and latest cyber attack data. Out of all the experiments, ImmuneNet performed the best on the CIC Bell DNS 2021 dataset with about 99.19% accuracy, 99.22% precision, 99.19% recall, and 99.2% ROC-AUC scores, which are comparatively better and up-to-date than other existing approaches in classifying between requests that are normal, intrusion, and other cyber attacks., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Akshay Kumaar, Samiayya, Vincent, Srinivasan, Chang and Ganesh.)

The exponential growth of social media users has changed the dynamics of retrieving the potential information from user-generated content and transformed the paradigm of information-retrieval mechanism with the novel developments on the concept of "web of data". In this regard, our proposed Ontology-Based Sentiment Analysis provides two novel approaches: First, the emotion extraction on tweets related to COVID-19 is carried out by a well-formed taxonomy that comprises possible emotional concepts with fine-grained properties and polarized values. Second, the potential entities present in the tweet can be analyzed for semantic associativity. The extraction of emotions can be performed in two cases: (i) words directly associated with the emotional concepts present in the taxonomy and (ii) words indirectly present in the emotional concepts. Though the latter case is very challenging in processing the tweets to find the hidden patterns and extract the meaningful facts associated with it, our proposed work is able to extract and detect almost 81% of true positives and considerably able to detect the false negatives. Finally, the proposed approach's superior performance is witnessed from its comparison with other peer-level approaches., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Narayanasamy, Srinivasan, Mian Qaisar and Chang.)

Alzheimer's is a progressive, irreversible, neurodegenerative brain disease. Even with prominent symptoms, it takes years to notice, decode, and reveal Alzheimer's. However, advancements in technologies, such as imaging techniques, help in early diagnosis. Still, sometimes the results are inaccurate, which delays the treatment. Thus, the research in recent times focused on identifying the molecular biomarkers that differentiate the genotype and phenotype characteristics. However, the gene expression dataset's generated features are huge, 1,000 or even more than 10,000. To overcome such a curse of dimensionality, feature selection techniques are introduced. We designed a gene selection pipeline combining a filter, wrapper, and unsupervised method to select the relevant genes. We combined the minimum Redundancy and maximum Relevance (mRmR), Wrapper-based Particle Swarm Optimization (WPSO), and Auto encoder to select the relevant features. We used the GSE5281 Alzheimer's dataset from the Gene Expression Omnibus We implemented an Improved Deep Belief Network (IDBN) with simple stopping criteria after choosing the relevant genes. We used a Bayesian Optimization technique to tune the hyperparameters in the Improved Deep Belief Network. The tabulated results show that the proposed pipeline shows promising results., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Mahendran, Vincent, Srinivasan and Chang.)

The cry is a loud, high pitched verbal communication of infants. The very high fundamental frequency and resonance frequency characterize a neonatal infant cry having certain sudden variations. Furthermore, in a tiny duration solitary utterance, the cry signal also possesses both voiced and unvoiced features. Mostly, infants communicate with their caretakers through cries, and sometimes, it becomes difficult for the caretakers to comprehend the reason behind the newborn infant cry. As a result, this research proposes a novel work for classifying the newborn infant cries under three groups such as hunger, sleep, and discomfort. For each crying frame, twelve features get extracted through acoustic feature engineering, and the variable selection using random forests was used for selecting the highly discriminative features among the twelve time and frequency domain features. Subsequently, the extreme gradient boosting-powered grouped-support-vector network is deployed for neonate cry classification. The empirical results show that the proposed method could effectively classify the neonate cries under three different groups. The finest experimental results showed a mean accuracy of around 91% for most scenarios, and this exhibits the potential of the proposed extreme gradient boosting-powered grouped-support-vector network in neonate cry classification. Also, the proposed method has a fast recognition rate of 27 seconds in the identification of these emotional cries., Competing Interests: The authors declare that they have no conflicts of interest to report regarding the present study., (Copyright © 2021 Chuan-Yu Chang et al.)

