Search

Objective: To assess the rate of occurrence of sub-acute Stent Thrombosis (SAT) after primary PCI in the patients presented with the acute coronary syndrome. Study Design: Retrospective cross-sectional study. Place and Duration of Study: At Tertiary Cardiac Care Center of Lahore Pakistan, from Jul 2019 to Jun 2021. Methodology: The retrospective demographical and angiographic data of the admitted patients who underwent PCI for ACS,was gathered from the Hospital Registry of a tertiary cardiac care center of Lahore. The sampling technique was nonprobability consecutive sampling, and all the data was analyzed using SPSS 20.0 and continuous data was presented as Mean±SD and frequencies & percentages for categorical variables. Chi square test (CI=95%, α=5%) was used to find the association of SAT with predisposing factors. p-value < 0.05 was taken as statistically significant. Results: Out of (n=551) patient underwent PPCI, the stent thrombosis was observed to occur in 29(5.2 %), among which 4.9 % were subacute stent thrombosis. The predisposing factors of sub-acute stent thrombosis were Diabetes Mellitus, ACS, smaller vessel size, presence of bifurcation lesion, under sizing of the stent and edge dissection and were in significant association with SAT (p < 0.05). Conclusion: Our study reveals that subacute stent thrombosis is an event with a comparatively higher frequency in patients who go through primary PCI for acute coronary syndrome, demonstrating a frequency of 4.9% and a mortality rate of 74% within 30 days of the procedure.

Background: Percutaneous Coronary intervention (PCI) is a routinely performed procedure in coronary care units. The aim of our study was to investigate the frequency of major adverse cardiac events (MACEs) after percutaneous coronary angiography in acute ST-elevation myocardial infarction (STEMI) patients in our institution. The objective of the study is to determine the frequency of MACEs after Percutaneous Coronary Intervention (PCI) in patients with acute myocardial infarction.Patients & Methods: This prospective observational study was carried out at Punjab Institute of Cardiology, Lahore from May 2017 to June 2017. A total 35 patients with STEMI who underwent Primary PCI were enrolled by consecutive sampling technique. An inclusion criterion was chest pain of 30 minutes to 12 hours duration with ECG showing ≥ 0.1mm ST-elevation in at least two contiguous leads. An exclusion criterion was thrombolysis within last 24 hours, malignancy, stroke and Left Main or equivalent disease on coronary Angiogram. Patients were followed after 2 weeks till 1 month for any MACES. (Including re-admission, need for repeat revascularization, stent thrombosis, recurrent acute MI, angina, stroke, and mortality). Frequency and percentages were calculated for MACEs by using SPSS 23.0.Results: Out of 35 cases, 34 (97.1%) were male and 1 (2.9%) were female. Mean age was 47.11±10.59 years, 14 (40%) patients had hypertension, 10 (28.6%) were diabetics and 12(34.3%) were current smokers while 4 (11.4%) were ex-smokers, 10 (28.6%) had family history of CAD, and 3 (8.6%) had hyperlipidemia. Successful revascularization with TIMI-III flow was attained in 34(97.1%) cases. 33minutes was mean door to balloon time. At one month follow-up, out of 35 patients, angina was reported only in 1 (2.9%) patient. There was no readmission, repeat revascularization, stent thrombosis, myocardial infarction, stroke and death reported in study subjects.Conclusion: Successful revascularization by Primary PCI was associated with very few early MACEs. For the treatment of coronary artery disease, PCI is an effective option. It has a few early MACEs and uses less contrast and has fewer distal complications than conventional angioplasty and invasive procedures.

