Cardiovascular disease are leading cause of death every year,approximately 17.9 million people die due to CVD ,Cholesterol plays a vital role in these kinds of sufferings,this paper proposes AI model to predict the level of cholesterol and haemoglobin , Predicting the risk of cardiovascular disease is the key for primary prevention . Using patient data and other information, AI can help doctors and medical providers deliver more accurate diagnoses and treatment plans. Traditionally, blood examination is done by gathering blood tests from patients and perform various tests on the samples. Our work gains ground towards non-invasive blood examinations by utilizing spectral data from the Near Infra-Red (NIR) frequencies instead of the latter.Most scientists are yet to adopt AI methods for spectral analysis on the account of a high risk of overfitting. One significant issue we faced was building a model that summed up well without overfitting. From our result, scientists will be able to use a provided application to input NIR spectroscopic data and receive relevant predictions. We recommend an AI model to estimate blood and cholesterol levels based on bloodstream test measures. This non-invasive measurement approach is proposed by framing the task as a multi-class and multi- target classification problem. We focus on Machine learning and one Neural Networks techniques to model the absorption data in order to classify the level of cholesterol and haemoglobin as high, low or ok.In this study two models has been build, One using a classical machine learning and the other a neural network. After the data analysis, we created three classification models for predicting cholesterol low, cholesterol high and haemoglobin with average accuracy between 86 - 93%.

Keywords : Artificialntelligence,spectralanalysis,AImodel,SVM,NLP,Classificationmodel,Neuralnetw ork,ANN,Cardiovascular disease.

Author : Kosala

Title : AI MODEL TO PREDICT CHOLESTEROL AND HAEMOGLOBIN LEVELS IN BLOOD using NEAR INFRA-RED (NIR) SPECTROSCOPY

Volume/Issue : 2024;06(10)

Page No : 1-9

In Construction planning the major problem is reducing the time- cost and it developed the time- cost trade-off (TCTO) problem moments. The time and cost is always identified with each other and if we assume time as precious as plutocrat (time value of money) TVOM also the dealing with these type of problem is must be easy. In moment’s competitive business terrain, delivering systems in the least possible time, with maximum quality and minimal cost has got a critical issue for design directors. Design time crashing plays an important part in design operation determining which conditioning duration to crash to complete the design in the quested time. TCTO problem in design operation have been traditionally answered by two distinctive approaches like CTM, PERT, Heuristic styles and so on. The relative analysis between mathematically (Linear Programming Method/ Traditional) and CTM is done by using an illustration.

Keywords : Project management; Time-cost trade-off, CPM, Optimization, Network Analysis.

Author : Varun Pratap Singh, B.P.Mudgal

Title : Time-Cost Trade-off Analysis for Building Construction Projects

Volume/Issue : 2024;06(10)

Page No : 10-20

Any teaching-learning (T-L) experience is planned and implemented to develop intended outcomes in the learners. A teacher has to be concerned about how learning can be made more effective and efficient and this is where the different types of instructional methods can be of great help. This paper endeavours to discuss the concept of instructional strategy and its importance in the realm of engineering education.

Keywords : Teacher-centred,Student-centred, Mixed strategy, Deductive strategy, Inductive strategy, Eclectic strategy.

Author : Dr. S. Arun Sankar

Title : DIFFERENT TYPES OF INTRUCTIONAL STRATAGIES IN TEACHING-LEARNING (T-L) PROCESS

Volume/Issue : 2024;06(10)

Page No : 21-27

we introduce the concepts of an ideal nano K-set, an ideal nano O-set, an ideal nano Kα-set and an ideal nano Oα-set are investigate and deal with an ideal nano topological spaces.

Keywords :

Author : D.ARUMUGAKANI, M. RAJA KALAIVANAN

Title : ON K-SETS AND NANO O-SETS IN IDEAL NANO TOPOLOGICAL SPACES

Volume/Issue : 2024;06(10)

Page No : 28-35

Giving or recommending appropriate content based on the quality of experience is the most important and challenging issue in recommender systems. As collaborative filtering (CF) is one of the most prominent and popular techniques used for recommender systems, we propose a new clustering- based CF (CBCF) method using an incentivized/penalized user (IPU) model only with the ratings given by users, which is thus easy to implement. We aim to design such a simple clustering- based approach with no further prior information while improving the recommendation accuracy. To be precise, the purpose of CBCF with the IPU model is to improve recommendation performance such as precision, recall, and F1 score by carefully exploiting different preferences among users. Specifically, we formulate a constrained optimization problem in which we aim to maximize the recall (or equivalently F1 score) for a given precision. To this end, users are divided into several clusters based on the actual rating data and Pearson correlation coefficient. Afterward, we give each item an incentive/penalty according to the preference tendency by users within the same cluster. Our experimental results show a significant performance improvement over the baseline CF scheme without clustering in terms of recall or F1 score for a given precision.

Keywords : Clustering, collaborative filtering, F1 score, incentivized/penalized user model, Pearson correlation coefficient, recommender system.

Author : Kaneez Fatima, Amer Noor Khan, Saleha Butool

Title : Clustering-Based Collaborative Filtering Using an Incentivized/Penalized User Model

Volume/Issue : 2024;06(10)

Page No : 36-43

Stress is a feeling of emotional or physical tension. It can cause from both physical and emotional reason like chronical disease, depression, negative thoughts, self-doubt, anger etc. It is both positive and negative. Positive stress helps in avoiding danger or deadline but when it lasts for longer period, it may harm your health and mind. To prevent last long stress, it is necessary to detect them in the early stages which is only possible if detects on time. In this paper, a comprehensive review has been presented which focused on stress detecting and monitoring using wearable sensors, Electroencephalography (EEG), Electrocardiogram (ECG) and photo plethysmography. The stressors techniques, results, advantages, limitations and issue for each study are highlighted and expected to provide a path for future research studies and multimodal stress detection based on deep learning technique has been proposed at last.

Keywords : Stress, Emotions, Galvanic Skin Response (GSR), Global System for Mobile Communication (GSM), Arduino (Microcontroller), Pulse Rate.

Author : Gaurav, Kishan Singh, Akash Sharma ,Akash Goswami ,Sanjeev Kumar Saini ,Manish Patel

Title : MENTAL HEALTH MONITORING SYSTEM

Volume/Issue : 2024;06(10)

Page No : 44-47