14 research outputs found
Network load prediction and anomaly detection using ensemble learning in 5G cellular networks
No full textNetwork data analytics significantly improved the 5G cellular networks. Data analytics allows network administrators and operators to use the machine and deep learning to analyse the network data efficiently. The standard protocols defined by the 3rd Generation Partnership Project (3GPP) for the network data analytics function are discussed to incorporate into the dataset. The dataset is based on cells in the network considering anomalies and fields of 3GPP, i.e., data rates and information related to the network area. Moreover, machine and deep learning techniques can be used to classify the anomalies. In this regard, we employed Decision trees (DT), Random Forest (RF), Support Vector Machines (SVM) and ensemble learning (EL) to enhance the network prediction performance. For this purpose, we used machine and deep learning techniques, i.e., one-dimensional Convolutional Neural Networks (1D CNN), Multi-Layer Perceptron (MLP), and k-Nearest Neighbours (kNN), respectively. We also used bagging-based three regressors, i.e., 1D CNN, MLP, and kNN, to predict the network load. In addition, we addressed both anomaly detection and load prediction because the presence of anomalies results in high load. The accurate detection of anomalies will result in less network load. Thus, anomalies like a sudden increase in network traffic from a certain cell are also added based on the network traffic pattern to make the dataset more realistic. The simulation results showed that the bagging-based EL outperformed the existing techniques in predicting network load. Moreover, the voting technique outperforms in the case of anomaly detection
Complexes of 2-Amino-3-methylpyridine and 2-Amino-4-methylbenzothiazole with Ag(I) and Cu(II): Structure and Biological Applications
No full textCoordination complexes (1–4) of 2-amino-4-methylbenzothiazole and 2-amino-3-methylpyridine with Cu(CH3COO)2 and AgNO3 were prepared and characterized by UV/Vis and FT-IR spectroscopy. The molecular structure for single crystals of silver complexes (2 and 4) were determined by X-ray diffraction. The coordination complex (2) is monoclinic with space group P21/c, wherein two ligands are coordinated to a metal ion, affording distorted trigonal geometry around the central Ag metal ion. The efficient nucleophilic center, i.e., the endocyclic nitrogen of the organic ligand, binds to the silver metal. Ligands are coordinated to adopt cis arrangement, predominantly due to steric reasons. The O(2) and O(3) atoms of the NO3− group further play an important role in such type of ligand arrangement by hydrogen bonding with the NH2 group of ligands. Complex (4) is orthorhombic, P212121, comprising two molecules of 2-amino-3-methylpyridine as ligand coordinated with the metal ion, affording a polymeric structure. The coordination behavior of the ligand is identical to that in complex 2, wherein ring nitrogen is coordinated to the metal center and bridged to another metal ion through an NH2 group. The resulting product is polymeric in nature with the Ag metal in the backbone and ligand as the bridge. Compounds (2–4) were found to be luminescent, while 1 did not show such activity. All compounds were screened for their preliminary biological activities such as antibacterial, antioxidant and enzyme inhibition. Compounds exhibited moderate activity in these tests
Effect of slope position on physico-chemical properties of eroded soil
No full textThe research work was conducted on eroded soil (Missa Series) in Samarbagh, District Lower Dir to determine the effect of slope position on soil physico-chemical properties. Soil samples were collected from top-slope, mid-slope and bottom slope positions at horizon-A, B and C. Results showed a significant difference among the physico-chemical properties of top, mid and bottom slope soils. Bulk density of the top-slope (1.51 g cm-3) was the highest followed by mid (1.39 g cm-3) and bottom slopes (1.32 g cm-3). Conversely, electrical conductivity EC-2.47 dS m-1), phosphorus (3.40 mg kg-1), Potassium (118.8 mg kg-1), Organic matter content (1.52 %), clay content (20.39 %) and silt content (49.17%) were the highest at bottom slope followed by mid and top-slopes, respectively. Soil A, B and C horizons were also significantly (p<0.05) different in their physico-chemical properties. Mean values showed that horizon Ap had the highest bulk density (1.43 g cm-3) and lower electrical conductivity (1.74 dS m-1), phosphorus (2.29 mg kg-1), potassium (84.86 mg kg-1), organic matter (1.08%), clay (12.83%) and silt content (40.49%) than both the B and C horizons. The deterioration in physico-chemical properties of top slope as compared to mid and bottom slopes and that of Ap horizon as compared to B and C horizons were presumed to be due to past soil erosion effect that removed the finer soil particles including soil organic matter and other plant nutrients. This study concluded that increasing extent of erosion due to slope effect can further deteriorate soil properties. The control of such damaging effects would require soil conservation strategies such as proper land levelling, afforestation, terracing and inclusion of restorative crops in cropping systems on these lands
