Search

BACKGROUND: Identification of implant model from primary knee arthroplasty in pre-op planning of revision surgery is a challenging task with added delay. The direct impact of this inability to identify the implants in time leads to the increase in complexity in surgery. Deep learning in the medical field for diagnosis has shown promising results in getting better with every iteration. This study aims to find an optimal solution for the problem of identification of make and model of knee arthroplasty prosthesis using automated deep learning models. METHODS: Deep learning algorithms were used to classify knee arthroplasty implant models. The training, validation and test comprised of 1078 radiographs with a total of 6 knee arthroplasty implant models with anterior–posterior (AP) and lateral views. The performance of the model was calculated using accuracy, sensitivity, and area under the receiver-operating characteristic curve (AUC), which were compared against multiple models trained for comparative in-depth analysis with saliency maps for visualization. RESULTS: After training for a total of 30 epochs on all 6 models, the model performing the best obtained an accuracy of 96.38%, the sensitivity of 97.2% and AUC of 0.985 on an external testing dataset consisting of 162 radiographs. The best performing model correctly and uniquely identified the implants which could be visualized using saliency maps. CONCLUSION: Deep learning models can be used to differentiate between 6 knee arthroplasty implant models. Saliency maps give us a better understanding of which regions the model is focusing on while predicting the results.

Undesirable operation of a distant relay at the occurrence of stressed conditions is a reason for blackouts. There are a few computational intelligent methods available in the literature for avoiding relay maloperations. However, because of variations in the system parameters and expansions of the network, the performance of these techniques can be degraded. To solve this issue, data mining approaches have been introduced. The existing data mining approaches need improvement in terms of accuracy and error rate while discriminating fault and stressed conditions. In this paper, a Convolutional Neural Network (CNN) based classifier is proposed for identifying various faults and differentiating fault and power swing situations. The data are collected from the IEEE-9 bus system by Phasor Measurement Units (PMU) and the proposed CNN classifier model classifies system conditions like normal, fault, and power swing. The outcome shows that the classifier has high accuracy and low error rate compared to other classification models such as Naïve Bayes, Decision Tree, and K-Nearest Neighbor. Furthermore, the proposed CNN model is validated with the use of TensorFlow framework to demonstrate its superior performance.

Feasibly synthesized novel rhodamine based chemosensor (RS) has been described for the detection of paramagnetic and biologically important Cu2+ and Fe3+ ions. Among all the transition metal ions, this chemosensor was able to precisely spot out the Cu2+/Fe3+ ion couple by its spirolactam cleavage, consequently enhanceing their absorbances at 521 and 529 nm for Cu2+ and Fe3+ ions respectively even at low concentrations [263 pM (Cu2+) and 2 nM (Fe3+)], which is prominently lower than the WHO and the United States Environmental Protection Agency (USEPA) strategies. This metal pair (Cu2+/Fe3+) has more tendencies to cleave the lactam ring even in the presence of higher concentrations of other relevant metal ions. Such remarkable behaviour of RS has been motivated us to apply zebrafish bio-imaging and molecular logic circuits.

Distance relay is one of the most important protection element of a transmission line used in protection schemes. Relay may malfunction if it is not able to distinguish faults from system stressed conditions. This work mainly focusses on enhancing the performance of the distance relay in a secured manner based on data mining approach which uses two phases of classification. Level 1 classifier identifies the system conditions like normal, fault, and power swing and level 2 classifier gets initiated when there is a power swing and distinguishes between the persistence of power swing condition and a three-phase fault. In both the phases, the protection scheme in the respective zone where the fault occurred gets activated. The proposed methodology is tested for an IEEE 9-bus system wherein the data is collected from phasor measurement units placed in optimal locations. Optimal PMU placement is economical since it overcomes issues like cost, communication infrastructure issues, maintenance and complexity. The results proved that the proposed method is effective with good efficiency and higher accuracy with less number of PMUs.

With the rise in Virtual Reality technology now it is possible to bring the same experience of offline shopping in the online platform. Virtual Dressing using Augmented Reality is a platform where users can try clothes virtually. As users cannot physically try the dress in online mode this application will help the user to make a better judgement on how the dress will look on him. The proposed system will consist of an application where users can create their 3D model with just their pictures and can apply the garment on their model, which can be viewed in AR space to make a judgement of how the model looks on a person.

