Computer Integrated Manufacturing Systems

ARTIFICIAL INTELLIGENCE AND MOTIVES OF MURDER BASED PREDICTION IN INDIA

Ritika Ranka & Rishabh Ranka — 2023-11-07

This paper presents a growing autonomy of AI decision-making raises questions about an individual's accountability (mens rea) in relation to criminal conduct (actus reus). Automated Decision Making refers to the use of artificial intelligence and related technologies to assist or replace human decision-making in the criminal justice system. AI is already in practice to assist with tasks such as predicting recidivism, identifying suspects, or determining sentences. The famous Loomis v. Wisconsin case , in which the court rejected the appeal against the decision supported by the COMPAS but also cautioned about the risks of using such algorithms and their transparency, questioned the use of the COMPAS algorithm in calculating the risk of reoffending in US courts. Later, ProPublica published a study demonstrating the algorithm's prejudice towards persons of colour.

THREE POROUS LAYERED FERROFLUID SQUEEZE FILM WITH A CONVEX PAD STATOR UNDER SLIP AND SQUEEZE VELOCITY EFFECTS

Darshana A Patel & Ramesh C Kataria* — 2023-11-07

This paper presents a mathematical model and analysis for a slider bearing consisting of a convex pad stator with three porous layers attached to the slider. As a lubricant, ferrofluid is used. The problem takes into account the influence of slip velocity, as proposed by Sparrow et al. [1] and modified by Shah et al. [2]. To describe magnetic fluid penetration dynamics through porous media, we have used modified Darcy's law given by Zahn and Rosensweig [3]. Solving the generalized Reynolds equation yields the expression for pressure. The equations for load carrying capacity can then be obtained by using this expression. Non-dimensional pressure, load carrying capacity, friction on the slider, coefficient of friction, and position of the centre of pressure are expressed analytically. A numerical computation is performed and graphical results are presented. The results indicate that a greater field strength or greater inlet to outlet film thickness ratio a increases load carrying capacity. Non-dimensional coefficient of friction and friction on the moving slider increase with decreasing inlet-to-outlet film thickness ratio a or higher crown ratio. When the film thickness ratio increased, the centre of pressure shifted towards the outlet. After the film thickness ratio a reached a particular level, it changed in the direction of the inlet as field strength became larger. However, it shifted towards the inlet when the magnetization parameter increased. When the slip parameter was increased, the non-dimensional load capacity, slider friction, and centre of pressure location all decreased. Overall, it can be said that smaller values of , , , and < < yield higher performance.

ANALYZING CUSTOMER SATISFACTION: AN INNOVATIVE DECISION SUPPORT SYSTEM BASED ON FUZZY INFERENCE RULES

Jugendra Kumar Dongre*, Dr. Ajay R. Raundale — 2023-11-25

Customer relationship management (CRM) is a big deal in business these days. It's all about making sure customers are happy. One way to measure customer satisfaction is by using a special system called a fuzzy rule based decision support system. This system is helpful when things aren't simple and straightforward. It can handle situations where different things are connected and when you need to make judgments based on the specific situation. In this paper, we're looking at how the cost of recharge coupons and the amount of talk time and validity affect customer satisfaction. We want to find the recharge coupon that makes customers happy and makes the company money. We're using a fuzzy logic approach to figure out what makes customers satisfied. In the end, we'll have a model that shows how satisfied customers are based on their recharge coupon and talk time.

UP GRADED CONVOLUTION ERROR DIMINUTION CODE PERFORMANCE IN SEA WATER COMMUNICATION

Smt .Y. Venkata Ratnam*, Dr. V.Malleswara Rao & Dr. B.Prabhakar Rao — 2023-11-27

Quality assurance of an image is an important task in underwater transmission systems. Underwater channel is characterized by speckle noise and multipath currents which lead to variations in Doppler frequency and also changes the distance between the nodes. As the reliability of an image in an acoustic channel can be judged in terms of Peak Signal to Noise Ratio (PSNR) and low Mean Square Error (MSE),Structural Similarity Index(SSIM),channel, Signal to Noise Ratio requirement, Band width efficiency can be obtained by employing suitable modulation techniques or efficient fault reduction coding techniques. While considering design and implementation fault reduction coding techniques are more prominent. This paper proposes a new channel coding technique that ensures secrecy , comparatively good PSNR low MSE, high SSIM . This paper addresses the comparison of proposed Upgraded Convolution code with convolution code, Reed Solomon(RS)code , Turbo code, Low Density Parity Check code (LDPC) for transmission of JPEG image through underwater acoustic channel by using frequency hopped M-ary FSK modulation (FH M-ary FSK).

Improve Term Weighting for Text Classification

Abdulmohsen Algarni — 2023-11-30

A large number of features can be extracted from text documents. The extracted features are mixed between positive, negative, and noise features. Improving the quality of extracted features can be a challenging task. The feature selection technique used in text classification is the team-based approach. The term “Frequency-Inverse Document Frequency” (TF-IDF) is widely used to extract all features from text documents. Based on the weight of the extracted features, the most important features can be selected. However, the selected features are based on the frequency of the term in the documents regardless of the importance of the feature. In this paper, we proposed a new method based on TF-IDF to improve the quality of extracted features and revise the weight. The extracted terms from the text are classified based on their importance. Then, the weight of the features can be revised based on the class that the feature belongs to. The proposed model shows significant improvement in the evaluation measures with an average of 3.6 in F-measure.