Cancer diagnosis using artificial intelligence: a review

Artificial intelligence (AI) is the usage of scientific techniques to simulate human intellectual skills and to tackle complex medical issues involving complicated genetic defects such as cancer. The rapid expansion of AI in the past era has paved the way to optimum judgment-making by superior intellect, where the human brain is constrained to manage large information in a limited period. Cancer is a complicated ailment along with several genomic variants. AI-centred systems carry enormous potential in detecting these genomic alterations and abnormal protein communications at a very initial phase. The contemporary biomedical study is also dedicated to bringing AI expertise to hospitals securely and ethically. AI-centred support to diagnosticians and doctors can be the big surge ahead for the forecast of illness threat, identification, diagnosis, and therapies. The applications related to AI and Machine Learning (ML) in the identification of cancer and its therapy possess the potential to provide therapeutic support for quicker planning of a novel therapy for each person. Through the utilization of AI- based methods, scientists can work together in real-time and distribute their expertise digitally to possibly cure billions. In this review, the focus was on the study of linking biology with AI and describe how AI-centred support could assist oncologists in accurate therapy. It is essential to identify new biomarkers that inject drug defiance and discover medicinal goals to improve medication methods. The advent of the “next-generation sequencing” (NGS) programs resolves these challenges and has transformed the prospect of “Precision Oncology” (PO). NGS delivers numerous medical functions which are vital for hazard prediction, initial diagnosis of infection, “Sequence” identification and “Medical Imaging” (MI), precise diagnosis, “biomarker” detection, and recognition of medicinal goals for innovation in medicine. NGS creates a huge repository that requires specific “bioinformatics” sources to examine the information that is pertinent and medically important. The malignancy diagnostics and analytical forecast are improved with NGS and MI that provide superior quality images via AI technology. Irrespective of the advancements in technology, AI faces a few problems and constraints, and the clinical application of NGS continues to be authenticated. Through the steady progress of invention and expertise, the prospects of AI and PO look promising. The purpose of this review was to assess, evaluate, classify, and tackle the present developments in cancer diagnosis utilizing AI methods for breast, lung, liver, skin cancer, and leukaemia. The research emphasizes in what way cancer identification, the treatment procedure is aided by utilizing AI with supervised, unsupervised, and deep learning (DL) methods. Numerous AI methods were assessed on benchmark datasets with respect to “accuracy”, “sensitivity”, “specificity”, and “false-positive” (FP) metrics. Lastly, challenges along with future work were discussed.

     

Predicting the delay of issues with due dates in software projects

Issue-tracking systems (e.g. JIRA) have increasingly been used in many software projects. An issue could represent a software bug, a new requirement or a user story, or even a project task. A deadline can be imposed on an issue by either explicitly assigning a due date to it, or implicitly assigning it to a release and having it inherit the release’s deadline. This paper presents a novel approach to providing automated support for project managers and other decision makers in predicting whether an issue is at risk of being delayed against its deadline. A set of features (hereafter called risk factors) characterizing delayed issues were extracted from eight open source projects: Apache, Duraspace, Java.net, JBoss, JIRA, Moodle, Mulesoft, and WSO2. Risk factors with good discriminative power were selected to build predictive models to predict if the resolution of an issue will be at risk of being delayed. Our predictive models are able to predict both the the extend of the delay and the likelihood of the delay occurrence. The evaluation results demonstrate the effectiveness of our predictive models, achieving on average 79 % precision, 61 % recall, 68 % F-measure, and 83 % Area Under the ROC Curve. Our predictive models also have low error rates: on average 0.66 for Macro-averaged Mean Cost-Error and 0.72 Macro-averaged Mean Absolute Error.     

KDSAE: Chronic kidney disease classification with multimedia data learning using deep stacked autoencoder network

In recent times, Chronic Kidney Disease (CKD) has affected more than 10% of the population worldwide and millions of people die every year. So, early-stage detection of CKD could be beneficial for increasing the life expectancy of suffering patients and reducing the treatment cost. It is required to build such a multimedia driven model which can help to diagnose the disease efficiently with higher accuracy before leading to worse conditions. Various techniques related to conventional machine learning models have been used by researchers in the past time without involvement of multimodal data-driven learning. This research paper offers a novel deep learning framework for chronic kidney disease classification using stacked autoencoder model utilizing multimedia data with a softmax classifier. The stacked autoencoder helps to extract the useful features from the dataset and then a softmax classifier is used to predict the final class. It has experimented on UCI dataset which contains early stages of 400 CKD patients with 25 attributes, which is a binary classification problem. Precision, recall, specificity and F1-score were used as evaluation metrics for the assessment of the proposed network. It was observed that this multimodal model outperformed the other conventional classifiers used for chronic kidney disease with a classification accuracy of 100%.

     

Keyword search on form results

In recent years there has been a good deal of research in the area of keyword search on structured and semistructured data. Most of this body of work has a significant limitation in the context of enterprise data, since it ignores the application code that has often been carefully designed to present data in a meaningful fashion to users. In this work, we consider how to perform keyword search on enterprise applications, which provide a number of forms that can take parameters; parameters may be explicit, or implicit such as the identifier of the user. In the context of such applications, the goal of keyword search is, given a set of keywords, to retrieve forms along with corresponding parameter values, such that result of each retrieved form executed on the corresponding retrieved parameter values will contain the specified keywords. Some earlier work in this area was based on creating keyword indices on form results, but there are problems in maintaining such indices in the face of updates. In contrast, we propose techniques based on creating inverted SQL queries from the SQL queries in the forms. Unlike earlier work, our techniques do not require any special purpose indices and instead make use of standard text indices supported by most database systems. We have implemented our techniques and show that keyword search can run at reasonable speeds even on large databases with a significant number of forms.     