With the design of an Internet of Things IoT and telemedicine based health monitoring system The Smart Chair. Sensors and associated hardware needed to monitor the vital physiological parameters of the human body are available on the chair, thereby leading to the idea of a Smart Chair. It enables the subject to be seated in a relaxed posture during the acquisition of physiological signals from various sensors attached to his her body. The raw signals from the sensors are processed digitally by an onboard microcontroller and analyzed for any common abnormalities in the health parameters of the subject. The results are then transmitted to a personal computer. The data can be viewed at any later time by a doctor's computer that is connected to Internet. The Smart Chair also sends an SMS with all the health details to a remote doctor's phone in case of an emergency, thus facilitating telemedicine in rural areas. The key focus of the presented work is to propose the design of a chair that will be useful and easily affordable by the people of developing nations who have limited access to proper healthcare facilities. The results Presented show that the proposed system is definitely a low cost affordable solution for IoT based telemedicine system, as compared to existing systems Ms. M. Kiruthika, II ME (MPC) | Mrs. K.Abhirami M.E., (Ph.D) "Design and implementation of Smart Sensor Integrated Chair for Medical Diagnosis" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-1 , December 2018, URL: https://www.ijtsrd.com/papers/ijtsrd19182.pdf

A mononuclear copper(II) complex of 1-(1H-benzimidazol-2-yl)-N-(tetrahydrofuran-2- ylmethyl)methanamine) was synthesized and characterized by various physicochemical techniques like cyclic voltammetry and elemental analysis, ESI-MS, UV–Visible, Infra red and EPR spectroscopy. The antibacterial activities of the ligand and its complex were screened by disc diffusion method and found that the metal complexes have higher antimicrobial activity than the free ligand.

The present work focussed on the effect of UV light radiation and Direct current glow Discharge Plasma (DC) on Polyethylene Terephthalate (PET) surface for food packaging applications. The PET was treated by three different plasma such as air, argon, and oxygen with a treatment time of 5–25 min and pressure kept as 3 Pa. The PET film was exposed by UV radiation using the wavelength between 200–400 nm UV light Lamp with a treatment time of 5–25 min. And also we measured the electron temperature (Te) and electron density (Ne) of the three different plasmas by Single Langmuir probe method. The surface properties of UV light radiated and plasma treated PET films were characterized by static contact angle, x-ray diffraction, Optical analysis (UV–vis), ATR-FTIR, Structural analysis (AFM)) and the results were compared. We observed that the bulk properties of the treated materials remained unchanged. This was confirmed by x-ray diffraction results. The new polar functional groups were also detected on the treated films by FTIR spectrum analysis. The surface roughness was calculated from AFM analysis for both untreated and treated PET films. The oxygen plasma treated sample showed higher roughness, which indicated that a large amount of oxygen containing polar groups appeared on the surface of the PET film. The obtained results reveal that the plasma treated PET films were more effective than the Ultra-violet (UV) light radiated film.

This paper discusses a Domain Specific Language (DSL) that has been developed to enable implementation of concepts of discrete mathematics. A library of data types and functions provides functionality which is frequently required by users. Covering the areas of Mathematical Logic, Set Theory, Functions, Graph Theory, Number Theory, Linear Algebra and Combinatorics, the language's syntax is close to the actual notation used in the specific fields.

Aim This study was aimed to evaluate the DNA cleavage efficiency of a copper complex. Methods A new copper(II) complex of 1-(1H-benzimidazol-2-yl)-N-(tetrahydrofuran-2-ylmethyl)methanamine) was synthesized. Results The complex was characterized by various physico-chemical techniques like cyclic voltammetry and elemental analysis, ESI-MS, UV–Visible, Infra red and EPR spectroscopy. Moreover the complex successfully promoted an oxidative cleavage of plasmid DNA, producing single strand break. Conclusion In this study, it was concluded that the present complex showed a higher DNA cleavage activity due to the presence of hydroxyl radicals.

Bismaleimides containing pyrimidine and dithiane group were synthesized from the diamines APPB and APDB and maleic anhydride via bismaleiamic acid as the intermediate followed by cyclodehydration . The structure of the monomers was confirmed by FT-IR, 1H-NMR and 13C-NMR spectral techniques. Further, a series of polyaspartimides were synthesized by addition reaction of bismaleimides with the prepared diamines. The polymers were characterized by using FT-IR, 1H-NMR and 13C-NMR. All the polymers are soluble in aprotic solvents such as NMP, DMF, DMAc and DMSO. The activation energies (Ea) of the thermal curing were calculated using Ozawa and Kissinger method from DSC (Ea 103 KJ/mol and 106 KJ/mol). The Tg and T10% of the polyaspartimides are in the range of 199-280oC and 360-480oC respectively.&nbsp

