Search

Automated segmentation of histopathological images is a challenging task to detect cancerous cells in breast tissue. Recent reviews state high accuracy to segment image, but depends on user input, say window area size, time steps, level set, magnification factor and so on. To extract the region of interest effectively, the subject expert performs post-processing operations several times on the segmentation results with different input values for different parameters say, area opening, fill holes and selects most appropriate enhanced image required for further analysis. The authors proposed an automated segmentation technique followed by self-driven post-processing operations to detect cancerous cells effectively. The post-processing method itself determines the value of different parameters for different operations based on segmented results obtained. The proposed technique has the following features: (i) technique is context sensitive; (ii) no prior setting of time step, weighted area coefficient parameters is required; (iii) magnification independent; (iv) post-processing operations are self-driven which enhance segmentation results adaptively. The experimental results are compared with four state-of-the-art techniques: fuzzy C-means, spatial fuzzy C-means, spatial neutrosophic distance regularised level set and convolutional neural network-based PangNet. Experimental results obtained on two publicly available data sets show that the proposed technique outperforms effectively.

Nature-inspired algorithms emulate the mathematical and innovative techniques for non-linear and real-life problems worldwide. Imaging technology is emerging out as one of the most prominent and wi...

The abnormal growth of the skin cells is known as skin cancer. It is one of the main problems in the dermatology area. Skin lesions or malignancies have been a source of worry for many individuals in recent years. Irrespective of the skin tone, there exist three major classes of skin lesions, i.e., basal cell carcinoma, squamous cell carcinoma, and melanoma. The early diagnosis of these lesions is equally important for human life. In the proposed work, a secure IoMT-Assisted framework is introduced that can help the patients to do the initial screening of skin lesions remotely. The initially proposed approach uses an IoMT-based data collection device which is accessible by patients to capture skin lesions images. Next, the captured skin sample is encrypted and sent to the collected image toward cloud storage. Later, the received sample image is classified into appropriate class labels using an ensemble classifier. In the proposed framework, four CNN models were ensemble i.e., VGG-16, DenseNet-201, Inception-V3, and Efficient-B7. The framework has experimented with the “HAM10000” dataset having 7 different kinds of skin lesions data. Although DenseNet-201 performed well, the ensemble model provides the highest accuracy with 87.22 percent as well as its test loss/error is lower than others with 0.4131. Moreover, the ensemble model’s classification ability is much higher with an AUC score of 0.9745. Moreover, A recommendation team has been assigned to assess the sample of the patient as well as suggest the patient according to classified results by the CAD.

Deep learning's rapid gains in automation are making it more popular in a variety of complex jobs. The self-driving object is an emerging technology that has the potential to transform the entire planet. The steering control of an automated item is critical to ensuring a safe and secure voyage. Consequently, in this study, we developed a methodology for predicting the steering angle only by looking at the front images of a vehicle. In addition, we used an Internet of Things-based system for collecting front images and steering angles. A Raspberry Pi (RP) camera is used in conjunction with a Raspberry Pi (RP) processing unit to capture images from vehicles, and the RP processing unit is used to collect the angles associated with each image. Apart from that, we've made use of deep learning-based algorithms such as VGG16, ResNet-152, DenseNet-201, and Nvidia's models, all of which were trained using labeled training data. Our models are End-to-End CNN models, which do not require extracting elements from data such as roads, lanes, or other objects before predicting steering angle. As a result of our comparative investigation, we can conclude that the Nvidia model's performance was satisfactory, with a Mean Squared Error (MSE) value of 0. But the Nvidia model outperforms the other pre-trained models, even though other models work well.

Communication through email plays an essential part especially in every sector of our day-to-day life. Considering its significance, it is important to filter spam emails from emails. Spam email, also known as junk email, is unwanted messages that are sent by the electronic medium in large quantities. Most of the spam emails are commercial in nature that is not only irritating but also harmful due to malicious scams or malware-hosting sites or use viruses attached to the message. In this paper, we identify spam emails and expose how spam emails can be distinguished from legitimate/normal emails. We deployed four machine learning models and two deep learning models over the datasets including the combined dataset. Besides, we also try to find the important keywords that are found repeatedly from spam emails repository. This type of knowledge will enable us to detect spam emails for our personnel and community security purpose.

Skin lesions or malignancies have been a source of worry for many individuals in recent years. The underline reason behind it mainly the diet and environmental pollution. Yet many individuals are unaware of the issue and, more importantly, many people do not want to visit a hospital for diagnostic or therapeutic purposes. So, we have come up with a pipeline to diagnose skin lesions at home. Firstly, we proposed a IoT base data collection device which is accessible by patient to capture skin lesions image. This IoT device will encrypt and send the collected image towards a cloud storage; then it will decrypt the image send to the computer assisted diagnosis system. In CAD, we have implemented ensemble classifier. Ensemble classifier created depending on four deep learning classifiers namely VGG16, DenseNet201, Inception V3 and Efficient B7; whereas encryption and decryption performed in order to secure a patient data from unauthorized access. For skin lesions classification, we have used "HAM10000" dataset where 7 kind of skin lesions data included; Although DenseNet201 performed well, the ensemble model provides the highest accuracy with 87.22\% as well as its test loss/error is lower than others with 0.4131.