Economic Reliability Acceptance Sampling Plans from Truncated Life Tests based on the Burr Type XII Percentiles
No full textIn this article, economic reliability acceptance sampling plan (ERASP) is developed for the Burr type XII distribution when the life test is truncated at pre-specified designed parameters. The minimum termination time is necessary to ensure that the specified life percentile is found under a given producer’s risk. The operating characteristic values of the proposed plan are presented for various parameters. A comparative study of proposedplan and existing plan developed by Lio et al. (2010) is also discussed. The result is illustrated by a real dataset example
Dichromacy: Color Vision Impairment and Consanguinity in Heterogenous Population of Pakistan
No full textAbstract:
Background and Objectives: Dichromacy, an X-linked recessive disorder is identified worldwide, more in males than females. In European Caucasians, its incidence is 8% in males and 0.5% in females. In India, it is 8.73% in males and 1.69% in females, and in Iran, it is 8.18% in males and 0.43% in females. Population based epidemiological data about dichromacy in different ethnic groups in Pakistan is not available. The aim of this study was to find out the population prevalence of inherited red-green dichromacy in a heterogenous population of the district of Chiniot, Punjab, Pakistan, and to determine the impact of consanguinity and ethnicity.
Methods: In this cross-sectional study, boys and girls of the higher secondary schools were examined in the three tehsils of district Chiniot. Pseudoisochromatic Ishihara Test has been employed for detection of dichromacy in the study population. The sample size was calculated statistically as 260, which was expanded to 705 and divided by population density of the three tehsils.
Results: Screening of 359 males and 346 females revealed 19 (5.29%) dichromat males and only 2 (0.58%) females. The study population belonged to 23 castes / isonym groups. The consanguinity found in the district of Chiniot is 84.82% and in the dichromat families, it is 85.71%, of which 52.37% are first cousin.
Interpretation & Conclusion: The study has shown that the incidence of dichromacy could be reduced through genetic counselin
Stages prediction of Alzheimer’s disease with shallow 2D and 3D CNNs from intelligently selected neuroimaging data
No full textAbstract Detection of Alzheimer’s Disease (AD) is critical for successful diagnosis and treatment, involving the common practice of screening for Mild Cognitive Impairment (MCI). However, the progressive nature of AD makes it challenging to identify its causal factors. Modern diagnostic workflows for AD use cognitive tests, neurological examinations, and biomarker-based methods, e.g., cerebrospinal fluid (CSF) analysis and positron emission tomography (PET) imaging. While these methods are effective, non-invasive imaging techniques like Magnetic Resonance Imaging (MRI) are gaining importance. Deep Learning (DL) approaches for evaluating alterations in brain structure have focused on combining MRI and Convolutional Neural Networks (CNNs) within the spatial architecture of DL. This combination has garnered significant research interest due to its remarkable effectiveness in automating feature extraction across various multilayer perceptron models. Despite this, MRI’s noisy and multidimensional nature requires an intelligent preprocessing pipeline for effective disease prediction. Our study aims to detect different stages of AD from the multidimensional neuroimaging data obtained through MRI scans using 2D and 3D CNN architectures. The proposed preprocessing pipeline comprises skull stripping, spatial normalization, and smoothing. It is followed by a novel and efficient pixel count-based frame selection and cropping approach, which renders a notable dimension reduction. Furthermore, the learnable resizer method is applied to enhance the image quality while resizing the data. Finally, the proposed shallow 2D and 3D CNN architectures extract spatio-temporal attributes from the segmented MRI data. Furthermore, we merged both the CNNs for further comparative analysis. Notably, 2D CNN achieved a maximum accuracy of 93%, while 3D CNN reported the highest accuracy of 96.5%
Stages prediction of Alzheimer’s disease with shallow 2D and 3D CNNs from intelligently selected neuroimaging data