The aim of this paper is to distinguish the vehicle detection and count the class number in each classification from the inputs. We proposed the use of Fuzzy Guided Scale Choice (FGSC)-based SSD deep neural network architecture for vehicle detection and class counting with parameter optimization. The 'FGSC' blocks are integrated into the convolutional layers of the model, which emphasize essential features while ignoring less important ones that are not significant for the operation. We created the passing detection lines and class counting windows and connected them with the proposed FGSC-SSD deep neural network model. The 'FGSC' blocks in the convolution layer emphasize essential features and find out unnecessary features by using the scale choice method at the training stage and eliminate that significant speedup of the model. In addition, FGSC blocks avoided many unusable parameters in the saturation interval and improved the performance efficiency. In addition, the Fuzzy Sigmoid Function (FSF) increases the activation interval through fuzzy logic. While performing operations, the FGSC-SSD model reduces the computational complexity of convolutional layers and their parameters. As a result, the model tested Frames Per Second (FPS) on edge artificial intelligence (AI) and reached a real-time processing speed of 38.4 and an accuracy rate of more than 94%. Therefore, this work might be considered an improvement to the traffic monitoring approach by using edge AI applications.

IoT has played an essential role in many industries over the last few decades. Recent advancements in the healthcare industry have made it possible to make healthcare accessible to more people and improve their overall health. The next step in healthcare is to integrate it with IoT-assisted wearable sensor systems seamlessly. This review rigorously discusses the various IoT architectures, different methods of data processing, transfer, and computing paradigms. It compiles various communication technologies and the devices commonly used in IoT-assisted wearable sensor systems and deals with its various applications in healthcare and their advantages to the world. A comparative analysis of all the wearable technology in healthcare is also discussed with tabulation of various research and technology. This review also analyses all the problems commonly faced in IoT-assisted wearable sensor systems and the specific issues that need to be tackled to optimize these systems in healthcare and describes the various future implementations that can be made to the architecture and the technology to improve the healthcare industry.

This paper aims to evaluate the performance of multiple non-linear regression techniques, such as support-vector regression (SVR), k-nearest neighbor (KNN), Random Forest Regressor, Gradient Boosting, and XGBOOST for COVID-19 reproduction rate prediction and to study the impact of feature selection algorithms and hyperparameter tuning on prediction. Sixteen features (for example, Total&#95;cases&#95;per&#95;million and Total&#95;deaths&#95;per&#95;million) related to significant factors, such as testing, death, positivity rate, active cases, stringency index, and population density are considered for the COVID-19 reproduction rate prediction. These 16 features are ranked using Random Forest, Gradient Boosting, and XGBOOST feature selection algorithms. Seven features are selected from the 16 features according to the ranks assigned by most of the above mentioned feature-selection algorithms. Predictions by historical statistical models are based solely on the predicted feature and the assumption that future instances resemble past occurrences. However, techniques, such as Random Forest, XGBOOST, Gradient Boosting, KNN, and SVR considered the influence of other significant features for predicting the result. The performance of reproduction rate prediction is measured by mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), R-Squared, relative absolute error (RAE), and root relative squared error (RRSE) metrics. The performances of algorithms with and without feature selection are similar, but a remarkable difference is seen with hyperparameter tuning. The results suggest that the reproduction rate is highly dependent on many features, and the prediction should not be based solely upon past values. In the case without hyperparameter tuning, the minimum value of RAE is 0.117315935 with feature selection and 0.0968989 without feature selection, respectively. The KNN attains a low MAE value of 0.0008 and performs well without feature selection and with hyperparameter tuning. The results show that predictions performed using all features and hyperparameter tuning is more accurate than predictions performed using selected features., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Kaliappan, Srinivasan, Mian Qaisar, Sundararajan, Chang and C.)

Pneumonitis is an infectious disease that causes the inflammation of the air sac. It can be life-threatening to the very young and elderly. Detection of pneumonitis from X-ray images is a significant challenge. Early detection and assistance with diagnosis can be crucial. Recent developments in the field of deep learning have significantly improved their performance in medical image analysis. The superior predictive performance of the deep learning methods makes them ideal for pneumonitis classification from chest X-ray images. However, training deep learning models can be cumbersome and resource-intensive. Reusing knowledge representations of public models trained on large-scale datasets through transfer learning can help alleviate these challenges. In this paper, we compare various image classification models based on transfer learning with well-known deep learning architectures. The Kaggle chest X-ray dataset was used to evaluate and compare our models. We apply basic data augmentation and fine-tune our feed-forward classification head on the models pretrained on the ImageNet dataset. We observed that the DenseNet201 model outperforms other models with an AUROC score of 0.966 and a recall score of 0.99. We also visualize the class activation maps from the DenseNet201 model to interpret the patterns recognized by the model for prediction., Competing Interests: The authors declare that there is no conflict of interest regarding the publication of this paper., (Copyright © 2021 Surya Krishnamurthy et al.)

