Search

Parkinson's disease (PD) is the second most prevalent neurological disorder, predominantly affecting older people. With no existing cure, the early detection of PD, where symptoms are not entirely evident but indicative of the disease's onset, is critical. This study aims to design and develop AI-based diagnostic methods that can detect these early signs of PD with high accuracy, thereby facilitating more effective disease management. This study focuses on developing a method that not only identifies PD at an early stage but also provides clinicians with a tool to interpret the decisions taken by the AI models to avoid misdiagnosis. In this study, a T2-weighted 3D Magnetic resonance imaging (MRI) dataset is used to analyze detailed morphological, textural, and structural changes. The MRI scans are pre-processed using brain extraction, image registration, bias correction, normalization, and segmentation processes. Upon segmentation, feature extraction was applied to the segmented subcortical regions using radiomics tools, resulting in the extraction of 107 features. The top 20 features were selected through Pearson’s correlation, recursive feature elimination, and a ranking model, which are responsible for the ML model’s class prediction. Statistical validation of these features was also performed using Analysis of Variance (ANOVA), pairwise t-tests, and Kruskal-Wallis H-tests to ensure that the identified 20 features were dominant for the prediction. Based on the identified features, several Machine Learning (ML) models were used to identify the best classifier for the provided real-world MRI scans. The Gradient Boosting (GB) algorithm achieved better prediction accuracy among the compared models. Incorporating the Synthetic Minority Over-sampling Technique (SMOTE) to address data imbalances significantly improved the model's performance, boosting accuracy to 96.8 % from 87 %. Further, multiple Explainable Artificial Intelligence (XAI) techniques were deployed to enhance the transparency and interpretability of the models. These techniques provide insights into how each identified feature influences predictions by the classifier, assisting clinicians in making trustworthy decisions when planning diagnosis and treatment measures.

Abstract Parkinson’s disease (PD) is one of the most common neurodegenerative disorders that affect the quality of human life of millions of people throughout the world. The probability of getting affected by this disease increases with age, and it is common among the elderly population. Early detection can help in initiating medications at an earlier stage. It can significantly slow down the progression of this disease, assisting the patient to maintain a good quality of life for a more extended period. Magnetic resonance imaging (MRI)-based brain imaging is an area of active research that is used to diagnose PD disease early and to understand the key biomarkers. The prior research investigations using MRI data mainly focus on volume, structural, and morphological changes in the basal ganglia (BG) region for diagnosing PD. Recently, researchers have emphasized the significance of studying other areas of the human brain for a more comprehensive understanding of PD and also to analyze changes happening in brain tissue. Thus, to perform accurate diagnosis and treatment planning for early identification of PD, this work focuses on learning the onset of PD from images taken from whole-brain MRI using a novel 3D-convolutional neural network (3D-CNN) deep learning architecture. The conventional 3D-Resent deep learning model, after various hyper-parameter tuning and architectural changes, has achieved an accuracy of 90%. In this work, a novel 3D-CNN architecture was developed, and after several ablation studies, the model yielded results with an improved accuracy of 93.4%. Combining features from the 3D-CNN and 3D ResNet models using Canonical Correlation Analysis (CCA) resulted in 95% accuracy. For further enhancements of the model performance, feature fusion with optimization was employed, utilizing various optimization techniques. Whale optimization based on a biologically inspired approach was selected on the basis of a convergence diagram. The performance of this approach is compared to other methods and has given an accuracy of 97%. This work represents a critical advancement in improving PD diagnosis techniques and emphasizing the importance of deep nested 3D learning and bio-inspired feature selection.

Abstract The recent developments in quantum technology have opened up new opportunities for machine learning algorithms to assist the healthcare industry in diagnosing complex health disorders, such as heart disease. In this work, we summarize the effectiveness of QuEML in heart disease prediction. To evaluate the performance of QuEML against traditional machine learning algorithms, the Kaggle heart disease dataset was used which contains 1190 samples out of which 53% of samples are labeled as positive samples and rest 47% samples are labeled as negative samples. The performance of QuEML was evaluated in terms of accuracy, precision, recall, specificity, F1 score, and training time against traditional machine learning algorithms. From the experimental results, it has been observed that proposed quantum approaches predicted around 50.03% of positive samples as positive and an average of 44.65% of negative samples are predicted as negative whereas traditional machine learning approaches could predict around 49.78% of positive samples as positive and 44.31% of negative samples as negative. Furthermore, the computational complexity of QuEML was measured which consumed average of 670 µs for its training whereas traditional machine learning algorithms could consume an average 862.5 µs for training. Hence, QuEL was found to be a promising approach in heart disease prediction with an accuracy rate of 0.6% higher and training time of 192.5 µs faster than that of traditional machine learning approaches.

