R-CNN and YOLOV4 based Deep Learning Model for intelligent detection of weaponries in real time video.

The security of civilians and high-profile officials is of the utmost importance and is often challenging during continuous surveillance carried out by security professionals. Humans have limitations like attention span, distraction, and memory of events which are vulnerabilities of any security system. An automated model that can perform intelligent real-time weapon detection is essential to ensure that such vulnerabilities are prevented from creeping into the system. This will continuously monitor the specified area and alert the security personnel in case of security breaches like the presence of unauthorized armed people. The objective of the proposed system is to detect the presence of a weapon, identify the type of weapon, and capture the image of the attackers which will be useful for further investigation. A custom weapons dataset has been constructed, consisting of five different weapons, such as an axe, knife, pistol, rifle, and sword. Using this dataset, the proposed system is employed and compared with the faster Region Based Convolution Neural Network (R-CNN) and YOLOv4. The YOLOv4 model provided a 96.04% mAP score and frames per second (FPS) of 19 on GPU (GEFORCE MX250) with an average accuracy of 73%. The R-CNN model provided an average accuracy of 71%. The result of the proposed system shows that the YOLOv4 model achieves a higher mAP score on GPU (GEFORCE MX250) for weapon detection in surveillance video cameras.

Hippocampus Segmentation-Based Alzheimer's Disease Diagnosis and Classification of MRI Images.

Alzheimer's disease represents a neurological condition characterized by steady cognitive decline and eventual memory loss due to the death of brain cells. It is one of the most prominent dementia types observed in patients and which hence underlines the imminent need for potential methods to diagnose the disease early on. This work considers a novel approach by utilizing a reduced version of one of the datasets used in this work to achieve a considerably accurate prediction while also enabling quicker training. It leverages image segmentation to isolate the hippocampus region from brain MRI images and then strikes a comparison between models trained on the segmented portions and models trained on complete images. This research uses two datasets-4 classes of images from Kaggle and a popular OASIS 2 MRI and demographic dataset. A deep learning-based approach was adopted to train the Kaggle dataset to perform severity classification, and the hippocampus region segmented from a reduced version of the OASIS dataset was trained on supervised and ensemble learning algorithms to detect Alzheimer's disease. The metric used for the assessment of model performance is classification accuracy. A comparative analysis between the proposed approach and existing work was also performed, and it was observed that the proposed approach is effective in the early diagnosis of Alzheimer's disease.

Do post-concussion-like symptom responses change following exercise or sports participation in a non-concussed cohort?

The purposes of this study were (a) to determine the reliable change in post-concussion-like symptoms reported following self-selected exercise or sports activities and (b) to explore the potential influence of gender and exercise parameters on post-concussion-like symptoms reported by a non-concussed cohort following exercise/training. A pre-to-post observational design was used. A convenience sample of students aged 18-30 years who visited a university recreation center to engage in their chosen exercise activity and a purposeful sample of men's and women's rugby union players engaged in their regular training sessions were included in the study. All participants reported their symptoms using the symptom scale of the Sport Concussion Assessment Tool 2. The reliable change index was used to determine the change in symptom scores reported from pre-to post-exercise/training. Multiple linear regression analysis was used to model the exercise variables to explain the impact on the reporting of symptoms. A total of 260 participants (146 males and 114 females) completed their self-selected exercise activity or rugby union training. Approximately two-thirds of all participants did not demonstrate a change (increase or decrease) in total symptom score (201/260, 77.9%) and/or symptom severity score (212/260, 81.9%) from pre-to post-exercise/training. The symptom response following exercise or sports training did not change in the majority of participants. Clinicians need to be aware of these findings to make informed decisions on return-to-play following a concussive brain injury.

Linguistic Adaptation and Psychometric Properties of Tamil Version of General Oral Health Assessment Index-Tml.