Diabetes is a disease that affects how your body processes blood sugar and is often referred to as diabetes mellitus. Insulin insufficiency and ineffective insulin use coincide when the pancreas cannot produce enough insulin or the human body cannot use the insulin that is produced. Insulin is a hormone produced by the pancreas that helps in the transport of glucose from food into cells for use as energy. The common effect of uncontrolled diabetes is hyper-glycemia, or high blood sugar, which plus other health concerns, raises serious health issues, majorly towards the nerves and blood vessels. According to 2014 statistics, people aged 18 or older had diabetes and, according to 2019 statistics, diabetes alone caused 1.5 million deaths. However, because of the rapid growth of machine learning(ML) and deep learning (DL) classification algorithms. indifferent sectors, like health science, it is now remarkably easy to detect diabetes in its early stages. In this experiment, we have conducted a comparative analysis of several ML and DL techniques for early diabetes disease prediction. Additionally, we used a diabetes dataset from the UCI repository that has 17 attributes, including class, and evaluated the performance of all proposed machine learning and deep learning classification algorithms using a variety of performance metrics. According to our experiments, the XGBoost classifier outperformed the rest of the algorithms by approximately 100.0$\%$, while the rest of the algorithms were over 90.0$\%$ accurate.

In these days, research on the medical healthcare system is an emerging area and mainly focused on the designing of an efficient segmentation approach with the concept of Artificial Intelligence (AI) techniques for the appropriate and accurate region detection. A lot of clustering, as well as traditional segmentation approaches, are available for medical images, but most of them are depended on the data types. In this survey, various types of medical diagnosis systems are analyzed for segmentation such as segmentation of brain tumor, skin lesion, leukemia blood cell, and lungs nodules segmentation. In this paper, we presented a brief review on clustering-based medical image segmentation with their challenging factors faced by researchers. Owing to the great success rate of AI, Deep Learning (DL or), Machine Learning (ML) algorithms, there are many segmentation techniques aimed by researchers for medical image segmentation to overcome the existing challenges. Here, a survey of existing clustering-based segmentation and their hybridization with swarm-based optimization techniques are also discussed with a tabular representation. At the last, we compare the existing work based on the quantitative performance analyses in terms of Accuracy, Dice Coefficient, Jaccard Index, Sensitivity, and Specificity, etc. on some popular benchmark datasets.

This article acquaints a new generalized weighted active learning paradigm to classify patterns based on nature inspired phenomena and is competent when abundant of unlabeled data is present whereas labelled data is scarce. In literature, most informative samples are selected in successive iterations of active learning model depends on either uncertainty or diverse measures or both but sequentially. Study showed that the unsettled and distinct samples both are equally important to improve learning at every run and can be used simultaneously. To resolve the selection based on uncertainty and diversity measures sequentially, this article utilizes genetic algorithm (GA) which select the most informative samples based on real fact that uncertainty and diversity measures does not play equal role and can be utilized simultaneously. Thus, to improve the selection at successive iterations, decision maker (analyst) may give the preference in the form of weight vector to select the most uncertain as well as non-redundant samples. The proposed technique is verified and validated with four different standard UCI repository datasets: Ionosphere, Iris, Pima, and Vehicle. The comparative results numerically prove that the proposed technique is efficient over existing techniques in terms of average overall classification (OA), 94.85% for Ionosphere, 89.89% for Iris, 71.87% for Pima, and 65.63% for Vehicle. The low number of initial training samples and graphical results also prove that the proposed weighted active learning technique is reliable, adaptive and robust.

Breast cancer is one of the common type of cancer in females across the world. An early detection and diagnosis of breast cancer may reduce the mortality rate to a great extent. To diagnose breast cancer, different types of imaging modalities are used to collect samples like mammography, Computerized Tomography, Magnetic Resonance Imaging, Ultrasound and Biopsy. Histopathological images obtained from biopsy may influence how and at which stage the cancer is being diagnosed. The Computer Assisted Diagnosis (CAD) system helps the pathologists in early diagnosis of breast cancer. In this survey, the recently reported techniques for breast cancer diagnosis using histopathological images have been summarized. This study could be beneficial for: (i) Clinicians to receive second opinion from the CAD system for early diagnosis, and (ii) Researchers to analyze and enhance the existing state-of-art techniques used in CAD system, which may further reduce the gap of variability between intra and inter observer.