Background: Contrast induced nephropathy is a well-known entity but it is less known that whether cardiac disease is a risk factor for this complication. Contrast induced nephropathy (CIN) is related with increase mortality and morbidity and the chances of this complication rises in patients who have coronary artery disease (CAD). Objective: The objective of the study is to identify the frequency of contrast induced nephropathy in patients undergoing percutaneous coronary intervention who have normal baseline renal functions. Material and methods: This cross sectional study conducted at angiography department of Punjab Institute of Cardiology, Lahore over a period of 2 years from January 2015 to January 2017. Patients regardless of gender with age of 30 - 65 years, diabetic or non-diabetics were included. Patients with renal disease or serum creatinine > 2 mg/dl at presentation or any other co-morbid medical illness, LV ejection fraction 200ml, 612 (65.3%) patients. According to the age group following patients suffered from CIN: 30-40 years, 72 (8.6%) patients, 41-55 years, 288 (11.2 %) patients and 56-65 years 576 (28.5%) patients. Out of 2988 male patients, 324 (10.8 %) patients suffered from CIN (p=0.06). Similarly, out of 2412 females 612 (25.3 %) patients had CIN (p=0.05). In 936 patients suffering from CIN, 684(73.1%) patients were diabetic and 252 (26.9%) were non-diabetic. � Conclusion: There is a high frequency of contrast induced nephropathy in elderly and diabetic patients who undergo PCI even if they have normal preexisting renal functions, so this complication can be avoided by the minimum use of contrast during the procedure

Background: Pandemic caused by Corona virus infection has damaged the population throughout the universe. Cases of COVID-19 increased rapidly in whole world. COVID-19 has been associated with a number of cardiovascular co-morbidities including hypertension, ischemic heart disease, diabetes mellitus, dyslipidemia, atrial fibrillation and cardiac failure. Aims and objective: To determine the frequency of cardiovascular complications in patients with COVID-19. Material and methods: This observational cohort study was conducted in corona ward of DHQ Hospital, Gujrat from 1st January to 31st June 2021. Total 216 patients between 18-70 years of age, admitted who had COVID-19 confirmed by PCR after taking informed consent; patients already suffering from any cardiovascular, respiratory or other life threatening illness were excluded while hypertensive, diabetics and smoker were included in the study. Duration of admission was according to the severity of illness. Detailed history was taken from all patients followed by relevant examination. Investigations like ECG, echocardiographically and troponins were done to diagnose cardiovascular complications. All the patients were treated conservatively. Frequency of cardiovascular complications was noted. The patients who had clinical relief of symptoms, fever free, normal X-Ray chest and at least two consecutive negative PCR results for covid-19 were discharged. p value

Discovering structural, functional and evolutionary information in biological sequences have been considered as a core research area in Bioinformatics. Multiple Sequence Alignment (MSA) tries to align all sequences in a given query set to provide us ease in annotation of new sequences. Traditional methods to find the optimal alignment are computationally expensive in real time. This research presents an enhanced version of Bird Swarm Algorithm (BSA), based on bio inspired optimization. Enhanced Bird Swarm Align Algorithm (EBSAA) is proposed for multiple sequence alignment problem to determine the optimal alignment among different sequences. Twenty-one different datasets have been used in order to compare performance of EBSAA with Genetic Algorithm (GA) and Particle Swarm Align Algorithm (PSAA). The proposed technique results in better alignment as compared to GA and PSAA in most of the cases.