Neonatal infants communicate with us through cries. The infant cry signals have distinct patterns depending on the purpose of the cries. Preprocessing, feature extraction, and feature selection need expert attention and take much effort in audio signals in recent days. In deep learning techniques, it automatically extracts and selects the most important features. For this, it requires an enormous amount of data for effective classification. This work mainly discriminates the neonatal cries into pain, hunger, and sleepiness. The neonatal cry auditory signals are transformed into a spectrogram image by utilizing the short-time Fourier transform (STFT) technique. The deep convolutional neural network (DCNN) technique takes the spectrogram images for input. The features are obtained from the convolutional neural network and are passed to the support vector machine (SVM) classifier. Machine learning technique classifies neonatal cries. This work combines the advantages of machine learning and deep learning techniques to get the best results even with a moderate number of data samples. The experimental result shows that CNN-based feature extraction and SVM classifier provides promising results. While comparing the SVM-based kernel techniques, namely radial basis function (RBF), linear and polynomial, it is found that SVM-RBF provides the highest accuracy of kernel-based infant cry classification system provides 88.89% accuracy., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 K, Vincent, Srinivasan and Chang.)

In recent years, chip design technology and AI (artificial intelligence) have made significant progress. This forces all of fields to investigate how to increase the competitiveness of products with machine learning technology. In this work, we mainly use deep learning coupled with motor control to realize the real-time interactive system of air hockey, and to verify the feasibility of machine learning in the real-time interactive system. In particular, we use the convolutional neural network YOLO ("you only look once") to capture the hockey current position. At the same time, the law of reflection and neural networking are applied to predict the end position of the puck Based on the predicted location, the system will control the stepping motor to move the linear slide to realize the real-time interactive air hockey system. Finally, we discuss and verify the accuracy of the prediction of the puck end position and improve the system response time to meet the system requirements.

Gene Expression is the process of determining the physical characteristics of living beings by generating the necessary proteins. Gene Expression takes place in two steps, translation and transcription. It is the flow of information from DNA to RNA with enzymes' help, and the end product is proteins and other biochemical molecules. Many technologies can capture Gene Expression from the DNA or RNA. One such technique is Microarray DNA. Other than being expensive, the main issue with Microarray DNA is that it generates high-dimensional data with minimal sample size. The issue in handling such a heavyweight dataset is that the learning model will be over-fitted. This problem should be addressed by reducing the dimension of the data source to a considerable amount. In recent years, Machine Learning has gained popularity in the field of genomic studies. In the literature, many Machine Learning-based Gene Selection approaches have been discussed, which were proposed to improve dimensionality reduction precision. This paper does an extensive review of the various works done on Machine Learning-based gene selection in recent years, along with its performance analysis. The study categorizes various feature selection algorithms under Supervised, Unsupervised, and Semi-supervised learning. The works done in recent years to reduce the features for diagnosing tumors are discussed in detail. Furthermore, the performance of several discussed methods in the literature is analyzed. This study also lists out and briefly discusses the open issues in handling the high-dimension and less sample size data., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2020 Mahendran, Durai Raj Vincent, Srinivasan and Chang.)

In recent years, there are several cost-effective intelligent sensing systems such as ultrasound imaging systems for visualizing the internal body structures of the body. Further, such intelligent sensing systems such as ultrasound systems have been deployed by medical doctors around the globe for efficient detection of several diseases and disorders in the human body. Even though the ultrasound sensing system is a useful tool for obtaining the imagery of various body parts, there is always a possibility of inconsistencies in these images due to the variation in the settings of the system parameters. Therefore, in order to overcome such issues, this research devises an SVM-enabled intelligent genetic algorithmic model for choosing the universal features with four distinct settings of the parameters. Subsequently, the distinguishing characteristics of these features are assessed utilizing the Sorensen-Dice coefficient, T-test, and Pearson's R measure. It is apparent from the results of the SVM-enabled intelligent genetic algorithmic model that this approach aids in the effectual selection of universal features for the breast cyst images. In addition, this approach also accomplishes superior accuracy in the classification of the ultrasound image for four distinct settings of the parameters., Competing Interests: The authors declare no conflict of interest.