The neutrosophic theory is known for its prominent application in real life, possessing unclear, indeterminate information. Interval valued neutrosophic theory is even more flexible to handle indeterminacy effectively since the membership functions are depicted as intervals that lie in [0, 1]. In this article, the operations on Strong Interval Valued Neutrosophic graph have been newly defined along with their related theorems. The Strong Interval Valued Neutrosophic Digraph has been newly introduced for evaluating the blood pressure that fluctuates during the blood flow of the human heart. By considering the hemodynamic parameters of a healthy adult of age above 35 years without any cardiac malfunction, we model the cardiac functioning of the human heart during the Systolic and Diastolic phases as Strong Interval Valued Neutrosophic Digraph and its evaluation observed to be analogous to the conventional biological approach.

This work introduces the notion of a hesitant bipolar-valued intuitionistic fuzzy graph (HBVIFG), which reflects four different characterizations: membership with positive/negative aspects and non-membership with positive/negative aspects, incorporating multi-dimensional alternatives in all of its information. HBVIFG generalizes both HBVFG and BVHFG due to its diversified nature in observing four perspectives along with multiple attributes in a piece of information. Numerous studies, examples, and graphical representations emphasize the concept’s distinctiveness and importance. The following graph theory terms are defined: strong directed HBVIFG, full directed HBVIFG, directed spanning HBVIFSG, directed HBVIFSG, and partial directed hesitant bipolar-valued intuitionistic fuzzy subgraph (HBVIFSG). Examples of operations utilizing two HBVIFGs are Cartesian, direct, lexicographical, and strong products. A scenario is used to generate the mapping of relations, which includes homomorphism, isomorphism, weak isomorphism, and co-weak isomorphism. We describe a directed HBVIFG application that employs an algorithm to determine the most dominant person and self-persistent person in a social system and a comparative study is also provided. The proposed method provides a more detailed framework for assessing the most dominant and self-persistent individual in a social network across multi-level attributes along with positive and negative side membership and non-membership grades in each element of a network.

A blend of only commercial powders, including Ni625, CoCrF75, and 316L, were used as the raw material for fabricating non-equiatomic CoCrFeNiMoxNby high entropy alloys (HEAs) through laser powder bed fusion (PBF-LB/M) via in situ alloying, instead of using pure elemental powders, thus reducing the raw materials cost. The rapid cooling inherent in the PBF-LB/M process facilitated the dissolution of Mo and Nb, resulting in a single FCC phase characterized by high relative densities. High-temperature tensile tests were conducted at room temperature, 700 °C, 800 °C, and 900 °C, revealing mechanical properties that surpassed those reported in existing HEA literature. The remarkable strength of the HEAs developed in this study primarily stemmed from the incorporation of Mo and Nb, leading to the precipitation of Mo and Nb-rich lave phases at elevated temperatures. While constraining elongation when confined to grain boundaries, these precipitates enhanced strength without compromising elongation when distributed throughout the matrix. This work is a feasibility study to explore the usage of commodity compositions from the market to develop HEAs using PBF-LB/M, which opens the possibility of using scraps to further the development of new materials. Consequently, this study presents a rapid and cost-effective approach for HEA development, improving efficiency and sidestepping the direct utilization of critical raw metals for sustainable manufacturing. Moreover, this work also underscores the outstanding mechanical performance of these HEAs at high temperatures, paving the way for the design of innovative alloys for future high-temperature applications.

The study presents a review of research advancements in the field of gamma radiation detection systems for emergency radiation monitoring, particularly two major sub-systems namely (i) the radiation detector and (ii) the detection platform – air-borne and ground-based. The dynamics and functional characteristics of modern radiation detector active materials are summarized and discussed. The capabilities of both ground-based and aerial vehicle platforms employed in gamma radiation monitoring are deliberated in depth.