Thyroid is one of the frequently found types of cancer among both men and women globally. Earlier, doctors were detecting thyroid cancer manually which was time-consuming task, but nowadays computer-aided diagnosis (CAD) system is used. As frequency of cancer patients of thyroid is increasing day by day, the enhanced technology is always required with low false positive rate and early detection. Authors proposed a thresholding technique named as spatial contextual thresholding technique (SCTT) which has the following features: (i) Neighborhood information of each pixel of image have been utilized; hence, the technique is context sensitive, (ii) Provides all potential thresholds of image which experts can utilize to study the case more efficiently, (iii) The technique is device independent, i.e., no prior setting of parameters is required for different machines with which US image is captured, and (iv) No initial seed values and parameter selection/tuning are required for an algorithm. To prove the efficiency of proposed SCTT, comparison of results has been done with two state-of-the-art techniques present in literature: spatial fuzzy C-Means (SFCM) and spatial neutrosophic L-Means clustering (SNLM). The proposed SCTT reduces false positive rate and improves accuracy, sensitivity, specificity, and precision. It also yields the results closest to the ground truth as compared to the SFCM and SNLM techniques as revealed by five assessment measures: accuracy is 96.4 ± 0.005%, sensitivity is 97.6 ± 0.005%, specificity is 88.4 ± 0.018%, precision is 98.0 ± 0.004%, and false positive rate is 0.115 ± 0.018. Experimental results obtained affirm the efficiency of the proposed technique.

Breast cancer is the most common type of cancer that occurs in females. Histological images show noteworthy notch in the medical domain. Feature extraction and classification in computer-assisted diagnosis of breast cancer with histological images is an essential aspect. In literature, there exist variety of feature extraction and classification algorithms employed on different datasets and domains. This article presents different feature extraction algorithms in combination with different classification algorithms to diagnose breast cancer using large-scale standard histological dataset known as BreaKHis. The experimental results are analyzed with respect to five different evaluation metrics: accuracy, F-measure, precision, recall, and G-mean.

The innovations given by rapid development of science and technology may bless the society in handling environmental issues efficiently. The main driving force behind environmental issues is population growth. As the population is increasing, the management of waste is becoming a difficult and challenging task for the concerned authorities. The utilization and deployment of advanced technologies namely Internet of Things, Cloud Computing and Image processing may aid the authorities to timely manage the garbage and keep the environment clean. In time management of waste will help the society to meet the alarming situations like inhaling of toxic gases and various health diseases. This paper discusses the state-of-art technologies that have been employed in literature for waste management. Also, the authors proposed a novel architecture for waste management that utilizes the concept of IoT and image processing. The proposed architecture acts as a surveillance system to monitor the overflow of the garbage and delivers a message to the concerned authorities to take the necessary and immediate action.

Breast cancer is one of the most common disease from which most of the females are suffering. Histopathological images play remarkable notch in the medical domain. Segmentation of breast cancer images for cell analysis is the utmost thought-provoking task because of uncertainties present in these images. Identifying cancerous cells effectively in histopathological images may help in early diagnosis of breast cancer. In this paper, comparative analysis of different state-of-art segmentation techniques have been carried out to extract cancerous cells in histopathological images using Triple Negative Breast Cancer (TNBC) dataset. The experimental results of segmentation techniques have been analysed with respect to Accuracy, False Positive Rate (FPR), and True Positive Rate (TPR). Experiments using histopathological images validates Spatial Fuzzy C-Means with Level Set finds the cancerous breast cells effectively.

Large volume of data which is a combination of both structured as well as unstructured data is referred by the term Big Data. As the amount of data produced is very huge, it becomes really difficult and time consuming to manage this data. Hadoop is a Big Data technology that is extensively used for the manipulation and analysis of Big Data. The applications of Big Data introduce new scope to determine knowledge. In this paper, applications of Big Data in medical domain is presented. Also, the challenges and benefits of various tools of Big Data in various scenarios are discussed.

Big data refers to huge set of data which is very common these days due to the increase of internet utilities. Data generated from social media is a very common example for the same. This paper depicts the summary on big data and ways in which it has been utilized in all aspects. Data mining is radically a mode of deriving the indispensable knowledge from extensively vast fractions of data which is quite challenging to be interpreted by conventional methods. The paper mainly focuses on the issues related to the clustering techniques in big data. For the classification purpose of the big data, the existing classification algorithms are concisely acknowledged and after that, k-nearest neighbor algorithm is discreetly chosen among them and described along with an example.

In this paper, we have proposed two new approaches Per_SPAM and Mis_SPAM. Per_SPAM is the periodic approach to discover frequent patterns in item sequences. Mis_SPAM is the minimum item support approach to extract rare items. The outcome of these approaches is the proposal of a new algorithm called New_SPAM which incorporates periodic and minimum item support approach. The new algorithm assigns minimum item support values for frequent as well as rare items based on their item supports. The performance of proposed algorithm and approaches is compared against frequent sequence count and running time. Experimental results on real-life datasets show that the proposed approaches and new algorithm have better efficiency over the existing algorithm CM_SPAM.

As users access the web pages of a website, sequences containing the web pages are stored in the web server logs. These web server logs can be used to analyze the behavior of website users. This paper presents a pioneering comparison study of five most important sequential pattern mining algorithms on web click stream datasets. The performance of algorithms is compared against running time and maximum memory usage. Experimental results have been evaluated and compared to find an algorithm which has better performance on some real-life datasets.