Novel Privacy Preserving Non-Invasive Sensing-Based Diagnoses of Pneumonia Disease Leveraging Deep Network Model.

This article presents non-invasive sensing-based diagnoses of pneumonia disease, exploiting a deep learning model to make the technique non-invasive coupled with security preservation. Sensing and securing healthcare and medical images such as X-rays that can be used to diagnose viral diseases such as pneumonia is a challenging task for researchers. In the past few years, patients' medical records have been shared using various wireless technologies. The wireless transmitted data are prone to attacks, resulting in the misuse of patients' medical records. Therefore, it is important to secure medical data, which are in the form of images. The proposed work is divided into two sections: in the first section, primary data in the form of images are encrypted using the proposed technique based on chaos and convolution neural network. Furthermore, multiple chaotic maps are incorporated to create a random number generator, and the generated random sequence is used for pixel permutation and substitution. In the second part of the proposed work, a new technique for pneumonia diagnosis using deep learning, in which X-ray images are used as a dataset, is proposed. Several physiological features such as cough, fever, chest pain, flu, low energy, sweating, shaking, chills, shortness of breath, fatigue, loss of appetite, and headache and statistical features such as entropy, correlation, contrast dissimilarity, etc., are extracted from the X-ray images for the pneumonia diagnosis. Moreover, machine learning algorithms such as support vector machines, decision trees, random forests, and naive Bayes are also implemented for the proposed model and compared with the proposed CNN-based model. Furthermore, to improve the CNN-based proposed model, transfer learning and fine tuning are also incorporated. It is found that CNN performs better than other machine learning algorithms as the accuracy of the proposed work when using naive Bayes and CNN is 89% and 97%, respectively, which is also greater than the average accuracy of the existing schemes, which is 90%. Further, K-fold analysis and voting techniques are also incorporated to improve the accuracy of the proposed model. Different metrics such as entropy, correlation, contrast, and energy are used to gauge the performance of the proposed encryption technology, while precision, recall, F1 score, and support are used to evaluate the effectiveness of the proposed machine learning-based model for pneumonia diagnosis. The entropy and correlation of the proposed work are 7.999 and 0.0001, respectively, which reflects that the proposed encryption algorithm offers a higher security of the digital data. Moreover, a detailed comparison with the existing work is also made and reveals that both the proposed models work better than the existing work.

Future Forecasting of COVID-19: A Supervised Learning Approach.

A little over a year after the official announcement from the WHO, the COVID-19 pandemic has led to dramatic consequences globally. Today, millions of doses of vaccines have already been administered in several countries. However, the positive effect of these vaccines will probably be seen later than expected. In these circumstances, the rapid diagnosis of COVID-19 still remains the only way to slow the spread of this virus. However, it is difficult to predict whether a person is infected or not by COVID-19 while relying only on apparent symptoms. In this context, we propose to use machine learning (ML) algorithms in order to diagnose COVID-19 infected patients more effectively. The proposed diagnosis method takes into consideration several symptoms, such as flu symptoms, throat pain, immunity status, diarrhea, voice type, body temperature, joint pain, dry cough, vomiting, breathing problems, headache, and chest pain. Based on these symptoms that are modelled as ML features, our proposed method is able to predict the probability of contamination with the COVID-19 virus. This method is evaluated using different experimental analysis metrics such as accuracy, precision, recall, and F1-score. The obtained experimental results have shown that the proposed method can predict the presence of COVID-19 with over 97% accuracy.

Spectrum of pathologies in cases of intestinal obstruction & perforation based on histopathological examination of resected intestine - Report from a third world country.

BACKGROUND AND OBJECTIVE: Cases presenting with intestinal perforation and obstruction constitute a substantial work load on our surgical service. Etiologies vary in underdeveloped and developed countries. Histopathological examination of resected intestine is expected to provide the definite evidence of the underlying etiology- guiding a better health care planning for preventive measures. Our objective was to study the spectrum of histopathological findings in resected intestines from cases of intestinal obstruction and perforation in our local population to document the underlying etiology. METHODS: A total of 120 cases of intestinal resection were included. Detailed gross and microscopic examination with routine stains was performed. Definite evidence of any specific etiology on the basis of morphology was documented. RESULTS: A total of 95 cases with clinical/radiological diagnosis of obstruction (79.2%) and 25 of intestinal, perforation (20.8%) were included. Tuberculous enteritis was the commonest etiology (n=41; 43.1%) in cases of intestinal obstruction followed by malignant tumours (n=30; 31.5%). ischemic infarct/gangrene, post op illeal adhesions, polyps and ulcerative colitis followed. In cases of perforation, Typhoid enteritis (n=15; 60%), was the commonest pathology followed by idiopathic perforation (n=5; 20%), tuberculous enteritis (n=3;12%), carcinoma (4%) and ulcerative coliti (4%). Conclusion : In developing countries infective etiology remains a dominant cause of intestinal obstruction and perforation. Its presentation in younger age leading to intestinal resection demands effective preventive measures in this part of the world to prevent morbidity and mortality.