In machining processes, cutting tools play a dominant role in producing quality products. The quality of finished goods is directly related to the cutting tool condition. Several types of research have been carried out in cutting tool condition monitoring. On the other hand, the manufacturing industries should be aware of the cutting tool selection, operating conditions, and performance of cutting tools. This article emphasizes the performance of coated cutting tools and tool materials for various machining operations. Nowadays, the nanocoating of CNC tool inserts increases the wear resistance, vibration emissions, metal removal rate, etc. These coating techniques influence the manufacturing industry to increase the productivity and quality of the finished goods and reduce the machining cost. The performance of thin film multilayered coatings such as TiN, TiAlN, AlTiN, Ti, and TiCN on plain silicon carbide tool inserts is revealed by the researchers to guide the manufacturing industry for proper tool selection and standard machining inputs for metal removal operation. The influence of coating material such as TiBN, TiN, TiAlN, and CrAlSiN in cutting tools leads to increase the life time of the cutting tools, which decreases the material sticking and cutting forces. Titanium carbo nitride is wear-resistant and corrosion-resistant. Compared to TiCN, TiAlN is harder due to the higher hardness of 32 GPa. This article concludes the material selection based on the work piece material which yields good metal removal with less cutting forces. The article concludes the cutting material selection based on the work piece for machining operations.

Abstract Complex health problems require multi-strategy, multi-target interventions. We present a method that uses machine learning techniques to choose optimal interventions from a set of possible interventions within a case study aiming to increase General Practitioner (GP) discussions of physical activity (PA) with their patients. Interventions were developed based on a causal loop diagram with 26 GPs across 13 clinics in Geelong, Australia. GPs prioritised eight from more than 80 potential interventions to increase GP discussion of PA with patients. Following a 2-week baseline, a multi-arm bandit algorithm was used to assign optimal strategies to GP clinics with the target outcome being GP PA discussion rates. The algorithm was updated weekly and the process iterated until the more promising strategies emerged (a duration of seven weeks). The top three performing strategies were continued for 3 weeks to improve the power of the hypothesis test of effectiveness for each strategy compared to baseline. GPs recorded a total of 11,176 conversations about PA. GPs identified 15 factors affecting GP PA discussion rates with patients including GP skills and awareness, fragmentation of care and fear of adverse outcomes. The two most effective strategies were correctly identified within seven weeks of the algorithm-based assignment of strategies. These were clinic reception staff providing PA information to patients at check in and PA screening questionnaires completed in the waiting room. This study demonstrates an efficient way to test and identify optimal strategies from multiple possible solutions.

Most microorganisms are used as a foundation of bioplastic production and also used for the decomposition of plastics. Although bioplastics production is considered expensive than artificial plastic, it has many advantages over them. Some bio-polymers have also gained public acceptance and are now being produced. The useful breakdown of plastic bags takes more than a thousand years. For the decomposition of plastics, microorganisms should be calculated extensively so that solid wastes can be decomposed. Thus, microbes have been played an important role in decompose as well as the production of plastics.

The melt-quenching technique was used to produce 39CdO–10Al2O3-(51-x) P2O5: xMnO glasses (x = 0, 0.1, 0.2, 0.3, and 0.4 wt.%). Various stability factors were calculated and presented from DTA analysis. The stability of the glass network appears to increase with the increase of MnO concentration, according to the findings. IR spectral analysis of these glasses exhibited several symmetrical and asymmetrical bands due to phosphate groups. The observed change in these band intensities with the rise in MnO concentrations, ranging from 0.1 wt.% to 0.4 wt.%, shows an increase in the stability of the glass network. Optical absorption analyses of these glasses revealed an absorption band that shifted from 500 to 488 nm as the concentration of manganese oxide (MnO) increased from 0.1 wt.% to 0.4 wt.%, indicating that Mn2+ ions were gradually converted into Mn3+ ions. EPR spectra of these glasses were characterized by two signals due to Mn2+ and Mn3+ ions. Observations on these signal intensity variations revealed an increase in stability of the glass network with the increase of MnO concentration from 0.1 wt.% to 0.4 wt.%. Parameters, which describe the insulating characteristics, for example, dielectric constant, ε, dielectric loss, tan δ, and AC conductivity σac, were determined in relation to frequency (103 Hz to 105 Hz) and temperature (20°C to 400°C) and presented in the dielectric analysis of these glasses.