Background: Depression has a significant relationship with cardiovascular diseases. But evidence is scarce regarding its impact on adverse outcome in patients of non-obstructive coronary artery disease. Aim: To assess the association of depression with adverse outcome in patients with myocardial infarction with non-obstructive coronary arteries (MINOCA). Methods: This cohort study was conducted in the Department of Cardiology, Punjab Institute of Cardiology, Lahore for 12 months i.e. July 2017 to June 2018. 260 patients; 130 in exposed group and 130 in unexposed group fulfilling selection criteria were enrolled for the study with or without depression. Patients were then evaluated for adverse outcome. SPSS v. 25 was used to analyse the data. Results: The mean age of exposed group was 42.85±9.33 years and the mean age of unexposed group was 52.52± 8.18 years. There were 49(37.7%) males and 81(62.3%) females in exposed group with the male-to-female ratio was 1: 1.7, while in unexposed group there were 55(42.3%) males and 75(57.7%) females with the male-to-female ratio was 1: 1.4. ST-segment elevation was observed in 31(23.8%) exposed patients while in 27(20.8%) unexposed patients. In exposed group, cardiovascular events were noted in 44(33.8%) patients, while in 27(20.8%) patients in unexposed group (OR=1.362, 95% CI; 1.071, 1.731, P=0.018). In exposed group, cardiovascular related mortality were noted in 38(29.2%) patients, while in 17(13.1%) patients in unexposed group (OR=1.54, 95% CI; 1.22, 1.943, P = 0.001). In exposed group, all-cause mortality were noted in 19 (14.6%) patients, while in 9 (6.9%) patients in unexposed group (OR=1.418, 95% CI; 1.063, 1.892, p=0.045). Conclusions: Our study results showed that depression in patients having MINOCA is significantly related to adverse cardiovascular sequel and leads to more severe sequel. Keywords: Depression, adverse outcome, mortality, myocardial infarction, non-obstructive coronary arteries, MINOCA

Background: Pulmonary embolism is the lethal condition that is associated with higher rate of mortality in cardia patients. The diagnosis of the acute pulmonary embolism is frequently observed in patients presenting in emergency department or during hospitalization. Level of D-dimer may be assessed by blood test to help the physicians to diagnose the thrombosis. Literature showed variable evidence regarding predictive accuracy of D-dimer for detection of pulmonary embolism. So to get local data, we conducted this study. Aim: To determine the diagnostic accuracy of D-dimer assay for detection of pulmonary embolism in patients of acute myocardial infarction presenting in emergency department taking CTPA as gold standard Methods: Cross - sectional study conducted in Cardiology Department , Punjab Institute of Cardiology, Lahore for a period of six months from 1-9-2018 to 1-3-2019. One hundred patients, fulfilled the selection criteria were enrolled from emergency. Then blood sample was taken for evaluation of D-dimer level. Reports were checked and D-dimer level was noted. Pulmonary embolism was labeled as positive on D-dimer, if D-dimer level ≥500 and was labeled as negative if D-dimer level

Internet of things (IoT) and machine learning based systems incorporating smart wearable technology are rapidly evolving to monitor and manage healthcare and physical activities. This paper is focused on the proposition of a fog-centric wireless, real-time, smart wearable and IoT-based framework for ubiquitous health and fitness analysis in a smart gym environment. The proposed framework aims to aid in the health and fitness industry based on body vitals, body movement and health related data. The framework is expected to assist athletes, trainers and physicians with the interpretation of multiple physical signs and raise alerts in case of any health hazard. We proposed a method to collect and analyze exercise specific data which can be used to measure exercise intensity and its benefit to athlete’s health and serve as recommendation system for upcoming athletes. We determined the validity of the proposed framework by giving a six weeks workout plan with six days a week for workout activity targeting all muscles followed by one day for recovery. We recorded the electrocardiogram, heart rate, heart rate variability, breath rate, and determined athlete’s movement using a 3D-acceleration. The collected data in the research is used in two modules. A Health zone module implemented on body vitals data which categorizes athlete’s health state into various categories. Hzone module is responsible for health hazards identification and alarming. Outstandingly, the Hzone module is able to identify an athlete’s physical state with 97% accuracy. A gym activity recognition (GAR) module is implemented to recognize workout activity in real-time using body movements and body vitals data. The purpose of the GAR module is to collect and analyze exercise specific data. The GAR module achieved an accuracy of above 89% on athlete independent model based on muscle group.