The present methods of diagnosing depression are entirely dependent on self-report ratings or clinical interviews. Those traditional methods are subjective, where the individual may or may not be answering genuinely to questions. In this paper, the data has been collected using self-report ratings and also using electronic smartwatches. This study aims to develop a weighted average ensemble machine learning model to predict major depressive disorder (MDD) with superior accuracy. The data has been pre-processed and the essential features have been selected using a correlation-based feature selection method. With the selected features, machine learning approaches such as Logistic Regression, Random Forest, and the proposed Weighted Average Ensemble Model are applied. Further, for assessing the performance of the proposed model, the Area under the Receiver Optimization Characteristic Curves has been used. The results demonstrate that the proposed Weighted Average Ensemble model performs with better accuracy than the Logistic Regression and the Random Forest approaches.

Cleaning robot has the highest penetration rate among the service robots. This paper proposes a high-efficiency mechanism for an intelligent cleaning robot automatically returns to charging in a short time when the power is insufficient. The proposed mechanism initially combines the robot's own motor encoder with neural network linear regression to calculate the moving distance and rotation angle for the location estimation of the robot itself. At the same time, a self-rotating camera is applied to scan the number of infrared spots on the docking station to find the location of the docking station so that the cleaning robot returns to charging properly in two stages, existing infrared range and extended infrared range. In addition, six-axis acceleration and ultrasound are both applied to deal with the angle error that is caused by collision. Experimental results show that the proposed recharging mechanism significantly improves the efficiency of recharging.

Sonographic texture analysis can reflect histopathological components and their arrangement in metastatic and common benign lymph nodes. It is helpful in differentiation between metastatic and benign lymph node lesions for target selection during biopsy of multiple lymph nodes and the strategy of the management. Two ultrasound systems, 107 sonographic regions of interest (ROIs) of metastases and 174 sonographic ROIs of common benign lymph nodes, were recruited in the study. Thirteen texture features derived from co-occurrence matrix were used in characterization of above ROI ultrasound images. Support vector machine (SVM) was used as a classifier and a feature selector. The experimental results show that the entropy gains the best cross-validation accuracy of 94.66% and 87.73% in both ultrasound systems 1 and 2 for the classification of metastatic and benign lymph nodes disease. The accuracy can be further increased to 97.86% and 100% by the combination of the sum average in the study. There are significantly higher entropy and sum average values of the metastatic lymph nodes than of the benign lymph nodes, which are due to the heterogeneous compositions and arrangement of larger cancer cells, lymphocytes, and stroma in metastatic lymph nodes that contrast with simple inflammatory cells infiltration in common benign lymph nodes., (Crown Copyright © 2012. Published by Elsevier Inc. All rights reserved.)

In this study, the ultrasound images of thyroid nodules were classified to facilitate clinical diagnosis and management. The hierarchical support vector machines (SVM) classification system was used to select the characteristic sonographic textural feature that represents the major histopathologic components of the thyroid nodules. Two ultrasound systems (LA39 and i12L mentioned in the Materials and Methods section) were used for comparison. Seventy-six thyroid nodular lesions and 157 regions-of-interest thyroid ultrasound image from each system were recruited in the study. The parameters affecting image acquisition were kept in the same condition for all lesions. Commonly used texture analysis methods were applied to characterize thyroid ultrasound images. Image features were classified according to the corresponding pathologic findings. To estimate their relevance and performance to classification, SVMs were used as a feature selector and a classifier. The thyroid nodules are first categorized as two main types, i.e., follicle base and fibrosis base nodule, by sum average. The follicle base nodules can be further and completely classified into follicles with few cells, follicles with follicular cells and follicles with papillary cancer cells by run length nonuniformity (RLNU). The fibrosis base nodules are further classified by sum square into fibrosis with few cells and fibrosis with dominant cells. The fibrosis base neoplasm with dominant cells can be separated into fibrosis with follicular cells and fibrosis with papillary cancer cells by entropy. The hierarchical SVM classification system achieves a diagnostic accuracy between 96.34% and 100%. Besides, the best sonographic textural feature can be selected by the system for the differentiation between the follicle and fibrosis base thyroid nodules or the cell types mixed in them. In follicle base thyroid nodules, papillary cancers show higher sonographic textural RLNU but less than follicular cells. In fibrosis base thyroid nodules, papillary cancers show increased sonographic textural variance and entropy., (Crown Copyright © 2010. Published by Elsevier Inc. All rights reserved.)