BACKGROUND: Oral health has an impact on quality of life hence for research purpose validation of a Tamil version of General Oral Health Assessment Index would enable it to be used as a valuable tool among Tamil speaking population. AIM: In this study, we aimed to assess the psychometric properties of translated Tamil version of General Oral Health Assessment Index (GOHAI-Tml). SUBJECTS AND METHODS: Linguistic adaptation involved forward and backward blind translation process. Reliability was analyzed using test-retest, Cronbach alpha, and split half reliability. Inter-item and item-total correlation were evaluated using Spearman rank correlation. Convenience sampling was done, and 265 consecutive patients aged 20-70 years attending the outpatient department were recruited. Subjects were requested to fill a self-reporting questionnaire along with Tamil GOHAI version. Clinical examination was done on the same visit. Concurrent validity was measured by assessing the relationship between GOHAI scores and self-perceived oral health and general health status, satisfaction with oral health, need for dental treatment and esthetic satisfaction. Discriminant validity was evaluated by comparing the GOHAI scores with the objectively assessed clinical parameters. Exploratory factor analysis was done to examine the factor structure. RESULTS: Mean GOHAI-Tml was 52.7 (6.8, range 22-60, median 54). The mean number of negative impacts was 2 (2.4, range 0-11, median 1). The Spearman rank correlation for test-retest ranged from 0.8 to 0.9 (P < 0.001) for all the 12 items between visits. The Cronbach alpha for 265 samples was 0.8 suggesting good internal consistency and homogeneity between items. Item scale correlation ranged from 0.4 to 0.8 (P < 0.001). Concurrent and discriminant validity was established. Principal component analysis resulted in extraction of four factors which together accounted for 66.4% (7.9/12) variance. CONCLUSION: GOHAI-Tml has shown acceptable psychometric properties, so that it can be used as an efficient tool in identifying the impact of oral health on quality of life among the Tamil speaking population.

A study on genetic variability of pathogenic Aeromonas hydrophila strains and the varied responses of the strains towards phyto-extracts.

The present study evaluated genetic variation in Aeromonas hydrophila strains using PCR-RAPD and their varied susceptibility to phyto-extract. Four strains of Aeromonas hydrophila isolated from skin infections of common freshwater fish, Cyprinus carpio were characterized by various biochemical methods, physiological tests and PCR- RAPD. Antimicrobial activity of the leaf extracts of three medicinal plants, Ocimum sanctum, Adathoda vasica and Calendula officinalis were tested against the four strains of A. hydrophila by disc diffusion (Kirby-Bauer) method. Antagonistic effects of leaf extracts against A. hydrophila strains were assessed by co-culture method. RAPD analysis showed that all the microbes isolated from skin infection belong to the same species but there was no 100% genetic similarity among them Dendrogram constructed by UPGMA clearly supported the PCR pattern of genetic variability among the strains. This study revealed that Aeromonas hydophila exhibits genetic variability and varied susceptibility towards phyto-extracts. Results indicated that phyto-extracts offers a promising alternative to the use of antibiotics in controlling Aeromonas hydrophila.

In vitro cone beam computed tomography imaging of periodontal bone.

OBJECTIVES: To assess the accuracy of NewTom 9000 cone beam CT (CBCT) images for the detection and quantification of periodontal bone defects in three dimensions. METHODS: A sample of 146 sites in 5 dry skulls provided the ground truth (GT). Half of the sample had bone loss of at least 3 mm. Two metal spheres at each site ensured correspondence between GT and CBCT measurements. Skulls were submerged in water and scanned with the NewTom QR-DVT-9000. A full mouth series (FMX) was obtained of each skull using photostimulable phosphor plates. Six observers measured the bone height of each site and rated the presence or absence of bone loss. Measurements were compared to GT and A(z)-values were calculated from receiver operating characteristic curves. RESULTS: The A(z)-value for CBCT was 0.74 (standard deviation (SD) = 0.14) and for FMX 0.48 (SD = 0.09). The difference was significant (ANOVA: P < 0.01). The diagnostic accuracy of CBCT was lower for anterior teeth (A(z) = 0.59) than for molars (A(z) = 0.82) and premolars (A(z) = 0.79) (Tukey's HSD (honestly significant difference): P < 0.01). The mean absolute difference between CBCT and GT was 1.27 mm (SD = 1.43) and between FMX and GT 1.49 mm (SE = 1.24) (ANOVA: P < 0.01). Measurements in the anterior mandible were less accurate than in other areas (Tukey's HSD: P < 0.01). CONCLUSION: The NewTom 9000 cone beam CT scanner provides better diagnostic and quantitative information on periodontal bone levels in three dimensions than conventional radiography. The accuracy in the anterior aspect of the jaws is limited.

Cytogenetic studies on spray painters in south India.

Studies on the frequencies of chromosomal aberrations were carried out on 104 spray painters working in automobile body reconditioning, steel furniture making and refrigerator repainting workshops in the metro city, Chennai, of south India. Randomly selected 50 male subjects not connected with this occupation were included as controls in the study. Chromosomal analysis was carried out in 48h lymphocyte (short duration) cultures representing the first mitotic division, on a subset of samples consisting of 50 spray painters, 20 controls and 72h (longer duration) cultures representing the second cell division, on all subjects. Baseline frequency of chromosomal aberrations was significantly higher among painters as compared to matched controls. Smoking and alcoholism as modulating factors had no added effect on the frequency of aberrant metaphases. Stepwise multiple linear regression analysis indicated that duration of service and age were significant factors that influence the frequency of chromosomal aberrations observed.