Obesity is the fifth primary hazard for mortality in the world; hence different therapeutic targets are explored to overcome this problem. Endocannabinoid is identified as the emerging target for the treatment of obesity as Cannabinoid 1 (CB1) receptor over-activation resulted in abdominal obesity. Potent antagonists or inverse agonists for CB1 receptor are the new strategies to develop anti-obesity drugs. Here, ligand-based 3D-QSAR studies was performed on 100 analogues belonging to a class of 1,2,4-tirazole containing diarylpyrazolylcarboxamide as CB1 receptor antagonists. We developed three CoMFA models using different charge schemes, AM1BCC, Gasteiger-Huckle and MMFF. These models produced almost similar statistical results (q2cv = 0.725, 0.692, 0.719 and r2ncv = 0.929, 0.924, 0.928 for AM1BCC, Gasteiger-Huckle and MMFF, respectively). The said models were validated through 20 external test set compounds which resulted in significant r2pred values (r2pred = 0.747, 0.743 and 0.745 for AM1BCC, Gasteiger-Huckle and MMFF, respectively). Comparatively, AM1BCC model provided slightly better statistics among all three tested charges scheme models, hence AM1BCC model was further utilized to generate CoMSIA models considering different field combinations. The best selected CoMSIA model also produced substantial q2cv = 0.788, r2ncv = 0.916 and r2pred = 0.836 values. Furthermore, two new molecules were designed by modifying the same scaffolds on the basis contour map analysis. The activities of newly designed molecules were predicted through obtained CoMFA model ranked as better than their parent molecules. Moreover, these newly designed compounds were successfully docked on the complex crystal structure of CB1 receptor (PDB ID: 5XRA). The docked conformation of these newly designed inhibitor interacted with Ser173, His178, Lys192, Thr197 and Ser383 mainly by hydrophobic and pi-pi stacking interactions. The obtained results signify the potential of the developed model; suggesting that the models can be useful to test and design potent novel CB1 receptor antagonists or inverse agonists prior to the synthesis.

In this research we propose a framework that will strengthen the IoT devices security from dual perspectives; avoid devices to become attack target as well as a source of an attack. Unlike traditional devices, IoT devices are equipped with insufficient host-based defense system and a continuous internet connection. All time internet enabled devices with insufficient security allures the attackers to use such devices and carry out their attacks on rest of internet. When plethora of vulnerable devices become source of an attack, intensity of such attacks increases exponentially. Mirai was one of the first well-known attack that exploited large number of vulnerable IoT devices, that bring down a large part of Internet. To strengthen the IoT devices from dual security perspective, we propose a two step framework. Firstly, confine the communication boundary of IoT devices; IoT-Sphere. A sphere of IPs that are allowed to communicate with a device. Any communication that violates the sphere will be blocked at the gateway level. Secondly, only allowed communication will be evaluated for potential attacks and anomalies using advance detection engines. To show the effectiveness of our proposed framework, we perform couple of attacks on IoT devices; camera and google home and show the feasibility of IoT-Sphere.

Stroke is the second leading cause of death and disability worldwide, with ischemic stroke as the most common type. The preferred diagnostic procedure at the acute stage is the acquisition of multi-parametric magnetic resonance imaging (MRI). This type of imaging not only detects and locates the stroke lesion, but also provides the blood flow dynamics that helps clinicians in assessing the risks and benefits of reperfusion therapies. However, evaluating the outcome of these risky therapies beforehand is a complicated task due to the variability of lesion location, size, shape, and cerebral hemodynamics involved. Though the fully automated model for predicting treatment outcomes using multi-parametric imaging would be highly valuable in clinical settings, MRI datasets acquired at the acute stage are mostly scarce and suffer high class imbalance. In this paper, parallel multi-parametric feature embedded siamese network (PMFE-SN) is proposed that can learn with few samples and can handle skewness in multi-parametric MRI data. Moreover, five suitable evaluation metrics that are insensitive to imbalance are defined for this problem. The results show that PMFE-SN not only outperforms other state-of-the-art techniques in all these metrics but also can predict the class with a small number of samples, as well as the class with high number of samples. An accuracy of 0.67 on leave one cross out testing has been achieved with only two samples (minority class) for training and accuracy of 0.61 with the highest number of samples (majority class). In comparison, state-of-the-art using hand crafted features has 0 accuracy for minority class and 0.33 accuracy for majority class.