Thin films of zinc sulfide (ZnS) with different concentrations of zinc acetate have been made by chemical bath deposition technique in acidic medium (pH = 5) on glass substrate using zinc acetate and sodium sulfide as sources of Zn+2 ion and S−2 ion, respectively, and ethylenediaminetetraacetate as complexing agents and sulfuric acid to adjust pH value at a constant deposition temperature of 85°C, and the deposition time of 90 minutes was used. The effect of the concentration of metallic precursor on the structural, morphological, and optical properties of chemical bath deposited zinc sulfide thin films was investigated in this study. The XRD result confirmed mixed phases of crystalline and amorphous structure dominating other phases, which is witnessed by larger crystallite size than other phases. It reveals that the thin films had hexagonal structure at the medium concentration with preferred orientation along (111) plane, and at lower and higher concentration, it showed that film has an amorphous structure in nature. The crystallinity of all the phases significantly enlarged with increasing the zinc precursor concentration. The SEM micrographs showed high-pitched edged irregular-shaped grains covering the substrate with pinholes and bangs. The optical properties investigated by the UV-VIS spectrometer specified a decrease in the optical bandgap of the films between 3.5 eV and 2.6 eV as the zinc acetate concentration in the solution increased from 0.1 to 0.2 M. It showed that the zinc sulfide had high absorption in the UV radiation. The main finding of this paper is that metallic precursor concentration has a significant role in the optical, morphological, and microstructural properties of the cobalt sulfide thin films, which are most suitable for photovoltaic applications.

Introduction: Tuberculosis (TB) is a highly infectious disease which continues to be an important public health problem worldwide. Aim: This study puts an effort to determine patient and health system delay in diagnosis and treatment and association to specific types of delay among tribals in Mayurbhanj district, Odisha. Materials and Methods: A total of 261 TB patients reporting to 4 TB Units of Mayurbhanj were interviewed using pretested structured questionnaire. Extra-pulmonary TB patients and death cases were excluded. Data entry and analysis was carried out in Epi-info 3.32 version. Chi-square test was used to test the association between dependant variable (patient and health system delays) with different independent variables (age, sex, reasons for delay etc.). Results: Median patient, health system and total delay were 24, 3 and 24 days respectively. Risk factors that were significantly associated with patient delay were education (95% CI= 1.01- 1.11, p=0.015), cost of treatment/transport (95% CI=0.87-1.01, p=0.020), distance (95% CI=1.00-1.29, p=0.002) and lack of awareness about TB (95% CI=1.01-1.34, p=0.001). Health system delay risk factors were distance (95% CI=0.32-0.96, p=0.043), delay due to administrative verification (95% CI=1.18- 57.97, p= 0.005) and delay due to traditional healers/ private practitioners (95% CI=1.61-15.45, p=0.0008). Conclusion: This study revealed longer patient delay compared to health system delay. Therefore, public awareness in tribal dialect about chest symptoms and availability of free diagnostics services should be increased along with involvement of traditional healers.

We studied the nature of magnetic ordering in Mn-doped ZnO thin films that exhibited ferromagnetism at 300 K and superparamagnetism at 5 K. We directly inter-related the magnetisation and magnetoresistance by invoking the polaron percolation theory and variable range of hopping conduction below the metal-to-insulator transition. By obtaining a qualitative agreement between these two models, we attribute the ferromagnetism to the s-d exchange-induced spin splitting that was indicated by large positive magnetoresistance (∼40 %). Low temperature superparamagnetism was attributed to the localization of carriers and non-interacting polaron clusters. This analysis can assist in understanding the presence or absence of ferromagnetism in doped/un-doped ZnO.

Partial discharge (PD) is a major cause of failure of power apparatus and hence its measurement and analysis have emerged as a vital field in assessing the condition of the insulation system. Several efforts have been undertaken by researchers to classify PD pulses utilizing artificial intelligence techniques. Recently, the focus has shifted to the identification of multiple sources of PD since it is often encountered in real-time measurements. Studies have indicated that classification of multi-source PD becomes difficult with the degree of overlap and that several techniques such as mixed Weibull functions, neural networks, and wavelet transformation have been attempted with limited success. Since digital PD acquisition systems record data for a substantial period, the database becomes large, posing considerable difficulties during classification. This research work aims firstly at analyzing aspects concerning classification capability during the discrimination of multisource PD patterns. Secondly, it attempts at extending the previous work of the authors in utilizing the novel approach of probabilistic neural network versions for classifying moderate sets of PD sources to that of large sets. The third focus is on comparing the ability of partition-based algorithms, namely, the labelled (learning vector quantization) and unlabelled (K-means) versions, with that of a novel hypergraph-based clustering method in providing parsimonious sets of centers during classification.