No full textDetection of Alzheimer’s Disease (AD) is critical for successful diagnosis and treatment, involving the common practice of screening for Mild Cognitive Impairment (MCI). However, the progressive nature of AD makes it challenging to identify its causal factors. Modern diagnostic workflows for AD use cognitive tests, neurological examinations, and biomarker-based methods, e.g., cerebrospinal fluid (CSF) analysis and positron emission tomography (PET) imaging. While these methods are effective, non-invasive imaging techniques like Magnetic Resonance Imaging (MRI) are gaining importance. Deep Learning (DL) approaches for evaluating alterations in brain structure have focused on combining MRI and Convolutional Neural Networks (CNNs) within the spatial architecture of DL. This combination has garnered significant research interest due to its remarkable effectiveness in automating feature extraction across various multilayer perceptron models. Despite this, MRI’s noisy and multidimensional nature requires an intelligent preprocessing pipeline for effective disease prediction. Our study aims to detect different stages of AD from the multidimensional neuroimaging data obtained through MRI scans using 2D and 3D CNN architectures. The proposed preprocessing pipeline comprises skull stripping, spatial normalization, and smoothing. It is followed by a novel and efficient pixel count-based frame selection and cropping approach, which renders a notable dimension reduction. Furthermore, the learnable resizer method is applied to enhance the image quality while resizing the data. Finally, the proposed shallow 2D and 3D CNN architectures extract spatio-temporal attributes from the segmented MRI data. Furthermore, we merged both the CNNs for further comparative analysis. Notably, 2D CNN achieved a maximum accuracy of 93%, while 3D CNN reported the highest accuracy of 96.5%
Secure and Smart Supply Chains: Design, Traceability, and Transparency
No full textThanks to the Effat University for supporting this work under the grant number UC#9/12June2023/7.1-21(4)13.Mobile healthcare is an appealing approach based on the Internet of Medical Things (IoMT) and cloud computing. It can lead to unobstructed, economical, and patient-centric healthcare solutions. The key performance indicators of such systems are dimensionality reduction, computational effectiveness, low latency, and accuracy. In this context, a novel approach is devised for EEG-based schizophrenia, a severe mental disorder that adversely affects a person’s behavior and classification. A multichannel EEG recording with suitable granularity is required for precise analysis. It can increase exponentially the data dimensionality plus complexity and computational load. The proposed solution attains an interesting trade-off between dimensionality reduction plus computational effectiveness versus accuracy. It uses the penalized sequential dictionary learning (PSDL) that incorporates channel selection. First, PSDL learns a dictionary from the input data and evaluates its performance on all EEG channels. Based on this evaluation, a subset of six channels is selected for further training in the dictionary. The proposed PSDL algorithm then incorporates a penalty term that enhances the power of the learned dictionary on the selected channels. We evaluate the proposed approach on the multi-channel EEG dataset from the Institute of Psychiatry and Neurology in Warsaw, Poland. A performance comparison is also made with counterparts. The models’ performance depends on the EEG signals’ complexity. Therefore, we tried to make our models robust and straightforward, achieving appropriate performance with minimal computational cost. The proposed method reduces the dimension in two steps. First, the count of channels is reduced to 68.42%. In the second step, the kept information, 31.58% of channels, is further reduced to 83.75% using dictionary learning. The proposed framework secures a remarkable data dimension reduction and a lower computational cost and latency than the counterparts while attaining the sparse representation classification accuracy of 89.12%. These findings are promising and confirm the potential of investing in incorporating the proposed method in contemporary mobile healthcare solutions.Effat Universit
Impact of Financial Reforms on Efficiency of State-owned, Private and Foreign Banks in Pakistan
No full textThis paper uses a unique bank level data from 1991 to 2000 and evaluates how financial reforms affect banking efficiency of domestic and foreign banks in Pakistan. The results suggest that banking efficiency falls during initial reform period when banks adjust to enhanced competition, but increases in more advanced stages of reform. While in general foreign and private banks show superior efficiency and factor productivity than state-owned banks, the relative performance of foreign banks worsens after the consolidation stage of the financial reforms is over. We show the importance of link between bank size, asset quality and bank branches with efficiency indexes, and also note that every 10% increase in share of nonperforming to total loans decreases banking efficiency from 6% to 10%.Bank efficiency, Financial Reforms, frontier analysis