Dynamic route planning is a classical problem with interesting applications in optimizing car navigation, fleet management, urban evacuation planning, unmanned ground and airborne vehicle movement, and maritime route planning. While numerous traditional and heuristic-based algorithms have been proposed to address deficiencies in dynamic route planning, ongoing efforts are increasingly focusing on deriving scalable solutions from nature motivated schemes. The present work inspired by the behavior and prey hunting skills of sea predator, the hammerhead shark, seeks to devise a new dynamic route optimization algorithm. The proposed hammerhead shark optimization algorithm (HOA) finds destination in an unknown solution space by applying the natural route optimization behavior inherent in the hammerhead shark. Once the destination location is identified, HOA attempts to determine the path starting from source employing targeted movement towards the destination. The proposed algorithm can deal with static as well as dynamic environments. During validation, the proposed algorithm is performance tested against two state of the art algorithms A* and ant colony optimization (ACO). Attributes including the iteration count, path length (cells) and time complexity are compared. The results show that proposed algorithm outperforms A* in terms of latency, and ACO in terms of path optimality. The highly satisfactory performance of HOA leads us to recommend it as a suitable candidate for further adoption in optimal, scalable and dynamic path calculation concerns.

As the source code of various IoT botnet families including Mirai has been made publicly available, the adversaries are drastically introducing new variants of these IoT Botnet families. However, there is a lack of generic mechanism for the detection of these emerging variants. As a consequence, it is infeasible for security solution providers to effectively identify new variants of IoT botnets. In this paper, we have done static code analysis of 17 IoT botnet variants of family Mirai and Qbot in order to dig out the attacker's perspective, generic behavior, employed technologies and implemented techniques. With the help of this analysis, we have identified generic behavioral patterns of IoT botnets and have developed generic signatures for the identification of IoT botnets. These signatures includes identification on the basis of CPU architectures, Bot control commands, Bot scanning commands, obfuscation methods, botnet specific exploits and attacks. A comparative analysis of analyzed IoT-Botnet families has been presented. For the evaluation of identified signatures, we first tested them on unknown Mirai and Qbot variants and gained a detection rate of 100% for both the variants. Secondly, we tested those signatures on other IoT-Botnet families: IRC-Bot, Perl ShellBot, Trick-Bot and gained a detection rate of 98%, 96.79% and 98.2% respectively. Further, we have presented open research challenges in the field of IoT-Botnet detection. This research will enhance IoT botnets understanding and pave the way for generic detection and prevention methods of IoT botnets.

Starch/chitosan modified polyurethanes (PUs) were synthesized by step growth polymerization reaction between −NCO terminated prepolymer and chain extenders (1,4-Butanediol/starch/chitosan). Isophorone diisocyanate (IPDI) was reacted with hydroxyl-terminated polybutadiene (HTPB) to synthesize prepolymer and was further reacted with different moles ratio of starch/chitosan to produced five samples of polyurethane (PU). These samples were characterized by Fourier transformed infrared (FTIR) and Proton nuclear magnetic resonance (1H NMR) spectroscopy. The surface characterizations of PUs were done by scanning electron microscope (SEM). Thermogravimetric analysis showed that the thermal stability of PUs was higher when the mixture of both natural materials was used at equal amounts. It is concluded that combination of both starch and chitosan are efficient for the synthesis of PUs.