Dissecting SpyEye – Understanding the design of third generation botnets

Botnet malware is improving with the latest (3rd) generation exemplified by the SpyEye and Zeus botnets. These botnets are important to understand because they target online financial transactions, primarily with banks. In this paper, we analyze the components from multiple generations of the SpyEye botnet in order to understand both how it works and how it is evolving. SpyEye is a sophisticated piece of malware with a modular design that eases the incorporation of improvements. We will discuss in detail the complete framework of SpyEye botnet consisting of the Bot Development Kit (BDK), the plugin architecture, the backend storage server, the bot design and the web-based Command and Control (C&C) management system. In addition, we also examine the techniques used by SpyEye to steal money.     

Influence of pozzolanic additives on hydration mechanisms of tricalcium silicate

Pozzolanic mineral additives, such as silica fume (SF) and metakaolin (MK), are used to partially replace cement in concrete. This study employs extensive experimentation and simulations to elucidate and contrast the influence of SF and MK on the early age hydration rates of tricalcium silicate (triclinic C₃S), the major phase in cement. Results show that at low replacement levels (i.e., ≤10%), both SF and MK accelerate C₃S hydration rates via the filler effect, that is, enhanced heterogeneous nucleation of the main hydration product (C–S–H: calcium‐silicate‐hydrate) on the extra surfaces provided by the additive. The filler effect of SF is inferior to that of MK because of agglomeration of the fine particles of SF, which causes significant reduction (i.e., up to 97%) in its surface area. At higher replacement levels (i.e., ≥20%), while SF continues to serve as a filler, the propensity of MK to allow nucleation of C–S–H on its surface is substantially suppressed. This reversal in the filler effect of MK is attributed to the abundance of aluminate [Al(OH)₄^?] ions in the solution—released from the dissolution of MK—which inhibit topographical sites for C–S–H nucleation and impede its subsequent growth. Results also show that in the first 24 hours of hydration, MK is a superior pozzolan compared to SF. However, the pozzolanic activities of both SF and MK are limited and, thus, do not produce significant alterations in the early age hydration kinetics of C₃S. Overall, the outcomes of this study provide novel insights into the mechanistic origins of the filler and pozzolanic effects of SF and MK, and their impact on cementitious reaction rates.     

Outage and energy efficiency analysis for cognitive based heterogeneous cellular networks

Cognitive radio and small cells are the promising techniques to minimize energy consumption and satisfy the exponentially increasing data rates for the heterogeneous cellular network (HCN). In this paper, a theoretical framework is developed to calculate the outage probability of the HCN based on the opportunistic utilization of the traditional cellular bandwidth and television white space (TVWS) for the cognitive femto base stations. This work investigates overlay, underlay, mixed overlay-underlay based two tiers cognitive HCN. It also investigates the impact of the TVWS in the overlay-TVWS mixed spectrum sharing technique (SST). Tools from stochastic geometry are used to model cognitive HCN. Furthermore, the tier selection probability, average ergodic rate, area spectral efficiency (ASE), and energy efficiency (EE) of the HCN are also calculated for different SSTs. Numerical results show that mixed SST achieves a significant reduction in tier outage probability and total outage probability as compared to underlay and overlay techniques alone. It is also demonstrated that compared to the traditional single tier network, cognitive based HCN can improve the total ASE and EE of the order of \(10^{2}\) and 10, respectively.     

An Exploratory User Study of Visual Causality Analysis

Interactive visualization tools are being used by an increasing number of members of the general public; however, little is known about how, and how well, people use visualizations to infer causality. Adapted from the mediation causal model, we designed an analytic framework to systematically evaluate human performance, strategies, and pitfalls in a visual causal reasoning task. We recruited 24 participants and asked them to identify the mediators in a fictitious dataset using bar charts and scatter plots within our visualization interface. The results showed that the accuracy of their responses as to whether a variable is a mediator significantly decreased when a confounding variable directly influenced the variable being analyzed. Further analysis demonstrated how individual visualization exploration strategies and interfaces might influence reasoning performance. We also identified common strategies and pitfalls in their causal reasoning processes. Design implications for how future visual analytics tools can be designed to better support causal inference are discussed.     

An Optimal Information Hiding Approach Based on Pixel Value Differencing and Modulus Function

Wireless Personal Communications - This paper introduces the use of rhombus shaped dipole nanoantenna coupled to geometric diode in energy harvesting at 19.4 THz. An...     

Robust adaptive boundary control of semilinear PDE systems using a dyadic controller

In this paper, we describe a dyadic adaptive control framework for output tracking in a class of semilinear systems of partial differential equations with boundary actuation and unknown distributed nonlinearities. The dyadic adaptive control framework uses the linear terms in the system to split the plant into 2 virtual subsystems, one of which contains the nonlinearities, whereas the other contains the control input. Full‐plant‐state feedback is used to estimate the unmeasured individual states of the 2 subsystems as well as the nonlinearities. The control signal is designed to ensure that the controlled subsystem tracks a suitably modified reference signal. We prove the well posedness of the closed‐loop system rigorously and derive conditions for closed‐loop stability and robustness using finite‐gain stability theory.