Physicians usually diagnose the pathology of the thyroid gland by its volume. However, even if the thyroid glands are found and the shapes are hand-marked from ultrasound (US) images, most physicians still depend on computed tomography (CT) images, which are expensive to obtain, for precise measurements of the volume of the thyroid gland. This approach relies heavily on the experience of the physicians and is very time consuming. Patients are exposed to high radiation when obtaining CT images. In contrast, US imaging does not require ionizing radiation and is relatively inexpensive. US imaging is thus one of the most commonly used auxiliary tools in clinical diagnosis. The present study proposes a complete solution to estimate the volume of the thyroid gland directly from US images. The radial basis function neural network is used to classify blocks of the thyroid gland. The integral region is acquired by applying a specific-region-growing method to potential points of interest. The parameters for evaluating the thyroid volume are estimated using a particle swarm optimization algorithm. Experimental results of the thyroid region segmentation and volume estimation in US images show that the proposed approach is very promising.

Compared to object-based registration, feature-based registration is much less complex. However, in order for feature-based registration to work, the two image stacks under consideration must have the same acquisition tilt angle and the same anatomical location - two requirements that are not always fulfilled. In this paper, we propose a technique that reconstructs two sets of medical images acquired with different acquisition angles and anatomical cross sections into one set of images of identical scanning orientation and positions. The space correlation information among the two image stacks is first extracted and is used to correct the tilt angle and anatomical position differences in the image stacks. Satisfactory reconstruction results were presented to prove our points.

Background and Purpose: The purpose of this study was to determine whether diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) can be used to distinguish brain abscesses from cystic or necrotic brain tumors, which are difficult to distinguish by conventional magnetic resonance imaging (MRI) techniques., Methods: Eleven consecutive patients with brain abscesses [10 pyogenic and 1 toxoplasmosis (in an AIDS patient)] and 15 with cystic or necrotic brain gliomas or metastases were enrolled in this study. None of these lesions had apparent hemorrhage based on T1-weighted image (T1WI). The DWI was performed using a 1.5-T system, single-shot spin-echo echo-planar pulse sequence with b=1000 s/mm(2). The ADC was calculated using a two-point linear regression method at b=0 and b=1000 s/mm(2). The ratio (ADCR) of the lesion ADC to control region ADC was also measured., Results: Increased signal was seen in all of the pyogenic abscess cavities to variable degrees on DWI. In vivo ADC maps showed restricted diffusion in the abscess cavity in all pyogenic abscesses [0.65+/-0.16 x 10(-3) (mean+/-S.D.) mm(2)/s, mean ADCR=0.63]. The case with multiple toxoplasmosis abscesses showed low signal intensity on DWI and high ADC values (mean 1.9 x 10(-3) mm(2)/s, ADCR=2.24). All cystic or necrotic tumors but one showed low signal intensity on DWI and their cystic or necrotic areas had high ADC values (2.70+/-0.31 x 10(-3) mm(2)/s, mean ADCR=3.42). One fibrillary low-grade astrocytoma had a high DWI signal intensity and a low ADC value in its central cystic area (0.44 x 10(-3) mm(2)/s, ADCR=0.49). Postcontrast T1WIs yielded a sensitivity of 60%, a specificity of 27.27%, a positive predictive value (PPV) of 52.94%, and a negative predictive value (NPV) of 33.33% in the diagnosis of necrotic tumors. DWI yielded a sensitivity of 93.33%, a specificity of 90.91%, a PPV of 93.33%, and a NPV of 90.91%. The area under receiver operating characteristic (ROC) curves for postcontrast T1WI was 0.44 and DWI was 0.92. Analysis of these areas under the ROC curves indicates significant difference between postcontrast T1WI and DWI (P<.001)., Conclusion: With some exceptions, DWI is useful in providing a greater degree of confidence in distinguishing brain abscesses from cystic or necrotic brain tumors than conventional MRI and seems to be a valuable diagnostic tool.