Feature subset selection is a process to choose a set of relevant features from a high dimensionality dataset to improve the performance of classifiers. The meaningful words extracted from data forms a set of features for sentiment analysis. Many evolutionary algorithms, like the Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), have been applied to feature subset selection problem and computational performance can still be improved. This research presents a solution to feature subset selection problem for classification of sentiments using ensemble-based classifiers. It consists of a hybrid technique of minimum redundancy and maximum relevance (mRMR) and Forest Optimization Algorithm (FOA)-based feature selection. Ensemble-based classification is implemented to optimize the results of individual classifiers. The Forest Optimization Algorithm as a feature selection technique has been applied to various classification datasets from the UCI machine learning repository. The classifiers used for ensemble methods for UCI repository datasets are the k-Nearest Neighbor (k-NN) and Na&iuml, ve Bayes (NB). For the classification of sentiments, 15&ndash, 20% improvement has been recorded. The dataset used for classification of sentiments is Blitzer&rsquo, s dataset consisting of reviews of electronic products. The results are further improved by ensemble of k-NN, NB, and Support Vector Machine (SVM) with an accuracy of 95% for the classification of sentiment tasks.

A number of different feature selection and classification techniques have been proposed in literature including parameter-free and parameter-based algorithms. The former are quick but may result in local maxima while the latter use dataset-specific parameter-tuning for higher accuracy. However, higher accuracy may not necessarily mean higher reliability of the model. Thus, generalized optimization is still a challenge open for further research. This paper presents a warzone inspired &ldquo, infiltration tactics&rdquo, based optimization algorithm (ITO)&mdash, not to be confused with the ITO algorithm based on the It&otilde, Process in the field of Stochastic calculus. The proposed ITO algorithm combines parameter-free and parameter-based classifiers to produce a high-accuracy-high-reliability (HAHR) binary classifier. The algorithm produces results in two phases: (i) Lightweight Infantry Group (LIG) converges quickly to find non-local maxima and produces comparable results (i.e., 70 to 88% accuracy) (ii) Followup Team (FT) uses advanced tuning to enhance the baseline performance (i.e., 75 to 99%). Every soldier of the ITO army is a base model with its own independently chosen Subset selection method, pre-processing, and validation methods and classifier. The successful soldiers are combined through heterogeneous ensembles for optimal results. The proposed approach addresses a data scarcity problem, is flexible to the choice of heterogeneous base classifiers, and is able to produce HAHR models comparable to the established MAQC-II results.

Publically available relational data without security protection may cause data protection issues. Watermarking facilitates solution for remote sharing of relational database by ensuring data integrity and security. In this research, a reversible watermarking for numerical relational database by using evolutionary technique has been proposed that ensure the integrity of underlying data and robustness of watermark. Moreover, mRMR based feature subset selection technique has been used to select attributes for implementation of watermark instead of watermarking whole database. Binary Bat algorithm has been used as constraints optimization technique for watermark creation. Experimental results have shown the effectiveness of the proposed technique against data tempering attacks. In case of alteration attacks, almost 70% data has been recovered, 50% in deletion attacks and 100% data is retrieved after insertion attacks. The watermarking based on evolutionary technique (WET) i.e., mRMR based Binary Bat Algorithm ensures the data accuracy and it is resilient against malicious attacks.

Urdu language uses cursive script which results in connected characters constituting ligatures. For identifying characters within ligatures of different scales (font sizes), Convolution Neural Network (CNN) and Long Short Term Memory (LSTM) Network are used. Both network models are trained on formerly extracted ligature thickness graphs, from which models extract Meta features. These thickness graphs provide consistent information across different font sizes. LSTM and CNN are also trained on raw images to compare performance on both forms of inputs. For this research, two corpora, i.e. Urdu Printed Text Images (UPTI) and Centre for Language Engineering (CLE) Text Images are used. Overall performance of networks ranges between 90% and 99.8%. Average accuracy on Meta features is 98.08% while using raw images, 97.07% average accuracy is achieved.