Nanocrystalline ITO thin films were deposited on glass substrates by a new spray pyrolysis route, Jet nebulizer spray (JNS) pyrolysis technique, for the first time at different substrate temperatures varying from 350 to 450 °C using a precursor containing indium and tin solution with 90:10 at% concentration. The structural, optical and electrical properties have been investigated as a function of temperature. X-ray diffraction analysis showed that the deposited films were well crystallized and polycrystalline with cubic structure having (222) preferred orientation. The optical band gap values calculated from the transmittance spectra of all the ITO films showed a blue shift of the absorbance edge from 3.60 to 3.76 eV revealing the presence of nanocrystalline particles. AFM analysis showed uniform surface morphology with very low surface roughness values. XPS results showed the formation of ITO films with In3+ and Sn4+ states. TEM results showed the nanocrystalline nature with grain size about 12-15 nm and SAED pattern confirmed cubic structure of the ITO films. The electrical parameters like the resistivity, mobility and carrier concentration are found as 1.82 × 10−3 Ω cm, 8.94 cm2/Vs and 4.72 × 1020 cm−3, respectively for ITO film deposited at 400 °C. These results show that the ITO films, prepared using the new JNS pyrolysis technique, have the device quality optoelectronic properties when deposited under the proposed conditions at 400 °C.

Investigations on the effect of seed pelleting and foliar spraying on physiology and productivity in sesame were done at the Department of Crop Physiology, Tamil Nadu Agricultural University, Coimbatore, Tamil Nadu during the year 2016–17. The study was conducted to understand the physiological basis for yield improvement in sesame. Sesame seeds were pelleted using TNAU pelleting mixture. Foliar treatments included urea 1 per cent, diammonium phosphate (DAP) spray 1 per cent, NPK (19: 19: 19) 1 per cent, manganese sulphate (MnSO4) 0.5 per cent, monoammonium phosphate (MAP) 0.5 per cent, nutrient consortium 2 per cent and salicylic acid 100 ppm. Foliar sprays were given on 30 and 45 DAS. In general pelleted seeds gave better seedling characters such as germination percentage and vigour. Plants that received two sprays of nutrient consortium were taller at physiological maturity followed by foliar spray of NPK (19: 19: 19). Nutrient consortium and NPK (19: 19: 19) treatments also recorded a higher CGR and TDM content. The plants that received nutrient consortium 2 per cent on 30 and 45 DAS showed superiority in recording higher seed yield per plant followed by NPK (19: 19: 19) in both the factors (non-pelleted and pelleted seeds). Control plants recorded least seed yield compared to other treatments in both the factors.

Web usage mining is an application of data mining techniques to discover usage patterns from web data, in order to understand and better serve the needs of web based application. The aim of this paper is to discuss about a system proposed which would perform clustering of user sessions extracted from the web logs.HTML links are extracted from these web logs for each user which constitutes the dataset. Clustering is then performed on these datasets based on the key attributes to partition the users into several homogenous groups such that similar user access patterns belong to the same cluster. Implementation and the results are also discussed.

Hydrous ruthenium oxide, which exhibits both protonic and electronic conduction, is incorporated in the cathode electrocatalyst layer of the membrane electrode assembly for polymer electrolyte fuel cells (PEFCs). The supercapacitive behavior of ruthenium oxide helps realize a fuel cell–supercapacitor hybrid. Platinum (Pt) nanoparticles are deposited onto carbon-supported hydrous ruthenium oxide and the resulting electrocatalyst is subjected to both physical and electrochemical characterization. Powder X-ray diffraction and transmission electron microscopy reflect the hydrous ruthenium oxide to be amorphous and well-dispersed onto the catalyst. X-ray photoelectron spectroscopy data confirm that the oxidation state of ruthenium in Pt anchored on carbon-supported hydrous ruthenium oxide is Ru4+. Electrochemical studies, namely cyclic voltammetry, cell polarization, intrinsic proton conductivity, and impedance measurements, suggest that the proton-conducting nature of hydrous ruthenium oxide helps extend the three-phase boundary in the catalyst layer, which facilitates improvement in performance of the PEFC. The aforesaid PEFC operating with hydrogen fuel and oxygen as oxidant shows a higher power density (0.62 W/cm2 @ 0.6 V) in relation to the PEFC comprising carbon-supported Pt electrodes (0.4 W/cm2 @ 0.6 V). Potential square-wave voltammetry study corroborates that the supercapacitive behavior of hydrous ruthenium oxide helps ameliorate the pulse-power output of the fuel cell.