Design of Multiplexers for IoT-Based Applications Using Stub-Loaded Coupled-Line Resonators.

This paper presents the design of microstrip-based multiplexers using stub-loaded coupled-line resonators. The proposed multiplexers consist of a diplexer and a triplexer, meticulously engineered to operate at specific frequency bands relevant to IoT systems: 2.55 GHz, 3.94 GHz, and 5.75 GHz. To enhance isolation and selectivity between the two passband regions, the diplexer incorporates five transmission poles (TPs) within its design. Similarly, the triplexer filter employs seven transmission poles to attain the desired performance across all three passbands. A comprehensive comparison was conducted against previously reported designs, considering crucial parameters such as size, insertion loss, return loss, and isolation between the two frequency bands. The fabrication of the diplexer and triplexer was carried out on a compact Rogers Duroid 5880 substrate. The experimental results demonstrate an exceptional performance, with the diplexer exhibiting a low insertion loss of 0.3 dB at 2.55 GHz and 0.4 dB at 3.94 GHz. The triplexer exhibits an insertion loss of 0.3 dB at 2.55 GHz, 0.37 dB at 3.94 GHz, and 0.2 dB at 5.75 GHz. The measured performance of the fabricated diplexer and triplexer aligns well with the simulated results, validating their effectiveness in meeting the desired specifications.

A Novel Synthesis of Quasi-Chebyshev Ultra-Wideband Bandpass Filter Using Nth Order Stub Loaded Coupled-Line Resonator.

This paper presents a novel synthesis of a quasi-Chebyshev Nth order stub-loaded coupled-line ultra-wideband bandpass filter. A unit element of a proposed filter topology consists of two short-circuited stubs loaded at the edges of coupled lines. A distributed equivalent circuit model of a proposed topology is extracted and used to acquire a generalized filtering function. The extracted filtering function is of rational form. The denominator of the filtering function causes a mismatch with Chebyshev type-I polynomials. For conventional narrowband filters, the denominator term can be neglected because of the close vicinity of band-edge frequencies; however, for the ultra-wideband filter response, the factor in the denominator cannot be neglected and hence requires a new mathematical procedure to compensate for the effect of the frequency-dependent term in the denominator. The electrical parameters are calculated using the proposed synthesis and used to design an ideal filter topology on ADS. To validate the proposed design procedure, fabrication is performed on a high-frequency substrate. The proposed filter is miniaturized in size and has good out-of-band performance. The simulated and measured results provide good agreement.

Design of a novel compact highly selective wideband bandstop RF filter using dual path lossy resonator for next generation applications.

This article presents the design of a wideband bandstop RF filter intending to improve selectivity and compactness. Conventional bandstop filter topology with finite unloaded quality factor produces degraded bandstop filter performance due to dissipation loss. In the proposed filter design, a novel dual path Capacitive Coupled Step Impedance Resonator (CCSIR) structure is used to obtain an infinite stopband attenuation. A uniform impedance resonator is used in Path 1, whereas Path 2 contains a resonator that is twice coupled to the transmission lines. The electrical length of both paths is chosen to be out of phase, resulting in a high rejection level at higher frequencies. It has been analyzed that the selectivity can be improved by increasing the order of the dual coupled step impedance resonator. The proposed design produces a wideband BSF centered at 5.25 GHz with a high rejection level of 104.3 dB and fractional bandwidth of 58.5%. The results have demonstrated that the resonant frequencies are regulated by varying the electrical length of CCSIR. Moreover, it has been realized that out of phase signal cancellation due to the dual path is involved in producing the finite frequency transmission poles, which further enhances the filter selectivity. However, the same electrical performance can only be achieved from coaxial cavities and waveguides due to the high-quality factor. The proposed topology is fabricated and measured on a high-frequency microstrip substrate having a low-quality factor with a compact output and better electrical performance compared to coaxial cavities or waveguides. Due to its high electrical performance and small size, the proposed BSF is appropriate for 4G and 5G (FR1) applications. The measurement shows good concurrence with the full-wave EM simulated results. The fabricated prototype of third order BSF has a compact size of (0.7 × 0.77)λg at 5.25 GHz.