Sentiment classification of social media has recently become popular among scientists due to the emergence of product reviews, blogs and social networking sites. A large number of reviews are difficult to evaluate personally. Moreover due to variable nature of reviews it becomes difficult, to compile overall result of reviews, to know which product is better than other. Researchers have already implemented machine learning techniques to analyze sentiment present in the given document. But execution time for these techniques increases due to the increase in feature set of data. Also irrelevant features participate in determining the sentiment of the given document, thereby varying the accuracy of the algorithm. In order to get much better classification, we propose a Biogeography based optimization algorithm to select optimal features set from given data. Then by using Naive Bayes and Support Vector Machine techniques, we perform sentiment classification of product reviews. The proposed technique can be applied to other classification problems where feature set is large.

Structure-based 3D-QSAR study was performed on a class of 5-benzylidene-2-phenylthiazolinones non-redox type 5-LOX inhibitors. In this study, binding pocket of 5-Lipoxygenase (pdb id 3o8y) was identified by manual docking using 15-LOX (pdb id 2p0m) as a reference structure. Additionally, most of the binding site residues were found conserved in both structures. These non-redox inhibitors were then docked into the binding site of 5-LOX. To generate reliable CoMFA and CoMSIA models, atom fit data base alignment method using docked conformation of the most active compound was employed. The q(2)cv and r(2)ncv values for CoMFA model were found to be 0.549 and 0.702, respectively. The q(2)cv and r(2)ncv values for the selected CoMSIA model comprised four descriptors steric, electrostatic, hydrophobic and hydrogen bond donor fields were found to be 0.535 and 0.951, respectively. Obtained results showed that our generated model was statistically reliable. Furthermore, an external test set validates the reliability of the predicted model by calculating r(2)pred i.e.0.787 and 0.571 for CoMFA and CoMSIA model, respectively. 3D contour maps generated from CoMFA and CoMSIA models were utilized to determine the key structural features of ligands responsible for biological activities. The applied protocol will be helpful to design more potent and selective inhibitors of 5-LOX.

Most of the data mining projects generate information (summarized in the form of graphs and charts) for business executives and decision makers; however it leaves to the choice of decision makers either to use it or disregard it. The manual use of the extracted knowledge limits the effectiveness of data mining technology considerably. This chapter proposes an architecture, in which data mining module is utilized to provide continuous supply of knowledge to a rule based expert system. Proposed approach solves the knowledge acquisition problem of rule based systems and also enhances effective utilization of data mining techniques (i.e. by supplying extracted knowledge to rule based system for automated use). The chapter describes the details of a data mining driven rule based expert system applied in medical billing domain. Main modules of the system along with the final analysis of performance of the system have also been presented.

This paper proposes an automated sign language to speech interpreter that begins by capturing the 3D video stream through Kinect and the joints of interest in the human skeleton are then worked upon. The proposed system deals with the problems faced by mute people in conveying their message through Pakistani sign language. This research makes use of the 3D trajectory algorithm for processing the normalized data. Performed gestures are classified using the robust learning technique of ensemble. Once recognized, the gestures are translated to speech. This system has been tested on several signs taken from PSL, demonstrating the real time practicality of using ASLSI.

Most of the research in the area of performance evaluation of rule-based expert systems (RBESs) is focused on verification and validation issues. Many researchers discuss usability, usefulness, portability, and response time for the evolution of RBES. The final goal of all such studies is to construct a system with optimal, accurate knowledge base. Arguably, a system with best knowledge base is actually worthless if it is never utilized in the real world. We have proposed “benefit” as a measure of evaluation and suggested some guidelines for performance evaluation of RBESs. The proposed measure has been demonstrated for performance evaluation of an RBES applied in the medical billing domain. Results showed that the system has saved hundreds of working hours during the evaluation period of 3 months. Moreover, other associated measures have also been considered. Associated measures in the medical billing domain are “claim rejection rate”—reduced by 54%—and “claim aging,” which has decreased from 34 to 28 days due to the RBES. Guidelines proposed by this research can be applied for the evaluation of expert systems implemented in other application domains, including in the first place business decision support systems.